From d566429ab3c43daff17f049fdb37b08d05b6de39 Mon Sep 17 00:00:00 2001 From: zianekhodja Date: Wed, 16 Dec 2015 23:14:24 +0100 Subject: [PATCH] new figures --- Full_mpi.pdf | Bin 0 -> 7989 bytes Full_mpivsomp.pdf | Bin 0 -> 7616 bytes Full_openmp.pdf | Bin 0 -> 7988 bytes GPU_mpi.pdf | Bin 8808 -> 0 bytes GPU_openmp.pdf | Bin 8826 -> 0 bytes Simulations/Full_mpi.eps | 913 +++++++++++++++++ Simulations/Full_mpivsomp.eps | 827 +++++++++++++++ Simulations/Full_openmp.eps | 913 +++++++++++++++++ Simulations/Sparse_mpi.eps | 955 ++++++++++++++++++ Simulations/Sparse_mpivsomp.eps | 827 +++++++++++++++ Simulations/Sparse_openmp.eps | 955 ++++++++++++++++++ Simulations/full_mpi/full_mpi_1GPU.o140161 | 515 ++++++++++ Simulations/full_mpi/full_mpi_1GPU.sge | 25 + Simulations/full_mpi/full_mpi_2GPU.o140160 | 562 +++++++++++ Simulations/full_mpi/full_mpi_2GPU.sge | 25 + Simulations/full_mpi/full_mpi_3GPU.o140159 | 604 +++++++++++ Simulations/full_mpi/full_mpi_3GPU.sge | 25 + Simulations/full_mpi/full_mpi_4GPU.o140132 | 622 ++++++++++++ Simulations/full_mpi/full_mpi_4GPU.sge | 25 + .../full_openmp/full_openmp_1GPU.o140165 | 511 ++++++++++ Simulations/full_openmp/full_openmp_1GPU.sge | 27 + .../full_openmp/full_openmp_2GPU.o140164 | 540 ++++++++++ Simulations/full_openmp/full_openmp_2GPU.sge | 27 + .../full_openmp/full_openmp_3GPU.o140163 | 565 +++++++++++ Simulations/full_openmp/full_openmp_3GPU.sge | 27 + .../full_openmp/full_openmp_4GPU.o140162 | 590 +++++++++++ Simulations/full_openmp/full_openmp_4GPU.sge | 27 + Simulations/mpi.txt | 9 + Simulations/mpivsomp.txt | 5 + Simulations/openmp.txt | 9 + .../sparse_mpi/sparse_mpi_1GPU.o140032 | 642 ++++++++++++ Simulations/sparse_mpi/sparse_mpi_1GPU.sge | 25 + .../sparse_mpi/sparse_mpi_2GPU.o140031 | 662 ++++++++++++ Simulations/sparse_mpi/sparse_mpi_2GPU.sge | 25 + .../sparse_mpi/sparse_mpi_3GPU.o140030 | 758 ++++++++++++++ Simulations/sparse_mpi/sparse_mpi_3GPU.sge | 25 + .../sparse_mpi/sparse_mpi_4GPU.o140023 | 841 +++++++++++++++ Simulations/sparse_mpi/sparse_mpi_4GPU.sge | 25 + .../sparse_openmp/sparse_openmp_1GPU.o140100 | 512 ++++++++++ .../sparse_openmp/sparse_openmp_1GPU.sge | 27 + .../sparse_openmp/sparse_openmp_2GPU.o140099 | 534 ++++++++++ .../sparse_openmp/sparse_openmp_2GPU.sge | 27 + .../sparse_openmp/sparse_openmp_3GPU.o140098 | 602 +++++++++++ .../sparse_openmp/sparse_openmp_3GPU.sge | 27 + .../sparse_openmp/sparse_openmp_4GPU.o140097 | 621 ++++++++++++ .../sparse_openmp/sparse_openmp_4GPU.sge | 27 + Sparse_mpi.pdf | Bin 0 -> 8094 bytes Sparse_mpivsomp.pdf | Bin 0 -> 7614 bytes Sparse_openmp.pdf | Bin 0 -> 8085 bytes paper.tex | 36 +- 50 files changed, 15542 insertions(+), 4 deletions(-) create mode 100644 Full_mpi.pdf create mode 100644 Full_mpivsomp.pdf create mode 100644 Full_openmp.pdf delete mode 100644 GPU_mpi.pdf delete mode 100644 GPU_openmp.pdf create mode 100644 Simulations/Full_mpi.eps create mode 100644 Simulations/Full_mpivsomp.eps create mode 100644 Simulations/Full_openmp.eps create mode 100644 Simulations/Sparse_mpi.eps create mode 100644 Simulations/Sparse_mpivsomp.eps create mode 100644 Simulations/Sparse_openmp.eps create mode 100644 Simulations/full_mpi/full_mpi_1GPU.o140161 create mode 100644 Simulations/full_mpi/full_mpi_1GPU.sge create mode 100644 Simulations/full_mpi/full_mpi_2GPU.o140160 create mode 100644 Simulations/full_mpi/full_mpi_2GPU.sge create mode 100644 Simulations/full_mpi/full_mpi_3GPU.o140159 create mode 100644 Simulations/full_mpi/full_mpi_3GPU.sge create mode 100644 Simulations/full_mpi/full_mpi_4GPU.o140132 create mode 100644 Simulations/full_mpi/full_mpi_4GPU.sge create mode 100644 Simulations/full_openmp/full_openmp_1GPU.o140165 create mode 100644 Simulations/full_openmp/full_openmp_1GPU.sge create mode 100644 Simulations/full_openmp/full_openmp_2GPU.o140164 create mode 100644 Simulations/full_openmp/full_openmp_2GPU.sge create mode 100644 Simulations/full_openmp/full_openmp_3GPU.o140163 create mode 100644 Simulations/full_openmp/full_openmp_3GPU.sge create mode 100644 Simulations/full_openmp/full_openmp_4GPU.o140162 create mode 100644 Simulations/full_openmp/full_openmp_4GPU.sge create mode 100644 Simulations/mpi.txt create mode 100644 Simulations/mpivsomp.txt create mode 100644 Simulations/openmp.txt create mode 100644 Simulations/sparse_mpi/sparse_mpi_1GPU.o140032 create mode 100644 Simulations/sparse_mpi/sparse_mpi_1GPU.sge create mode 100644 Simulations/sparse_mpi/sparse_mpi_2GPU.o140031 create mode 100644 Simulations/sparse_mpi/sparse_mpi_2GPU.sge create mode 100644 Simulations/sparse_mpi/sparse_mpi_3GPU.o140030 create mode 100644 Simulations/sparse_mpi/sparse_mpi_3GPU.sge create mode 100644 Simulations/sparse_mpi/sparse_mpi_4GPU.o140023 create mode 100644 Simulations/sparse_mpi/sparse_mpi_4GPU.sge create mode 100644 Simulations/sparse_openmp/sparse_openmp_1GPU.o140100 create mode 100644 Simulations/sparse_openmp/sparse_openmp_1GPU.sge create mode 100644 Simulations/sparse_openmp/sparse_openmp_2GPU.o140099 create mode 100644 Simulations/sparse_openmp/sparse_openmp_2GPU.sge create mode 100644 Simulations/sparse_openmp/sparse_openmp_3GPU.o140098 create mode 100644 Simulations/sparse_openmp/sparse_openmp_3GPU.sge create mode 100644 Simulations/sparse_openmp/sparse_openmp_4GPU.o140097 create mode 100644 Simulations/sparse_openmp/sparse_openmp_4GPU.sge create mode 100644 Sparse_mpi.pdf create mode 100644 Sparse_mpivsomp.pdf create mode 100644 Sparse_openmp.pdf diff --git a/Full_mpi.pdf b/Full_mpi.pdf new file mode 100644 index 0000000000000000000000000000000000000000..14df67e5f819830b659265d47dfe122fc07a0f71 GIT binary patch literal 7989 zcmb_>3pkWp^mnI@%BYm0(B+L7a(UTOPZfIp8@DVGj^aUlf|cT0nn61=F>40DJS z_dlP7nuG-A9=4!kjW)eFZ1#N9moHO6pIR&1N8W!?iF{dVL6{sFR9WxodG0X(!}e-f z?(Kkz$P3}8l6~G`1|QPXl9JK_S580jd{|hWB+Z)&A>lSo8zc*ZZ;slfuD+BhDzV*B zT{ZT;ZD90M)mLp#{O;?Owpo6>*nx;wbSBTZ8aH@#JOh)}pp@veyi5Y+wuN!R)Hqxl ztDq%=vB=CIu9nR-38OPHnAeugj3eo;3d@({@)NTz9Tnwo@zsd#a8{b3ON{GyqyEC@ zh;@mMXXwQ=-i22KHZNJ(^wCi+Kd(OJ7xnvVa#x=}LHp~CU>@&y_#-7^2}VJIe{$rU zXh(zQpOJF7I6B1`re()$PTybR5cX?*BZJY9@9wfqtb(W!iQACbgw)0bx!m5_#yG(d z?Z`9<6=hNeU!9DL8|@OUzh=0>et5&`XhE?kIfIrOzD!O|2iWio*G*_0Nc9Vhe$tKGwIAz!~>KTvHo9jew#2i!W5+?|D zNLPjnG07Ewn4XWR+g=3=3Tk7v?5xtnTu5)9s%Fd$^%pchG(UEE1-c}s`SVDDbyF)d zb=u}Ys(uqc`z*5bRABaA3Ex$M$FA|OAG^x&Ub3i7e0=jm3QrqTK>9h z*-X(LwdR$nbMngWyqHt6!F{SJCe&@j#(ipalI$2ZUnZ0O@sgWSXRAYX-P?leAyeMx zN(;1A0{f%yKHl3GktZvXP-)UoYt|Gw`CdJHcfeiM?fjNHZvPD!&RZJyXm%5&EAur- zZ()zhA{hB?_BNtMgw%44*G?5nqh^$9j-7ygExT1&FkI+9F)2%Ui@sJ&e(jR>e14iXea}Ay^A1~-l4_%IX5f6+rnIl0 z@1HMa$9eAY*c9)~jvJ4E*mXT{AtwGYX`nmpDt~6Ho7)lJ^Av^ z%lrG{;~U}4fr}qBr1C1S1k1%2R!+uO?tBrSed9%Ao1&8YF*O+4HlOhEME;K2j>kK# zY|dkj+ZiTO;!jXB$1_P8T+o~*d5~- z(#9_39DzfGK-9B}W&E;&d%^1S%|08fIm;dMYD>}e?lw(pM!ZQ+7P4ShDjN0MolCAM z4IABil+&H~<7&t&-R<_7UA9?4!9IAzuyABmT!>puALNz|6AK<(R_BNf@8hVf zWQ>=0u9#Xa>fHZ-pFR} z>^&3q<5kl6-4qL+VLs|NQEAhG3`Fdz7K)-V_cj5RKn$TO6+MtB zEK$4jtl@<)#<|P=i1QtHFLn0XOZC^Kz$FrgVEyZr<+K=DfkfF{i9{pi3+Zz2jbwTP zQ-{NLUfoYjP4;0XENmZSpBs&|o02Ak3Rc%D7aVm)e}$)Mk4*H@(fgugIoQ(n!f~I8`avEPm!7^KO@7~u{mi% z`(#?k$#JlfURgOMSujM=r1??j-q+Ab{EipD*~Q;TeXJgAZVvPP{qGRSp@Ft!ZyIPt zqcX|c*+Re_0WD(@7(f?=@PI*!T$&#rK#Ma37-&c1u?1WTjR)lpwp=#Fp2l|vq3i+x z9cV&6L~bJFo7wZB`~g6UaUd2`HpGrZ&OAWr1ZWIBLx?;;oQBxJps6{v#3E+X5(o{_ z3z$)i2Y?n#Di3gniPg4)c>oZCKn(c&Fwn-<3P2JFb4t$aYEG1$E=yLKMWXR2TqcLl<^uX+h#7OttU%^ua(R4X2AK<>QJ^JxZj3}B zL1!kF&)~VkP`YA4-~Ui3v3bOQSUvH+XZ~PVtPb$ce~4mkc8=;B_4j8T9r2!Z{~-ff zht00cQtF~m^SnQP!)7IjjH5w&ffrvK*y31#TsI$JGpj#@$u~Yw?2dU5$c}zQKOXbjGl@y3)1X5D zMZG%=tq=MO*if3x^k(oqzGI91^dq#`x!>J5<2!4zFYVv`y&XDt(6Q4(A@u-V9TcF8 zL3)U@aBm)ffq_IGMSKFGN$Bv9IXh@#(X)?Y3F0*|Ck!-)VxCDM`gyZxkUKzoKF!w& zI(ZO;6_dw<>@yP~VjIFhmpK?LS|37%!U;ObYM=>d2HJv-AQ_~9RFDSJp~DV(gG`VG z`htES8)W;@Kn_d5`@skx7vzCFS^&)tf$*(Fadeb&uy>X_fb6;E z99yJn^~<9zPgjJc2a}GVepmX18n&s&-r@1mRchwjmU`ZC%imOy-Yk)5hgoH!Ht6tp zVT|pr$DcEIn8`0(jQBl#h40{a#RbLIx`=`Y-ub0NLF3o=Kj>h;<9+Pi6=1KnFGJaGQ0Iy-U%vFZOHEHGNjrMyWWVmw?on~hudR8U zC-}VJ6Rg-h)7;`{4g-d=FX_$ep$guUTvB#sS|=UKW;UYGXl`$T#vr|64KQ$DG*)9>b4ihR)mPf2;~FuXBfLR0Y^j%5>E3hNf2Bfl7p^Rg zucNA-J>j`1C8dZIaAn6G${%XP)9Y@nKyPvDx*z!A{R7wZj$4P&&-5kFyh5)%)ZOsn z>hr~;rlEh(E;f#P4`^#h9yNTs^cMU18=pn^wWi}?>qxqm6jVm@>f{#}iax!4y;^rgok)1w>9gH^`5HxUsf>u>gFyTyIXqCa;kL1~>TgCT ze?JgO#KYaemgW>g-Uqs*!R!wY)8>Krd0F!|`e%H*`^X6d^1}kRQ<& zB~g8I60|&hy36?|dT7mFPFbTv*I2#2hh?q<1D~r~MMS4yV^3AzSgJc!zryP@ z_K#ybhL?xd+{+wM9Fn@&^ggOY%RNi6pkI@5JYskgd8_8HA)y}@hJVn%wqbWs$I2Dk z2#g3qP-dFfA~|5-h8Mo>?w*9<1D?iRrH%cc!rTv@4Ekd17n1avGO=KZjEUzB3rbV{5-&NVjTc!-O}AU$ByGXZ0XmwhM5PWUARmHWonItgB8w7_ifiLr#3 z=iIK9mCp}b_$w-V<_vq}mI%FghCc+9coGebdFw$8L7S97=I6Jojj! zY|pU8Gw=MP_&ZA)LT>j5IJDF}*Fnp5MylMrm(t_F4CtGD+AR!7AOyS%PL(Xe|0yq7 zynbYi&AQIlzI|Jk5I3H4kD&@i^zNPuun!7(C$+tUkoB`iOnC)nQlA$91tD z!0s^AM>+bNS{|66olO---7kRxer0j!CG$u+nf z%q&`ZR$?RO!i`=%nBuPwnVc{Z=SFmx|0xnVwe54+AJzIYawBQ1jY8E|n};)q}v+^j#` zJoIq1-_9*jusN%zPv~W^K5UU$FJdkI!`O|ty(puy8g}f~HAQET_+bUT-Dv!vU#Ehd z_GzGP4W;L}>QYqHUQLeRw@=DT{5O}j<|RhCCv`XR_fD3%Nz@wLUoy&B;N*gk?yI>S z5o+w~4R&}}ZA4y4us>3tsk?A^nW3-m4W);U@x-OK+T+u#H#SJE@_62^QC7qBJq6F& zaFzQ+h4^K%V4x!5tCTd7Qt@^zNthg9b8c>Fjh1$FT9mA1^jevdIR2_E6_is zCGifx?$l^at0{aoIWip-AnDQfw0!Yj%Bw&3)p;tq`gh&YNK8c>P+e;-^Kwe9ma!iZ za0BfXzBcfV1uNc@3B=;Z^!4faZU&WC!$l2cR_x0=mseyU z{rcCX`KaWz-CI}M&^(d&q+ZtBE?fOl#PZj;`-xgx-aZ*~wsBc;6VWSwWye)iWRIDt z&$&NZO^)tQ_^mSOY4nBo>FOFZeB+XliL4}}GYAv(==j^x@}c02xP&1UvfZ}}ESmkA6Nw08oT6o`J`qRP= zqE+ptLnT=gau$(KTZI!B;)2_a^4`7~ZY|Y1cq@pj`ljWbX2t!KxQC9etGDQ+g7Clm zfzGv&9xpkoCJ$d<5U9LT`g+1$7`fbWxa4)`lfUR(`De}!cGkb@zX{wlPsqAqu4n!W_4Q&@cIdus$D&&?u;rP-=Tr_AlFkd- zTi~W|@TwmB*hX^UOX_r2KZ@OUYBc`O@vQczEssqBora;nSOa9@?b{N5Qo12a{8zTV zpZY|~R`OXW9Vb2dLeF_?QQ`{s)h#H6y8G?X-m=B_Bu^ZP@EPd!pFY@CB^Ny?TQ<<= zz5GOB$d$f{FP928DoK?k9`F$C5fG+HzrHtJ^``cG$>Va}wS~VOdQ;^b*Rr9oz^`m~ zQ{0p3!p!j2YvsgbrP0IH1tIQAAH6`hweeSNsz7>RK-Rzb(ZyX}Ll-w#9*ut;DRWcU z-lsx9`kxt6ESwVAm}*~n{odE{&8u7G_SMk|+7C4mJj^9u^Hj^Jvn73_m)YK7!-I#O z$XCj*kLr-#dFaj2zm#)~aI`B8!JlznR$9^bWniLO18UnlpB1DHUT|57Qi8R)=9RRD z25F+qddxCn<%jy-%Oup5YB?>Jnj6go$p>dQOAWyee%||l@w-}h@hKgv4MEKxGOm5G zP5y$3`K;R~FPSb*t^Zzd&XiU^X2SDD*Y_08#maI%e?wvsP=Y>(U}z+Sl1CpJAMm1i zGyU-Jcjc9EfJw!}ov~I3D~>UZ!Q2tVrP&8rJ5YjrDEd^m5dmgsM20F|nwF5v(W1|E zuz3KK7UPwS?JP}|!~{Z|(3j&2)qa4`m*vO93Gwh5792DdPlIq^hJ^2fhr3wW0(>@` z<-_CyC~bXhq!tpb3DCJv?!J%B^#PFDI&cV*OQqxNpt5%s5PHJH8GJqm2ZH|CLsdZ~om1 zkVEIpU(3j}8x70@Elv?zcBQU?d1a3~yF2Zz%G48ea;Le7U+jiFyK zpkFlp2dqC({=mxSIzS;o@b(jMSZqFk(bfStWIlz#f~p=CfS8p!!#YQ42#WpmgN6QU zn~^zIR{w9S`TB~(T17N`z+#He6OKjp^Txx4 zT2vaHEMW2B1XBTv<>|{|YSTEpS&y)ogxSFiFZdk~8d1bS!sgCG+SB~!u?Z|Di%I?m z|IE6W{~H%Hrp~o(AccQMnGYUu1pVK@{s!wT#3EAFT(V5J)UU z2i*}fBqW@80&0rspio#n6hZ@mgd-4eh{8b}KWaZl#ymWmt2XbWe;#m%1ZqF*rBV3b zNW^Z0rilVR17e&B5%q6PLLrw%huT(1EKGbC&wcK|}qkf5_1P7d*7?&vY2XPjhG# z8fxhM15Xe2lP*|Y4Ak74r{i{VWZD_RJutgNy}0J2rIT&NPn!(Anu zP_K&wxEtytOi0@i+ffJ<35_6{AdJy^7-K93WvYun=@a$z2>*Wy4{;Zn$0u|7GfvaR OqIF;@Dke6ju>S*R#IDu= literal 0 HcmV?d00001 diff --git a/Full_mpivsomp.pdf b/Full_mpivsomp.pdf new file mode 100644 index 0000000000000000000000000000000000000000..eb6228160dbbab34df1f96245808e41ff48cf8e2 GIT binary patch literal 7616 zcmb_B2{@G9_o+mqO-fnHD~ZCqvlufb`@UxF+8}QfEo<31&wHQF2n{vBRYu-89-zv1=7+&aJX!Uc8UX zd5fl=RAi2gz5sppj_o;+_r369cCM4TbDBz7)b&sCt%Y|4e5TEJuPfW`Kcq?ik?T1| z4cvC3G4{Lq+18J_d%lyF=? zq_&AnZt^S_)UWye?5lN&4i#%(;!Y|(9$jzUwlG@7x$RO|z62uqT)v>l)_3moLsgqR z>6KMhWs=F~^A=0G=H+!qZG3F<1{r_-*uopeRWn5Gjc22+i>Q6{s*H&>11aYio@uo$ zW|kRatB5UBci|qC#1(RlG}WN_rxdgx8M{hNmn$YQI`OGqYZjUV1=p!S@)uzAV+dueRQ^ zezVatRgjY+CzUA5S-jZ+z@l>#>W(CaCu}~RxSHM{b;i^raeiXr;rcq0WofTDh=eMM zQ>sxH?;pyH(oxCpTP=QDy89Z~s=aCKvB@Z^%>TfZw=DEwZ}p6XZl#2%ypzOxNu!Hy zf4tbauHoxdS+gZyJ>4Upe-^GN!`)a(ys>;|&O$;^RMDFE7_aZoNH2QqgJnMAKHX|= zZ1>g(sxNANk89Z5${4+JJN9!@a7R**rEzX(jnT=mbIO6uUA4j4a`c_I-)>L4;`Z3N z92Zp-di}NQ*-))-KbpTAq>6n}sBFWmSGO*)I%*J_`aPI4^{s#C=FN$x9b@%VpBU2t zoFM(XmQ-%Ekgx7+Bj|Mviq|X=@EKmaO}zVFR&BJK znrV4Lo7EV`P;LB~{Y!bD8adsM)a1nM_LH^)E%7#ytIb{L@}r%PN>n3jU&@o5&5Z(m ztnWIyXxzSQG4d>IYs3JpQc}Yx*tsp5;Te&qS<-leqHlU;EZgK#T!8kEy&V6Es)^v@ zH|^`Ir?x)7<%W{7G(D6-8L3vyK%eZ%JXC&n@Ww^OUH#mAV?@aN7Fx5N`oQp>^V=Y@ z=e1t@SmEI5A`i@6_gs{Do}CRYmFU%A^^RSqm{{zKJHIFRJx%i-O2mV*BF>?;lOT{$ z@cebR-Va2tw|(!((Rum#qtgZSU2$*gDBugoL$N@AbB)Z-v7%T}<_EgJ$NsMc`u)u! z5@r@R^-h^OuxQsijV5dosd(f%t@W|}3)3?KSKJXM?OV|&scLf(_w;VN7Lqe0LA;5r zGQ`|FGp1p&fvfF8N%&MBZ{h#M?ok_O$GfB@LwgR@YfEe%T6S^mz-t}bY*pRj-u`~N zOl#Su>Yyl+_~SbYFEpN+sY`pMIGyV3Jd@>Pzpk0~_IkZ{ORu+idh^%A?)!$V?Q_tD9f03(Xm)`PB!#!83)Rek{Qe#C&QF3=r z8TUkx95w4F7bYtd#w%)+pV&0GBTF{d+^wv0e$nzvKC7=S5Yx?xTd^mI*`#$=oavyp z$F5HDh0VRY>og87&9MHQ(UK5Y+-ueROfPBV`TL9@V|m|*3z_RHoL3wT@e*3^aWGdl z~SS4u9=XnGcyeaWicUjKQ`fYNx1hRmp) zlj8OVc!|CDOA8z-*5|7pFfXL~Q7s?!KYf!;AXwmgi7kP;n8lKA+i72R9}8r9Stho+ zynkkiyC{*H+o&`YV&i+O3Z=dA@xwk_&FARx1r+;H^xJp$Y59wCR+70})nh147o?U7 zEUNW9I2A3I(bYq{EsuO*|E67N;Gx*A5Xj=ua_p4xjVoUo@e>bwwNt*Pi$Dy@Y}SHD zyiCW-Z@h0b9z{UR!c>1{LHj@!1X`0kAkY$`&`5gB0KgRmFXK?E03L(diGUZ`5Q7U~ zd3h26+Cm(rFPjW;;0$WbW|Hk7t}6)VSOBz#0=O``VF1_Ijtgf|0L|kAlNd2!ax|Jh zfs-nz56@wa9DtXMZ4oeNRxO^0ndA&}gY^RVig5tYoJQdQt_Ysmwuqeo%)yt(@;6c* z_u0HYL#a>VlITp2ITo|pTS8nC1zrKrGk{;R@qaS-wG9Ng&Ds(`YiZ3Y$=}tiC|f*& zM`!zs4S$<+s{{n$&sE-Zc2SSSfp~@i_4FL=Z48x6Ai5vKrIAT|a~VJ!GMmQYGTDGS zj|JZx{1w=oG&YB;?@3|YQW$BGZZ}N zAGC;HGc`5de(`+%Gg4+C1S}Sg77T9%F$0;Q;lX}U{~Yl-@};BTNSoDUPHW6h8Xni# zRldF`0Lz2GG(6lnJ>fYo>=T7la@YtR972gx7>gh0MfkP1@a;|kJ1ACLhuK_&wNSs)8y)0h;H z4RSyZi$sP%F39y{L-4mh6Z8cGz#xdt+|0KDTo*%F0L}B_?@`X1&suM$a{j$=hBxxN z&GqLhZ46c&cEHb?+QC7@Ud%}{^*DukMHts_B5JwelXVxEAEvxYR=5p7gc<4@2*)M? z^GCggp0_Ygiu&x#Ybo9&xT{z*>_+4<;N0bGZ$p=J3nlN|ZR0L5$Si^YQb84D){DPuk z-KnN81*74SKBl=2%m?O=cV$^^c6La~aR?V$bT}M|NWZ+wYjttb=!K@sxCH!3E6BP$ zLHnd>jg8rs;WceaFh*6+P3BFJ! zL=?4O;i^YZ~0IwWj;dJ;Pf`_F5?C~d2hoKZ1qm3mK{?$g0FIu zqvOq#TXgK1xyD5N=CIb?VfrFbp9J&P2};rWHG`)U#QX0{71TB%S*NWFT9nK5hp(F| zd?0+e-us;RL6k-hxW?CrlZ`@r*9{02KB4%=XgXFCBNEv zVnwzNa>tAAaPI)|2KUnymqX+pzpEZ|DLX&){8NUR+fX^D(3Agw5P3!OT zhSog!I()6X8I^W-`puVY<3lMTBC!wTVmE$E@4=QgPd7!_?JadRYkBr?2i#nl6~!TM&JM-ZMn3u zZhez$rPQ%atc@}cY8@_8RgUh8tztirW!h+1&7Sb4EhUzGTe%GsRn)nWyq)Y_cVfv%qRDt}4W-u)k~jzRNI z+M6<>E6elG$Zo*ds~b-V_gC*xNH;mQ-28#2zuloTtebc-Kcyk33q_>z?tt2LYNup_ z$AXe=6~6QySb?FtAa|R6-S3w&Jl=Q2!G!zCe;GCY>Ju&fC042*jLiDNti zwMQ3Z7CF|6js)3X61!vQ`BrDK%+Up&%9UBp^RwLdNxospS=}R!=u39WN_DbI0^(C0 z`z1APB>)$Neu+qlgUAid57vi4W)Drg4>O)Ni6}Mro?a5L|IvK+BN2Ty+wzq^Of)%6 zvI%wj*R*h2JX|c@B)=J-|Bg(uGe9T57X4h=yKa}`S>-|Nvr+N|+gF4e62y(SuX?q( z(D=}+2&2iBL0{ve%gj=jx?mSJ9CVF+9lEb0qs?f;RHaA4lEf#Wg)3IqAK0k9!D>q#fK!4a>=g4lN4Kn% z@5B+h!UgkmklE8QA2mWp#BYWiuPjzPZBa6A6ff+N9kXLq(Wnqh;B;>2^=;OxHS{NL zOVmBm>)0{+($G)ICoTG#J1Ddg8%=Gmf0OytV7b1#O!!js$FkWwIj1iwdxe*(hmKF1 zGta7&OSSjv?+*}M;ponKG%YxcA;eAyWGh^=S8mv1(S!Z6wBGgk6|I+(fjif@zN{Te zyA{ew@rcHYiGO_S-#T<^+q-2+s))zVPh_vIDC_VdT)US_SmD&|1*oh#V;tk}b~?6` zA%tFz-Tp=Cl>WR>eR0{a#$EYXN75w)+Wb9@daOeRCLwxBI+I1VHhMAvOH8!nkFL~w zo0qa+qfJ%RIPFEI$ET0I12OkMpqjt>4QBPW_YJ134fG7rtI+gb0wtcISypRDH|}25 zSz2}5RQB>K?`2+nZr|U$F3jwBypHycS%})#j|w$C6nx|&tw%O&(f!>Yd~;)?9y!aH z=_H6Qf9h0OvZWH=tv4*+akyiGTx6-_@-WRr8;ugYc`5p5^lEU{ZwG*OkYlk+SP05kgCZsgo z582mywLEv*RWT^w{pSx(DwC!$$fO1hlaHfE8?tv4TV<3bb)@Jhb1|t6T{m=VmJx0D zy2K9G00~kXvrnxSzbv=BKwwm-Vb21edX;7K!%2(ciwoBnl1R3k*ZxwJrdso{F-ODt z8crxeKu|HXV4lJWt5LbYR=LLoXCfAKHeO2UH637|QgLndyP2ErV;!^Au&MT~6z#RS zZIhmO=6Fo>i|bygTGa~kpNh#|)O;{Wwx^{_o|P z!!hm8JJ!Fl{5CPFROZ2MxHhdCxBRsj{#|B5mVeJ+47q;1%UtH{x9eH`RTVM5V}pIs z&zzoiIp=Ok5X!FUGFRJFe)!;vxVMS9x=&Z!!YS*rAF}ldSC@nx*s4?dL3Eqn+gmGd zY?8YV4m5Rt?!BmbNlje3t24fFm#XQ56Riux9u=?hEoa*z_m0=+gIg=kiXhE}@`T*J zc&+->A&-3;j2!gV8czH`cO6@uiYxM{rL=gCy-YY=kv<8O#rWRM6iO4lxPhTz=D9Y) zbD43n>{R~|h3D79D)m3v?*SIy7(_y)_k_Ev*4AlS%ic zaRCfc9f?*!W0e6a8?Md$nQU(WjZ{;BS+XfqqAmOionZ*iG!;C#Tow@o{r&xs{#YcF z?E#|I)zv{12E<@gULd%2U%c3*6fGScAV3D|FPdelW(E-$qR6gk}rUuCK({C2~w{1pZ zSz7+jR`c=Ug*6Y4Xuu@<`oOP1Q-l9c(EQterjUOs%<^T^`6q-z1|d4c(~SeW8Vzeq zArq-gwhsx8ZxV|Izg9_HIP5_?tw!J{CTr!A%K7B^Y1bG zb)CaWLQ}z?cUk`Vb2R9#eamyoD3#gan4bHA9WZ7ZZ>#9 zWbRKCo-bjrt}oXUCgjJ-=AYfW05(L0yH99U1n*X!`2cD-92N&qfms*^g@L<+ybr*b zgQ=;j!QHDrVQ6(VxFh)&jKIscf5K4kuK$Li@#_D;!=MOo-|kOZxJ?9is{Vq(#`^~h zjrk`Y8uw3_Itp%;{>cxA#lu~_IT)8sf_pw}_!m+Dw4(*VZCq6Vv}MBAEWd*bfTj#8 z6W}+5;0Bff;HrUEN24(WeM3D03I~@D7$bc{BZ3ji0A;AAi`G*kX#MXPJ9({K4wuB{ S@*RXn6R-$*dBbf+i2nkiX$dL- literal 0 HcmV?d00001 diff --git a/Full_openmp.pdf b/Full_openmp.pdf new file mode 100644 index 0000000000000000000000000000000000000000..0404dad9cf8acc1a478583a08c5d8886a6571554 GIT binary patch literal 7988 zcmb_B2{=^k_bp$G5uy-MH^mU+&T5b)J6W@2OTIC4hq29=MaWXJ6onSaQV40WWJ{q` zDod0SlBk3zTSZy(zhi0pe*f)xzL{s9`@ZKr+k4J=-+Rs(X$xI_6h;w`kggtxy?`J9 zXn^kGj!;trO(1Vqwi}=XLo7jknkO4#0-(Mpi4EyOWI6@X&_J-*Oo-%#@Jl(D_$Wr0 zxHjV3d$|D73rEZnhCB7O4Gm8Ki8&S`f+lMPUG?`~*hb%MJ7WW-F5kU`&*gjG_d4Hl z#i5AO_JStgk=XCSJ{m!@Rvr6pX+ABO;Y1y14_1?Ge`i&v?up7CT+?>hn+_P8H`iyC z;0H7XQf;$K)mG2;<%_-_j7-J^x667FD+MC1N2<}clP{F@l)Yz%4fX~GpaXB;ns_(b z*E>3JT9%OPNO`12G)|UCs=HR*QuZuPJKEZT&=;^RLobv{!{ht**0`NWvlr*%Q_b=$ zHf&Tl9ItyZyY ziwya2ph4Op#WhXmvd9`k`-_I>>`D}H$1X{rgz&~0=~|I~8x}^Jw{DIX;YrGR+Nf=n zucVaOC>6hlugpeXdS0+oa@LAD!Sbfv_!CXKr)11|x66q)2ptlk759Ps`1tGJ1l`0# zBE|Z|Xo$$+vxYgRvKrQ)J`U9Wz58CF<$BAS6SljegigkvjMEk=G!T{ECNI4u+@#~- z`taVSAQQv&W~G^e;Zh&ZW8)lL?#e6psYKX2Z<<}}<-5D4s;@}L9bdkx=zzl18fZ4k zaOF!@e^4|nyXB09;-J5}__CI3c{2CYu7hWZ&2Y1aZJBxk2p1*B&@ozL>whvoRqjnzR%)RQ%-z@y_=m@wlb|{SCs-jC+$n$rUld$ z>K6v^9$6$2@jZ>4X=rhna!~wznx11>qRKP(na>uHf*;Z5v$15!o6p!;7ciws{#ouT zyu@lpO={gtXV6z0kMh69Jxyz_FLuzXt|~Gseun1dlkbx@XsUmTXW>yQNp)Ig^SZ5Y zy1b*ofp#`LLU{D#EUh;rX(IK^wE3$&_!ipr4FpzB^JGtfSypVBxA@2Q;TWdahm^w! z=iN+lsrxQDXgOM9)lXSAXnVAtv9*r64P7WPzNe7QpOZ!&&0Lp@uh*_Z1QB&;!>x$R=I&TN; zKOnD>ehkOR96CGI)4$X!HuZZ~?8ymo{~I=KBj1UVT_Te2-sWgt-P*rI#b9wm0O<1q-ORK3u2P=~1;K zGoD{{daF3Rk0yNk#iPKp^gBsU?;g2E^>BGH_$lHq=YgQY_k-a!58u9yrHC@kT}~A$ z*FAW#YOG4c_{L-8z_n_#Wk$#E3+y&Enz^7BQfpIYsXm}Rn7I`{a`|Gh(=TyFu zlm12cu_`@F&CP-vhn3s&4+r~;+qn0mESq*58?pO*Tw!F?yBkSMTd#I&0_rf|{(1DG z@?^BPY1GMxJl6=_~)jP8()ra!$&Q9Az$ zwZbUKoL;1yzKK^$2sHn^(?*DO@up*nMXdd5C#I*&fqYAAWkX0*ysQ1LI|`=`R%`#2_`u^(*X~Sr8s%j^zcXP?2)*RE%!H!C^U zJ`BiZFf+}C`Dd$=D$8OK70O$##n@weE@U42I<>(Ar7GF6ddx0L(P(_^^iiYG;p}4? zI7h+N-f)-V+|TVB`C2C zr<$xvvs`SMw#>G6UhDxS(X5%<#|bx#?Is9)htZU)s`$W zD(two?)OVGJwm=AD>l#-f}CTB&vQx%)+3$=c0HL=h1qw79Us0wp3*jBD)l~^$U`%1 z5$bVK($yKu?OgdXi9Gz}H zwsF=tRCe-)d&W)Qu}C#%HT2%SvDUoX;qRjdty@2pVC28N zY~DW|STM!N+GX4ZGgxvC49&{hy4+QLZ+U>)6Wao)^;tq#<>%A7Iy^T|e||SBQ&o{V zeKyEiyWeDPcRGa%4{q#DbFs3nrax1+g7LIIRFcYsilcqwD#x z4XoI3;s9W{d|(oNI!uni%uV1t0@Q)$Fh>@^%|9#=Fla$7u88@31m*_o1oB)^uhs*L8QZDy}RA!!1hr}j%(p?u>ENE{Eu}Kto1;EVn`YD_EJARBqF$UmOt6dZF6x|8KM09DtEfDs7+!)T*H9oR(cjj=JJM+ zr!T~&kx6sr(uG)LCXK4V%&*L260z7t z+FzfDc?sP3`c)QJDjL8p&~Ts1INYKxFbx{Oapy1%cW?993p~)=7}fKJlT@0wD}b4E zG-$V(8oK|*SM4j&Cpf^Yd>D~~? z@Z_+5F#^a0Ss)AYg}gx)%@1TTNMs0PgKRe@1V8uFK@R8#`hx)wlP))B2e`g~Z~%rI zAio|R?tH<5^A*Ui1qi&GUwx{xSg~O77!?hTAGL{%4X?G8tw<22`<88VfsEZIT1pAs+-+t3e6^sg(azP*4;*qgSEMzsh_}QG>d6jTKVKGQvHSUChM|Gj zvX$tAhxxq*zg6T&wAP2`J$B749SZn%`@rK4`Y`Kj&u(8U*-f!Tf_84L&Bvyb*6VNr zj}xmKlI}J1Zp|s$bX{aM)vE4Fc2k`C=C*d5CrKZ+hZ^A0TvWR&^*{MnOh2m=7E4@V zPm{YGaMQz+U6EW~UL9gvF*7sM(%i)bF;PORtW3+TM1fkD+!CbuxB^_`dDVBUETR4t)sG-F;(ewN|TzK^z&o;w2pg`xK}DX=ilQ*BfA>k-h8w2i+;!<=-RVy zt^CDjZ;3NGS0ik z=!OcleWPqwMSZc~{XLVGkHl&uTzS*ON5X*E%_8bRjpThD0hzxw&mIhl&{9V_f-TJ{ zYOGNz&yM@+1!Q63y`)BO<&51tT{N&16+Zt;S8&_zLXCU3&s& zA5#2G<#9c)6|OwibI%_8_?oXRGfz2QzQg8bJ~L!_`4NrKY))=?+mRL3cc(y;F@6>P$*9gc+by+R~ z4BT;1uYb5NZY0QA=XL3`4-=t|VP^wobi9KT`pDx;Rtf1j-@)8#aPjky3zo-EJ0_>Z z?8v@FN1qP1lOLq|ZhpmaTjgTa3DV=124gSx>zE}V%QTl5tUNOo7xjkudTr&KW5zxb zTb;8@x;k#Yw&m2_j;P2K+x$yUmkD=|7{7AOJ*oa+ zRb%k|55CqdHE)z~BApS^ck5ERt!ci!Q!l&xeB(5HhXc>?6sR8;<0;&@GOKrJ?@dwj z4toX=)OtmsL4W<@s4wcOwzDtW_5}@|u@00Qax?u(c)#6xcfi*T(N4hLQ0!L`YJaVg z>B|<$kLR{Fj}5j;xEpMzR8^aAyqx>@(cYSx9x*=#kC`#BJ_aGuXcv}Iu=>J^P57KU zJ<14)zn;(-p}LGaM?-y*bV=vhCd&?0s|bmFO7-02C-Z*GNV*p3s+n_{hhy;W?aTlH z;dqgaqy&u3fh+te+OE5u+Af>Bo9#J2nJE~Rqg_3_ey{rF>ukR*DkIH9PriJxbcp9{ z$?Wd+bJ?*mbh$wfT9i6EcIRUcRz9=&~i!Fi1Oh`91zocf@5r?{nJGSIf3+U}M)bDZZNI`5K~?t# zN)LQ;v+FfId`p-5NCe8nxi}H)&!#Cg16PXfBpkkbi@!_bar6=4 z`XklDmpU&;Gaj0Co_(MdeO1_$r;s;!$8~3ebA3!NV`Oq|TBEunlcSP^S}_a|cFDJ< z*5tpM`t&`(m&d91W%UHMirxi|!G-VR#c8(QTmbap_R2-pK=T ze^(~FJem{xy}Aa6+_dV`cxHm;d9)tx%eRlEzf9Atv-x<9#Za9xCpMOMaQ0 z^-Yf!V}j(BrnmP|)xxqqQ!>(1ZiQD(8SVJL16{fZu{)b&Q`^n4qRS+vmsrWJm3zLu zr}vtgbC~q%$^fYwyZtpLV$L!^C!1~%Fi2w z%KR-l8{U7o3*0q|%e-TxY_ycpw-TEbvVZ5Pqpf%ZUq;|1>BxNDtDN>0q<+7;jMIL) zrpVz{^~7~gqjx5Ki9P-;v;AeubA3RmamYV<2PXdh{T1H4#NbsvYg<20Pv~Yzc`Or% z5%}^}*>-zDJip_*7OZ&vqxPe&!i9A_XHJBB4D|SX4|`oDa&%C*Y@pYb?@WI1jo$H@ zlKf3lyk+r0PMm!ljqkdDebyK3uf1CIyqqYS|9516m2FImWPYA^+1{p@7vJ+U4!7Pa z*GiQ7a;!Qp*iq`M3y3t+nN_541O^6#eF~pm+wC%RP159KY+r=XUBC8TX$_3e`5}q? z>0)zz#T$K}y=?m5-z&GOJ{qU^L;=mhmv|YSGnu|n)cfT+-8FP%F!F_1rP#(J9Rj-| z`%hlnnysk{-DnJ)RCO^$9epH(D6ZW>X&d(7*OhcZ3a=>DFf&rPk=ocOpe3{szecNa zw4vv^F7`&X2+FSJPO}Ej;|p7OhY(?t?vLFL${sFEQZkhcXdX?!HDi%DgO8dd_KNYO zaZ~Hx3(mRH>eozovFQ4l!r7UcEaq<*xX}EOzo}{Z!O5cs#0Fd-SDLpva=5$_3D79& zNLzv_+LWOKxzP**n2=R~nKe1UgRDY9YHA?VG)Zu!3!(f-3>0;)bgUDqf@?p(&&$)BrRt}SoFh?%$6PRo1m;lK9_mOtQwxAir+a$P*Z@{hMG=F- z;1mEV6VBcD)0rLsMo|d~vt&}Js+MrsJI@fFsUzLkY=$Zb?%%&(aX(Ix&U6JaDk>@< z8Vh2vC>R69^7m$w{7~Mkt+2c~MQC0Ths4#X&;!9_ufbp(y>4R8gM zT<9FOI+DYoQB+;9cmf$sB%&x}0vUzDP|+wf{6XO{R5D(Ph=a%wbx|DS7d3yA2QR<^ zaj+fWkt$r*Q#fRZsg5+TFaZqQ=q&bpISQyKq6tWFVf+76E|@_L#!)qe zOFXK-F5Ftsu!Sf9N*6+r0c(tsDu7kRs^XMYRh0lW@DEJb`7o&t{MQBiSH}N=^cT!u zNa;*#I3zS&y*Ug|Ivc<%Dgg`n!2$o11N7W%hsMq-$n{?AtP z^5TXy7f)4}PUd*QWulSp|0ihvZ9h}UKNMzgn4WVdghB=(Pl&4<3wAXI)|f(8rP7&R zBsjiF39Rz>~&3PpY0IZ&!7sABqA|NgPi$ zQbV8P>FG>oK;B*qMTo(gcZw%XV}3A44*p~bkI39Op)=>XT0uUG>@_@To;1=Q^mFT6 z`X5yAn6l8hfpz{Tm&N$u2GM`V>^BDgA&TZe@XZ4U6!_y_(?9_K(&yh}^z$-@UlHoa z{oJeiA1{kvYW~GrNA^EmI&yH2g6kXDtlU#9%e?^LeC~yeT(2ng*(v?v~YSDT`eMB34UT#ly$Vwx_bI}eHEgf#{Z7t#O)=s*d!)< R&S^y0M+j+YJ#&4;e*yTfm{2{@E()Ntu73~l!4t%(>C&+L{MWZ(BC``2z$@ZzZYzPJl zhtk}RLR3@$Ba*iVlMKaz5DP$uLS>TZP(X)@XOgr?1R9Zq!$BBKItlLu2~5v8VqE(B zt*yf^T@bggOCx*d+pE-fTvZRd?r*Ch9L73Y{jrk2QGoLOnEsxG?%z4d)WF&E`I`Eu zoNY?a)P8>*qx0oOiz$w9H9{-W|z#8IUWCsAMD{_dKV zn^qHRes4KE^u_bzZ?qS#EC>0iEq_kv+pBx9z4HVgY>&%aL+%qD7Wqq8LC)Jz*4N&h zC%%7jxkYn+(Qx~sRi2lekJXFREU&G*#fCIx+l08VnuJX}haUALZIz~m-M8WWdd8nm zy=<4Ln8;M-^u>+g4<7g5alNG+Be#PZ)wX5J?T1uqm@5j6ExXAGz-p5CnN_Z3ogV|5 zc4P^Wsdt4YU+#7v95G_$vx+3`E=RO0wNF0Uzax)GUgYSMdHT6%gFux!Np?#}4tbRg zykB)tf5TmOGS#&#ZF~o`-)l79t<1BsXv1%5S><7O<(qGEtVp);|C%R|KUJ5>Co-iH zUcO8GAxEs-Ld9F7fCVZ`dTy$c6g>xFLR$A4K+ktP#%@U_w7sTmT-}p@TyHy0uut4Sc-*;B_6j|8CZF*gEUB^yggeWBTEF)}M+DWDB~JExm$kO`-{DvPZ@* zIX(;Q!;W9*+|}OSRQ+bbjK%-3?1~g6cd_W0;f%$Xf_bixua5Jv^|}Mq+OAVYV*=qv zA~TRqb|juH4iCC)WcxqYra!P7fb)pil)>uv5KuPQuBIsKex)aZR-oT{yQr1nPVeeP z)5>q+g|J1gx61n5i>Q|)x61a{e-jf}8=|y${%|EVcV*eUA8%K_<(sU8?lV2XHI3*Y zX>C94N-cKB<=aO(Rk-gj-yBiw?p`Q3mC3ruy&_96mU{1QfB2W|yKGq*Hs>HV{+|S_ zW&3j%^?#EUbH_JB{IB`n>5sX%wW18)yCpQY(Ur8_^h71D>VrOJM8hP(?}iJrI0VhR5!OgPxXC_6Rl{&H!2qPOwH@x|Ay z*}0*`r?X#KvrC^Rn-`xws{5`yx;r60tVdT($$4p^xqUqEZTt3_<;CS@*7Ww7GWero|{Eh50y_fj^V9$A7xOe=&F4zPVA}sDcM$?<$|?>j|4AnBOx{m2gn{ ztp?3adsvX+Z_;#x6A3eo?><8EHfZ#6E)mUcihaZK@g zEW8sqbANy6Y%NhTGd7XK&N%;VSFg_Hi^BG=qs`+!4CxTD#6wkz)Kf>e)nh-7nr|z= zOv|iGJQtYr%w3|3e&-$fqxQmx0MenlCpD+t@pLScG$`|^q=D~)P?y4HXPwQswggkt zFyYi4IW8ZygNZK{++g>P@dk3_bnzHoMfck3JarS$9Mip&lO0v8E9ROo=k>=%TcXSP zxRQj3u^Zf!63g@STf~cmPt-(oLel8@l798E{V9YUy1XMbLEg+P`tg@E2_3O}>BQq& z2Ck3gBvMBz9Jkn8B8O>PO3v=T$Yzhyc<*N}Uoc4qlcn{%G=>b+M*S<#-KM?|eAhTlaRUJ$jYSGSU? z^)#Ewd{us_H~nK?2F0x4#bGmh*t4rfk`|gTCgjPyGHTaaNlDYzCrY>9Z3NQOMtYjU z?6V15(ro|a%Qc4@NU5NF()}mQqftEsf|dS7N%cz2Ovmu9n<5|kMLtKuZdw_)aO5>h zX}kMI1ykKHxAoGvEg(na=Mwf;9_$Ejm$(0&{<;Ybl}bYwwC2P+gcRfQyAxNeIQl@W@pKynF12xRXL*8YP)cSe2ekJF4sAO`EMeUy^g*4dRzqVG=~`co`)ic z=)rf3=Wd$E#YHz!xpCKB$=Q9xBl#ILB6ne3#rPba#XWOO2VFw}~oZ!`8 zD)6$<^C~yoM=CSi=cIS3Nh!_nHT1kbe#Q_&(Y z)1IofqKl{7j51rT%(fUxTs&G)+m&h?5fagWW*XeLBPblj&9`kUeb~!TIht4QbfUbk zq_MWP)T|UToEz%E=)bQxKW5f6dO!M=+^}`kqapj~tmMk@l133pudVL)r?c+%2q1cs zpIo18s|s@RB=k=Y_rC@?$lmIl^o*nzGm7=U^jxpc!i7BDmQoHm z{p1F%?JHZge73W#&Fglem&@<9I%YKLrP=Co4c~~p?>txA*LISGV6s}(N1v5)zKLUe z4|P>?x+wUj_5jd76xz_|J}sM$e}9OuO~B#XZz*&+7XNP?CDyw(m3HV<4)_)fxR(Xx zmZoO<@`X0H?4GPS)Y#Fi`W;!kDL~E^VW;{{*FiW=H6h#d8wQys=bHM zXWWeSvZiiI?e89cU5eh9fF%pPyIneA>OZ?M*IXeI3R4?@;>hce(y07rqFTe|YN-Ws zWJ7g{u-}P5%4F&%8^_X;W#^ggGyRUuHo|JYmGI|#4`-Kb@AoBtc&|8@Eq$U; z)XC8{erEed+h_Y?qlFR*3&&en`_y`@J+~db)7xwLZaLm$a`27ROIzDV)r*>6Qwk5% zOV7YclCRF6CPu!GpS!_yR#DBE32}d)tleXxJyV+t`_6hTp6~fw@crau!07QBg{i@@ z>-xf`7dZ0MHMvG+qZ@KvSZ9}R4}IU@YO-M~$(y*A1A-%V-pI}t*>5BUgNCfZ&_8oZ zs~{f|V21Y~0mdXE1%H?p2z7vi%NRHss(^$$LBK^i$(sp9v9nGHU_oNg{OAM{1I$Ow z=rn>QiRl1<87ma9A_X!*bnQTneM?ws;uNAh8VtnCe>{(Xx@%BT@ZHObP+NVlFKbgFvVFFlltC5}U<}IaXFcb5iIG zrY0FrhoX>x5q@oqKq3HJ3Xw@>I6#mJY(YPNNF>`l>>oyvz3-JD1cSjs|NaMJtU=eX zeqjHcW3lW#EBs9cxDHuefkW3YkjQoFU*C{b8SDuART^6^9Ex0{VZRkosC8{tbcI7v zYzRoj-rp+z8W%V_PPM(k8i?ZU0Y$7h8?f|qW3q#r9S@-U)`M(i^_NijK?ks1vd#pw zrMHGRgYsjpMR9j0fd>JMd1UpQAJwojHniW@z++S;4a7VxTRdc;4 zMq*J|9PUT?Yi-SKW%*3#7-FP;{8TD>^X`Ov79>3U%q9!<3tZi=?hwt*CA6-dIN^Emj!3_;J;AXBelk|bL76pYr%jmgKEK2J&&=dnI&L4+JRa{y~yY_!~Hd@h@qDyRQxBx!@!4WtB0 zS*H?-#i1QD6iu-wYAc4Q^GbUJD#Pvdi?gqrXIY7i>P1@aOxi1`U!1ihqg0ucYP{J( zBZ(6e2f3bX=`Rp>Gtcg*0OmZOh4|zq10!Q8X$!Pcre;duwmL57xA1wq!|9B1&e?!Z zGXrO+e_*$SY5C}XJmqXE{KWQhd6&F9z=)i1T_!g7qx;}0ZVUVJ)v;BMn!cj9z7>=i z&ph3H`p~r27`DXjV7J4$+gHzhv$Y)ROuj*m{O$WdM~8@|*;Dk{dsDIE{MVNH_e9xw zeo2qc47mH-Rw-QisQj5(=DbY*-o<&Njj+ov<_{eVC+%s(dr(T^7W@*oFYkyuGCHj+ ztF>Kx#|!M`TpQRH?Kbhh)k=*rnHUS^6@HCfM9Y8K# zi$8VQwQBfu*ult!(;+;wiYoMPhZPF+)I6*?W5N&t%E38R5heGyPRGW334BfQ@C`~< zG4X)CdBy)uh>;kZ+!6nvW*5c0RC2~iJWs+Uy)~{X^3rb!y{b*^`}Z6&pC`!fi7O6F zCq16auI(Jn)%J*c(LuVMGF4Y!b7-gR0l@L?&OaLd5C?JQ9r z&N!WeRV+J1bH#xzZBhnXcLm%u?2f;We~|iUsjtu^-6U~J`nhd&V?u`J-n-WvZ13(* zxOL2S?j&CGOHYMGY4*udOrCje^OwnUeKP>L>C^tI2yJ_b-RLHzYh`V`tv*9f$*`Ne zI&?Qg!!&ot1bX>#kd(jO?!XfNYs6{eSne<7J3jKnoIG-8hAX8Yu`cUYxJ1=NoAbTj z<(@l#NV!7R{SCV%`nw|I zgkHrhZOXJGGFu{B+%x27qLKPy6?3o7YYy!YyIpwI0JDp+`?NhrIU+-7G5b!}HI#1)I zh}S^k#Ujb}p4qgj;*=dZH^|l2NBTkz4>Fc|F5KilSfF%ZtlLke8sgFNYP;@c6y;#c zK0B^`9Kxc>uQ+zc_=PK=71ag$UrTGK85fncDK3PaZy(?nn0`A$E29l^yYoT)Je|guITLfUi%wkq zlVO`Sko!m^y;Y{;b;FQzj*M>Ur_{H#OPl+{r&+?KQSy&9U1bB`MP91WivClQqFb`T z|BQKi!}}qiwefT9gjSttntrzPDdGB5-lupg58219`;Sg{`;~`Da}=vpR;}z z?HH>(7x(4mvHnQAx6LPOl%&Va9-0jaHw#LPhy|5)Jsx_*xmjh0rqnSpC)J>d&jM3Fdlw;BqUDVK~xzq1#X_wd%!Txp($Qym-=Dpx=kZo}vpTV^gk( z3!VcWXWo~7KG(Yp@!yj%lkdV!h~IeZ#Mc??qI}k;FHJ%ss7xO5^S(M|)unfZhhF=> zZeTobiaK?(SZ$Ogn_Uz-!svgjS(M%A0bh7 z)7)@=nbEH2zO(x-PxhQule!nI80;1@KlpfWVs06=SiNUa)1Y@OepXsa&OYOYe%xRU z-?5mc=r=bK8dyuAAFQ)=YQkXHB;9A6%vO%QDUbP`rXy<&1s}ZIH_7AWt8!YcpaOOy zL@KL@vQ#lvd+QEXw|a!ncd!Vv&45|wjZ$dp8lU8fIQT6l@jKYD4sAYL;hWHZv&euM zJ^IPx!m+7^)3OJ*xQKiey{=y!8Z~n694E`K&L$zB2a)+*{z>ZViti~l`hD#tJ!aV_m<}RSbd!1)?s{0A4*4AJc!OBLvOx0<)!P1jwx02Sgqk46@K-k+b-v`t4eIk z9z_YXZJ6Jh(F$y>OLflw@RqT7cKo30vAqOHkVK6^L4O%~coQDcBw_l^Mn*nL#Z0Vd zuHd^zd^n4W66$D9uqn)`DXX4n-}rfhb$h7bodliBvLC$dCf+oNle0X0-WO(u%p2#V z3yzp%@1_~od8S7_%Gezv;DFwfex~h3;7f}sk+6z^XP+hYW+HoEZJaHVqy8?iBo#_@ zcG2AORDz?k=e^N~8&f&etfF%@^Q{5T%s3CJTLf*q;H4r>e#;QN%Kw&pCiyLSw;boE zqnmE#yeurgd#CV2#C;qt=|bnFEWy+Vp4s7*@|ygvrkp}yJY8@;4)=)tUrzhQ?N57e zo4i@PZ)nW87`3xHKR?B!qOU%Z>rDQ!xwb(J8J@t|9)yYprG)LkayFTYiFGvAKuEM5_%sYnXkPNN$JnFslPDNsj?ZI)^& z(zBU<9$#^4I%~U&n*H&*oSZ-HDVy95eTZC$I$mY7Q`XNZ_V;lb@AHV^-HI4iL%if8 z{B7rZ`ise5FKBFXxC>oQDCrXX{ET*ae2>uU$+{1JmM-QH`=bP?xD=m#SLI5s2+#*T z`D13H3$NJ93vT@*>A3B8qDsGf=sDP{f`%9U->&AIeprm7k99t+HN<#$@9Q%YtCU8f z5bkMc(xpGuKkoC-&wkbOQ0AWEJ1CraGEQXi^T|gu)0Wk-8obB7xp#KCy>h=T0(%@zeyujiX8t6s! zW+(@$!d6I>!7&>Qz@RHAOixvqov|5|NuyCcDNHC*UP&Gyhd>>Ky3@hJB!EWugd*gz zFpwpk=&o!5*7d6l!I>(I%w+l~13*APfP4T-o<{co5K2l)02~P*k#Zo090P2s;sfQp z84{qp6-6j^Kghfp@+&&Y6KGxl#STEo!+~`{>qQcU<_%>F#=Ft{n5r;8KMGM9<&MG< zPy~b=Q9%(ehd{W)<>25Whg4L;BJd;Y&>Nx8o|#C ztbz5l{x?DMU;CLz_@S_mADy~#LWl%_L?y9xV}PzkfEp7C%I-9}7aojnypIo9tK*qq z*aKi(!f-0!B9p?Tl5i{MPlL)_9Z)Ik^Q270dwZzD0_BJ#cf22!3B&1{S-W`oP~=HI zj8%tFDY(_a3MufD9XKMeV}wRuQm7RC-{@D?+4MiCz%g;HEd}cPPcG}R z!w#VT8?(PK_?HM;0fDy;7)-#AI}Hbc{zuP$$LQxp4*q*kg$1y$>3{sA_@$Ate&b00 z+l3{aE;~_8*_D#I{K(QDM3IlbAuECIsSg;+&exTm#Fhv9k>`eX@hE!yCRR0FUV*Wu3 z2lx9=Jk&q%kV+`9$N5)&C^)Fu-(i@4;ishVPdqsMpD;!AKXgW+kzn8PuX3>%EZBKn zhcW4Ru;E1q^I|AqNeKoUi>h>Y$=^SP_0$Q(H*` zja1as)=|VDv=t94qTmXeXpDlEf)?)okKx2_k~5fiI&;NoiYN>QA}OhDsss5y7wSP6 diff --git a/GPU_openmp.pdf b/GPU_openmp.pdf deleted file mode 100644 index 6ce9386f0767f0522c1953f967fae15234bf354c..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 8826 zcmb_B2{@GN_w8!vsw~;kAcid8?3NhGzOQ9a7&C*(m>IKJk{0`w?8z=7${LYMt3(nd zB$Tp7mZX$K|8GQf@BRI^=egfJp6`9nd$#wS^S;hGpRARhfigk`4UugakIjW(pl~SN z?Jz`B6EGvwJlLL4EC{gy3@B7KnF$39s021yk4&VK$T%E?#b%NT-VpzcOovCMJL><) zoGN?!V*R0~?ehrzeMUw`4A$gE#NLN;5EEG3+BJ(=6=x?dO$uz zr7XQ?VfbzKx1eLaxbH46opG;fdlqZzZ+iFj_Re-F4@p)hKl5GX>vHw^iTr{~!)=aY zvmSLLLlgFnp^Fc*M;d19>+rX|ao+sen`8QL=YwoT#XCv{wZa9fBL-$44r>Q}nVTJ| zo4DZwx%RG;&*?(Rrm@aDx8h!&$)kq53fN)cl|+91t`p7f^3=Pos%4gIHez+iYeNp5 zKZe{}zG=6($aq3}g=nz3)r&i>Ba&wxZ=nV^Z4mY?ejq15zWVfIk@5EN^euXYqPx>C zhktd62%uI(TpzkVGKg+&>6Zwq_H&CY*i|^cX2v$0=CHbv8h%fh&zINv1>aq{LaJ+d z(R0}9b?N6SPTo~X);-~RHdQzHZi_?Znk6Y4_Fx`EmXyGEJ$;psQ$BFi)U}+*YLbgo zL)l>m_+w_&>H;r1jRiiIJ)GfjF2r=!hHpA$9f#<8%&bpIc~$CTtFGX?r8vcOsjhWr zHuL%VeBE_oY13WmZ+X`K5Nu)mY(*T_oOfB=U9Pw~t~gx`R%cyWPKD@k#<>Q$dA#D> z&FAp7S~4#aZwbmAGuc<64Amx@U$Tl$F*Zs$(X3?AswLyTZJQhvRr&0tC?YWqzS*f?R&3%GcXzLA8W(x6RS-)ouQ#J! z4$geww;xL&)HPG_cU5Sm=J+l+O8h{%*JYq_d3a++%=5v$@YH?Eo&2#JC2z}{#>G?L zIYSa-?X_Vch-zV!Rv|t$^E_$L6}7>s`M$7X7p5CVRHCM&ZdMd?*q&J-`bZ~)tIwWh zL9)`gtHSOB<+fEY!Viot@|Cqsa!cbP^lQ|DDDMr2uctosUgvolmzc3`!cKb(|Gee~ zroCfd$@Ta)wOQS=f!WCx`wd?|Pi9YT&VEyhT-59PJQ$%gcr!lqsk_T!!12X-dfBU6 zFOCIrdav5ks~hHLuF{<~+ZJaO0tZ6bxhkK=;=9K^10Att-)CxW z*4#eoce~QdlVhn6`>4r3a{E=wZ?hd&zhCuhVmsvq?^AxZ8n2l7+$aBHXW{iiH=%n* zr1;#|iRm9ulBV^tpGa+655ozO#2s3*S!!yxl=U^zlag;%d!t_n-Z0@g<(!ZQM>>2FfwsUudIpPN}ZvAOZ)QBI#U?kU}-jgLoJvvh)V zb2kaO_eI6PO|v}&jlc90r%g291;EZwrqW{IkFrsxfY?j+eQ%nmk=20uyGW1exk?Wg zN&S(;ufuz(@r-PfCtF*YHAiFL>%ae^;P1Qcbk`R4&V*+m(4ScLUcdYl%4M-ddWzWj z&d6T!Y|-v{Y4zL*@%PPJ0;i^%jZ!?)aH|ms*3U(%ntE(Zc3d64`GW*O$?#dj6mW6g>_gX{*}4-hsfp;zJM*za zInP$N`m_a-)^6CJn8Q3bClTFw8MEWPMD~`L1*s56&TXUlGY7A!*%z$MI$xPBApJ0; z9~1Z8SzlaG`Pq%=UAs;~^3-DG)cfd3U9@?^6PI2a)sr#uvXZ%=C}C9lXBntl3fK#!l<|v=?vcJom}Iel>DIr&xE7tV&jO1%2UWt$tp1 z@Q0*y33;k5qy5~>zU-Nk9%gK}*BAAD+mWL0@u3PcTT}aOzpN_xAR|nSY`7OGnvf@* zw1&4cNvcXjS5r8At!}-1&4U7;rg*&YhQQ)r*@#X(V~dZ{rf#Wx{z}nLM&mE2=^Hif zwk$WB3vRgAct%vtMz%s;87aHO&nQ#&+5O!f!tDz7?$+T)%nSxY5ii9k4*2#9>_6*8 z`Y*%x4a00V&BVVO%5~$iEaq#yk&+S6hldyBrh*8BXt4n6{nbtBCEaoxGPhrU97sB4 zoMDJn2AL8gBM=D@AOGx@JyxSXb>DU7-0@J!n00}<5!06sb8i2Z3Dx!M#v>$s~?dXzw(CII*T_a zl)MaGWJMJ+XFQ*Jli$@ASHamFCn=Yry0;8JFB?PMtl50yGgs_73Z6O&C6&zJy~uCJ zs`nkUaj2-O9_aP!l=fo#2wrh(yqofAUl+@{6B+JUJpA@6>vXh7vb*}5xnhUm0gsLi z5k8$_gr3^cDmxkcFr;FUbfxi(uGpmGr5HxoIT`vH$Qt;&q;hZP=V^SGn}tXV1feP4A?x5x8_ zS}IID+8jK@K42gDuDHatHQFqgGS}O6P!VNN$yDqa2CX8s zagc{)-`qZ+sCn7p(I*;G@IgX^%UupMV zteBr5A7qsIUB+~@D9EVj<<~f@e0M~2VC*L;-IC#{hcd7${G%%Poo&4zOzH1BBc2?W z^4gi;*pVceld-*0%5;jNcWGc}SPemBACVB38U7>0KMYMx7CN3fFMJby ztuYyQFyAU4D4j9gQBZcF^xG91*X)|H2rY}94hM=z?>Q zBMZt+b8R3XXjv_;h#zS$$PLsBx}+Ej3YbzzET|KNtF{f~5ESIV;j;XVl*@fNWBx&@ zOJEbIbdMDl%i5ch*#r`}0!94b^-H$uUm5(`1_ZFQGKV5?xMd}mcC{?ZMis)Pv-!nl zX`3snY7n)*u5zc#i~9&HGS@JGrLmoZ-T_4;GS!#NrVt5B=F%gxh)fEDO=m*Yxh$5< zv9to3lfq=Nbv+48C<+Of5thdYBm%Ifkl3CqCkRrNE9ln`iR7Ax`@^Vl_r3IkU@%zd z-~T|2W#}^2PwZcFES9@x)xXIA*C9Vv;Lv3ZByxrN_c!E+3~q$|E{!V}4n;20aNlYu z)QUDsy27C-E(E0F?(YZwG8Z^EPW5SEJw%~-KoLvM25dQQY;JIK;{kNvN{}tB{uU}f z=>V=vR+xacr0LLDl%I1win}`*JP2UqJ3&zDfDeZbmSPkSPxhf-yt%&moi*3Nzg)TG zKMR64`9J%7A9(h_qo<5Ss6kb+NT@0rafn;#d9a{p2%y6va!(-$1P>5_VMOMN{xRiB z;I45gA%HO$_Y|TI&4Wq?T>{v$$=(OR(+9FJr?6O{eU_qxYeNWtUuJ_rse@d>kOEJ$ zJfII40#<-6upb}*M1Ta40eA4o10DbcpaR|i4WI*b8W~^!3@V59n;`%uzyergUos6~ zQTzcGgFqw$Y=G^_B!h21I=}(^fdJqLnMqezvISVql2K3uH%xv%LfrYX6@L`Gzt_9q zj(+#6?n;4-#GY|Nc#Ow$Fuw5Q8^ILetReB@zl3Ai=?rYi;(%Z)|&ghh%Ln zqjxSea*IK|hNAP6vEaiOx9M#)nHS>OyH)VMgM7dJ@iiOZCr%4HX)Mg(RZADe4=&U> z(rzy;nywLW*P_aaDJ8eyDx>|JleM3CT-yd!Z|I;Sp zC`Rmb|9NYytbk$nrW~S#V9d$r%YxYrj~W#ZR>&%#)Nxn~MHU~w!^GhD_=mpC7g8u9a9jtP*S4o0KNayZ^8a3E~jB8@s>6Z1J{vR4yq^+4#d? z(kkyuNEwudK@}2QzZ;=Id>Al6Ww&kPFGSzJjq81^B~)n3!!g(qn5)%*^HFZP4mjx~cwu)NXVhfPW@9 zMP!cfO#6M9dJ##zg57XZk74{i)Y)?TQ~Q+5%_{ByD{RztkyO`(?u2W)eUU2Mi>*GW z>mzn`?qa$5)U)*wdnWXTv88yWHm9f?=c4B9ZF?RiU-ArF_x;7gha$FC&(ME1j-Qqm zIRC9nG92&qDdSX@-`#ba!b#*` z+!E_BG@+rW$1lC*6*eXR0Bi#-T&K%(^PBL87J2mhVm{lG+Awc83MG+Yn{M7&3%t+f ztt+?NjhsIp7nK;CIJP3GJ_)r&^j9{YKsPa^y@j^tH`ls0aRI34FL zIGgI>6OgQF;Q{M^E$~*Dm3TV&Vcg?uq7>^g*{MU)1u`xf^|94qXV)ckXx(erCAr7? zGf`18w!}Y!{A4Eg`lF$IeUI2z56L%D$7^q1+p|@1><`2AZJkFd=^Lea`ebapf?vwv zw%>md#lIlN;E6R*s$Re&>MD0{cpzu8S=6t>v@NcQ@HnmYTW66)hDGAIe6M}Y?SxF- zop;YW+27rja5cz&<^)0aQ+uUNS?-B4Oo4TN-KVjr&MCn2-iKY)A^MIo66kyC=gS}P z)iZjYdBQ6A447_+TN9fej-nTz1jzZ~CHzZ$&yyz1PjC8kdCPm==o1cirZ%QtOsvhh z8Z1*i`oOtyhw{_#;&i~})cTD*m+`!b<>Gpa?anV2^=y#3jI*n3bAp;4dkP&}A9z_c zr)iahOjmPQtnlmDZ)>ygB=-HV`|g=4Q>T!|;*~S6V|07Ah~FqWX9M{%w8bHdnZ_ot zU=pJTKW12+Hl4RZ-w^`te2P}Go4jlmFqacb6vj)4#tuJm+4$^Z;pD-W#7=r+jrn2{ z>lts686)`Mu`~147PWguR&~eXA6MVAQRww(Ui}F_USxFo&&0f46DG|LkA0suNFGvB zh0X?aBpXq7hxE5q13e*z)K<;7a$-QmksT0MeNh!<#YInwJf&7~>!H(Xj%jUbZ+2opS5oM2V7+Frq~H}X2#=Eda?)V`dIX?P(ZINhhD;;%U( z%_z{JDH!9ywv>Ud1oMjod4w!U*p7htWot6TGIfXM3T~??@77%42$A@^yT3;;ghIVH z!J#+?al~(Q=rSjYslD&o!_uw|^Mom!sM$%MiPkqEYetW11TGrnYr7q)%c{edd!cI& z7rhv?e}7A$E=oOY^-=ac8-d>OgWsAhlIkZ!%>+-43BN|M59)fRW_-zf8xzpQ`^Y?n zCow;_`1rZ6Ec^5q`K=-u^$HK)-0E@8Q!p(1kT!7r+xo8HiG}TD;VMsbT^0S`hMm2p zcj~Jw#jtdhZ=`j@t#>^@{q2v}NA+qg(~WbTL$}{d<9kN1^H6+Jzw7Ws8|U&#`86fl zmHBcD={Nf%u0I^Eii-Wz7t|GoAE-NVOP~jd!3NXpm;!8^OK%dp7okrbmfA? z4`~IA9(_EN>-bTNH&J+O+HhO%7nP@GECDKXr*z7z@G58LtzIun;@!-}qbv7`7YHP$ zzcx8r_R6BYEffVj$!e1Co#|MF_)2C@6}oI9#;p!IK0CF)xNzaar+dO8s4QOT7$1Z3 znzFmwd*1lGxy9oYBtGS>d5wp`;8wIgnUpSz#zOw2E*mh5ex*EQ)Fj+>U3 zQ+CX}WE|UlZCg{5^gPgJ36^P*WlVo7&gi9IS;#j&Cb*(0*5BTuA2%yek(P` z>+Pc%p?$Fub}3LUr#h5=#*tIm2>b>TXv5g^0bJ2<4!S40Z zx<4y@61pmiP1vV~K6u0jjem(yRNCMoGAnk$xaMg1U{n;(0;l#sLLo0A>$}R+v^SOC zQx6z-HdwT4qsyJ~>$@Aj&2%nw@{H_1x$WCz+0X(n;!&|FZQG2-w+o2}Q>&S$^S147ra142|uh$I8c;#t-NNmVfDvV`x}l5-AOP=QJkdVNBeI{ zd**mB-W6p9em2j`5E`_|m7tr~dS!&SW=cd0I-w;qA|Jf+@3R>fIa&GQ`A1o!sj!aM ztEY>VsXGL}$sHv*yXbCsCbQ;I`#ZDAOXGPp3&l~_KG*v_x8m8e*Ct?fytk&j=KxFS zoWOu*Wb%Nggfh>E!)q(@`id^!y;C$9(uBh$#XmZmBb4^oD>t}GMOVPpl1KO?Z!>(` z8uyT0pCUN1yVBp;C$E?8>=`yML2a!mEKIei?7SJaF|sgd=0P{c6Q01+5cq|W@kqew z!;uX#_K3sHrhPFm_sbB)rpEjGM*}iocR!aKQ$;OC`sS+J*aIU5^Vwo_Oj0lm7x$vY*UQ~6HaalT8&?@Rk;Ctz?Rcy#V z*BkOuLJhNUD^9kRaKpLLcs_YHUT3Y-UFc#$X|vGB=k$~jN#QqRwUb}V=JQBh;eu3L zDnsg=a%r|8v)fA`dg@eBw!Mnb<||3Z?7x#VyHt)w!Cqgy^{Q*`TwX*=3644Z=-G8s zj0a7s(@MNb9*IJ@r=!VdzwUi6J>(qp8&1oIJW3)|M zo84Z!-w=U4i{s;8U){Z}6wh;4Lw}RE$WyJh_w|L=FXzr1*tXwZeWx#E9k*`yYel_O zJN};LuT+)4a#Osy*-B!Hz`#*I6H`rXe=sZdBD0}xWDg2W3pRD*HVjH3X~FC<=5TX{ zF4>b}bc9K^Jz`-;JmN)EC&9FF5KV0YSjv-?{Rs?Z_oYujEGU@sYf0EcO5&Sj$ zy&2wMaSQeLrqWm%{#vjl5)E+71p_eX5(?W(3x+qhg0ks!suzU~MXIQ)Ae0d(C8#?S zEKL09OfM)x1q%aNGD+?lHeg-GP}hJXG&HbKP2g{spz}deUGNhi_(|~pK>8czZ=`gl z9T*Zg4;qI-rL&=E6)coNU=uy5U^z#H!hc9zB3;JR1h{_s%|idS%?J#0^Z(gu-rn4> z=HhAS(TN;yum(2P`~L*ZzwKud@u$KJ4wJfcLP$h_OeJ%5V}Y(lfEtsC8t!zaHvx=q z0)qk8>I60z_5c`{Fq|g1$fmHVWZcsE)1k6|45$?DdD5T~XdYTHe`ONcoxq{8VK_sp z{VsF{ndZ$xiN+JA>ercUc|C0(F zla@PEpvwQ`vJyVr82ay+{e{7Q2%;qrc=3So1pK_#a1iLf^!$5_e%b-3)eTGS-FQ;o_qem5B%I7Dq`vAqp?sV9DxDxz*}MoMNfkZ z0Q-J$ggP1t$11`RFgP3rV%Tvb2o&>sY^(^NGv!yj^!Gy!qJX`X!(<}+Ckoe*AXtaP z_5=x+f<)nGC)A%wb_ct82n>XKAOCouSPTY*fx1JNVMsMKu=mJ)ptKd38Uh1$=>7^r zs&PAie}iFF|3M1}xBO2$%s=pu>Y%~?#t#KYgPqI2%0OX||9~OY)&2oP!4dz2sbT)1 zGYSpv{%?NnEp;S>2 LSy_Ec1IT{?x>ZA> diff --git a/Simulations/Full_mpi.eps b/Simulations/Full_mpi.eps new file mode 100644 index 0000000..1ffb068 --- /dev/null +++ b/Simulations/Full_mpi.eps @@ -0,0 +1,913 @@ +%!PS-Adobe-2.0 +%%Title: Full_mpi.eps +%%Creator: gnuplot 4.6 patchlevel 0 +%%CreationDate: Wed Dec 16 22:36:38 2015 +%%DocumentFonts: (atend) +%%BoundingBox: 50 50 554 770 +%%Orientation: Landscape +%%Pages: (atend) +%%EndComments +%%BeginProlog +/gnudict 256 dict def +gnudict begin +% +% The following true/false flags may be edited by hand if desired. +% The unit line width and grayscale image gamma correction may also be changed. +% +/Color false def +/Blacktext false def +/Solid false def +/Dashlength 1 def +/Landscape true def +/Level1 false def +/Rounded false def +/ClipToBoundingBox false def +/SuppressPDFMark false def +/TransparentPatterns false def +/gnulinewidth 5.000 def +/userlinewidth gnulinewidth def +/Gamma 1.0 def +/BackgroundColor {-1.000 -1.000 -1.000} def +% +/vshift -46 def +/dl1 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul sub dup 0 le { pop 0.01 } if } if +} def +/dl2 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul add } if +} def +/hpt_ 31.5 def +/vpt_ 31.5 def +/hpt hpt_ def +/vpt vpt_ def +/doclip { + ClipToBoundingBox { + newpath 50 50 moveto 554 50 lineto 554 770 lineto 50 770 lineto closepath + clip + } if +} def +% +% Gnuplot Prolog Version 4.4 (August 2010) +% +%/SuppressPDFMark true def +% +/M {moveto} bind def +/L {lineto} bind def +/R {rmoveto} bind def +/V {rlineto} bind def +/N {newpath moveto} bind def +/Z {closepath} bind def +/C {setrgbcolor} bind def +/f {rlineto fill} bind def +/g {setgray} bind def +/Gshow {show} def % May be redefined later in the file to support UTF-8 +/vpt2 vpt 2 mul def +/hpt2 hpt 2 mul def +/Lshow {currentpoint stroke M 0 vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Rshow {currentpoint stroke M dup stringwidth pop neg vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Cshow {currentpoint stroke M dup stringwidth pop -2 div vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/UP {dup vpt_ mul /vpt exch def hpt_ mul /hpt exch def + /hpt2 hpt 2 mul def /vpt2 vpt 2 mul def} def +/DL {Color {setrgbcolor Solid {pop []} if 0 setdash} + {pop pop pop 0 setgray Solid {pop []} if 0 setdash} ifelse} def +/BL {stroke userlinewidth 2 mul setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/AL {stroke userlinewidth 2 div setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/UL {dup gnulinewidth mul /userlinewidth exch def + dup 1 lt {pop 1} if 10 mul /udl exch def} def +/PL {stroke userlinewidth setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +3.8 setmiterlimit +% Default Line colors +/LCw {1 1 1} def +/LCb {0 0 0} def +/LCa {0 0 0} def +/LC0 {1 0 0} def +/LC1 {0 1 0} def +/LC2 {0 0 1} def +/LC3 {1 0 1} def +/LC4 {0 1 1} def +/LC5 {1 1 0} def +/LC6 {0 0 0} def +/LC7 {1 0.3 0} def +/LC8 {0.5 0.5 0.5} def +% Default Line Types +/LTw {PL [] 1 setgray} def +/LTb {BL [] LCb DL} def +/LTa {AL [1 udl mul 2 udl mul] 0 setdash LCa setrgbcolor} def +/LT0 {PL [] LC0 DL} def +/LT1 {PL [4 dl1 2 dl2] LC1 DL} def +/LT2 {PL [2 dl1 3 dl2] LC2 DL} def +/LT3 {PL [1 dl1 1.5 dl2] LC3 DL} def +/LT4 {PL [6 dl1 2 dl2 1 dl1 2 dl2] LC4 DL} def +/LT5 {PL [3 dl1 3 dl2 1 dl1 3 dl2] LC5 DL} def +/LT6 {PL [2 dl1 2 dl2 2 dl1 6 dl2] LC6 DL} def +/LT7 {PL [1 dl1 2 dl2 6 dl1 2 dl2 1 dl1 2 dl2] LC7 DL} def +/LT8 {PL [2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 4 dl2] LC8 DL} def +/Pnt {stroke [] 0 setdash gsave 1 setlinecap M 0 0 V stroke grestore} def +/Dia {stroke [] 0 setdash 2 copy vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke + Pnt} def +/Pls {stroke [] 0 setdash vpt sub M 0 vpt2 V + currentpoint stroke M + hpt neg vpt neg R hpt2 0 V stroke + } def +/Box {stroke [] 0 setdash 2 copy exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke + Pnt} def +/Crs {stroke [] 0 setdash exch hpt sub exch vpt add M + hpt2 vpt2 neg V currentpoint stroke M + hpt2 neg 0 R hpt2 vpt2 V stroke} def +/TriU {stroke [] 0 setdash 2 copy vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke + Pnt} def +/Star {2 copy Pls Crs} def +/BoxF {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath fill} def +/TriUF {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath fill} def +/TriD {stroke [] 0 setdash 2 copy vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke + Pnt} def +/TriDF {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath fill} def +/DiaF {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath fill} def +/Pent {stroke [] 0 setdash 2 copy gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore Pnt} def +/PentF {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath fill grestore} def +/Circle {stroke [] 0 setdash 2 copy + hpt 0 360 arc stroke Pnt} def +/CircleF {stroke [] 0 setdash hpt 0 360 arc fill} def +/C0 {BL [] 0 setdash 2 copy moveto vpt 90 450 arc} bind def +/C1 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + vpt 0 360 arc closepath} bind def +/C2 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C3 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C4 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C5 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc + 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc} bind def +/C6 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C7 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C8 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C9 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 450 arc closepath fill + vpt 0 360 arc closepath} bind def +/C10 {BL [] 0 setdash 2 copy 2 copy moveto vpt 270 360 arc closepath fill + 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C11 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C12 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C13 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C14 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 360 arc closepath fill + vpt 0 360 arc} bind def +/C15 {BL [] 0 setdash 2 copy vpt 0 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/Rec {newpath 4 2 roll moveto 1 index 0 rlineto 0 exch rlineto + neg 0 rlineto closepath} bind def +/Square {dup Rec} bind def +/Bsquare {vpt sub exch vpt sub exch vpt2 Square} bind def +/S0 {BL [] 0 setdash 2 copy moveto 0 vpt rlineto BL Bsquare} bind def +/S1 {BL [] 0 setdash 2 copy vpt Square fill Bsquare} bind def +/S2 {BL [] 0 setdash 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S3 {BL [] 0 setdash 2 copy exch vpt sub exch vpt2 vpt Rec fill Bsquare} bind def +/S4 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S5 {BL [] 0 setdash 2 copy 2 copy vpt Square fill + exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S6 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S7 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S8 {BL [] 0 setdash 2 copy vpt sub vpt Square fill Bsquare} bind def +/S9 {BL [] 0 setdash 2 copy vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S10 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt Square fill + Bsquare} bind def +/S11 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt2 vpt Rec fill + Bsquare} bind def +/S12 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill Bsquare} bind def +/S13 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S14 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S15 {BL [] 0 setdash 2 copy Bsquare fill Bsquare} bind def +/D0 {gsave translate 45 rotate 0 0 S0 stroke grestore} bind def +/D1 {gsave translate 45 rotate 0 0 S1 stroke grestore} bind def +/D2 {gsave translate 45 rotate 0 0 S2 stroke grestore} bind def +/D3 {gsave translate 45 rotate 0 0 S3 stroke grestore} bind def +/D4 {gsave translate 45 rotate 0 0 S4 stroke grestore} bind def +/D5 {gsave translate 45 rotate 0 0 S5 stroke grestore} bind def +/D6 {gsave translate 45 rotate 0 0 S6 stroke grestore} bind def +/D7 {gsave translate 45 rotate 0 0 S7 stroke grestore} bind def +/D8 {gsave translate 45 rotate 0 0 S8 stroke grestore} bind def +/D9 {gsave translate 45 rotate 0 0 S9 stroke grestore} bind def +/D10 {gsave translate 45 rotate 0 0 S10 stroke grestore} bind def +/D11 {gsave translate 45 rotate 0 0 S11 stroke grestore} bind def +/D12 {gsave translate 45 rotate 0 0 S12 stroke grestore} bind def +/D13 {gsave translate 45 rotate 0 0 S13 stroke grestore} bind def +/D14 {gsave translate 45 rotate 0 0 S14 stroke grestore} bind def +/D15 {gsave translate 45 rotate 0 0 S15 stroke grestore} bind def +/DiaE {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke} def +/BoxE {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke} def +/TriUE {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke} def +/TriDE {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke} def +/PentE {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore} def +/CircE {stroke [] 0 setdash + hpt 0 360 arc stroke} def +/Opaque {gsave closepath 1 setgray fill grestore 0 setgray closepath} def +/DiaW {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V Opaque stroke} def +/BoxW {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V Opaque stroke} def +/TriUW {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V Opaque stroke} def +/TriDW {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V Opaque stroke} def +/PentW {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + Opaque stroke grestore} def +/CircW {stroke [] 0 setdash + hpt 0 360 arc Opaque stroke} def +/BoxFill {gsave Rec 1 setgray fill grestore} def +/Density { + /Fillden exch def + currentrgbcolor + /ColB exch def /ColG exch def /ColR exch def + /ColR ColR Fillden mul Fillden sub 1 add def + /ColG ColG Fillden mul Fillden sub 1 add def + /ColB ColB Fillden mul Fillden sub 1 add def + ColR ColG ColB setrgbcolor} def +/BoxColFill {gsave Rec PolyFill} def +/PolyFill {gsave Density fill grestore grestore} def +/h {rlineto rlineto rlineto gsave closepath fill grestore} bind def +% +% PostScript Level 1 Pattern Fill routine for rectangles +% Usage: x y w h s a XX PatternFill +% x,y = lower left corner of box to be filled +% w,h = width and height of box +% a = angle in degrees between lines and x-axis +% XX = 0/1 for no/yes cross-hatch +% +/PatternFill {gsave /PFa [ 9 2 roll ] def + PFa 0 get PFa 2 get 2 div add PFa 1 get PFa 3 get 2 div add translate + PFa 2 get -2 div PFa 3 get -2 div PFa 2 get PFa 3 get Rec + gsave 1 setgray fill grestore clip + currentlinewidth 0.5 mul setlinewidth + /PFs PFa 2 get dup mul PFa 3 get dup mul add sqrt def + 0 0 M PFa 5 get rotate PFs -2 div dup translate + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 M 0 PFs V} for + 0 PFa 6 get ne { + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 2 1 roll M PFs 0 V} for + } if + stroke grestore} def +% +/languagelevel where + {pop languagelevel} {1} ifelse + 2 lt + {/InterpretLevel1 true def} + {/InterpretLevel1 Level1 def} + ifelse +% +% PostScript level 2 pattern fill definitions +% +/Level2PatternFill { +/Tile8x8 {/PaintType 2 /PatternType 1 /TilingType 1 /BBox [0 0 8 8] /XStep 8 /YStep 8} + bind def +/KeepColor {currentrgbcolor [/Pattern /DeviceRGB] setcolorspace} bind def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke} +>> matrix makepattern +/Pat1 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke + 0 4 M 4 8 L 8 4 L 4 0 L 0 4 L stroke} +>> matrix makepattern +/Pat2 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 0 8 L + 8 8 L 8 0 L 0 0 L fill} +>> matrix makepattern +/Pat3 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 8 M 8 -4 L + 0 12 M 12 0 L stroke} +>> matrix makepattern +/Pat4 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 0 M 8 12 L + 0 -4 M 12 8 L stroke} +>> matrix makepattern +/Pat5 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 8 M 4 -4 L + 0 12 M 8 -4 L 4 12 M 10 0 L stroke} +>> matrix makepattern +/Pat6 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 0 M 4 12 L + 0 -4 M 8 12 L 4 -4 M 10 8 L stroke} +>> matrix makepattern +/Pat7 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 8 -2 M -4 4 L + 12 0 M -4 8 L 12 4 M 0 10 L stroke} +>> matrix makepattern +/Pat8 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 -2 M 12 4 L + -4 0 M 12 8 L -4 4 M 8 10 L stroke} +>> matrix makepattern +/Pat9 exch def +/Pattern1 {PatternBgnd KeepColor Pat1 setpattern} bind def +/Pattern2 {PatternBgnd KeepColor Pat2 setpattern} bind def +/Pattern3 {PatternBgnd KeepColor Pat3 setpattern} bind def +/Pattern4 {PatternBgnd KeepColor Landscape {Pat5} {Pat4} ifelse setpattern} bind def +/Pattern5 {PatternBgnd KeepColor Landscape {Pat4} {Pat5} ifelse setpattern} bind def +/Pattern6 {PatternBgnd KeepColor Landscape {Pat9} {Pat6} ifelse setpattern} bind def +/Pattern7 {PatternBgnd KeepColor Landscape {Pat8} {Pat7} ifelse setpattern} bind def +} def +% +% +%End of PostScript Level 2 code +% +/PatternBgnd { + TransparentPatterns {} {gsave 1 setgray fill grestore} ifelse +} def +% +% Substitute for Level 2 pattern fill codes with +% grayscale if Level 2 support is not selected. +% +/Level1PatternFill { +/Pattern1 {0.250 Density} bind def +/Pattern2 {0.500 Density} bind def +/Pattern3 {0.750 Density} bind def +/Pattern4 {0.125 Density} bind def +/Pattern5 {0.375 Density} bind def +/Pattern6 {0.625 Density} bind def +/Pattern7 {0.875 Density} bind def +} def +% +% Now test for support of Level 2 code +% +Level1 {Level1PatternFill} {Level2PatternFill} ifelse +% +/Symbol-Oblique /Symbol findfont [1 0 .167 1 0 0] makefont +dup length dict begin {1 index /FID eq {pop pop} {def} ifelse} forall +currentdict end definefont pop +/MFshow { + { dup 5 get 3 ge + { 5 get 3 eq {gsave} {grestore} ifelse } + {dup dup 0 get findfont exch 1 get scalefont setfont + [ currentpoint ] exch dup 2 get 0 exch R dup 5 get 2 ne {dup dup 6 + get exch 4 get {Gshow} {stringwidth pop 0 R} ifelse }if dup 5 get 0 eq + {dup 3 get {2 get neg 0 exch R pop} {pop aload pop M} ifelse} {dup 5 + get 1 eq {dup 2 get exch dup 3 get exch 6 get stringwidth pop -2 div + dup 0 R} {dup 6 get stringwidth pop -2 div 0 R 6 get + show 2 index {aload pop M neg 3 -1 roll neg R pop pop} {pop pop pop + pop aload pop M} ifelse }ifelse }ifelse } + ifelse } + forall} def +/Gswidth {dup type /stringtype eq {stringwidth} {pop (n) stringwidth} ifelse} def +/MFwidth {0 exch { dup 5 get 3 ge { 5 get 3 eq { 0 } { pop } ifelse } + {dup 3 get{dup dup 0 get findfont exch 1 get scalefont setfont + 6 get Gswidth pop add} {pop} ifelse} ifelse} forall} def +/MLshow { currentpoint stroke M + 0 exch R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MRshow { currentpoint stroke M + exch dup MFwidth neg 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MCshow { currentpoint stroke M + exch dup MFwidth -2 div 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/XYsave { [( ) 1 2 true false 3 ()] } bind def +/XYrestore { [( ) 1 2 true false 4 ()] } bind def +Level1 SuppressPDFMark or +{} { +/SDict 10 dict def +systemdict /pdfmark known not { + userdict /pdfmark systemdict /cleartomark get put +} if +SDict begin [ + /Title (Full_mpi.eps) + /Subject (gnuplot plot) + /Creator (gnuplot 4.6 patchlevel 0) + /Author (lilia) +% /Producer (gnuplot) +% /Keywords () + /CreationDate (Wed Dec 16 22:36:38 2015) + /DOCINFO pdfmark +end +} ifelse +end +%%EndProlog +%%Page: 1 1 +gnudict begin +gsave +doclip +50 50 translate +0.100 0.100 scale +90 rotate +0 -5040 translate +0 setgray +newpath +(Helvetica) findfont 140 scalefont setfont +BackgroundColor 0 lt 3 1 roll 0 lt exch 0 lt or or not {gsave BackgroundColor C clippath fill grestore} if +1.000 UL +LTb +854 448 M +63 0 V +6030 0 R +-63 0 V +stroke +770 448 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10)] +] -46.7 MRshow +1.000 UL +LTb +854 892 M +31 0 V +6062 0 R +-31 0 V +854 1151 M +31 0 V +6062 0 R +-31 0 V +854 1336 M +31 0 V +6062 0 R +-31 0 V +854 1479 M +31 0 V +6062 0 R +-31 0 V +854 1595 M +31 0 V +6062 0 R +-31 0 V +854 1694 M +31 0 V +6062 0 R +-31 0 V +854 1779 M +31 0 V +6062 0 R +-31 0 V +854 1855 M +31 0 V +6062 0 R +-31 0 V +854 1922 M +63 0 V +6030 0 R +-63 0 V +stroke +770 1922 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 100)] +] -46.7 MRshow +1.000 UL +LTb +854 2366 M +31 0 V +6062 0 R +-31 0 V +854 2626 M +31 0 V +6062 0 R +-31 0 V +854 2810 M +31 0 V +6062 0 R +-31 0 V +854 2953 M +31 0 V +6062 0 R +-31 0 V +854 3070 M +31 0 V +6062 0 R +-31 0 V +854 3168 M +31 0 V +6062 0 R +-31 0 V +854 3254 M +31 0 V +6062 0 R +-31 0 V +854 3329 M +31 0 V +6062 0 R +-31 0 V +854 3397 M +63 0 V +6030 0 R +-63 0 V +stroke +770 3397 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1000)] +] -46.7 MRshow +1.000 UL +LTb +854 3840 M +31 0 V +6062 0 R +-31 0 V +854 4100 M +31 0 V +6062 0 R +-31 0 V +854 4284 M +31 0 V +6062 0 R +-31 0 V +854 4427 M +31 0 V +6062 0 R +-31 0 V +854 4544 M +31 0 V +6062 0 R +-31 0 V +854 4643 M +31 0 V +6062 0 R +-31 0 V +854 4728 M +31 0 V +6062 0 R +-31 0 V +854 4804 M +31 0 V +6062 0 R +-31 0 V +854 4871 M +63 0 V +6030 0 R +-63 0 V +stroke +770 4871 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10000)] +] -46.7 MRshow +1.000 UL +LTb +854 448 M +0 63 V +0 4360 R +0 -63 V +stroke +854 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10000)] +] -46.7 MCshow +1.000 UL +LTb +1465 448 M +0 31 V +0 4392 R +0 -31 V +1823 448 M +0 31 V +0 4392 R +0 -31 V +2077 448 M +0 31 V +0 4392 R +0 -31 V +2274 448 M +0 31 V +0 4392 R +0 -31 V +2434 448 M +0 31 V +0 4392 R +0 -31 V +2570 448 M +0 31 V +0 4392 R +0 -31 V +2688 448 M +0 31 V +0 4392 R +0 -31 V +2792 448 M +0 31 V +0 4392 R +0 -31 V +2885 448 M +0 63 V +0 4360 R +0 -63 V +stroke +2885 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 100000)] +] -46.7 MCshow +1.000 UL +LTb +3496 448 M +0 31 V +0 4392 R +0 -31 V +3854 448 M +0 31 V +0 4392 R +0 -31 V +4108 448 M +0 31 V +0 4392 R +0 -31 V +4305 448 M +0 31 V +0 4392 R +0 -31 V +4465 448 M +0 31 V +0 4392 R +0 -31 V +4601 448 M +0 31 V +0 4392 R +0 -31 V +4719 448 M +0 31 V +0 4392 R +0 -31 V +4823 448 M +0 31 V +0 4392 R +0 -31 V +4916 448 M +0 63 V +0 4360 R +0 -63 V +stroke +4916 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1e+06)] +] -46.7 MCshow +1.000 UL +LTb +5527 448 M +0 31 V +0 4392 R +0 -31 V +5885 448 M +0 31 V +0 4392 R +0 -31 V +6139 448 M +0 31 V +0 4392 R +0 -31 V +6336 448 M +0 31 V +0 4392 R +0 -31 V +6496 448 M +0 31 V +0 4392 R +0 -31 V +6632 448 M +0 31 V +0 4392 R +0 -31 V +6750 448 M +0 31 V +0 4392 R +0 -31 V +6854 448 M +0 31 V +0 4392 R +0 -31 V +6947 448 M +0 63 V +0 4360 R +0 -63 V +stroke +6947 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1e+07)] +] -46.7 MCshow +1.000 UL +LTb +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +LCb setrgbcolor +112 2659 M +currentpoint gsave translate -270 rotate 0 0 moveto +[ [(Helvetica) 140.0 0.0 true true 0 (Execution time in seconds)] +] -46.7 MCshow +grestore +LTb +LCb setrgbcolor +3900 98 M +[ [(Helvetica) 140.0 0.0 true true 0 (Polynomial's degrees)] +] -46.7 MCshow +LTb +1.000 UP +1.000 UL +LTb +% Begin plot #1 +1.000 UP +1.000 UL +LT0 +LCb setrgbcolor +6296 4738 M +[ [(Helvetica) 140.0 0.0 true true 0 (1 GPU)] +] -46.7 MRshow +LT0 +6380 4738 M +399 0 V +2885 1013 M +611 1154 V +612 459 V +357 593 V +254 266 V +197 374 V +161 203 V +136 104 V +2885 1013 Pls +3496 2167 Pls +4108 2626 Pls +4465 3219 Pls +4719 3485 Pls +4916 3859 Pls +5077 4062 Pls +5213 4166 Pls +6579 4738 Pls +% End plot #1 +% Begin plot #2 +1.000 UP +1.000 UL +LT1 +LCb setrgbcolor +6296 4598 M +[ [(Helvetica) 140.0 0.0 true true 0 (2 GPU)] +] -46.7 MRshow +LT1 +6380 4598 M +399 0 V +2885 746 M +611 1021 V +612 491 V +357 638 V +254 212 V +197 323 V +161 219 V +136 111 V +2885 746 Crs +3496 1767 Crs +4108 2258 Crs +4465 2896 Crs +4719 3108 Crs +4916 3431 Crs +5077 3650 Crs +5213 3761 Crs +6579 4598 Crs +% End plot #2 +% Begin plot #3 +1.000 UP +1.000 UL +LT2 +LCb setrgbcolor +6296 4458 M +[ [(Helvetica) 140.0 0.0 true true 0 (3 GPU)] +] -46.7 MRshow +LT2 +6380 4458 M +399 0 V +2885 763 M +611 867 V +612 423 V +357 673 V +254 101 V +197 331 V +161 229 V +136 136 V +2885 763 Star +3496 1630 Star +4108 2053 Star +4465 2726 Star +4719 2827 Star +4916 3158 Star +5077 3387 Star +5213 3523 Star +6579 4458 Star +% End plot #3 +% Begin plot #4 +1.000 UP +1.000 UL +LT3 +LCb setrgbcolor +6296 4318 M +[ [(Helvetica) 140.0 0.0 true true 0 (4 GPU)] +] -46.7 MRshow +LT3 +6380 4318 M +399 0 V +2885 617 M +611 882 V +612 414 V +357 689 V +254 137 V +197 263 V +161 306 V +136 33 V +2885 617 Box +3496 1499 Box +4108 1913 Box +4465 2602 Box +4719 2739 Box +4916 3002 Box +5077 3308 Box +5213 3341 Box +6579 4318 Box +% End plot #4 +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +1.000 UP +1.000 UL +LTb +stroke +grestore +end +showpage +%%Trailer +%%DocumentFonts: Helvetica +%%Pages: 1 diff --git a/Simulations/Full_mpivsomp.eps b/Simulations/Full_mpivsomp.eps new file mode 100644 index 0000000..b5f9e19 --- /dev/null +++ b/Simulations/Full_mpivsomp.eps @@ -0,0 +1,827 @@ +%!PS-Adobe-2.0 +%%Title: Full_mpivsomp.eps +%%Creator: gnuplot 4.6 patchlevel 0 +%%CreationDate: Wed Dec 16 22:55:31 2015 +%%DocumentFonts: (atend) +%%BoundingBox: 50 50 554 770 +%%Orientation: Landscape +%%Pages: (atend) +%%EndComments +%%BeginProlog +/gnudict 256 dict def +gnudict begin +% +% The following true/false flags may be edited by hand if desired. +% The unit line width and grayscale image gamma correction may also be changed. +% +/Color false def +/Blacktext false def +/Solid false def +/Dashlength 1 def +/Landscape true def +/Level1 false def +/Rounded false def +/ClipToBoundingBox false def +/SuppressPDFMark false def +/TransparentPatterns false def +/gnulinewidth 5.000 def +/userlinewidth gnulinewidth def +/Gamma 1.0 def +/BackgroundColor {-1.000 -1.000 -1.000} def +% +/vshift -46 def +/dl1 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul sub dup 0 le { pop 0.01 } if } if +} def +/dl2 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul add } if +} def +/hpt_ 31.5 def +/vpt_ 31.5 def +/hpt hpt_ def +/vpt vpt_ def +/doclip { + ClipToBoundingBox { + newpath 50 50 moveto 554 50 lineto 554 770 lineto 50 770 lineto closepath + clip + } if +} def +% +% Gnuplot Prolog Version 4.4 (August 2010) +% +%/SuppressPDFMark true def +% +/M {moveto} bind def +/L {lineto} bind def +/R {rmoveto} bind def +/V {rlineto} bind def +/N {newpath moveto} bind def +/Z {closepath} bind def +/C {setrgbcolor} bind def +/f {rlineto fill} bind def +/g {setgray} bind def +/Gshow {show} def % May be redefined later in the file to support UTF-8 +/vpt2 vpt 2 mul def +/hpt2 hpt 2 mul def +/Lshow {currentpoint stroke M 0 vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Rshow {currentpoint stroke M dup stringwidth pop neg vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Cshow {currentpoint stroke M dup stringwidth pop -2 div vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/UP {dup vpt_ mul /vpt exch def hpt_ mul /hpt exch def + /hpt2 hpt 2 mul def /vpt2 vpt 2 mul def} def +/DL {Color {setrgbcolor Solid {pop []} if 0 setdash} + {pop pop pop 0 setgray Solid {pop []} if 0 setdash} ifelse} def +/BL {stroke userlinewidth 2 mul setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/AL {stroke userlinewidth 2 div setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/UL {dup gnulinewidth mul /userlinewidth exch def + dup 1 lt {pop 1} if 10 mul /udl exch def} def +/PL {stroke userlinewidth setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +3.8 setmiterlimit +% Default Line colors +/LCw {1 1 1} def +/LCb {0 0 0} def +/LCa {0 0 0} def +/LC0 {1 0 0} def +/LC1 {0 1 0} def +/LC2 {0 0 1} def +/LC3 {1 0 1} def +/LC4 {0 1 1} def +/LC5 {1 1 0} def +/LC6 {0 0 0} def +/LC7 {1 0.3 0} def +/LC8 {0.5 0.5 0.5} def +% Default Line Types +/LTw {PL [] 1 setgray} def +/LTb {BL [] LCb DL} def +/LTa {AL [1 udl mul 2 udl mul] 0 setdash LCa setrgbcolor} def +/LT0 {PL [] LC0 DL} def +/LT1 {PL [4 dl1 2 dl2] LC1 DL} def +/LT2 {PL [2 dl1 3 dl2] LC2 DL} def +/LT3 {PL [1 dl1 1.5 dl2] LC3 DL} def +/LT4 {PL [6 dl1 2 dl2 1 dl1 2 dl2] LC4 DL} def +/LT5 {PL [3 dl1 3 dl2 1 dl1 3 dl2] LC5 DL} def +/LT6 {PL [2 dl1 2 dl2 2 dl1 6 dl2] LC6 DL} def +/LT7 {PL [1 dl1 2 dl2 6 dl1 2 dl2 1 dl1 2 dl2] LC7 DL} def +/LT8 {PL [2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 4 dl2] LC8 DL} def +/Pnt {stroke [] 0 setdash gsave 1 setlinecap M 0 0 V stroke grestore} def +/Dia {stroke [] 0 setdash 2 copy vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke + Pnt} def +/Pls {stroke [] 0 setdash vpt sub M 0 vpt2 V + currentpoint stroke M + hpt neg vpt neg R hpt2 0 V stroke + } def +/Box {stroke [] 0 setdash 2 copy exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke + Pnt} def +/Crs {stroke [] 0 setdash exch hpt sub exch vpt add M + hpt2 vpt2 neg V currentpoint stroke M + hpt2 neg 0 R hpt2 vpt2 V stroke} def +/TriU {stroke [] 0 setdash 2 copy vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke + Pnt} def +/Star {2 copy Pls Crs} def +/BoxF {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath fill} def +/TriUF {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath fill} def +/TriD {stroke [] 0 setdash 2 copy vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke + Pnt} def +/TriDF {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath fill} def +/DiaF {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath fill} def +/Pent {stroke [] 0 setdash 2 copy gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore Pnt} def +/PentF {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath fill grestore} def +/Circle {stroke [] 0 setdash 2 copy + hpt 0 360 arc stroke Pnt} def +/CircleF {stroke [] 0 setdash hpt 0 360 arc fill} def +/C0 {BL [] 0 setdash 2 copy moveto vpt 90 450 arc} bind def +/C1 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + vpt 0 360 arc closepath} bind def +/C2 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C3 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C4 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C5 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc + 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc} bind def +/C6 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C7 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C8 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C9 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 450 arc closepath fill + vpt 0 360 arc closepath} bind def +/C10 {BL [] 0 setdash 2 copy 2 copy moveto vpt 270 360 arc closepath fill + 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C11 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C12 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C13 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C14 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 360 arc closepath fill + vpt 0 360 arc} bind def +/C15 {BL [] 0 setdash 2 copy vpt 0 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/Rec {newpath 4 2 roll moveto 1 index 0 rlineto 0 exch rlineto + neg 0 rlineto closepath} bind def +/Square {dup Rec} bind def +/Bsquare {vpt sub exch vpt sub exch vpt2 Square} bind def +/S0 {BL [] 0 setdash 2 copy moveto 0 vpt rlineto BL Bsquare} bind def +/S1 {BL [] 0 setdash 2 copy vpt Square fill Bsquare} bind def +/S2 {BL [] 0 setdash 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S3 {BL [] 0 setdash 2 copy exch vpt sub exch vpt2 vpt Rec fill Bsquare} bind def +/S4 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S5 {BL [] 0 setdash 2 copy 2 copy vpt Square fill + exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S6 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S7 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S8 {BL [] 0 setdash 2 copy vpt sub vpt Square fill Bsquare} bind def +/S9 {BL [] 0 setdash 2 copy vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S10 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt Square fill + Bsquare} bind def +/S11 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt2 vpt Rec fill + Bsquare} bind def +/S12 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill Bsquare} bind def +/S13 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S14 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S15 {BL [] 0 setdash 2 copy Bsquare fill Bsquare} bind def +/D0 {gsave translate 45 rotate 0 0 S0 stroke grestore} bind def +/D1 {gsave translate 45 rotate 0 0 S1 stroke grestore} bind def +/D2 {gsave translate 45 rotate 0 0 S2 stroke grestore} bind def +/D3 {gsave translate 45 rotate 0 0 S3 stroke grestore} bind def +/D4 {gsave translate 45 rotate 0 0 S4 stroke grestore} bind def +/D5 {gsave translate 45 rotate 0 0 S5 stroke grestore} bind def +/D6 {gsave translate 45 rotate 0 0 S6 stroke grestore} bind def +/D7 {gsave translate 45 rotate 0 0 S7 stroke grestore} bind def +/D8 {gsave translate 45 rotate 0 0 S8 stroke grestore} bind def +/D9 {gsave translate 45 rotate 0 0 S9 stroke grestore} bind def +/D10 {gsave translate 45 rotate 0 0 S10 stroke grestore} bind def +/D11 {gsave translate 45 rotate 0 0 S11 stroke grestore} bind def +/D12 {gsave translate 45 rotate 0 0 S12 stroke grestore} bind def +/D13 {gsave translate 45 rotate 0 0 S13 stroke grestore} bind def +/D14 {gsave translate 45 rotate 0 0 S14 stroke grestore} bind def +/D15 {gsave translate 45 rotate 0 0 S15 stroke grestore} bind def +/DiaE {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke} def +/BoxE {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke} def +/TriUE {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke} def +/TriDE {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke} def +/PentE {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore} def +/CircE {stroke [] 0 setdash + hpt 0 360 arc stroke} def +/Opaque {gsave closepath 1 setgray fill grestore 0 setgray closepath} def +/DiaW {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V Opaque stroke} def +/BoxW {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V Opaque stroke} def +/TriUW {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V Opaque stroke} def +/TriDW {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V Opaque stroke} def +/PentW {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + Opaque stroke grestore} def +/CircW {stroke [] 0 setdash + hpt 0 360 arc Opaque stroke} def +/BoxFill {gsave Rec 1 setgray fill grestore} def +/Density { + /Fillden exch def + currentrgbcolor + /ColB exch def /ColG exch def /ColR exch def + /ColR ColR Fillden mul Fillden sub 1 add def + /ColG ColG Fillden mul Fillden sub 1 add def + /ColB ColB Fillden mul Fillden sub 1 add def + ColR ColG ColB setrgbcolor} def +/BoxColFill {gsave Rec PolyFill} def +/PolyFill {gsave Density fill grestore grestore} def +/h {rlineto rlineto rlineto gsave closepath fill grestore} bind def +% +% PostScript Level 1 Pattern Fill routine for rectangles +% Usage: x y w h s a XX PatternFill +% x,y = lower left corner of box to be filled +% w,h = width and height of box +% a = angle in degrees between lines and x-axis +% XX = 0/1 for no/yes cross-hatch +% +/PatternFill {gsave /PFa [ 9 2 roll ] def + PFa 0 get PFa 2 get 2 div add PFa 1 get PFa 3 get 2 div add translate + PFa 2 get -2 div PFa 3 get -2 div PFa 2 get PFa 3 get Rec + gsave 1 setgray fill grestore clip + currentlinewidth 0.5 mul setlinewidth + /PFs PFa 2 get dup mul PFa 3 get dup mul add sqrt def + 0 0 M PFa 5 get rotate PFs -2 div dup translate + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 M 0 PFs V} for + 0 PFa 6 get ne { + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 2 1 roll M PFs 0 V} for + } if + stroke grestore} def +% +/languagelevel where + {pop languagelevel} {1} ifelse + 2 lt + {/InterpretLevel1 true def} + {/InterpretLevel1 Level1 def} + ifelse +% +% PostScript level 2 pattern fill definitions +% +/Level2PatternFill { +/Tile8x8 {/PaintType 2 /PatternType 1 /TilingType 1 /BBox [0 0 8 8] /XStep 8 /YStep 8} + bind def +/KeepColor {currentrgbcolor [/Pattern /DeviceRGB] setcolorspace} bind def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke} +>> matrix makepattern +/Pat1 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke + 0 4 M 4 8 L 8 4 L 4 0 L 0 4 L stroke} +>> matrix makepattern +/Pat2 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 0 8 L + 8 8 L 8 0 L 0 0 L fill} +>> matrix makepattern +/Pat3 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 8 M 8 -4 L + 0 12 M 12 0 L stroke} +>> matrix makepattern +/Pat4 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 0 M 8 12 L + 0 -4 M 12 8 L stroke} +>> matrix makepattern +/Pat5 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 8 M 4 -4 L + 0 12 M 8 -4 L 4 12 M 10 0 L stroke} +>> matrix makepattern +/Pat6 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 0 M 4 12 L + 0 -4 M 8 12 L 4 -4 M 10 8 L stroke} +>> matrix makepattern +/Pat7 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 8 -2 M -4 4 L + 12 0 M -4 8 L 12 4 M 0 10 L stroke} +>> matrix makepattern +/Pat8 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 -2 M 12 4 L + -4 0 M 12 8 L -4 4 M 8 10 L stroke} +>> matrix makepattern +/Pat9 exch def +/Pattern1 {PatternBgnd KeepColor Pat1 setpattern} bind def +/Pattern2 {PatternBgnd KeepColor Pat2 setpattern} bind def +/Pattern3 {PatternBgnd KeepColor Pat3 setpattern} bind def +/Pattern4 {PatternBgnd KeepColor Landscape {Pat5} {Pat4} ifelse setpattern} bind def +/Pattern5 {PatternBgnd KeepColor Landscape {Pat4} {Pat5} ifelse setpattern} bind def +/Pattern6 {PatternBgnd KeepColor Landscape {Pat9} {Pat6} ifelse setpattern} bind def +/Pattern7 {PatternBgnd KeepColor Landscape {Pat8} {Pat7} ifelse setpattern} bind def +} def +% +% +%End of PostScript Level 2 code +% +/PatternBgnd { + TransparentPatterns {} {gsave 1 setgray fill grestore} ifelse +} def +% +% Substitute for Level 2 pattern fill codes with +% grayscale if Level 2 support is not selected. +% +/Level1PatternFill { +/Pattern1 {0.250 Density} bind def +/Pattern2 {0.500 Density} bind def +/Pattern3 {0.750 Density} bind def +/Pattern4 {0.125 Density} bind def +/Pattern5 {0.375 Density} bind def +/Pattern6 {0.625 Density} bind def +/Pattern7 {0.875 Density} bind def +} def +% +% Now test for support of Level 2 code +% +Level1 {Level1PatternFill} {Level2PatternFill} ifelse +% +/Symbol-Oblique /Symbol findfont [1 0 .167 1 0 0] makefont +dup length dict begin {1 index /FID eq {pop pop} {def} ifelse} forall +currentdict end definefont pop +/MFshow { + { dup 5 get 3 ge + { 5 get 3 eq {gsave} {grestore} ifelse } + {dup dup 0 get findfont exch 1 get scalefont setfont + [ currentpoint ] exch dup 2 get 0 exch R dup 5 get 2 ne {dup dup 6 + get exch 4 get {Gshow} {stringwidth pop 0 R} ifelse }if dup 5 get 0 eq + {dup 3 get {2 get neg 0 exch R pop} {pop aload pop M} ifelse} {dup 5 + get 1 eq {dup 2 get exch dup 3 get exch 6 get stringwidth pop -2 div + dup 0 R} {dup 6 get stringwidth pop -2 div 0 R 6 get + show 2 index {aload pop M neg 3 -1 roll neg R pop pop} {pop pop pop + pop aload pop M} ifelse }ifelse }ifelse } + ifelse } + forall} def +/Gswidth {dup type /stringtype eq {stringwidth} {pop (n) stringwidth} ifelse} def +/MFwidth {0 exch { dup 5 get 3 ge { 5 get 3 eq { 0 } { pop } ifelse } + {dup 3 get{dup dup 0 get findfont exch 1 get scalefont setfont + 6 get Gswidth pop add} {pop} ifelse} ifelse} forall} def +/MLshow { currentpoint stroke M + 0 exch R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MRshow { currentpoint stroke M + exch dup MFwidth neg 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MCshow { currentpoint stroke M + exch dup MFwidth -2 div 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/XYsave { [( ) 1 2 true false 3 ()] } bind def +/XYrestore { [( ) 1 2 true false 4 ()] } bind def +Level1 SuppressPDFMark or +{} { +/SDict 10 dict def +systemdict /pdfmark known not { + userdict /pdfmark systemdict /cleartomark get put +} if +SDict begin [ + /Title (Full_mpivsomp.eps) + /Subject (gnuplot plot) + /Creator (gnuplot 4.6 patchlevel 0) + /Author (lilia) +% /Producer (gnuplot) +% /Keywords () + /CreationDate (Wed Dec 16 22:55:31 2015) + /DOCINFO pdfmark +end +} ifelse +end +%%EndProlog +%%Page: 1 1 +gnudict begin +gsave +doclip +50 50 translate +0.100 0.100 scale +90 rotate +0 -5040 translate +0 setgray +newpath +(Helvetica) findfont 140 scalefont setfont +BackgroundColor 0 lt 3 1 roll 0 lt exch 0 lt or or not {gsave BackgroundColor C clippath fill grestore} if +1.000 UL +LTb +854 448 M +63 0 V +6030 0 R +-63 0 V +stroke +770 448 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10)] +] -46.7 MRshow +1.000 UL +LTb +854 892 M +31 0 V +6062 0 R +-31 0 V +854 1151 M +31 0 V +6062 0 R +-31 0 V +854 1336 M +31 0 V +6062 0 R +-31 0 V +854 1479 M +31 0 V +6062 0 R +-31 0 V +854 1595 M +31 0 V +6062 0 R +-31 0 V +854 1694 M +31 0 V +6062 0 R +-31 0 V +854 1779 M +31 0 V +6062 0 R +-31 0 V +854 1855 M +31 0 V +6062 0 R +-31 0 V +854 1922 M +63 0 V +6030 0 R +-63 0 V +stroke +770 1922 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 100)] +] -46.7 MRshow +1.000 UL +LTb +854 2366 M +31 0 V +6062 0 R +-31 0 V +854 2626 M +31 0 V +6062 0 R +-31 0 V +854 2810 M +31 0 V +6062 0 R +-31 0 V +854 2953 M +31 0 V +6062 0 R +-31 0 V +854 3070 M +31 0 V +6062 0 R +-31 0 V +854 3168 M +31 0 V +6062 0 R +-31 0 V +854 3254 M +31 0 V +6062 0 R +-31 0 V +854 3329 M +31 0 V +6062 0 R +-31 0 V +854 3397 M +63 0 V +6030 0 R +-63 0 V +stroke +770 3397 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1000)] +] -46.7 MRshow +1.000 UL +LTb +854 3840 M +31 0 V +6062 0 R +-31 0 V +854 4100 M +31 0 V +6062 0 R +-31 0 V +854 4284 M +31 0 V +6062 0 R +-31 0 V +854 4427 M +31 0 V +6062 0 R +-31 0 V +854 4544 M +31 0 V +6062 0 R +-31 0 V +854 4643 M +31 0 V +6062 0 R +-31 0 V +854 4728 M +31 0 V +6062 0 R +-31 0 V +854 4804 M +31 0 V +6062 0 R +-31 0 V +854 4871 M +63 0 V +6030 0 R +-63 0 V +stroke +770 4871 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10000)] +] -46.7 MRshow +1.000 UL +LTb +854 448 M +0 63 V +0 4360 R +0 -63 V +stroke +854 308 M +[ [(Helvetica) 140.0 0.0 true true 0 (1)] +] -46.7 MCshow +1.000 UL +LTb +2885 448 M +0 63 V +0 4360 R +0 -63 V +stroke +2885 308 M +[ [(Helvetica) 140.0 0.0 true true 0 (2)] +] -46.7 MCshow +1.000 UL +LTb +4916 448 M +0 63 V +0 4360 R +0 -63 V +stroke +4916 308 M +[ [(Helvetica) 140.0 0.0 true true 0 (3)] +] -46.7 MCshow +1.000 UL +LTb +6947 448 M +0 63 V +0 4360 R +0 -63 V +stroke +6947 308 M +[ [(Helvetica) 140.0 0.0 true true 0 (4)] +] -46.7 MCshow +1.000 UL +LTb +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +LCb setrgbcolor +112 2659 M +currentpoint gsave translate -270 rotate 0 0 moveto +[ [(Helvetica) 140.0 0.0 true true 0 (Execution time in seconds)] +] -46.7 MCshow +grestore +LTb +LCb setrgbcolor +3900 98 M +[ [(Helvetica) 140.0 0.0 true true 0 (Number of GPU)] +] -46.7 MCshow +LTb +1.000 UP +1.000 UL +LTb +% Begin plot #1 +1.000 UP +1.000 UL +LT0 +LCb setrgbcolor +6296 4738 M +[ [(Helvetica) 140.0 0.0 true true 0 (200K MPI)] +] -46.7 MRshow +LT0 +6380 4738 M +399 0 V +854 2167 M +2885 1767 L +4916 1630 L +6947 1499 L +854 2167 Pls +2885 1767 Pls +4916 1630 Pls +6947 1499 Pls +6579 4738 Pls +% End plot #1 +% Begin plot #2 +1.000 UP +1.000 UL +LT1 +LCb setrgbcolor +6296 4598 M +[ [(Helvetica) 140.0 0.0 true true 0 (200K OpenMP)] +] -46.7 MRshow +LT1 +6380 4598 M +399 0 V +854 2188 M +2885 1801 L +4916 1593 L +2031 -39 V +854 2188 Crs +2885 1801 Crs +4916 1593 Crs +6947 1554 Crs +6579 4598 Crs +% End plot #2 +% Begin plot #3 +1.000 UP +1.000 UL +LT2 +LCb setrgbcolor +6296 4458 M +[ [(Helvetica) 140.0 0.0 true true 0 (800K MPI)] +] -46.7 MRshow +LT2 +6380 4458 M +399 0 V +854 3485 M +2885 3108 L +4916 2827 L +2031 -88 V +854 3485 Star +2885 3108 Star +4916 2827 Star +6947 2739 Star +6579 4458 Star +% End plot #3 +% Begin plot #4 +1.000 UP +1.000 UL +LT3 +LCb setrgbcolor +6296 4318 M +[ [(Helvetica) 140.0 0.0 true true 0 (800K OpenMP)] +] -46.7 MRshow +LT3 +6380 4318 M +399 0 V +854 3511 M +2885 3100 L +4916 2861 L +6947 2700 L +854 3511 Box +2885 3100 Box +4916 2861 Box +6947 2700 Box +6579 4318 Box +% End plot #4 +% Begin plot #5 +1.000 UP +1.000 UL +LT4 +LCb setrgbcolor +6296 4178 M +[ [(Helvetica) 140.0 0.0 true true 0 (1.4M MPI)] +] -46.7 MRshow +LT4 +6380 4178 M +399 0 V +854 4166 M +2885 3761 L +4916 3523 L +6947 3341 L +854 4166 BoxF +2885 3761 BoxF +4916 3523 BoxF +6947 3341 BoxF +6579 4178 BoxF +% End plot #5 +% Begin plot #6 +1.000 UP +1.000 UL +LT5 +LCb setrgbcolor +6296 4038 M +[ [(Helvetica) 140.0 0.0 true true 0 (1.4M OpenMP)] +] -46.7 MRshow +LT5 +6380 4038 M +399 0 V +854 4188 M +2885 3765 L +4916 3509 L +6947 3347 L +854 4188 Circle +2885 3765 Circle +4916 3509 Circle +6947 3347 Circle +6579 4038 Circle +% End plot #6 +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +1.000 UP +1.000 UL +LTb +stroke +grestore +end +showpage +%%Trailer +%%DocumentFonts: Helvetica +%%Pages: 1 diff --git a/Simulations/Full_openmp.eps b/Simulations/Full_openmp.eps new file mode 100644 index 0000000..d612e35 --- /dev/null +++ b/Simulations/Full_openmp.eps @@ -0,0 +1,913 @@ +%!PS-Adobe-2.0 +%%Title: Full_openmp.eps +%%Creator: gnuplot 4.6 patchlevel 0 +%%CreationDate: Wed Dec 16 22:38:26 2015 +%%DocumentFonts: (atend) +%%BoundingBox: 50 50 554 770 +%%Orientation: Landscape +%%Pages: (atend) +%%EndComments +%%BeginProlog +/gnudict 256 dict def +gnudict begin +% +% The following true/false flags may be edited by hand if desired. +% The unit line width and grayscale image gamma correction may also be changed. +% +/Color false def +/Blacktext false def +/Solid false def +/Dashlength 1 def +/Landscape true def +/Level1 false def +/Rounded false def +/ClipToBoundingBox false def +/SuppressPDFMark false def +/TransparentPatterns false def +/gnulinewidth 5.000 def +/userlinewidth gnulinewidth def +/Gamma 1.0 def +/BackgroundColor {-1.000 -1.000 -1.000} def +% +/vshift -46 def +/dl1 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul sub dup 0 le { pop 0.01 } if } if +} def +/dl2 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul add } if +} def +/hpt_ 31.5 def +/vpt_ 31.5 def +/hpt hpt_ def +/vpt vpt_ def +/doclip { + ClipToBoundingBox { + newpath 50 50 moveto 554 50 lineto 554 770 lineto 50 770 lineto closepath + clip + } if +} def +% +% Gnuplot Prolog Version 4.4 (August 2010) +% +%/SuppressPDFMark true def +% +/M {moveto} bind def +/L {lineto} bind def +/R {rmoveto} bind def +/V {rlineto} bind def +/N {newpath moveto} bind def +/Z {closepath} bind def +/C {setrgbcolor} bind def +/f {rlineto fill} bind def +/g {setgray} bind def +/Gshow {show} def % May be redefined later in the file to support UTF-8 +/vpt2 vpt 2 mul def +/hpt2 hpt 2 mul def +/Lshow {currentpoint stroke M 0 vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Rshow {currentpoint stroke M dup stringwidth pop neg vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Cshow {currentpoint stroke M dup stringwidth pop -2 div vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/UP {dup vpt_ mul /vpt exch def hpt_ mul /hpt exch def + /hpt2 hpt 2 mul def /vpt2 vpt 2 mul def} def +/DL {Color {setrgbcolor Solid {pop []} if 0 setdash} + {pop pop pop 0 setgray Solid {pop []} if 0 setdash} ifelse} def +/BL {stroke userlinewidth 2 mul setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/AL {stroke userlinewidth 2 div setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/UL {dup gnulinewidth mul /userlinewidth exch def + dup 1 lt {pop 1} if 10 mul /udl exch def} def +/PL {stroke userlinewidth setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +3.8 setmiterlimit +% Default Line colors +/LCw {1 1 1} def +/LCb {0 0 0} def +/LCa {0 0 0} def +/LC0 {1 0 0} def +/LC1 {0 1 0} def +/LC2 {0 0 1} def +/LC3 {1 0 1} def +/LC4 {0 1 1} def +/LC5 {1 1 0} def +/LC6 {0 0 0} def +/LC7 {1 0.3 0} def +/LC8 {0.5 0.5 0.5} def +% Default Line Types +/LTw {PL [] 1 setgray} def +/LTb {BL [] LCb DL} def +/LTa {AL [1 udl mul 2 udl mul] 0 setdash LCa setrgbcolor} def +/LT0 {PL [] LC0 DL} def +/LT1 {PL [4 dl1 2 dl2] LC1 DL} def +/LT2 {PL [2 dl1 3 dl2] LC2 DL} def +/LT3 {PL [1 dl1 1.5 dl2] LC3 DL} def +/LT4 {PL [6 dl1 2 dl2 1 dl1 2 dl2] LC4 DL} def +/LT5 {PL [3 dl1 3 dl2 1 dl1 3 dl2] LC5 DL} def +/LT6 {PL [2 dl1 2 dl2 2 dl1 6 dl2] LC6 DL} def +/LT7 {PL [1 dl1 2 dl2 6 dl1 2 dl2 1 dl1 2 dl2] LC7 DL} def +/LT8 {PL [2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 4 dl2] LC8 DL} def +/Pnt {stroke [] 0 setdash gsave 1 setlinecap M 0 0 V stroke grestore} def +/Dia {stroke [] 0 setdash 2 copy vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke + Pnt} def +/Pls {stroke [] 0 setdash vpt sub M 0 vpt2 V + currentpoint stroke M + hpt neg vpt neg R hpt2 0 V stroke + } def +/Box {stroke [] 0 setdash 2 copy exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke + Pnt} def +/Crs {stroke [] 0 setdash exch hpt sub exch vpt add M + hpt2 vpt2 neg V currentpoint stroke M + hpt2 neg 0 R hpt2 vpt2 V stroke} def +/TriU {stroke [] 0 setdash 2 copy vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke + Pnt} def +/Star {2 copy Pls Crs} def +/BoxF {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath fill} def +/TriUF {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath fill} def +/TriD {stroke [] 0 setdash 2 copy vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke + Pnt} def +/TriDF {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath fill} def +/DiaF {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath fill} def +/Pent {stroke [] 0 setdash 2 copy gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore Pnt} def +/PentF {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath fill grestore} def +/Circle {stroke [] 0 setdash 2 copy + hpt 0 360 arc stroke Pnt} def +/CircleF {stroke [] 0 setdash hpt 0 360 arc fill} def +/C0 {BL [] 0 setdash 2 copy moveto vpt 90 450 arc} bind def +/C1 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + vpt 0 360 arc closepath} bind def +/C2 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C3 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C4 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C5 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc + 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc} bind def +/C6 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C7 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C8 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C9 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 450 arc closepath fill + vpt 0 360 arc closepath} bind def +/C10 {BL [] 0 setdash 2 copy 2 copy moveto vpt 270 360 arc closepath fill + 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C11 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C12 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C13 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C14 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 360 arc closepath fill + vpt 0 360 arc} bind def +/C15 {BL [] 0 setdash 2 copy vpt 0 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/Rec {newpath 4 2 roll moveto 1 index 0 rlineto 0 exch rlineto + neg 0 rlineto closepath} bind def +/Square {dup Rec} bind def +/Bsquare {vpt sub exch vpt sub exch vpt2 Square} bind def +/S0 {BL [] 0 setdash 2 copy moveto 0 vpt rlineto BL Bsquare} bind def +/S1 {BL [] 0 setdash 2 copy vpt Square fill Bsquare} bind def +/S2 {BL [] 0 setdash 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S3 {BL [] 0 setdash 2 copy exch vpt sub exch vpt2 vpt Rec fill Bsquare} bind def +/S4 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S5 {BL [] 0 setdash 2 copy 2 copy vpt Square fill + exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S6 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S7 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S8 {BL [] 0 setdash 2 copy vpt sub vpt Square fill Bsquare} bind def +/S9 {BL [] 0 setdash 2 copy vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S10 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt Square fill + Bsquare} bind def +/S11 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt2 vpt Rec fill + Bsquare} bind def +/S12 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill Bsquare} bind def +/S13 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S14 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S15 {BL [] 0 setdash 2 copy Bsquare fill Bsquare} bind def +/D0 {gsave translate 45 rotate 0 0 S0 stroke grestore} bind def +/D1 {gsave translate 45 rotate 0 0 S1 stroke grestore} bind def +/D2 {gsave translate 45 rotate 0 0 S2 stroke grestore} bind def +/D3 {gsave translate 45 rotate 0 0 S3 stroke grestore} bind def +/D4 {gsave translate 45 rotate 0 0 S4 stroke grestore} bind def +/D5 {gsave translate 45 rotate 0 0 S5 stroke grestore} bind def +/D6 {gsave translate 45 rotate 0 0 S6 stroke grestore} bind def +/D7 {gsave translate 45 rotate 0 0 S7 stroke grestore} bind def +/D8 {gsave translate 45 rotate 0 0 S8 stroke grestore} bind def +/D9 {gsave translate 45 rotate 0 0 S9 stroke grestore} bind def +/D10 {gsave translate 45 rotate 0 0 S10 stroke grestore} bind def +/D11 {gsave translate 45 rotate 0 0 S11 stroke grestore} bind def +/D12 {gsave translate 45 rotate 0 0 S12 stroke grestore} bind def +/D13 {gsave translate 45 rotate 0 0 S13 stroke grestore} bind def +/D14 {gsave translate 45 rotate 0 0 S14 stroke grestore} bind def +/D15 {gsave translate 45 rotate 0 0 S15 stroke grestore} bind def +/DiaE {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke} def +/BoxE {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke} def +/TriUE {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke} def +/TriDE {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke} def +/PentE {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore} def +/CircE {stroke [] 0 setdash + hpt 0 360 arc stroke} def +/Opaque {gsave closepath 1 setgray fill grestore 0 setgray closepath} def +/DiaW {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V Opaque stroke} def +/BoxW {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V Opaque stroke} def +/TriUW {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V Opaque stroke} def +/TriDW {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V Opaque stroke} def +/PentW {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + Opaque stroke grestore} def +/CircW {stroke [] 0 setdash + hpt 0 360 arc Opaque stroke} def +/BoxFill {gsave Rec 1 setgray fill grestore} def +/Density { + /Fillden exch def + currentrgbcolor + /ColB exch def /ColG exch def /ColR exch def + /ColR ColR Fillden mul Fillden sub 1 add def + /ColG ColG Fillden mul Fillden sub 1 add def + /ColB ColB Fillden mul Fillden sub 1 add def + ColR ColG ColB setrgbcolor} def +/BoxColFill {gsave Rec PolyFill} def +/PolyFill {gsave Density fill grestore grestore} def +/h {rlineto rlineto rlineto gsave closepath fill grestore} bind def +% +% PostScript Level 1 Pattern Fill routine for rectangles +% Usage: x y w h s a XX PatternFill +% x,y = lower left corner of box to be filled +% w,h = width and height of box +% a = angle in degrees between lines and x-axis +% XX = 0/1 for no/yes cross-hatch +% +/PatternFill {gsave /PFa [ 9 2 roll ] def + PFa 0 get PFa 2 get 2 div add PFa 1 get PFa 3 get 2 div add translate + PFa 2 get -2 div PFa 3 get -2 div PFa 2 get PFa 3 get Rec + gsave 1 setgray fill grestore clip + currentlinewidth 0.5 mul setlinewidth + /PFs PFa 2 get dup mul PFa 3 get dup mul add sqrt def + 0 0 M PFa 5 get rotate PFs -2 div dup translate + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 M 0 PFs V} for + 0 PFa 6 get ne { + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 2 1 roll M PFs 0 V} for + } if + stroke grestore} def +% +/languagelevel where + {pop languagelevel} {1} ifelse + 2 lt + {/InterpretLevel1 true def} + {/InterpretLevel1 Level1 def} + ifelse +% +% PostScript level 2 pattern fill definitions +% +/Level2PatternFill { +/Tile8x8 {/PaintType 2 /PatternType 1 /TilingType 1 /BBox [0 0 8 8] /XStep 8 /YStep 8} + bind def +/KeepColor {currentrgbcolor [/Pattern /DeviceRGB] setcolorspace} bind def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke} +>> matrix makepattern +/Pat1 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke + 0 4 M 4 8 L 8 4 L 4 0 L 0 4 L stroke} +>> matrix makepattern +/Pat2 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 0 8 L + 8 8 L 8 0 L 0 0 L fill} +>> matrix makepattern +/Pat3 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 8 M 8 -4 L + 0 12 M 12 0 L stroke} +>> matrix makepattern +/Pat4 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 0 M 8 12 L + 0 -4 M 12 8 L stroke} +>> matrix makepattern +/Pat5 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 8 M 4 -4 L + 0 12 M 8 -4 L 4 12 M 10 0 L stroke} +>> matrix makepattern +/Pat6 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 0 M 4 12 L + 0 -4 M 8 12 L 4 -4 M 10 8 L stroke} +>> matrix makepattern +/Pat7 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 8 -2 M -4 4 L + 12 0 M -4 8 L 12 4 M 0 10 L stroke} +>> matrix makepattern +/Pat8 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 -2 M 12 4 L + -4 0 M 12 8 L -4 4 M 8 10 L stroke} +>> matrix makepattern +/Pat9 exch def +/Pattern1 {PatternBgnd KeepColor Pat1 setpattern} bind def +/Pattern2 {PatternBgnd KeepColor Pat2 setpattern} bind def +/Pattern3 {PatternBgnd KeepColor Pat3 setpattern} bind def +/Pattern4 {PatternBgnd KeepColor Landscape {Pat5} {Pat4} ifelse setpattern} bind def +/Pattern5 {PatternBgnd KeepColor Landscape {Pat4} {Pat5} ifelse setpattern} bind def +/Pattern6 {PatternBgnd KeepColor Landscape {Pat9} {Pat6} ifelse setpattern} bind def +/Pattern7 {PatternBgnd KeepColor Landscape {Pat8} {Pat7} ifelse setpattern} bind def +} def +% +% +%End of PostScript Level 2 code +% +/PatternBgnd { + TransparentPatterns {} {gsave 1 setgray fill grestore} ifelse +} def +% +% Substitute for Level 2 pattern fill codes with +% grayscale if Level 2 support is not selected. +% +/Level1PatternFill { +/Pattern1 {0.250 Density} bind def +/Pattern2 {0.500 Density} bind def +/Pattern3 {0.750 Density} bind def +/Pattern4 {0.125 Density} bind def +/Pattern5 {0.375 Density} bind def +/Pattern6 {0.625 Density} bind def +/Pattern7 {0.875 Density} bind def +} def +% +% Now test for support of Level 2 code +% +Level1 {Level1PatternFill} {Level2PatternFill} ifelse +% +/Symbol-Oblique /Symbol findfont [1 0 .167 1 0 0] makefont +dup length dict begin {1 index /FID eq {pop pop} {def} ifelse} forall +currentdict end definefont pop +/MFshow { + { dup 5 get 3 ge + { 5 get 3 eq {gsave} {grestore} ifelse } + {dup dup 0 get findfont exch 1 get scalefont setfont + [ currentpoint ] exch dup 2 get 0 exch R dup 5 get 2 ne {dup dup 6 + get exch 4 get {Gshow} {stringwidth pop 0 R} ifelse }if dup 5 get 0 eq + {dup 3 get {2 get neg 0 exch R pop} {pop aload pop M} ifelse} {dup 5 + get 1 eq {dup 2 get exch dup 3 get exch 6 get stringwidth pop -2 div + dup 0 R} {dup 6 get stringwidth pop -2 div 0 R 6 get + show 2 index {aload pop M neg 3 -1 roll neg R pop pop} {pop pop pop + pop aload pop M} ifelse }ifelse }ifelse } + ifelse } + forall} def +/Gswidth {dup type /stringtype eq {stringwidth} {pop (n) stringwidth} ifelse} def +/MFwidth {0 exch { dup 5 get 3 ge { 5 get 3 eq { 0 } { pop } ifelse } + {dup 3 get{dup dup 0 get findfont exch 1 get scalefont setfont + 6 get Gswidth pop add} {pop} ifelse} ifelse} forall} def +/MLshow { currentpoint stroke M + 0 exch R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MRshow { currentpoint stroke M + exch dup MFwidth neg 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MCshow { currentpoint stroke M + exch dup MFwidth -2 div 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/XYsave { [( ) 1 2 true false 3 ()] } bind def +/XYrestore { [( ) 1 2 true false 4 ()] } bind def +Level1 SuppressPDFMark or +{} { +/SDict 10 dict def +systemdict /pdfmark known not { + userdict /pdfmark systemdict /cleartomark get put +} if +SDict begin [ + /Title (Full_openmp.eps) + /Subject (gnuplot plot) + /Creator (gnuplot 4.6 patchlevel 0) + /Author (lilia) +% /Producer (gnuplot) +% /Keywords () + /CreationDate (Wed Dec 16 22:38:26 2015) + /DOCINFO pdfmark +end +} ifelse +end +%%EndProlog +%%Page: 1 1 +gnudict begin +gsave +doclip +50 50 translate +0.100 0.100 scale +90 rotate +0 -5040 translate +0 setgray +newpath +(Helvetica) findfont 140 scalefont setfont +BackgroundColor 0 lt 3 1 roll 0 lt exch 0 lt or or not {gsave BackgroundColor C clippath fill grestore} if +1.000 UL +LTb +854 448 M +63 0 V +6030 0 R +-63 0 V +stroke +770 448 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10)] +] -46.7 MRshow +1.000 UL +LTb +854 892 M +31 0 V +6062 0 R +-31 0 V +854 1151 M +31 0 V +6062 0 R +-31 0 V +854 1336 M +31 0 V +6062 0 R +-31 0 V +854 1479 M +31 0 V +6062 0 R +-31 0 V +854 1595 M +31 0 V +6062 0 R +-31 0 V +854 1694 M +31 0 V +6062 0 R +-31 0 V +854 1779 M +31 0 V +6062 0 R +-31 0 V +854 1855 M +31 0 V +6062 0 R +-31 0 V +854 1922 M +63 0 V +6030 0 R +-63 0 V +stroke +770 1922 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 100)] +] -46.7 MRshow +1.000 UL +LTb +854 2366 M +31 0 V +6062 0 R +-31 0 V +854 2626 M +31 0 V +6062 0 R +-31 0 V +854 2810 M +31 0 V +6062 0 R +-31 0 V +854 2953 M +31 0 V +6062 0 R +-31 0 V +854 3070 M +31 0 V +6062 0 R +-31 0 V +854 3168 M +31 0 V +6062 0 R +-31 0 V +854 3254 M +31 0 V +6062 0 R +-31 0 V +854 3329 M +31 0 V +6062 0 R +-31 0 V +854 3397 M +63 0 V +6030 0 R +-63 0 V +stroke +770 3397 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1000)] +] -46.7 MRshow +1.000 UL +LTb +854 3840 M +31 0 V +6062 0 R +-31 0 V +854 4100 M +31 0 V +6062 0 R +-31 0 V +854 4284 M +31 0 V +6062 0 R +-31 0 V +854 4427 M +31 0 V +6062 0 R +-31 0 V +854 4544 M +31 0 V +6062 0 R +-31 0 V +854 4643 M +31 0 V +6062 0 R +-31 0 V +854 4728 M +31 0 V +6062 0 R +-31 0 V +854 4804 M +31 0 V +6062 0 R +-31 0 V +854 4871 M +63 0 V +6030 0 R +-63 0 V +stroke +770 4871 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10000)] +] -46.7 MRshow +1.000 UL +LTb +854 448 M +0 63 V +0 4360 R +0 -63 V +stroke +854 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10000)] +] -46.7 MCshow +1.000 UL +LTb +1465 448 M +0 31 V +0 4392 R +0 -31 V +1823 448 M +0 31 V +0 4392 R +0 -31 V +2077 448 M +0 31 V +0 4392 R +0 -31 V +2274 448 M +0 31 V +0 4392 R +0 -31 V +2434 448 M +0 31 V +0 4392 R +0 -31 V +2570 448 M +0 31 V +0 4392 R +0 -31 V +2688 448 M +0 31 V +0 4392 R +0 -31 V +2792 448 M +0 31 V +0 4392 R +0 -31 V +2885 448 M +0 63 V +0 4360 R +0 -63 V +stroke +2885 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 100000)] +] -46.7 MCshow +1.000 UL +LTb +3496 448 M +0 31 V +0 4392 R +0 -31 V +3854 448 M +0 31 V +0 4392 R +0 -31 V +4108 448 M +0 31 V +0 4392 R +0 -31 V +4305 448 M +0 31 V +0 4392 R +0 -31 V +4465 448 M +0 31 V +0 4392 R +0 -31 V +4601 448 M +0 31 V +0 4392 R +0 -31 V +4719 448 M +0 31 V +0 4392 R +0 -31 V +4823 448 M +0 31 V +0 4392 R +0 -31 V +4916 448 M +0 63 V +0 4360 R +0 -63 V +stroke +4916 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1e+06)] +] -46.7 MCshow +1.000 UL +LTb +5527 448 M +0 31 V +0 4392 R +0 -31 V +5885 448 M +0 31 V +0 4392 R +0 -31 V +6139 448 M +0 31 V +0 4392 R +0 -31 V +6336 448 M +0 31 V +0 4392 R +0 -31 V +6496 448 M +0 31 V +0 4392 R +0 -31 V +6632 448 M +0 31 V +0 4392 R +0 -31 V +6750 448 M +0 31 V +0 4392 R +0 -31 V +6854 448 M +0 31 V +0 4392 R +0 -31 V +6947 448 M +0 63 V +0 4360 R +0 -63 V +stroke +6947 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1e+07)] +] -46.7 MCshow +1.000 UL +LTb +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +LCb setrgbcolor +112 2659 M +currentpoint gsave translate -270 rotate 0 0 moveto +[ [(Helvetica) 140.0 0.0 true true 0 (Execution time in seconds)] +] -46.7 MCshow +grestore +LTb +LCb setrgbcolor +3900 98 M +[ [(Helvetica) 140.0 0.0 true true 0 (Polynomial's degrees)] +] -46.7 MCshow +LTb +1.000 UP +1.000 UL +LTb +% Begin plot #1 +1.000 UP +1.000 UL +LT0 +LCb setrgbcolor +6296 4738 M +[ [(Helvetica) 140.0 0.0 true true 0 (1 GPU)] +] -46.7 MRshow +LT0 +6380 4738 M +399 0 V +2885 1017 M +611 1171 V +612 430 V +357 662 V +254 231 V +197 307 V +161 286 V +136 84 V +2885 1017 Pls +3496 2188 Pls +4108 2618 Pls +4465 3280 Pls +4719 3511 Pls +4916 3818 Pls +5077 4104 Pls +5213 4188 Pls +6579 4738 Pls +% End plot #1 +% Begin plot #2 +1.000 UP +1.000 UL +LT1 +LCb setrgbcolor +6296 4598 M +[ [(Helvetica) 140.0 0.0 true true 0 (2 GPU)] +] -46.7 MRshow +LT1 +6380 4598 M +399 0 V +2885 780 M +611 1021 V +612 428 V +357 669 V +254 202 V +197 328 V +161 265 V +136 72 V +2885 780 Crs +3496 1801 Crs +4108 2229 Crs +4465 2898 Crs +4719 3100 Crs +4916 3428 Crs +5077 3693 Crs +5213 3765 Crs +6579 4598 Crs +% End plot #2 +% Begin plot #3 +1.000 UP +1.000 UL +LT2 +LCb setrgbcolor +6296 4458 M +[ [(Helvetica) 140.0 0.0 true true 0 (3 GPU)] +] -46.7 MRshow +LT2 +6380 4458 M +399 0 V +2885 814 M +611 779 V +612 403 V +357 700 V +254 165 V +197 301 V +161 268 V +136 79 V +2885 814 Star +3496 1593 Star +4108 1996 Star +4465 2696 Star +4719 2861 Star +4916 3162 Star +5077 3430 Star +5213 3509 Star +6579 4458 Star +% End plot #3 +% Begin plot #4 +1.000 UP +1.000 UL +LT3 +LCb setrgbcolor +6296 4318 M +[ [(Helvetica) 140.0 0.0 true true 0 (4 GPU)] +] -46.7 MRshow +LT3 +6380 4318 M +399 0 V +2885 642 M +611 912 V +612 300 V +357 727 V +254 119 V +197 285 V +161 305 V +136 57 V +2885 642 Box +3496 1554 Box +4108 1854 Box +4465 2581 Box +4719 2700 Box +4916 2985 Box +5077 3290 Box +5213 3347 Box +6579 4318 Box +% End plot #4 +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +1.000 UP +1.000 UL +LTb +stroke +grestore +end +showpage +%%Trailer +%%DocumentFonts: Helvetica +%%Pages: 1 diff --git a/Simulations/Sparse_mpi.eps b/Simulations/Sparse_mpi.eps new file mode 100644 index 0000000..f9e6d5f --- /dev/null +++ b/Simulations/Sparse_mpi.eps @@ -0,0 +1,955 @@ +%!PS-Adobe-2.0 +%%Title: Sparse_mpi.eps +%%Creator: gnuplot 4.6 patchlevel 0 +%%CreationDate: Wed Dec 16 22:35:02 2015 +%%DocumentFonts: (atend) +%%BoundingBox: 50 50 554 770 +%%Orientation: Landscape +%%Pages: (atend) +%%EndComments +%%BeginProlog +/gnudict 256 dict def +gnudict begin +% +% The following true/false flags may be edited by hand if desired. +% The unit line width and grayscale image gamma correction may also be changed. +% +/Color false def +/Blacktext false def +/Solid false def +/Dashlength 1 def +/Landscape true def +/Level1 false def +/Rounded false def +/ClipToBoundingBox false def +/SuppressPDFMark false def +/TransparentPatterns false def +/gnulinewidth 5.000 def +/userlinewidth gnulinewidth def +/Gamma 1.0 def +/BackgroundColor {-1.000 -1.000 -1.000} def +% +/vshift -46 def +/dl1 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul sub dup 0 le { pop 0.01 } if } if +} def +/dl2 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul add } if +} def +/hpt_ 31.5 def +/vpt_ 31.5 def +/hpt hpt_ def +/vpt vpt_ def +/doclip { + ClipToBoundingBox { + newpath 50 50 moveto 554 50 lineto 554 770 lineto 50 770 lineto closepath + clip + } if +} def +% +% Gnuplot Prolog Version 4.4 (August 2010) +% +%/SuppressPDFMark true def +% +/M {moveto} bind def +/L {lineto} bind def +/R {rmoveto} bind def +/V {rlineto} bind def +/N {newpath moveto} bind def +/Z {closepath} bind def +/C {setrgbcolor} bind def +/f {rlineto fill} bind def +/g {setgray} bind def +/Gshow {show} def % May be redefined later in the file to support UTF-8 +/vpt2 vpt 2 mul def +/hpt2 hpt 2 mul def +/Lshow {currentpoint stroke M 0 vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Rshow {currentpoint stroke M dup stringwidth pop neg vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Cshow {currentpoint stroke M dup stringwidth pop -2 div vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/UP {dup vpt_ mul /vpt exch def hpt_ mul /hpt exch def + /hpt2 hpt 2 mul def /vpt2 vpt 2 mul def} def +/DL {Color {setrgbcolor Solid {pop []} if 0 setdash} + {pop pop pop 0 setgray Solid {pop []} if 0 setdash} ifelse} def +/BL {stroke userlinewidth 2 mul setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/AL {stroke userlinewidth 2 div setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/UL {dup gnulinewidth mul /userlinewidth exch def + dup 1 lt {pop 1} if 10 mul /udl exch def} def +/PL {stroke userlinewidth setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +3.8 setmiterlimit +% Default Line colors +/LCw {1 1 1} def +/LCb {0 0 0} def +/LCa {0 0 0} def +/LC0 {1 0 0} def +/LC1 {0 1 0} def +/LC2 {0 0 1} def +/LC3 {1 0 1} def +/LC4 {0 1 1} def +/LC5 {1 1 0} def +/LC6 {0 0 0} def +/LC7 {1 0.3 0} def +/LC8 {0.5 0.5 0.5} def +% Default Line Types +/LTw {PL [] 1 setgray} def +/LTb {BL [] LCb DL} def +/LTa {AL [1 udl mul 2 udl mul] 0 setdash LCa setrgbcolor} def +/LT0 {PL [] LC0 DL} def +/LT1 {PL [4 dl1 2 dl2] LC1 DL} def +/LT2 {PL [2 dl1 3 dl2] LC2 DL} def +/LT3 {PL [1 dl1 1.5 dl2] LC3 DL} def +/LT4 {PL [6 dl1 2 dl2 1 dl1 2 dl2] LC4 DL} def +/LT5 {PL [3 dl1 3 dl2 1 dl1 3 dl2] LC5 DL} def +/LT6 {PL [2 dl1 2 dl2 2 dl1 6 dl2] LC6 DL} def +/LT7 {PL [1 dl1 2 dl2 6 dl1 2 dl2 1 dl1 2 dl2] LC7 DL} def +/LT8 {PL [2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 4 dl2] LC8 DL} def +/Pnt {stroke [] 0 setdash gsave 1 setlinecap M 0 0 V stroke grestore} def +/Dia {stroke [] 0 setdash 2 copy vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke + Pnt} def +/Pls {stroke [] 0 setdash vpt sub M 0 vpt2 V + currentpoint stroke M + hpt neg vpt neg R hpt2 0 V stroke + } def +/Box {stroke [] 0 setdash 2 copy exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke + Pnt} def +/Crs {stroke [] 0 setdash exch hpt sub exch vpt add M + hpt2 vpt2 neg V currentpoint stroke M + hpt2 neg 0 R hpt2 vpt2 V stroke} def +/TriU {stroke [] 0 setdash 2 copy vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke + Pnt} def +/Star {2 copy Pls Crs} def +/BoxF {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath fill} def +/TriUF {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath fill} def +/TriD {stroke [] 0 setdash 2 copy vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke + Pnt} def +/TriDF {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath fill} def +/DiaF {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath fill} def +/Pent {stroke [] 0 setdash 2 copy gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore Pnt} def +/PentF {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath fill grestore} def +/Circle {stroke [] 0 setdash 2 copy + hpt 0 360 arc stroke Pnt} def +/CircleF {stroke [] 0 setdash hpt 0 360 arc fill} def +/C0 {BL [] 0 setdash 2 copy moveto vpt 90 450 arc} bind def +/C1 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + vpt 0 360 arc closepath} bind def +/C2 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C3 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C4 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C5 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc + 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc} bind def +/C6 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C7 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C8 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C9 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 450 arc closepath fill + vpt 0 360 arc closepath} bind def +/C10 {BL [] 0 setdash 2 copy 2 copy moveto vpt 270 360 arc closepath fill + 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C11 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C12 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C13 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C14 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 360 arc closepath fill + vpt 0 360 arc} bind def +/C15 {BL [] 0 setdash 2 copy vpt 0 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/Rec {newpath 4 2 roll moveto 1 index 0 rlineto 0 exch rlineto + neg 0 rlineto closepath} bind def +/Square {dup Rec} bind def +/Bsquare {vpt sub exch vpt sub exch vpt2 Square} bind def +/S0 {BL [] 0 setdash 2 copy moveto 0 vpt rlineto BL Bsquare} bind def +/S1 {BL [] 0 setdash 2 copy vpt Square fill Bsquare} bind def +/S2 {BL [] 0 setdash 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S3 {BL [] 0 setdash 2 copy exch vpt sub exch vpt2 vpt Rec fill Bsquare} bind def +/S4 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S5 {BL [] 0 setdash 2 copy 2 copy vpt Square fill + exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S6 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S7 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S8 {BL [] 0 setdash 2 copy vpt sub vpt Square fill Bsquare} bind def +/S9 {BL [] 0 setdash 2 copy vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S10 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt Square fill + Bsquare} bind def +/S11 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt2 vpt Rec fill + Bsquare} bind def +/S12 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill Bsquare} bind def +/S13 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S14 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S15 {BL [] 0 setdash 2 copy Bsquare fill Bsquare} bind def +/D0 {gsave translate 45 rotate 0 0 S0 stroke grestore} bind def +/D1 {gsave translate 45 rotate 0 0 S1 stroke grestore} bind def +/D2 {gsave translate 45 rotate 0 0 S2 stroke grestore} bind def +/D3 {gsave translate 45 rotate 0 0 S3 stroke grestore} bind def +/D4 {gsave translate 45 rotate 0 0 S4 stroke grestore} bind def +/D5 {gsave translate 45 rotate 0 0 S5 stroke grestore} bind def +/D6 {gsave translate 45 rotate 0 0 S6 stroke grestore} bind def +/D7 {gsave translate 45 rotate 0 0 S7 stroke grestore} bind def +/D8 {gsave translate 45 rotate 0 0 S8 stroke grestore} bind def +/D9 {gsave translate 45 rotate 0 0 S9 stroke grestore} bind def +/D10 {gsave translate 45 rotate 0 0 S10 stroke grestore} bind def +/D11 {gsave translate 45 rotate 0 0 S11 stroke grestore} bind def +/D12 {gsave translate 45 rotate 0 0 S12 stroke grestore} bind def +/D13 {gsave translate 45 rotate 0 0 S13 stroke grestore} bind def +/D14 {gsave translate 45 rotate 0 0 S14 stroke grestore} bind def +/D15 {gsave translate 45 rotate 0 0 S15 stroke grestore} bind def +/DiaE {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke} def +/BoxE {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke} def +/TriUE {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke} def +/TriDE {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke} def +/PentE {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore} def +/CircE {stroke [] 0 setdash + hpt 0 360 arc stroke} def +/Opaque {gsave closepath 1 setgray fill grestore 0 setgray closepath} def +/DiaW {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V Opaque stroke} def +/BoxW {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V Opaque stroke} def +/TriUW {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V Opaque stroke} def +/TriDW {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V Opaque stroke} def +/PentW {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + Opaque stroke grestore} def +/CircW {stroke [] 0 setdash + hpt 0 360 arc Opaque stroke} def +/BoxFill {gsave Rec 1 setgray fill grestore} def +/Density { + /Fillden exch def + currentrgbcolor + /ColB exch def /ColG exch def /ColR exch def + /ColR ColR Fillden mul Fillden sub 1 add def + /ColG ColG Fillden mul Fillden sub 1 add def + /ColB ColB Fillden mul Fillden sub 1 add def + ColR ColG ColB setrgbcolor} def +/BoxColFill {gsave Rec PolyFill} def +/PolyFill {gsave Density fill grestore grestore} def +/h {rlineto rlineto rlineto gsave closepath fill grestore} bind def +% +% PostScript Level 1 Pattern Fill routine for rectangles +% Usage: x y w h s a XX PatternFill +% x,y = lower left corner of box to be filled +% w,h = width and height of box +% a = angle in degrees between lines and x-axis +% XX = 0/1 for no/yes cross-hatch +% +/PatternFill {gsave /PFa [ 9 2 roll ] def + PFa 0 get PFa 2 get 2 div add PFa 1 get PFa 3 get 2 div add translate + PFa 2 get -2 div PFa 3 get -2 div PFa 2 get PFa 3 get Rec + gsave 1 setgray fill grestore clip + currentlinewidth 0.5 mul setlinewidth + /PFs PFa 2 get dup mul PFa 3 get dup mul add sqrt def + 0 0 M PFa 5 get rotate PFs -2 div dup translate + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 M 0 PFs V} for + 0 PFa 6 get ne { + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 2 1 roll M PFs 0 V} for + } if + stroke grestore} def +% +/languagelevel where + {pop languagelevel} {1} ifelse + 2 lt + {/InterpretLevel1 true def} + {/InterpretLevel1 Level1 def} + ifelse +% +% PostScript level 2 pattern fill definitions +% +/Level2PatternFill { +/Tile8x8 {/PaintType 2 /PatternType 1 /TilingType 1 /BBox [0 0 8 8] /XStep 8 /YStep 8} + bind def +/KeepColor {currentrgbcolor [/Pattern /DeviceRGB] setcolorspace} bind def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke} +>> matrix makepattern +/Pat1 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke + 0 4 M 4 8 L 8 4 L 4 0 L 0 4 L stroke} +>> matrix makepattern +/Pat2 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 0 8 L + 8 8 L 8 0 L 0 0 L fill} +>> matrix makepattern +/Pat3 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 8 M 8 -4 L + 0 12 M 12 0 L stroke} +>> matrix makepattern +/Pat4 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 0 M 8 12 L + 0 -4 M 12 8 L stroke} +>> matrix makepattern +/Pat5 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 8 M 4 -4 L + 0 12 M 8 -4 L 4 12 M 10 0 L stroke} +>> matrix makepattern +/Pat6 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 0 M 4 12 L + 0 -4 M 8 12 L 4 -4 M 10 8 L stroke} +>> matrix makepattern +/Pat7 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 8 -2 M -4 4 L + 12 0 M -4 8 L 12 4 M 0 10 L stroke} +>> matrix makepattern +/Pat8 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 -2 M 12 4 L + -4 0 M 12 8 L -4 4 M 8 10 L stroke} +>> matrix makepattern +/Pat9 exch def +/Pattern1 {PatternBgnd KeepColor Pat1 setpattern} bind def +/Pattern2 {PatternBgnd KeepColor Pat2 setpattern} bind def +/Pattern3 {PatternBgnd KeepColor Pat3 setpattern} bind def +/Pattern4 {PatternBgnd KeepColor Landscape {Pat5} {Pat4} ifelse setpattern} bind def +/Pattern5 {PatternBgnd KeepColor Landscape {Pat4} {Pat5} ifelse setpattern} bind def +/Pattern6 {PatternBgnd KeepColor Landscape {Pat9} {Pat6} ifelse setpattern} bind def +/Pattern7 {PatternBgnd KeepColor Landscape {Pat8} {Pat7} ifelse setpattern} bind def +} def +% +% +%End of PostScript Level 2 code +% +/PatternBgnd { + TransparentPatterns {} {gsave 1 setgray fill grestore} ifelse +} def +% +% Substitute for Level 2 pattern fill codes with +% grayscale if Level 2 support is not selected. +% +/Level1PatternFill { +/Pattern1 {0.250 Density} bind def +/Pattern2 {0.500 Density} bind def +/Pattern3 {0.750 Density} bind def +/Pattern4 {0.125 Density} bind def +/Pattern5 {0.375 Density} bind def +/Pattern6 {0.625 Density} bind def +/Pattern7 {0.875 Density} bind def +} def +% +% Now test for support of Level 2 code +% +Level1 {Level1PatternFill} {Level2PatternFill} ifelse +% +/Symbol-Oblique /Symbol findfont [1 0 .167 1 0 0] makefont +dup length dict begin {1 index /FID eq {pop pop} {def} ifelse} forall +currentdict end definefont pop +/MFshow { + { dup 5 get 3 ge + { 5 get 3 eq {gsave} {grestore} ifelse } + {dup dup 0 get findfont exch 1 get scalefont setfont + [ currentpoint ] exch dup 2 get 0 exch R dup 5 get 2 ne {dup dup 6 + get exch 4 get {Gshow} {stringwidth pop 0 R} ifelse }if dup 5 get 0 eq + {dup 3 get {2 get neg 0 exch R pop} {pop aload pop M} ifelse} {dup 5 + get 1 eq {dup 2 get exch dup 3 get exch 6 get stringwidth pop -2 div + dup 0 R} {dup 6 get stringwidth pop -2 div 0 R 6 get + show 2 index {aload pop M neg 3 -1 roll neg R pop pop} {pop pop pop + pop aload pop M} ifelse }ifelse }ifelse } + ifelse } + forall} def +/Gswidth {dup type /stringtype eq {stringwidth} {pop (n) stringwidth} ifelse} def +/MFwidth {0 exch { dup 5 get 3 ge { 5 get 3 eq { 0 } { pop } ifelse } + {dup 3 get{dup dup 0 get findfont exch 1 get scalefont setfont + 6 get Gswidth pop add} {pop} ifelse} ifelse} forall} def +/MLshow { currentpoint stroke M + 0 exch R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MRshow { currentpoint stroke M + exch dup MFwidth neg 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MCshow { currentpoint stroke M + exch dup MFwidth -2 div 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/XYsave { [( ) 1 2 true false 3 ()] } bind def +/XYrestore { [( ) 1 2 true false 4 ()] } bind def +Level1 SuppressPDFMark or +{} { +/SDict 10 dict def +systemdict /pdfmark known not { + userdict /pdfmark systemdict /cleartomark get put +} if +SDict begin [ + /Title (Sparse_mpi.eps) + /Subject (gnuplot plot) + /Creator (gnuplot 4.6 patchlevel 0) + /Author (lilia) +% /Producer (gnuplot) +% /Keywords () + /CreationDate (Wed Dec 16 22:35:02 2015) + /DOCINFO pdfmark +end +} ifelse +end +%%EndProlog +%%Page: 1 1 +gnudict begin +gsave +doclip +50 50 translate +0.100 0.100 scale +90 rotate +0 -5040 translate +0 setgray +newpath +(Helvetica) findfont 140 scalefont setfont +BackgroundColor 0 lt 3 1 roll 0 lt exch 0 lt or or not {gsave BackgroundColor C clippath fill grestore} if +1.000 UL +LTb +854 448 M +63 0 V +6030 0 R +-63 0 V +stroke +770 448 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1)] +] -46.7 MRshow +1.000 UL +LTb +854 781 M +31 0 V +6062 0 R +-31 0 V +854 976 M +31 0 V +6062 0 R +-31 0 V +854 1114 M +31 0 V +6062 0 R +-31 0 V +854 1221 M +31 0 V +6062 0 R +-31 0 V +854 1308 M +31 0 V +6062 0 R +-31 0 V +854 1382 M +31 0 V +6062 0 R +-31 0 V +854 1447 M +31 0 V +6062 0 R +-31 0 V +854 1503 M +31 0 V +6062 0 R +-31 0 V +854 1554 M +63 0 V +6030 0 R +-63 0 V +stroke +770 1554 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10)] +] -46.7 MRshow +1.000 UL +LTb +854 1887 M +31 0 V +6062 0 R +-31 0 V +854 2081 M +31 0 V +6062 0 R +-31 0 V +854 2219 M +31 0 V +6062 0 R +-31 0 V +854 2327 M +31 0 V +6062 0 R +-31 0 V +854 2414 M +31 0 V +6062 0 R +-31 0 V +854 2488 M +31 0 V +6062 0 R +-31 0 V +854 2552 M +31 0 V +6062 0 R +-31 0 V +854 2609 M +31 0 V +6062 0 R +-31 0 V +854 2660 M +63 0 V +6030 0 R +-63 0 V +stroke +770 2660 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 100)] +] -46.7 MRshow +1.000 UL +LTb +854 2992 M +31 0 V +6062 0 R +-31 0 V +854 3187 M +31 0 V +6062 0 R +-31 0 V +854 3325 M +31 0 V +6062 0 R +-31 0 V +854 3432 M +31 0 V +6062 0 R +-31 0 V +854 3520 M +31 0 V +6062 0 R +-31 0 V +854 3594 M +31 0 V +6062 0 R +-31 0 V +854 3658 M +31 0 V +6062 0 R +-31 0 V +854 3715 M +31 0 V +6062 0 R +-31 0 V +854 3765 M +63 0 V +6030 0 R +-63 0 V +stroke +770 3765 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1000)] +] -46.7 MRshow +1.000 UL +LTb +854 4098 M +31 0 V +6062 0 R +-31 0 V +854 4293 M +31 0 V +6062 0 R +-31 0 V +854 4431 M +31 0 V +6062 0 R +-31 0 V +854 4538 M +31 0 V +6062 0 R +-31 0 V +854 4626 M +31 0 V +6062 0 R +-31 0 V +854 4700 M +31 0 V +6062 0 R +-31 0 V +854 4764 M +31 0 V +6062 0 R +-31 0 V +854 4820 M +31 0 V +6062 0 R +-31 0 V +854 4871 M +63 0 V +6030 0 R +-63 0 V +stroke +770 4871 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10000)] +] -46.7 MRshow +1.000 UL +LTb +854 448 M +0 63 V +0 4360 R +0 -63 V +stroke +854 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10000)] +] -46.7 MCshow +1.000 UL +LTb +1465 448 M +0 31 V +0 4392 R +0 -31 V +1823 448 M +0 31 V +0 4392 R +0 -31 V +2077 448 M +0 31 V +0 4392 R +0 -31 V +2274 448 M +0 31 V +0 4392 R +0 -31 V +2434 448 M +0 31 V +0 4392 R +0 -31 V +2570 448 M +0 31 V +0 4392 R +0 -31 V +2688 448 M +0 31 V +0 4392 R +0 -31 V +2792 448 M +0 31 V +0 4392 R +0 -31 V +2885 448 M +0 63 V +0 4360 R +0 -63 V +stroke +2885 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 100000)] +] -46.7 MCshow +1.000 UL +LTb +3496 448 M +0 31 V +0 4392 R +0 -31 V +3854 448 M +0 31 V +0 4392 R +0 -31 V +4108 448 M +0 31 V +0 4392 R +0 -31 V +4305 448 M +0 31 V +0 4392 R +0 -31 V +4465 448 M +0 31 V +0 4392 R +0 -31 V +4601 448 M +0 31 V +0 4392 R +0 -31 V +4719 448 M +0 31 V +0 4392 R +0 -31 V +4823 448 M +0 31 V +0 4392 R +0 -31 V +4916 448 M +0 63 V +0 4360 R +0 -63 V +stroke +4916 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1e+06)] +] -46.7 MCshow +1.000 UL +LTb +5527 448 M +0 31 V +0 4392 R +0 -31 V +5885 448 M +0 31 V +0 4392 R +0 -31 V +6139 448 M +0 31 V +0 4392 R +0 -31 V +6336 448 M +0 31 V +0 4392 R +0 -31 V +6496 448 M +0 31 V +0 4392 R +0 -31 V +6632 448 M +0 31 V +0 4392 R +0 -31 V +6750 448 M +0 31 V +0 4392 R +0 -31 V +6854 448 M +0 31 V +0 4392 R +0 -31 V +6947 448 M +0 63 V +0 4360 R +0 -63 V +stroke +6947 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1e+07)] +] -46.7 MCshow +1.000 UL +LTb +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +LCb setrgbcolor +112 2659 M +currentpoint gsave translate -270 rotate 0 0 moveto +[ [(Helvetica) 140.0 0.0 true true 0 (Execution time in seconds)] +] -46.7 MCshow +grestore +LTb +LCb setrgbcolor +3900 98 M +[ [(Helvetica) 140.0 0.0 true true 0 (Polynomial's degrees)] +] -46.7 MCshow +LTb +1.000 UP +1.000 UL +LTb +% Begin plot #1 +1.000 UP +1.000 UL +LT0 +LCb setrgbcolor +6296 4738 M +[ [(Helvetica) 140.0 0.0 true true 0 (1 GPU)] +] -46.7 MRshow +LT0 +6380 4738 M +399 0 V +2885 1782 M +611 660 V +612 942 V +357 171 V +254 453 V +197 312 V +161 100 V +136 -92 V +2885 1782 Pls +3496 2442 Pls +4108 3384 Pls +4465 3555 Pls +4719 4008 Pls +4916 4320 Pls +5077 4420 Pls +5213 4328 Pls +6579 4738 Pls +% End plot #1 +% Begin plot #2 +1.000 UP +1.000 UL +LT1 +LCb setrgbcolor +6296 4598 M +[ [(Helvetica) 140.0 0.0 true true 0 (2 GPU)] +] -46.7 MRshow +LT1 +6380 4598 M +399 0 V +2885 1484 M +611 747 V +612 525 V +357 426 V +254 443 V +197 41 V +161 339 V +136 91 V +2885 1484 Crs +3496 2231 Crs +4108 2756 Crs +4465 3182 Crs +4719 3625 Crs +4916 3666 Crs +5077 4005 Crs +5213 4096 Crs +6579 4598 Crs +% End plot #2 +% Begin plot #3 +1.000 UP +1.000 UL +LT2 +LCb setrgbcolor +6296 4458 M +[ [(Helvetica) 140.0 0.0 true true 0 (3 GPU)] +] -46.7 MRshow +LT2 +6380 4458 M +399 0 V +2885 1391 M +611 823 V +612 345 V +357 418 V +254 497 V +197 -2 V +161 524 V +136 26 V +2885 1391 Star +3496 2214 Star +4108 2559 Star +4465 2977 Star +4719 3474 Star +4916 3472 Star +5077 3996 Star +5213 4022 Star +6579 4458 Star +% End plot #3 +% Begin plot #4 +1.000 UP +1.000 UL +LT3 +LCb setrgbcolor +6296 4318 M +[ [(Helvetica) 140.0 0.0 true true 0 (4 GPU)] +] -46.7 MRshow +LT3 +6380 4318 M +399 0 V +2885 1181 M +611 742 V +612 519 V +357 423 V +254 293 V +197 213 V +161 666 V +136 -84 V +2885 1181 Box +3496 1923 Box +4108 2442 Box +4465 2865 Box +4719 3158 Box +4916 3371 Box +5077 4037 Box +5213 3953 Box +6579 4318 Box +% End plot #4 +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +1.000 UP +1.000 UL +LTb +stroke +grestore +end +showpage +%%Trailer +%%DocumentFonts: Helvetica +%%Pages: 1 diff --git a/Simulations/Sparse_mpivsomp.eps b/Simulations/Sparse_mpivsomp.eps new file mode 100644 index 0000000..8a99ac7 --- /dev/null +++ b/Simulations/Sparse_mpivsomp.eps @@ -0,0 +1,827 @@ +%!PS-Adobe-2.0 +%%Title: Sparse_mpivsomp.eps +%%Creator: gnuplot 4.6 patchlevel 0 +%%CreationDate: Wed Dec 16 22:52:50 2015 +%%DocumentFonts: (atend) +%%BoundingBox: 50 50 554 770 +%%Orientation: Landscape +%%Pages: (atend) +%%EndComments +%%BeginProlog +/gnudict 256 dict def +gnudict begin +% +% The following true/false flags may be edited by hand if desired. +% The unit line width and grayscale image gamma correction may also be changed. +% +/Color false def +/Blacktext false def +/Solid false def +/Dashlength 1 def +/Landscape true def +/Level1 false def +/Rounded false def +/ClipToBoundingBox false def +/SuppressPDFMark false def +/TransparentPatterns false def +/gnulinewidth 5.000 def +/userlinewidth gnulinewidth def +/Gamma 1.0 def +/BackgroundColor {-1.000 -1.000 -1.000} def +% +/vshift -46 def +/dl1 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul sub dup 0 le { pop 0.01 } if } if +} def +/dl2 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul add } if +} def +/hpt_ 31.5 def +/vpt_ 31.5 def +/hpt hpt_ def +/vpt vpt_ def +/doclip { + ClipToBoundingBox { + newpath 50 50 moveto 554 50 lineto 554 770 lineto 50 770 lineto closepath + clip + } if +} def +% +% Gnuplot Prolog Version 4.4 (August 2010) +% +%/SuppressPDFMark true def +% +/M {moveto} bind def +/L {lineto} bind def +/R {rmoveto} bind def +/V {rlineto} bind def +/N {newpath moveto} bind def +/Z {closepath} bind def +/C {setrgbcolor} bind def +/f {rlineto fill} bind def +/g {setgray} bind def +/Gshow {show} def % May be redefined later in the file to support UTF-8 +/vpt2 vpt 2 mul def +/hpt2 hpt 2 mul def +/Lshow {currentpoint stroke M 0 vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Rshow {currentpoint stroke M dup stringwidth pop neg vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Cshow {currentpoint stroke M dup stringwidth pop -2 div vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/UP {dup vpt_ mul /vpt exch def hpt_ mul /hpt exch def + /hpt2 hpt 2 mul def /vpt2 vpt 2 mul def} def +/DL {Color {setrgbcolor Solid {pop []} if 0 setdash} + {pop pop pop 0 setgray Solid {pop []} if 0 setdash} ifelse} def +/BL {stroke userlinewidth 2 mul setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/AL {stroke userlinewidth 2 div setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/UL {dup gnulinewidth mul /userlinewidth exch def + dup 1 lt {pop 1} if 10 mul /udl exch def} def +/PL {stroke userlinewidth setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +3.8 setmiterlimit +% Default Line colors +/LCw {1 1 1} def +/LCb {0 0 0} def +/LCa {0 0 0} def +/LC0 {1 0 0} def +/LC1 {0 1 0} def +/LC2 {0 0 1} def +/LC3 {1 0 1} def +/LC4 {0 1 1} def +/LC5 {1 1 0} def +/LC6 {0 0 0} def +/LC7 {1 0.3 0} def +/LC8 {0.5 0.5 0.5} def +% Default Line Types +/LTw {PL [] 1 setgray} def +/LTb {BL [] LCb DL} def +/LTa {AL [1 udl mul 2 udl mul] 0 setdash LCa setrgbcolor} def +/LT0 {PL [] LC0 DL} def +/LT1 {PL [4 dl1 2 dl2] LC1 DL} def +/LT2 {PL [2 dl1 3 dl2] LC2 DL} def +/LT3 {PL [1 dl1 1.5 dl2] LC3 DL} def +/LT4 {PL [6 dl1 2 dl2 1 dl1 2 dl2] LC4 DL} def +/LT5 {PL [3 dl1 3 dl2 1 dl1 3 dl2] LC5 DL} def +/LT6 {PL [2 dl1 2 dl2 2 dl1 6 dl2] LC6 DL} def +/LT7 {PL [1 dl1 2 dl2 6 dl1 2 dl2 1 dl1 2 dl2] LC7 DL} def +/LT8 {PL [2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 4 dl2] LC8 DL} def +/Pnt {stroke [] 0 setdash gsave 1 setlinecap M 0 0 V stroke grestore} def +/Dia {stroke [] 0 setdash 2 copy vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke + Pnt} def +/Pls {stroke [] 0 setdash vpt sub M 0 vpt2 V + currentpoint stroke M + hpt neg vpt neg R hpt2 0 V stroke + } def +/Box {stroke [] 0 setdash 2 copy exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke + Pnt} def +/Crs {stroke [] 0 setdash exch hpt sub exch vpt add M + hpt2 vpt2 neg V currentpoint stroke M + hpt2 neg 0 R hpt2 vpt2 V stroke} def +/TriU {stroke [] 0 setdash 2 copy vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke + Pnt} def +/Star {2 copy Pls Crs} def +/BoxF {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath fill} def +/TriUF {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath fill} def +/TriD {stroke [] 0 setdash 2 copy vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke + Pnt} def +/TriDF {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath fill} def +/DiaF {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath fill} def +/Pent {stroke [] 0 setdash 2 copy gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore Pnt} def +/PentF {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath fill grestore} def +/Circle {stroke [] 0 setdash 2 copy + hpt 0 360 arc stroke Pnt} def +/CircleF {stroke [] 0 setdash hpt 0 360 arc fill} def +/C0 {BL [] 0 setdash 2 copy moveto vpt 90 450 arc} bind def +/C1 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + vpt 0 360 arc closepath} bind def +/C2 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C3 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C4 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C5 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc + 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc} bind def +/C6 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C7 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C8 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C9 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 450 arc closepath fill + vpt 0 360 arc closepath} bind def +/C10 {BL [] 0 setdash 2 copy 2 copy moveto vpt 270 360 arc closepath fill + 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C11 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C12 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C13 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C14 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 360 arc closepath fill + vpt 0 360 arc} bind def +/C15 {BL [] 0 setdash 2 copy vpt 0 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/Rec {newpath 4 2 roll moveto 1 index 0 rlineto 0 exch rlineto + neg 0 rlineto closepath} bind def +/Square {dup Rec} bind def +/Bsquare {vpt sub exch vpt sub exch vpt2 Square} bind def +/S0 {BL [] 0 setdash 2 copy moveto 0 vpt rlineto BL Bsquare} bind def +/S1 {BL [] 0 setdash 2 copy vpt Square fill Bsquare} bind def +/S2 {BL [] 0 setdash 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S3 {BL [] 0 setdash 2 copy exch vpt sub exch vpt2 vpt Rec fill Bsquare} bind def +/S4 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S5 {BL [] 0 setdash 2 copy 2 copy vpt Square fill + exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S6 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S7 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S8 {BL [] 0 setdash 2 copy vpt sub vpt Square fill Bsquare} bind def +/S9 {BL [] 0 setdash 2 copy vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S10 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt Square fill + Bsquare} bind def +/S11 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt2 vpt Rec fill + Bsquare} bind def +/S12 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill Bsquare} bind def +/S13 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S14 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S15 {BL [] 0 setdash 2 copy Bsquare fill Bsquare} bind def +/D0 {gsave translate 45 rotate 0 0 S0 stroke grestore} bind def +/D1 {gsave translate 45 rotate 0 0 S1 stroke grestore} bind def +/D2 {gsave translate 45 rotate 0 0 S2 stroke grestore} bind def +/D3 {gsave translate 45 rotate 0 0 S3 stroke grestore} bind def +/D4 {gsave translate 45 rotate 0 0 S4 stroke grestore} bind def +/D5 {gsave translate 45 rotate 0 0 S5 stroke grestore} bind def +/D6 {gsave translate 45 rotate 0 0 S6 stroke grestore} bind def +/D7 {gsave translate 45 rotate 0 0 S7 stroke grestore} bind def +/D8 {gsave translate 45 rotate 0 0 S8 stroke grestore} bind def +/D9 {gsave translate 45 rotate 0 0 S9 stroke grestore} bind def +/D10 {gsave translate 45 rotate 0 0 S10 stroke grestore} bind def +/D11 {gsave translate 45 rotate 0 0 S11 stroke grestore} bind def +/D12 {gsave translate 45 rotate 0 0 S12 stroke grestore} bind def +/D13 {gsave translate 45 rotate 0 0 S13 stroke grestore} bind def +/D14 {gsave translate 45 rotate 0 0 S14 stroke grestore} bind def +/D15 {gsave translate 45 rotate 0 0 S15 stroke grestore} bind def +/DiaE {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke} def +/BoxE {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke} def +/TriUE {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke} def +/TriDE {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke} def +/PentE {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore} def +/CircE {stroke [] 0 setdash + hpt 0 360 arc stroke} def +/Opaque {gsave closepath 1 setgray fill grestore 0 setgray closepath} def +/DiaW {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V Opaque stroke} def +/BoxW {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V Opaque stroke} def +/TriUW {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V Opaque stroke} def +/TriDW {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V Opaque stroke} def +/PentW {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + Opaque stroke grestore} def +/CircW {stroke [] 0 setdash + hpt 0 360 arc Opaque stroke} def +/BoxFill {gsave Rec 1 setgray fill grestore} def +/Density { + /Fillden exch def + currentrgbcolor + /ColB exch def /ColG exch def /ColR exch def + /ColR ColR Fillden mul Fillden sub 1 add def + /ColG ColG Fillden mul Fillden sub 1 add def + /ColB ColB Fillden mul Fillden sub 1 add def + ColR ColG ColB setrgbcolor} def +/BoxColFill {gsave Rec PolyFill} def +/PolyFill {gsave Density fill grestore grestore} def +/h {rlineto rlineto rlineto gsave closepath fill grestore} bind def +% +% PostScript Level 1 Pattern Fill routine for rectangles +% Usage: x y w h s a XX PatternFill +% x,y = lower left corner of box to be filled +% w,h = width and height of box +% a = angle in degrees between lines and x-axis +% XX = 0/1 for no/yes cross-hatch +% +/PatternFill {gsave /PFa [ 9 2 roll ] def + PFa 0 get PFa 2 get 2 div add PFa 1 get PFa 3 get 2 div add translate + PFa 2 get -2 div PFa 3 get -2 div PFa 2 get PFa 3 get Rec + gsave 1 setgray fill grestore clip + currentlinewidth 0.5 mul setlinewidth + /PFs PFa 2 get dup mul PFa 3 get dup mul add sqrt def + 0 0 M PFa 5 get rotate PFs -2 div dup translate + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 M 0 PFs V} for + 0 PFa 6 get ne { + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 2 1 roll M PFs 0 V} for + } if + stroke grestore} def +% +/languagelevel where + {pop languagelevel} {1} ifelse + 2 lt + {/InterpretLevel1 true def} + {/InterpretLevel1 Level1 def} + ifelse +% +% PostScript level 2 pattern fill definitions +% +/Level2PatternFill { +/Tile8x8 {/PaintType 2 /PatternType 1 /TilingType 1 /BBox [0 0 8 8] /XStep 8 /YStep 8} + bind def +/KeepColor {currentrgbcolor [/Pattern /DeviceRGB] setcolorspace} bind def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke} +>> matrix makepattern +/Pat1 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke + 0 4 M 4 8 L 8 4 L 4 0 L 0 4 L stroke} +>> matrix makepattern +/Pat2 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 0 8 L + 8 8 L 8 0 L 0 0 L fill} +>> matrix makepattern +/Pat3 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 8 M 8 -4 L + 0 12 M 12 0 L stroke} +>> matrix makepattern +/Pat4 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 0 M 8 12 L + 0 -4 M 12 8 L stroke} +>> matrix makepattern +/Pat5 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 8 M 4 -4 L + 0 12 M 8 -4 L 4 12 M 10 0 L stroke} +>> matrix makepattern +/Pat6 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 0 M 4 12 L + 0 -4 M 8 12 L 4 -4 M 10 8 L stroke} +>> matrix makepattern +/Pat7 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 8 -2 M -4 4 L + 12 0 M -4 8 L 12 4 M 0 10 L stroke} +>> matrix makepattern +/Pat8 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 -2 M 12 4 L + -4 0 M 12 8 L -4 4 M 8 10 L stroke} +>> matrix makepattern +/Pat9 exch def +/Pattern1 {PatternBgnd KeepColor Pat1 setpattern} bind def +/Pattern2 {PatternBgnd KeepColor Pat2 setpattern} bind def +/Pattern3 {PatternBgnd KeepColor Pat3 setpattern} bind def +/Pattern4 {PatternBgnd KeepColor Landscape {Pat5} {Pat4} ifelse setpattern} bind def +/Pattern5 {PatternBgnd KeepColor Landscape {Pat4} {Pat5} ifelse setpattern} bind def +/Pattern6 {PatternBgnd KeepColor Landscape {Pat9} {Pat6} ifelse setpattern} bind def +/Pattern7 {PatternBgnd KeepColor Landscape {Pat8} {Pat7} ifelse setpattern} bind def +} def +% +% +%End of PostScript Level 2 code +% +/PatternBgnd { + TransparentPatterns {} {gsave 1 setgray fill grestore} ifelse +} def +% +% Substitute for Level 2 pattern fill codes with +% grayscale if Level 2 support is not selected. +% +/Level1PatternFill { +/Pattern1 {0.250 Density} bind def +/Pattern2 {0.500 Density} bind def +/Pattern3 {0.750 Density} bind def +/Pattern4 {0.125 Density} bind def +/Pattern5 {0.375 Density} bind def +/Pattern6 {0.625 Density} bind def +/Pattern7 {0.875 Density} bind def +} def +% +% Now test for support of Level 2 code +% +Level1 {Level1PatternFill} {Level2PatternFill} ifelse +% +/Symbol-Oblique /Symbol findfont [1 0 .167 1 0 0] makefont +dup length dict begin {1 index /FID eq {pop pop} {def} ifelse} forall +currentdict end definefont pop +/MFshow { + { dup 5 get 3 ge + { 5 get 3 eq {gsave} {grestore} ifelse } + {dup dup 0 get findfont exch 1 get scalefont setfont + [ currentpoint ] exch dup 2 get 0 exch R dup 5 get 2 ne {dup dup 6 + get exch 4 get {Gshow} {stringwidth pop 0 R} ifelse }if dup 5 get 0 eq + {dup 3 get {2 get neg 0 exch R pop} {pop aload pop M} ifelse} {dup 5 + get 1 eq {dup 2 get exch dup 3 get exch 6 get stringwidth pop -2 div + dup 0 R} {dup 6 get stringwidth pop -2 div 0 R 6 get + show 2 index {aload pop M neg 3 -1 roll neg R pop pop} {pop pop pop + pop aload pop M} ifelse }ifelse }ifelse } + ifelse } + forall} def +/Gswidth {dup type /stringtype eq {stringwidth} {pop (n) stringwidth} ifelse} def +/MFwidth {0 exch { dup 5 get 3 ge { 5 get 3 eq { 0 } { pop } ifelse } + {dup 3 get{dup dup 0 get findfont exch 1 get scalefont setfont + 6 get Gswidth pop add} {pop} ifelse} ifelse} forall} def +/MLshow { currentpoint stroke M + 0 exch R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MRshow { currentpoint stroke M + exch dup MFwidth neg 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MCshow { currentpoint stroke M + exch dup MFwidth -2 div 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/XYsave { [( ) 1 2 true false 3 ()] } bind def +/XYrestore { [( ) 1 2 true false 4 ()] } bind def +Level1 SuppressPDFMark or +{} { +/SDict 10 dict def +systemdict /pdfmark known not { + userdict /pdfmark systemdict /cleartomark get put +} if +SDict begin [ + /Title (Sparse_mpivsomp.eps) + /Subject (gnuplot plot) + /Creator (gnuplot 4.6 patchlevel 0) + /Author (lilia) +% /Producer (gnuplot) +% /Keywords () + /CreationDate (Wed Dec 16 22:52:50 2015) + /DOCINFO pdfmark +end +} ifelse +end +%%EndProlog +%%Page: 1 1 +gnudict begin +gsave +doclip +50 50 translate +0.100 0.100 scale +90 rotate +0 -5040 translate +0 setgray +newpath +(Helvetica) findfont 140 scalefont setfont +BackgroundColor 0 lt 3 1 roll 0 lt exch 0 lt or or not {gsave BackgroundColor C clippath fill grestore} if +1.000 UL +LTb +854 448 M +63 0 V +6030 0 R +-63 0 V +stroke +770 448 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10)] +] -46.7 MRshow +1.000 UL +LTb +854 892 M +31 0 V +6062 0 R +-31 0 V +854 1151 M +31 0 V +6062 0 R +-31 0 V +854 1336 M +31 0 V +6062 0 R +-31 0 V +854 1479 M +31 0 V +6062 0 R +-31 0 V +854 1595 M +31 0 V +6062 0 R +-31 0 V +854 1694 M +31 0 V +6062 0 R +-31 0 V +854 1779 M +31 0 V +6062 0 R +-31 0 V +854 1855 M +31 0 V +6062 0 R +-31 0 V +854 1922 M +63 0 V +6030 0 R +-63 0 V +stroke +770 1922 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 100)] +] -46.7 MRshow +1.000 UL +LTb +854 2366 M +31 0 V +6062 0 R +-31 0 V +854 2626 M +31 0 V +6062 0 R +-31 0 V +854 2810 M +31 0 V +6062 0 R +-31 0 V +854 2953 M +31 0 V +6062 0 R +-31 0 V +854 3070 M +31 0 V +6062 0 R +-31 0 V +854 3168 M +31 0 V +6062 0 R +-31 0 V +854 3254 M +31 0 V +6062 0 R +-31 0 V +854 3329 M +31 0 V +6062 0 R +-31 0 V +854 3397 M +63 0 V +6030 0 R +-63 0 V +stroke +770 3397 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1000)] +] -46.7 MRshow +1.000 UL +LTb +854 3840 M +31 0 V +6062 0 R +-31 0 V +854 4100 M +31 0 V +6062 0 R +-31 0 V +854 4284 M +31 0 V +6062 0 R +-31 0 V +854 4427 M +31 0 V +6062 0 R +-31 0 V +854 4544 M +31 0 V +6062 0 R +-31 0 V +854 4643 M +31 0 V +6062 0 R +-31 0 V +854 4728 M +31 0 V +6062 0 R +-31 0 V +854 4804 M +31 0 V +6062 0 R +-31 0 V +854 4871 M +63 0 V +6030 0 R +-63 0 V +stroke +770 4871 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10000)] +] -46.7 MRshow +1.000 UL +LTb +854 448 M +0 63 V +0 4360 R +0 -63 V +stroke +854 308 M +[ [(Helvetica) 140.0 0.0 true true 0 (1)] +] -46.7 MCshow +1.000 UL +LTb +2885 448 M +0 63 V +0 4360 R +0 -63 V +stroke +2885 308 M +[ [(Helvetica) 140.0 0.0 true true 0 (2)] +] -46.7 MCshow +1.000 UL +LTb +4916 448 M +0 63 V +0 4360 R +0 -63 V +stroke +4916 308 M +[ [(Helvetica) 140.0 0.0 true true 0 (3)] +] -46.7 MCshow +1.000 UL +LTb +6947 448 M +0 63 V +0 4360 R +0 -63 V +stroke +6947 308 M +[ [(Helvetica) 140.0 0.0 true true 0 (4)] +] -46.7 MCshow +1.000 UL +LTb +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +LCb setrgbcolor +112 2659 M +currentpoint gsave translate -270 rotate 0 0 moveto +[ [(Helvetica) 140.0 0.0 true true 0 (Execution time in seconds)] +] -46.7 MCshow +grestore +LTb +LCb setrgbcolor +3900 98 M +[ [(Helvetica) 140.0 0.0 true true 0 (Number of GPU)] +] -46.7 MCshow +LTb +1.000 UP +1.000 UL +LTb +% Begin plot #1 +1.000 UP +1.000 UL +LT0 +LCb setrgbcolor +6296 4738 M +[ [(Helvetica) 140.0 0.0 true true 0 (200K MPI)] +] -46.7 MRshow +LT0 +6380 4738 M +399 0 V +854 1632 M +2885 1351 L +2031 -23 V +6947 941 L +854 1632 Pls +2885 1351 Pls +4916 1328 Pls +6947 941 Pls +6579 4738 Pls +% End plot #1 +% Begin plot #2 +1.000 UP +1.000 UL +LT1 +LCb setrgbcolor +6296 4598 M +[ [(Helvetica) 140.0 0.0 true true 0 (200K OpenMP)] +] -46.7 MRshow +LT1 +6380 4598 M +399 0 V +854 1695 M +2885 1261 L +2031 39 V +6947 980 L +854 1695 Crs +2885 1261 Crs +4916 1300 Crs +6947 980 Crs +6579 4598 Crs +% End plot #2 +% Begin plot #3 +1.000 UP +1.000 UL +LT2 +LCb setrgbcolor +6296 4458 M +[ [(Helvetica) 140.0 0.0 true true 0 (800K MPI)] +] -46.7 MRshow +LT2 +6380 4458 M +399 0 V +854 3720 M +2885 3209 L +4916 3008 L +6947 2587 L +854 3720 Star +2885 3209 Star +4916 3008 Star +6947 2587 Star +6579 4458 Star +% End plot #3 +% Begin plot #4 +1.000 UP +1.000 UL +LT3 +LCb setrgbcolor +6296 4318 M +[ [(Helvetica) 140.0 0.0 true true 0 (800K OpenMP)] +] -46.7 MRshow +LT3 +6380 4318 M +399 0 V +854 3503 M +2885 3044 L +4916 2727 L +6947 2531 L +854 3503 Box +2885 3044 Box +4916 2727 Box +6947 2531 Box +6579 4318 Box +% End plot #4 +% Begin plot #5 +1.000 UP +1.000 UL +LT4 +LCb setrgbcolor +6296 4178 M +[ [(Helvetica) 140.0 0.0 true true 0 (1.4M MPI)] +] -46.7 MRshow +LT4 +6380 4178 M +399 0 V +854 4147 M +2885 3838 L +2031 -99 V +2031 -92 V +854 4147 BoxF +2885 3838 BoxF +4916 3739 BoxF +6947 3647 BoxF +6579 4178 BoxF +% End plot #5 +% Begin plot #6 +1.000 UP +1.000 UL +LT5 +LCb setrgbcolor +6296 4038 M +[ [(Helvetica) 140.0 0.0 true true 0 (1.4M OpenMP)] +] -46.7 MRshow +LT5 +6380 4038 M +399 0 V +854 4203 M +2885 3949 L +4916 3768 L +2031 -30 V +854 4203 Circle +2885 3949 Circle +4916 3768 Circle +6947 3738 Circle +6579 4038 Circle +% End plot #6 +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +1.000 UP +1.000 UL +LTb +stroke +grestore +end +showpage +%%Trailer +%%DocumentFonts: Helvetica +%%Pages: 1 diff --git a/Simulations/Sparse_openmp.eps b/Simulations/Sparse_openmp.eps new file mode 100644 index 0000000..b816be4 --- /dev/null +++ b/Simulations/Sparse_openmp.eps @@ -0,0 +1,955 @@ +%!PS-Adobe-2.0 +%%Title: Sparse_openmp.eps +%%Creator: gnuplot 4.6 patchlevel 0 +%%CreationDate: Wed Dec 16 22:37:48 2015 +%%DocumentFonts: (atend) +%%BoundingBox: 50 50 554 770 +%%Orientation: Landscape +%%Pages: (atend) +%%EndComments +%%BeginProlog +/gnudict 256 dict def +gnudict begin +% +% The following true/false flags may be edited by hand if desired. +% The unit line width and grayscale image gamma correction may also be changed. +% +/Color false def +/Blacktext false def +/Solid false def +/Dashlength 1 def +/Landscape true def +/Level1 false def +/Rounded false def +/ClipToBoundingBox false def +/SuppressPDFMark false def +/TransparentPatterns false def +/gnulinewidth 5.000 def +/userlinewidth gnulinewidth def +/Gamma 1.0 def +/BackgroundColor {-1.000 -1.000 -1.000} def +% +/vshift -46 def +/dl1 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul sub dup 0 le { pop 0.01 } if } if +} def +/dl2 { + 10.0 Dashlength mul mul + Rounded { currentlinewidth 0.75 mul add } if +} def +/hpt_ 31.5 def +/vpt_ 31.5 def +/hpt hpt_ def +/vpt vpt_ def +/doclip { + ClipToBoundingBox { + newpath 50 50 moveto 554 50 lineto 554 770 lineto 50 770 lineto closepath + clip + } if +} def +% +% Gnuplot Prolog Version 4.4 (August 2010) +% +%/SuppressPDFMark true def +% +/M {moveto} bind def +/L {lineto} bind def +/R {rmoveto} bind def +/V {rlineto} bind def +/N {newpath moveto} bind def +/Z {closepath} bind def +/C {setrgbcolor} bind def +/f {rlineto fill} bind def +/g {setgray} bind def +/Gshow {show} def % May be redefined later in the file to support UTF-8 +/vpt2 vpt 2 mul def +/hpt2 hpt 2 mul def +/Lshow {currentpoint stroke M 0 vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Rshow {currentpoint stroke M dup stringwidth pop neg vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/Cshow {currentpoint stroke M dup stringwidth pop -2 div vshift R + Blacktext {gsave 0 setgray show grestore} {show} ifelse} def +/UP {dup vpt_ mul /vpt exch def hpt_ mul /hpt exch def + /hpt2 hpt 2 mul def /vpt2 vpt 2 mul def} def +/DL {Color {setrgbcolor Solid {pop []} if 0 setdash} + {pop pop pop 0 setgray Solid {pop []} if 0 setdash} ifelse} def +/BL {stroke userlinewidth 2 mul setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/AL {stroke userlinewidth 2 div setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +/UL {dup gnulinewidth mul /userlinewidth exch def + dup 1 lt {pop 1} if 10 mul /udl exch def} def +/PL {stroke userlinewidth setlinewidth + Rounded {1 setlinejoin 1 setlinecap} if} def +3.8 setmiterlimit +% Default Line colors +/LCw {1 1 1} def +/LCb {0 0 0} def +/LCa {0 0 0} def +/LC0 {1 0 0} def +/LC1 {0 1 0} def +/LC2 {0 0 1} def +/LC3 {1 0 1} def +/LC4 {0 1 1} def +/LC5 {1 1 0} def +/LC6 {0 0 0} def +/LC7 {1 0.3 0} def +/LC8 {0.5 0.5 0.5} def +% Default Line Types +/LTw {PL [] 1 setgray} def +/LTb {BL [] LCb DL} def +/LTa {AL [1 udl mul 2 udl mul] 0 setdash LCa setrgbcolor} def +/LT0 {PL [] LC0 DL} def +/LT1 {PL [4 dl1 2 dl2] LC1 DL} def +/LT2 {PL [2 dl1 3 dl2] LC2 DL} def +/LT3 {PL [1 dl1 1.5 dl2] LC3 DL} def +/LT4 {PL [6 dl1 2 dl2 1 dl1 2 dl2] LC4 DL} def +/LT5 {PL [3 dl1 3 dl2 1 dl1 3 dl2] LC5 DL} def +/LT6 {PL [2 dl1 2 dl2 2 dl1 6 dl2] LC6 DL} def +/LT7 {PL [1 dl1 2 dl2 6 dl1 2 dl2 1 dl1 2 dl2] LC7 DL} def +/LT8 {PL [2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 2 dl2 2 dl1 4 dl2] LC8 DL} def +/Pnt {stroke [] 0 setdash gsave 1 setlinecap M 0 0 V stroke grestore} def +/Dia {stroke [] 0 setdash 2 copy vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke + Pnt} def +/Pls {stroke [] 0 setdash vpt sub M 0 vpt2 V + currentpoint stroke M + hpt neg vpt neg R hpt2 0 V stroke + } def +/Box {stroke [] 0 setdash 2 copy exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke + Pnt} def +/Crs {stroke [] 0 setdash exch hpt sub exch vpt add M + hpt2 vpt2 neg V currentpoint stroke M + hpt2 neg 0 R hpt2 vpt2 V stroke} def +/TriU {stroke [] 0 setdash 2 copy vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke + Pnt} def +/Star {2 copy Pls Crs} def +/BoxF {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath fill} def +/TriUF {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath fill} def +/TriD {stroke [] 0 setdash 2 copy vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke + Pnt} def +/TriDF {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath fill} def +/DiaF {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath fill} def +/Pent {stroke [] 0 setdash 2 copy gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore Pnt} def +/PentF {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath fill grestore} def +/Circle {stroke [] 0 setdash 2 copy + hpt 0 360 arc stroke Pnt} def +/CircleF {stroke [] 0 setdash hpt 0 360 arc fill} def +/C0 {BL [] 0 setdash 2 copy moveto vpt 90 450 arc} bind def +/C1 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + vpt 0 360 arc closepath} bind def +/C2 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C3 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C4 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C5 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc + 2 copy moveto + 2 copy vpt 180 270 arc closepath fill + vpt 0 360 arc} bind def +/C6 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C7 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 270 arc closepath fill + vpt 0 360 arc closepath} bind def +/C8 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C9 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 270 450 arc closepath fill + vpt 0 360 arc closepath} bind def +/C10 {BL [] 0 setdash 2 copy 2 copy moveto vpt 270 360 arc closepath fill + 2 copy moveto + 2 copy vpt 90 180 arc closepath fill + vpt 0 360 arc closepath} bind def +/C11 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 180 arc closepath fill + 2 copy moveto + 2 copy vpt 270 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C12 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C13 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 0 90 arc closepath fill + 2 copy moveto + 2 copy vpt 180 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/C14 {BL [] 0 setdash 2 copy moveto + 2 copy vpt 90 360 arc closepath fill + vpt 0 360 arc} bind def +/C15 {BL [] 0 setdash 2 copy vpt 0 360 arc closepath fill + vpt 0 360 arc closepath} bind def +/Rec {newpath 4 2 roll moveto 1 index 0 rlineto 0 exch rlineto + neg 0 rlineto closepath} bind def +/Square {dup Rec} bind def +/Bsquare {vpt sub exch vpt sub exch vpt2 Square} bind def +/S0 {BL [] 0 setdash 2 copy moveto 0 vpt rlineto BL Bsquare} bind def +/S1 {BL [] 0 setdash 2 copy vpt Square fill Bsquare} bind def +/S2 {BL [] 0 setdash 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S3 {BL [] 0 setdash 2 copy exch vpt sub exch vpt2 vpt Rec fill Bsquare} bind def +/S4 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S5 {BL [] 0 setdash 2 copy 2 copy vpt Square fill + exch vpt sub exch vpt sub vpt Square fill Bsquare} bind def +/S6 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S7 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt vpt2 Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S8 {BL [] 0 setdash 2 copy vpt sub vpt Square fill Bsquare} bind def +/S9 {BL [] 0 setdash 2 copy vpt sub vpt vpt2 Rec fill Bsquare} bind def +/S10 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt Square fill + Bsquare} bind def +/S11 {BL [] 0 setdash 2 copy vpt sub vpt Square fill 2 copy exch vpt sub exch vpt2 vpt Rec fill + Bsquare} bind def +/S12 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill Bsquare} bind def +/S13 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy vpt Square fill Bsquare} bind def +/S14 {BL [] 0 setdash 2 copy exch vpt sub exch vpt sub vpt2 vpt Rec fill + 2 copy exch vpt sub exch vpt Square fill Bsquare} bind def +/S15 {BL [] 0 setdash 2 copy Bsquare fill Bsquare} bind def +/D0 {gsave translate 45 rotate 0 0 S0 stroke grestore} bind def +/D1 {gsave translate 45 rotate 0 0 S1 stroke grestore} bind def +/D2 {gsave translate 45 rotate 0 0 S2 stroke grestore} bind def +/D3 {gsave translate 45 rotate 0 0 S3 stroke grestore} bind def +/D4 {gsave translate 45 rotate 0 0 S4 stroke grestore} bind def +/D5 {gsave translate 45 rotate 0 0 S5 stroke grestore} bind def +/D6 {gsave translate 45 rotate 0 0 S6 stroke grestore} bind def +/D7 {gsave translate 45 rotate 0 0 S7 stroke grestore} bind def +/D8 {gsave translate 45 rotate 0 0 S8 stroke grestore} bind def +/D9 {gsave translate 45 rotate 0 0 S9 stroke grestore} bind def +/D10 {gsave translate 45 rotate 0 0 S10 stroke grestore} bind def +/D11 {gsave translate 45 rotate 0 0 S11 stroke grestore} bind def +/D12 {gsave translate 45 rotate 0 0 S12 stroke grestore} bind def +/D13 {gsave translate 45 rotate 0 0 S13 stroke grestore} bind def +/D14 {gsave translate 45 rotate 0 0 S14 stroke grestore} bind def +/D15 {gsave translate 45 rotate 0 0 S15 stroke grestore} bind def +/DiaE {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V closepath stroke} def +/BoxE {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V closepath stroke} def +/TriUE {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V closepath stroke} def +/TriDE {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V closepath stroke} def +/PentE {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + closepath stroke grestore} def +/CircE {stroke [] 0 setdash + hpt 0 360 arc stroke} def +/Opaque {gsave closepath 1 setgray fill grestore 0 setgray closepath} def +/DiaW {stroke [] 0 setdash vpt add M + hpt neg vpt neg V hpt vpt neg V + hpt vpt V hpt neg vpt V Opaque stroke} def +/BoxW {stroke [] 0 setdash exch hpt sub exch vpt add M + 0 vpt2 neg V hpt2 0 V 0 vpt2 V + hpt2 neg 0 V Opaque stroke} def +/TriUW {stroke [] 0 setdash vpt 1.12 mul add M + hpt neg vpt -1.62 mul V + hpt 2 mul 0 V + hpt neg vpt 1.62 mul V Opaque stroke} def +/TriDW {stroke [] 0 setdash vpt 1.12 mul sub M + hpt neg vpt 1.62 mul V + hpt 2 mul 0 V + hpt neg vpt -1.62 mul V Opaque stroke} def +/PentW {stroke [] 0 setdash gsave + translate 0 hpt M 4 {72 rotate 0 hpt L} repeat + Opaque stroke grestore} def +/CircW {stroke [] 0 setdash + hpt 0 360 arc Opaque stroke} def +/BoxFill {gsave Rec 1 setgray fill grestore} def +/Density { + /Fillden exch def + currentrgbcolor + /ColB exch def /ColG exch def /ColR exch def + /ColR ColR Fillden mul Fillden sub 1 add def + /ColG ColG Fillden mul Fillden sub 1 add def + /ColB ColB Fillden mul Fillden sub 1 add def + ColR ColG ColB setrgbcolor} def +/BoxColFill {gsave Rec PolyFill} def +/PolyFill {gsave Density fill grestore grestore} def +/h {rlineto rlineto rlineto gsave closepath fill grestore} bind def +% +% PostScript Level 1 Pattern Fill routine for rectangles +% Usage: x y w h s a XX PatternFill +% x,y = lower left corner of box to be filled +% w,h = width and height of box +% a = angle in degrees between lines and x-axis +% XX = 0/1 for no/yes cross-hatch +% +/PatternFill {gsave /PFa [ 9 2 roll ] def + PFa 0 get PFa 2 get 2 div add PFa 1 get PFa 3 get 2 div add translate + PFa 2 get -2 div PFa 3 get -2 div PFa 2 get PFa 3 get Rec + gsave 1 setgray fill grestore clip + currentlinewidth 0.5 mul setlinewidth + /PFs PFa 2 get dup mul PFa 3 get dup mul add sqrt def + 0 0 M PFa 5 get rotate PFs -2 div dup translate + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 M 0 PFs V} for + 0 PFa 6 get ne { + 0 1 PFs PFa 4 get div 1 add floor cvi + {PFa 4 get mul 0 2 1 roll M PFs 0 V} for + } if + stroke grestore} def +% +/languagelevel where + {pop languagelevel} {1} ifelse + 2 lt + {/InterpretLevel1 true def} + {/InterpretLevel1 Level1 def} + ifelse +% +% PostScript level 2 pattern fill definitions +% +/Level2PatternFill { +/Tile8x8 {/PaintType 2 /PatternType 1 /TilingType 1 /BBox [0 0 8 8] /XStep 8 /YStep 8} + bind def +/KeepColor {currentrgbcolor [/Pattern /DeviceRGB] setcolorspace} bind def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke} +>> matrix makepattern +/Pat1 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 8 8 L 0 8 M 8 0 L stroke + 0 4 M 4 8 L 8 4 L 4 0 L 0 4 L stroke} +>> matrix makepattern +/Pat2 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 0 M 0 8 L + 8 8 L 8 0 L 0 0 L fill} +>> matrix makepattern +/Pat3 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 8 M 8 -4 L + 0 12 M 12 0 L stroke} +>> matrix makepattern +/Pat4 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -4 0 M 8 12 L + 0 -4 M 12 8 L stroke} +>> matrix makepattern +/Pat5 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 8 M 4 -4 L + 0 12 M 8 -4 L 4 12 M 10 0 L stroke} +>> matrix makepattern +/Pat6 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop -2 0 M 4 12 L + 0 -4 M 8 12 L 4 -4 M 10 8 L stroke} +>> matrix makepattern +/Pat7 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 8 -2 M -4 4 L + 12 0 M -4 8 L 12 4 M 0 10 L stroke} +>> matrix makepattern +/Pat8 exch def +<< Tile8x8 + /PaintProc {0.5 setlinewidth pop 0 -2 M 12 4 L + -4 0 M 12 8 L -4 4 M 8 10 L stroke} +>> matrix makepattern +/Pat9 exch def +/Pattern1 {PatternBgnd KeepColor Pat1 setpattern} bind def +/Pattern2 {PatternBgnd KeepColor Pat2 setpattern} bind def +/Pattern3 {PatternBgnd KeepColor Pat3 setpattern} bind def +/Pattern4 {PatternBgnd KeepColor Landscape {Pat5} {Pat4} ifelse setpattern} bind def +/Pattern5 {PatternBgnd KeepColor Landscape {Pat4} {Pat5} ifelse setpattern} bind def +/Pattern6 {PatternBgnd KeepColor Landscape {Pat9} {Pat6} ifelse setpattern} bind def +/Pattern7 {PatternBgnd KeepColor Landscape {Pat8} {Pat7} ifelse setpattern} bind def +} def +% +% +%End of PostScript Level 2 code +% +/PatternBgnd { + TransparentPatterns {} {gsave 1 setgray fill grestore} ifelse +} def +% +% Substitute for Level 2 pattern fill codes with +% grayscale if Level 2 support is not selected. +% +/Level1PatternFill { +/Pattern1 {0.250 Density} bind def +/Pattern2 {0.500 Density} bind def +/Pattern3 {0.750 Density} bind def +/Pattern4 {0.125 Density} bind def +/Pattern5 {0.375 Density} bind def +/Pattern6 {0.625 Density} bind def +/Pattern7 {0.875 Density} bind def +} def +% +% Now test for support of Level 2 code +% +Level1 {Level1PatternFill} {Level2PatternFill} ifelse +% +/Symbol-Oblique /Symbol findfont [1 0 .167 1 0 0] makefont +dup length dict begin {1 index /FID eq {pop pop} {def} ifelse} forall +currentdict end definefont pop +/MFshow { + { dup 5 get 3 ge + { 5 get 3 eq {gsave} {grestore} ifelse } + {dup dup 0 get findfont exch 1 get scalefont setfont + [ currentpoint ] exch dup 2 get 0 exch R dup 5 get 2 ne {dup dup 6 + get exch 4 get {Gshow} {stringwidth pop 0 R} ifelse }if dup 5 get 0 eq + {dup 3 get {2 get neg 0 exch R pop} {pop aload pop M} ifelse} {dup 5 + get 1 eq {dup 2 get exch dup 3 get exch 6 get stringwidth pop -2 div + dup 0 R} {dup 6 get stringwidth pop -2 div 0 R 6 get + show 2 index {aload pop M neg 3 -1 roll neg R pop pop} {pop pop pop + pop aload pop M} ifelse }ifelse }ifelse } + ifelse } + forall} def +/Gswidth {dup type /stringtype eq {stringwidth} {pop (n) stringwidth} ifelse} def +/MFwidth {0 exch { dup 5 get 3 ge { 5 get 3 eq { 0 } { pop } ifelse } + {dup 3 get{dup dup 0 get findfont exch 1 get scalefont setfont + 6 get Gswidth pop add} {pop} ifelse} ifelse} forall} def +/MLshow { currentpoint stroke M + 0 exch R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MRshow { currentpoint stroke M + exch dup MFwidth neg 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/MCshow { currentpoint stroke M + exch dup MFwidth -2 div 3 -1 roll R + Blacktext {gsave 0 setgray MFshow grestore} {MFshow} ifelse } bind def +/XYsave { [( ) 1 2 true false 3 ()] } bind def +/XYrestore { [( ) 1 2 true false 4 ()] } bind def +Level1 SuppressPDFMark or +{} { +/SDict 10 dict def +systemdict /pdfmark known not { + userdict /pdfmark systemdict /cleartomark get put +} if +SDict begin [ + /Title (Sparse_openmp.eps) + /Subject (gnuplot plot) + /Creator (gnuplot 4.6 patchlevel 0) + /Author (lilia) +% /Producer (gnuplot) +% /Keywords () + /CreationDate (Wed Dec 16 22:37:48 2015) + /DOCINFO pdfmark +end +} ifelse +end +%%EndProlog +%%Page: 1 1 +gnudict begin +gsave +doclip +50 50 translate +0.100 0.100 scale +90 rotate +0 -5040 translate +0 setgray +newpath +(Helvetica) findfont 140 scalefont setfont +BackgroundColor 0 lt 3 1 roll 0 lt exch 0 lt or or not {gsave BackgroundColor C clippath fill grestore} if +1.000 UL +LTb +854 448 M +63 0 V +6030 0 R +-63 0 V +stroke +770 448 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1)] +] -46.7 MRshow +1.000 UL +LTb +854 781 M +31 0 V +6062 0 R +-31 0 V +854 976 M +31 0 V +6062 0 R +-31 0 V +854 1114 M +31 0 V +6062 0 R +-31 0 V +854 1221 M +31 0 V +6062 0 R +-31 0 V +854 1308 M +31 0 V +6062 0 R +-31 0 V +854 1382 M +31 0 V +6062 0 R +-31 0 V +854 1447 M +31 0 V +6062 0 R +-31 0 V +854 1503 M +31 0 V +6062 0 R +-31 0 V +854 1554 M +63 0 V +6030 0 R +-63 0 V +stroke +770 1554 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10)] +] -46.7 MRshow +1.000 UL +LTb +854 1887 M +31 0 V +6062 0 R +-31 0 V +854 2081 M +31 0 V +6062 0 R +-31 0 V +854 2219 M +31 0 V +6062 0 R +-31 0 V +854 2327 M +31 0 V +6062 0 R +-31 0 V +854 2414 M +31 0 V +6062 0 R +-31 0 V +854 2488 M +31 0 V +6062 0 R +-31 0 V +854 2552 M +31 0 V +6062 0 R +-31 0 V +854 2609 M +31 0 V +6062 0 R +-31 0 V +854 2660 M +63 0 V +6030 0 R +-63 0 V +stroke +770 2660 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 100)] +] -46.7 MRshow +1.000 UL +LTb +854 2992 M +31 0 V +6062 0 R +-31 0 V +854 3187 M +31 0 V +6062 0 R +-31 0 V +854 3325 M +31 0 V +6062 0 R +-31 0 V +854 3432 M +31 0 V +6062 0 R +-31 0 V +854 3520 M +31 0 V +6062 0 R +-31 0 V +854 3594 M +31 0 V +6062 0 R +-31 0 V +854 3658 M +31 0 V +6062 0 R +-31 0 V +854 3715 M +31 0 V +6062 0 R +-31 0 V +854 3765 M +63 0 V +6030 0 R +-63 0 V +stroke +770 3765 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1000)] +] -46.7 MRshow +1.000 UL +LTb +854 4098 M +31 0 V +6062 0 R +-31 0 V +854 4293 M +31 0 V +6062 0 R +-31 0 V +854 4431 M +31 0 V +6062 0 R +-31 0 V +854 4538 M +31 0 V +6062 0 R +-31 0 V +854 4626 M +31 0 V +6062 0 R +-31 0 V +854 4700 M +31 0 V +6062 0 R +-31 0 V +854 4764 M +31 0 V +6062 0 R +-31 0 V +854 4820 M +31 0 V +6062 0 R +-31 0 V +854 4871 M +63 0 V +6030 0 R +-63 0 V +stroke +770 4871 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10000)] +] -46.7 MRshow +1.000 UL +LTb +854 448 M +0 63 V +0 4360 R +0 -63 V +stroke +854 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 10000)] +] -46.7 MCshow +1.000 UL +LTb +1465 448 M +0 31 V +0 4392 R +0 -31 V +1823 448 M +0 31 V +0 4392 R +0 -31 V +2077 448 M +0 31 V +0 4392 R +0 -31 V +2274 448 M +0 31 V +0 4392 R +0 -31 V +2434 448 M +0 31 V +0 4392 R +0 -31 V +2570 448 M +0 31 V +0 4392 R +0 -31 V +2688 448 M +0 31 V +0 4392 R +0 -31 V +2792 448 M +0 31 V +0 4392 R +0 -31 V +2885 448 M +0 63 V +0 4360 R +0 -63 V +stroke +2885 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 100000)] +] -46.7 MCshow +1.000 UL +LTb +3496 448 M +0 31 V +0 4392 R +0 -31 V +3854 448 M +0 31 V +0 4392 R +0 -31 V +4108 448 M +0 31 V +0 4392 R +0 -31 V +4305 448 M +0 31 V +0 4392 R +0 -31 V +4465 448 M +0 31 V +0 4392 R +0 -31 V +4601 448 M +0 31 V +0 4392 R +0 -31 V +4719 448 M +0 31 V +0 4392 R +0 -31 V +4823 448 M +0 31 V +0 4392 R +0 -31 V +4916 448 M +0 63 V +0 4360 R +0 -63 V +stroke +4916 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1e+06)] +] -46.7 MCshow +1.000 UL +LTb +5527 448 M +0 31 V +0 4392 R +0 -31 V +5885 448 M +0 31 V +0 4392 R +0 -31 V +6139 448 M +0 31 V +0 4392 R +0 -31 V +6336 448 M +0 31 V +0 4392 R +0 -31 V +6496 448 M +0 31 V +0 4392 R +0 -31 V +6632 448 M +0 31 V +0 4392 R +0 -31 V +6750 448 M +0 31 V +0 4392 R +0 -31 V +6854 448 M +0 31 V +0 4392 R +0 -31 V +6947 448 M +0 63 V +0 4360 R +0 -63 V +stroke +6947 308 M +[ [(Helvetica) 140.0 0.0 true true 0 ( 1e+07)] +] -46.7 MCshow +1.000 UL +LTb +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +LCb setrgbcolor +112 2659 M +currentpoint gsave translate -270 rotate 0 0 moveto +[ [(Helvetica) 140.0 0.0 true true 0 (Execution time in seconds)] +] -46.7 MCshow +grestore +LTb +LCb setrgbcolor +3900 98 M +[ [(Helvetica) 140.0 0.0 true true 0 (Polynomial's degrees)] +] -46.7 MCshow +LTb +1.000 UP +1.000 UL +LTb +% Begin plot #1 +1.000 UP +1.000 UL +LT0 +LCb setrgbcolor +6296 4738 M +[ [(Helvetica) 140.0 0.0 true true 0 (1 GPU)] +] -46.7 MRshow +LT0 +6380 4738 M +399 0 V +2885 1785 M +611 704 V +612 608 V +357 415 V +254 333 V +197 152 V +161 451 V +136 -78 V +2885 1785 Pls +3496 2489 Pls +4108 3097 Pls +4465 3512 Pls +4719 3845 Pls +4916 3997 Pls +5077 4448 Pls +5213 4370 Pls +6579 4738 Pls +% End plot #1 +% Begin plot #2 +1.000 UP +1.000 UL +LT1 +LCb setrgbcolor +6296 4598 M +[ [(Helvetica) 140.0 0.0 true true 0 (2 GPU)] +] -46.7 MRshow +LT1 +6380 4598 M +399 0 V +2885 1510 M +611 654 V +612 592 V +357 428 V +254 317 V +197 186 V +161 313 V +136 180 V +2885 1510 Crs +3496 2164 Crs +4108 2756 Crs +4465 3184 Crs +4719 3501 Crs +4916 3687 Crs +5077 4000 Crs +5213 4180 Crs +6579 4598 Crs +% End plot #2 +% Begin plot #3 +1.000 UP +1.000 UL +LT2 +LCb setrgbcolor +6296 4458 M +[ [(Helvetica) 140.0 0.0 true true 0 (3 GPU)] +] -46.7 MRshow +LT2 +6380 4458 M +399 0 V +2885 1447 M +611 746 V +612 395 V +357 410 V +254 265 V +197 256 V +161 592 V +136 -67 V +2885 1447 Star +3496 2193 Star +4108 2588 Star +4465 2998 Star +4719 3263 Star +4916 3519 Star +5077 4111 Star +5213 4044 Star +6579 4458 Star +% End plot #3 +% Begin plot #4 +1.000 UP +1.000 UL +LT3 +LCb setrgbcolor +6296 4318 M +[ [(Helvetica) 140.0 0.0 true true 0 (4 GPU)] +] -46.7 MRshow +LT3 +6380 4318 M +399 0 V +2885 1298 M +611 655 V +612 522 V +357 393 V +254 248 V +197 235 V +161 627 V +136 43 V +2885 1298 Box +3496 1953 Box +4108 2475 Box +4465 2868 Box +4719 3116 Box +4916 3351 Box +5077 3978 Box +5213 4021 Box +6579 4318 Box +% End plot #4 +1.000 UL +LTb +854 4871 N +854 448 L +6093 0 V +0 4423 V +-6093 0 V +Z stroke +1.000 UP +1.000 UL +LTb +stroke +grestore +end +showpage +%%Trailer +%%DocumentFonts: Helvetica +%%Pages: 1 diff --git a/Simulations/full_mpi/full_mpi_1GPU.o140161 b/Simulations/full_mpi/full_mpi_1GPU.o140161 new file mode 100644 index 0000000..a833c6c --- /dev/null +++ b/Simulations/full_mpi/full_mpi_1GPU.o140161 @@ -0,0 +1,515 @@ +REMAINING: 1 +Taking GPU #3 +proc 0 +zone limite de 'log-exp' 1.00593 +dimgrid 235 dimblock 256 degrePoly 60000 +proc 0, start 0 size 60160 +proc 0 start 0 size 60160 +iter : 1 Arret : 4.93627E-05 s/iter 0.751338 +iter : 2 Arret : 4.72892E-05 s/iter 0.751311 +iter : 3 Arret : 4.32282E-05 s/iter 0.751351 +iter : 4 Arret : 4.40808E-05 s/iter 0.751390 +iter : 5 Arret : 4.31866E-05 s/iter 0.751343 +iter : 6 Arret : 4.51897E-05 s/iter 0.751236 +iter : 7 Arret : 5.50757E-05 s/iter 0.751346 +iter : 8 Arret : 0.000600625 s/iter 0.751189 +iter : 9 Arret : 0.00351745 s/iter 0.751224 +iter : 10 Arret : 0.0225499 s/iter 0.751147 +iter : 11 Arret : 1.92525 s/iter 1.257596 +iter : 12 Arret : 0.0724798 s/iter 0.751219 +iter : 13 Arret : 0.100634 s/iter 0.751209 +iter : 14 Arret : 0.104374 s/iter 1.286622 +iter : 15 Arret : 0.016746 s/iter 1.271784 +iter : 16 Arret : 0.00784681 s/iter 1.261270 +iter : 17 Arret : 0.00523028 s/iter 1.249434 +iter : 18 Arret : 0.00797883 s/iter 0.731764 +iter : 19 Arret : 0.00389307 s/iter 0.711145 +iter : 20 Arret : 0.00132613 s/iter 0.695894 +iter : 21 Arret : 0.00054363 s/iter 0.683618 +iter : 22 Arret : 0.00764188 s/iter 0.655728 +iter : 23 Arret : 0.0109632 s/iter 0.663047 +iter : 24 Arret : 0.000483636 s/iter 0.647992 +iter : 25 Arret : 0.000266785 s/iter 0.645841 +iter : 26 Arret : 9.21069E-05 s/iter 0.650690 +iter : 27 Arret : 0.00137817 s/iter 0.518549 +iter : 28 Arret : 0.00413942 s/iter 0.516303 +iter : 29 Arret : 1.28264E-05 s/iter 0.521554 +iter : 30 Arret : 2.62246E-10 s/iter 0.521585 +iter : 31 Arret : 8.10539E-15 s/iter 0.520315 +temps : 24.1491 seconde(s) +Nb iterations : 31 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.35784E-10 +Stabilite : 8.10539E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540783 +i* 0.841162| 1|-7.58456E-14 +i* 3.78031E-14| +| 2| -0.992343 +i* -0.123513| 1|-4.36456E-15 +i* 3.59435E-15| +| 3| 0.0563346 +i* 0.998412| 1| 5.70377E-15 +i* 3.3501E-14| +| 4| -0.802793 +i* -0.596258| 1| 2.03657E-15 +i* 1.01915E-14| +| 5| 0.730552 +i* -0.682857| 1|-7.48429E-14 +i* 6.77011E-14| +| 6| -0.442728 +i* 0.896656| 1|-3.77198E-14 +i*-1.89779E-15| +| 7| -0.404888 +i* -0.914366| 1| 3.20195E-14 +i* 9.65894E-15| +| 8| 0.972126 +i* -0.23446| 1| 4.02421E-14 +i*-1.54755E-14| +| 9| -0.826939 +i* 0.562292| 1| -2.4928E-14 +i*-1.59889E-14| +| 10| 0.0979895 +i* -0.995187| 1| 2.27804E-14 +i*-1.97481E-14| +| 11| 0.961513 +i* 0.27476| 1|-9.39769E-14 +i*-2.63912E-13| +| 12| -0.996627 +i* 0.0820589| 1| 2.39773E-14 +i* 1.74825E-14| +| 13| 0.575447 +i* -0.817839| 1|-3.49894E-14 +i*-7.98545E-14| +| 14| 0.701466 +i* 0.712703| 1| 7.52211E-14 +i* 1.53991E-14| +| 15| 0.259346 +i* 0.965785| 1|-2.14863E-14 +i*-2.81355E-14| +| 16| -0.907773 +i* -0.419461| 1|-3.62869E-14 +i*-9.49414E-15| +| 17| 0.903623 +i* -0.428329| 1|-1.24969E-14 +i* 7.51222E-14| +| 18| -0.249979 +i* 0.968251| 1|-1.59074E-14 +i*-1.09721E-14| +| 19| -0.583341 +i* -0.812227| 1| 1.92242E-14 +i* 2.27058E-14| +| 20| 0.997383 +i* 0.072297| 1| 2.53037E-13 +i*-5.92819E-13| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 1 +proc 0 +zone limite de 'log-exp' 1.00237 +dimgrid 586 dimblock 256 degrePoly 150000 +proc 0, start 0 size 150016 +proc 0 start 0 size 150016 +iter : 1 Arret : 1.64136E-05 s/iter 4.670410 +iter : 2 Arret : 1.62219E-05 s/iter 4.668737 +iter : 3 Arret : 1.59634E-05 s/iter 4.668001 +iter : 4 Arret : 1.57203E-05 s/iter 4.668096 +iter : 5 Arret : 1.61134E-05 s/iter 4.668095 +iter : 6 Arret : 1.68096E-05 s/iter 4.667823 +iter : 7 Arret : 1.83395E-05 s/iter 4.668957 +iter : 8 Arret : 2.23347E-05 s/iter 4.668718 +iter : 9 Arret : 0.000193284 s/iter 4.669886 +iter : 10 Arret : 0.00650657 s/iter 4.666547 +iter : 11 Arret : 0.00202338 s/iter 4.668819 +iter : 12 Arret : 0.00858027 s/iter 4.668152 +iter : 13 Arret : 1.50198 s/iter 6.718188 +iter : 14 Arret : 0.0716136 s/iter 5.989323 +iter : 15 Arret : 0.0462949 s/iter 4.653326 +iter : 16 Arret : 0.0250802 s/iter 4.654335 +iter : 17 Arret : 0.014323 s/iter 6.635287 +iter : 18 Arret : 0.0102749 s/iter 6.598926 +iter : 19 Arret : 0.0107553 s/iter 6.248834 +iter : 20 Arret : 0.0163074 s/iter 5.917159 +iter : 21 Arret : 0.00966464 s/iter 5.868624 +iter : 22 Arret : 0.0126723 s/iter 4.502515 +iter : 23 Arret : 0.0194806 s/iter 5.728295 +iter : 24 Arret : 0.00314943 s/iter 4.460393 +iter : 25 Arret : 0.00455918 s/iter 4.451818 +iter : 26 Arret : 0.000131011 s/iter 4.482879 +iter : 27 Arret : 1.27601E-05 s/iter 4.481150 +iter : 28 Arret : 8.90079E-08 s/iter 4.447335 +iter : 29 Arret : 8.10668E-13 s/iter 4.446139 +temps : 146.49 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.26507E-09 +Stabilite : 8.10668E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540528 +i* 0.841326| 1| 8.68923E-14 +i* 2.2979E-13| +| 2| -0.905603 +i* -0.424127| 1| 6.50001E-14 +i* -3.0061E-14| +| 3| -0.774122 +i* 0.633037| 1|-3.89619E-14 +i*-6.71876E-14| +| 4| 0.317935 +i* -0.948113| 1| 4.656E-15 +i* 1.15645E-13| +| 5| 0.235897 +i* 0.971778| 1|-3.15963E-14 +i*-8.88994E-14| +| 6| -0.717299 +i* -0.696766| 1| 5.63785E-15 +i*-6.71685E-14| +| 7| 0.992349 +i* -0.123462| 1|-4.81056E-13 +i* 9.00335E-13| +| 8| -0.938482 +i* 0.345329| 1|-6.95555E-14 +i*-3.79159E-14| +| 9| 0.610294 +i* -0.792175| 1| -5.4852E-14 +i*-3.26232E-14| +| 10| -0.0945977 +i* 0.995516| 1| 4.45165E-14 +i* 9.42527E-14| +| 11| -0.450242 +i* -0.892906| 1| 2.41855E-14 +i*-3.23699E-15| +| 12| 0.978218 +i* 0.207583| 1|-2.84429E-13 +i* 4.69725E-13| +| 13| -0.999806 +i* 0.0197069| 1|-4.72365E-14 +i*-2.55716E-14| +| 14| 0.835648 +i* -0.549265| 1|-2.95892E-13 +i* 2.34143E-13| +| 15| -0.414707 +i* 0.909955| 1| 7.26225E-14 +i*-1.70003E-15| +| 16| -0.133754 +i* -0.991015| 1|-2.88485E-14 +i* 2.14499E-14| +| 17| 0.856687 +i* 0.515837| 1| 1.49106E-13 +i* 3.95153E-14| +| 18| -0.951361 +i* -0.308079| 1| 3.78308E-14 +i* 4.65843E-14| +| 19| 0.969257 +i* -0.24605| 1| 5.51163E-13 +i*-4.79498E-13| +| 20| -0.689285 +i* 0.724491| 1| 2.40086E-15 +i*-3.61777E-14| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 1 +proc 0 +zone limite de 'log-exp' 1.00142 +dimgrid 977 dimblock 256 degrePoly 250000 +proc 0, start 0 size 250112 +proc 0 start 0 size 250112 +iter : 1 Arret : 1.15411E-05 s/iter 13.046733 +iter : 2 Arret : 9.858E-06 s/iter 13.081326 +iter : 3 Arret : 1.15382E-05 s/iter 13.069120 +iter : 4 Arret : 9.47232E-06 s/iter 13.076010 +iter : 5 Arret : 1.17256E-05 s/iter 13.072118 +iter : 6 Arret : 9.56386E-06 s/iter 13.076291 +iter : 7 Arret : 9.97104E-06 s/iter 13.066170 +iter : 8 Arret : 1.14103E-05 s/iter 13.081314 +iter : 9 Arret : 2.05919E-05 s/iter 13.071473 +iter : 10 Arret : 0.000825792 s/iter 13.076037 +iter : 11 Arret : 0.00118923 s/iter 13.070033 +iter : 12 Arret : 0.000993305 s/iter 13.084702 +iter : 13 Arret : 0.00173445 s/iter 13.089852 +iter : 14 Arret : 0.00725752 s/iter 13.071956 +iter : 15 Arret : 0.00431675 s/iter 12.991545 +iter : 16 Arret : 0.00223336 s/iter 10.557352 +iter : 17 Arret : 0.00768504 s/iter 7.919767 +iter : 18 Arret : 0.0589957 s/iter 7.694604 +iter : 19 Arret : 0.25159 s/iter 7.214844 +iter : 20 Arret : 0.00281777 s/iter 7.197502 +iter : 21 Arret : 0.000159366 s/iter 7.094188 +iter : 22 Arret : 6.57562E-05 s/iter 7.066874 +iter : 23 Arret : 3.10389E-05 s/iter 7.014897 +iter : 24 Arret : 1.40727E-05 s/iter 7.069989 +iter : 25 Arret : 1.97654E-05 s/iter 7.070010 +iter : 26 Arret : 1.37694E-05 s/iter 7.006386 +iter : 27 Arret : 7.84672E-07 s/iter 7.000436 +iter : 28 Arret : 2.76696E-10 s/iter 6.995541 +iter : 29 Arret : 5.23691E-16 s/iter 6.993836 +temps : 300.171 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.05316E-09 +Stabilite : 5.23691E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540427 +i* 0.841391| 1| 9.7148E-14 +i*-1.98189E-13| +| 2| -0.997949 +i* 0.0640067| 1| 1.02696E-14 +i* 2.88415E-14| +| 3| 0.450991 +i* -0.892528| 1| 2.39739E-15 +i* 7.66835E-14| +| 4| 0.42851 +i* -0.903537| 1| 1.03733E-13 +i* 1.27433E-14| +| 5| -0.996035 +i* 0.0889649| 1| 5.1386E-14 +i* 4.21729E-14| +| 6| 0.581876 +i* 0.813277| 1| 3.29906E-13 +i* -3.5718E-15| +| 7| 0.405761 +i* -0.913979| 1| 1.69923E-13 +i*-8.86062E-14| +| 8| -0.993496 +i* 0.113867| 1| 6.34562E-14 +i* 6.04291E-14| +| 9| 0.60205 +i* 0.798458| 1| 2.39371E-13 +i* -2.2848E-13| +| 10| 0.382757 +i* -0.923849| 1| 6.36852E-14 +i* 1.1601E-13| +| 11| -0.990335 +i* 0.138698| 1| 8.32286E-14 +i* 4.57395E-14| +| 12| 0.621846 +i* 0.783139| 1| 3.5482E-14 +i*-1.57841E-13| +| 13| 0.359514 +i* -0.93314| 1| 1.00985E-13 +i*-2.52237E-13| +| 14| -0.986553 +i* 0.163442| 1| 3.24636E-14 +i* 4.58574E-14| +| 15| 0.641253 +i* 0.767329| 1| 1.79533E-13 +i* 3.03096E-13| +| 16| 0.336045 +i* -0.941846| 1| 1.38948E-13 +i*-8.14071E-14| +| 17| -0.982153 +i* 0.188084| 1| 6.94549E-14 +i* 3.09405E-14| +| 18| 0.660258 +i* 0.751039| 1| 4.21871E-13 +i* 5.02185E-14| +| 19| 0.312366 +i* -0.949962| 1|-6.37199E-14 +i*-7.39669E-14| +| 20| -0.977138 +i* 0.212608| 1|-3.80633E-14 +i* -8.4285E-14| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 1 +proc 0 +zone limite de 'log-exp' 1.00101 +dimgrid 1368 dimblock 256 degrePoly 350000 +proc 0, start 0 size 350208 +proc 0 start 0 size 350208 +iter : 1 Arret : 8.60988E-06 s/iter 25.315090 +iter : 2 Arret : 7.40762E-06 s/iter 25.250569 +iter : 3 Arret : 7.04966E-06 s/iter 25.240912 +iter : 4 Arret : 7.00431E-06 s/iter 25.295865 +iter : 5 Arret : 6.902E-06 s/iter 25.229976 +iter : 6 Arret : 7.05582E-06 s/iter 25.295774 +iter : 7 Arret : 7.08998E-06 s/iter 25.244072 +iter : 8 Arret : 7.80153E-06 s/iter 25.319330 +iter : 9 Arret : 3.47E-05 s/iter 25.270429 +iter : 10 Arret : 0.000704728 s/iter 25.254028 +iter : 11 Arret : 0.00103416 s/iter 25.267890 +iter : 12 Arret : 0.00106397 s/iter 25.219715 +iter : 13 Arret : 0.860111 s/iter 25.358661 +iter : 14 Arret : 3.1212 s/iter 25.438830 +iter : 15 Arret : 0.0931888 s/iter 25.230396 +iter : 16 Arret : 0.0389072 s/iter 25.512462 +iter : 17 Arret : 0.0434458 s/iter 25.567784 +iter : 18 Arret : 0.0492605 s/iter 25.737787 +iter : 19 Arret : 0.0322665 s/iter 25.683394 +iter : 20 Arret : 0.0311855 s/iter 25.569362 +iter : 21 Arret : 0.0249899 s/iter 24.998756 +iter : 22 Arret : 0.0236284 s/iter 25.007239 +iter : 23 Arret : 0.0147332 s/iter 24.894940 +iter : 24 Arret : 0.0045927 s/iter 25.318951 +iter : 25 Arret : 0.00241036 s/iter 24.996102 +iter : 26 Arret : 0.000981942 s/iter 24.881214 +iter : 27 Arret : 0.000188842 s/iter 24.914979 +iter : 28 Arret : 1.13979E-05 s/iter 24.908900 +iter : 29 Arret : 4.63289E-09 s/iter 24.885179 +iter : 30 Arret : 2.06854E-14 s/iter 24.907560 +temps : 757.352 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.46096E-08 +Stabilite : 2.06854E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540399 +i* 0.841409| 1| 5.12961E-13 +i*-3.37404E-15| +| 2| -0.385479 +i* 0.922716| 1| -1.616E-13 +i*-2.73566E-14| +| 3| -0.770131 +i* 0.637886| 1|-1.38431E-15 +i* 1.70921E-13| +| 4| -0.978357 +i* 0.206925| 1|-3.07393E-15 +i* 4.96131E-15| +| 5| -0.962455 +i* -0.27144| 1|-5.85088E-14 +i* 7.9714E-14| +| 6| -0.72607 +i* -0.687621| 1| -2.0612E-14 +i* 2.87948E-13| +| 7| -0.323352 +i* -0.946279| 1| 2.27159E-13 +i* 7.30891E-14| +| 8| 0.153441 +i* -0.988158| 1| 2.08479E-14 +i* 5.5551E-14| +| 9| 0.595097 +i* -0.803654| 1|-3.46265E-13 +i* 1.60098E-14| +| 10| 0.900408 +i* -0.435047| 1| 3.20081E-13 +i*-1.77827E-14| +| 11| 0.999448 +i* 0.0332229| 1|-5.70342E-13 +i* 1.21308E-12| +| 12| 0.869529 +i* 0.493882| 1| 3.01252E-14 +i* 6.11216E-13| +| 13| 0.211292 +i* 0.977423| 1|-6.97532E-14 +i* 1.23212E-13| +| 14| -0.267139 +i* 0.963658| 1|-9.26238E-14 +i*-7.20968E-14| +| 15| -0.684372 +i* 0.729133| 1| 1.64042E-13 +i*-1.89831E-14| +| 16| -0.944825 +i* 0.327574| 1| 3.70572E-14 +i*-6.84904E-14| +| 17| -0.988833 +i* -0.149027| 1|-1.41002E-13 +i* 2.02581E-14| +| 18| -0.806314 +i* -0.591488| 1| 1.24668E-13 +i*-2.62805E-13| +| 19| -0.439079 +i* -0.898448| 1|-1.76949E-13 +i*-1.05707E-13| +| 20| 0.0287415 +i* -0.999587| 1| 1.62724E-13 +i*-6.82891E-14| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 1 +proc 0 +zone limite de 'log-exp' 1.00071 +dimgrid 1954 dimblock 256 degrePoly 500000 +proc 0, start 0 size 500224 +proc 0 start 0 size 500224 +iter : 1 Arret : 6.15685E-06 s/iter 51.380314 +iter : 2 Arret : 6.30268E-06 s/iter 51.404717 +iter : 3 Arret : 5.43665E-06 s/iter 51.327440 +iter : 4 Arret : 5.82943E-06 s/iter 51.330423 +iter : 5 Arret : 5.29982E-06 s/iter 51.375294 +iter : 6 Arret : 5.48392E-06 s/iter 51.311003 +iter : 7 Arret : 4.9788E-06 s/iter 51.305802 +iter : 8 Arret : 5.28812E-06 s/iter 51.293377 +iter : 9 Arret : 8.66477E-06 s/iter 51.300327 +iter : 10 Arret : 6.18367E-05 s/iter 51.365604 +iter : 11 Arret : 0.00106682 s/iter 51.326802 +iter : 12 Arret : 0.00302391 s/iter 51.361010 +iter : 13 Arret : 0.00805823 s/iter 51.856360 +iter : 14 Arret : 0.00569434 s/iter 51.969477 +iter : 15 Arret : 0.0032212 s/iter 47.185741 +iter : 16 Arret : 1.43264 s/iter 37.596552 +iter : 17 Arret : 0.0261708 s/iter 34.701842 +iter : 18 Arret : 0.0335751 s/iter 32.177584 +iter : 19 Arret : 0.00563912 s/iter 31.261275 +iter : 20 Arret : 0.0024634 s/iter 29.073429 +iter : 21 Arret : 0.00305489 s/iter 28.085556 +iter : 22 Arret : 0.00365771 s/iter 26.833086 +iter : 23 Arret : 0.00250143 s/iter 25.441707 +iter : 24 Arret : 0.00549424 s/iter 24.484295 +iter : 25 Arret : 0.00252639 s/iter 23.169509 +iter : 26 Arret : 5.43905E-05 s/iter 22.350315 +iter : 27 Arret : 1.35324E-06 s/iter 21.912846 +iter : 28 Arret : 9.26795E-09 s/iter 22.036576 +iter : 29 Arret : 2.63961E-14 s/iter 21.824040 +temps : 1148.46 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.48768E-08 +Stabilite : 2.63961E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540372 +i* 0.841426| 1|-3.05235E-13 +i* 1.38721E-13| +| 2| 0.561316 +i* 0.827602| 1|-2.60021E-13 +i* 1.9206E-13| +| 3| 0.57165 +i* 0.820497| 1|-1.83308E-13 +i* 6.15844E-14| +| 4| 0.581895 +i* 0.813264| 1| 3.05839E-13 +i* 6.52482E-14| +| 5| 0.592048 +i* 0.805902| 1|-7.14016E-13 +i*-3.98882E-14| +| 6| 0.602109 +i* 0.798414| 1| 2.66658E-13 +i*-4.75979E-13| +| 7| 0.612074 +i* 0.7908| 1| 3.16743E-13 +i*-3.40844E-13| +| 8| 0.621943 +i* 0.783062| 1| 5.64146E-13 +i*-3.14632E-13| +| 9| 0.631715 +i* 0.775201| 1|-3.83756E-14 +i* 5.41086E-13| +| 10| 0.641387 +i* 0.767218| 1| 4.00499E-13 +i*-3.71465E-13| +| 11| 0.650958 +i* 0.759114| 1| 7.58768E-15 +i*-5.54055E-13| +| 12| 0.660427 +i* 0.750891| 1| 7.47999E-13 +i* 2.73089E-13| +| 13| 0.669792 +i* 0.742549| 1| 9.40577E-13 +i* 3.39433E-14| +| 14| 0.679051 +i* 0.734091| 1| 4.34264E-13 +i*-1.04887E-13| +| 15| 0.688204 +i* 0.725517| 1|-6.26926E-13 +i*-1.86798E-13| +| 16| 0.697248 +i* 0.71683| 1| 2.2389E-13 +i*-9.46795E-14| +| 17| 0.706183 +i* 0.708029| 1| 4.79186E-13 +i* 4.75144E-13| +| 18| 0.715007 +i* 0.699117| 1| 6.39138E-13 +i* 4.95824E-13| +| 19| 0.723718 +i* 0.690096| 1| -1.2694E-13 +i* 4.44528E-13| +| 20| 0.732316 +i* 0.680965| 1|-2.76158E-13 +i* 1.17734E-13| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +proc 0 +zone limite de 'log-exp' 1.00059 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 0, start 0 size 600064 +proc 0 start 0 size 600064 +iter : 1 Arret : 4.88741E-06 s/iter 73.643121 +iter : 2 Arret : 4.97199E-06 s/iter 73.660774 +iter : 3 Arret : 4.86258E-06 s/iter 73.959554 +iter : 4 Arret : 4.28624E-06 s/iter 73.918069 +iter : 5 Arret : 4.70264E-06 s/iter 73.933005 +iter : 6 Arret : 4.85459E-06 s/iter 73.951374 +iter : 7 Arret : 4.4341E-06 s/iter 73.800704 +iter : 8 Arret : 4.56391E-06 s/iter 73.596272 +iter : 9 Arret : 5.75896E-06 s/iter 73.751223 +iter : 10 Arret : 0.000763198 s/iter 73.862761 +iter : 11 Arret : 0.000582931 s/iter 81.937266 +iter : 12 Arret : 0.00224489 s/iter 73.950715 +iter : 13 Arret : 1.80799 s/iter 73.968738 +iter : 14 Arret : 0.0742277 s/iter 74.508413 +iter : 15 Arret : 0.0962999 s/iter 74.277195 +iter : 16 Arret : 0.108643 s/iter 73.517886 +iter : 17 Arret : 0.0724179 s/iter 71.659228 +iter : 18 Arret : 0.105199 s/iter 70.746803 +iter : 19 Arret : 0.146372 s/iter 69.276722 +iter : 20 Arret : 0.117759 s/iter 68.338548 +iter : 21 Arret : 0.00754357 s/iter 67.172870 +iter : 22 Arret : 0.000921826 s/iter 65.662508 +iter : 23 Arret : 0.000616312 s/iter 65.353341 +iter : 24 Arret : 0.00179901 s/iter 65.174928 +iter : 25 Arret : 1.77897E-05 s/iter 65.467629 +iter : 26 Arret : 3.63702E-06 s/iter 65.144205 +iter : 27 Arret : 1.82722E-07 s/iter 65.288149 +iter : 28 Arret : 3.58982E-11 s/iter 64.840549 +iter : 29 Arret : 1.57009E-16 s/iter 64.759606 +temps : 2059.61 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 5.38109E-08 +Stabilite : 1.57009E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540365 +i* 0.841431| 1| 4.39062E-13 +i* 5.83011E-13| +| 2| -0.553493 +i* -0.832854| 1|-5.02858E-13 +i* 3.83374E-15| +| 3| -0.579338 +i* -0.815087| 1| 4.42365E-13 +i* 2.65846E-14| +| 4| 0.592057 +i* 0.805896| 1| 2.06783E-13 +i* 1.94549E-13| +| 5| -0.604613 +i* -0.796519| 1| 2.39135E-13 +i* 2.96967E-13| +| 6| 0.617037 +i* 0.786934| 1|-3.70964E-13 +i* 2.85104E-13| +| 7| -0.629293 +i* -0.777168| 1| 3.4002E-13 +i* 1.14925E-14| +| 8| 0.641411 +i* 0.767198| 1|-6.01835E-13 +i* 5.70316E-13| +| 9| -0.653354 +i* -0.757052| 1| 3.00003E-14 +i* 4.1084E-13| +| 10| 0.665153 +i* 0.746707| 1|-9.55243E-14 +i* 7.739E-13| +| 11| -0.676773 +i* -0.736192| 1|-3.70891E-13 +i* 4.31963E-14| +| 12| 0.688242 +i* 0.725482| 1| 4.17319E-13 +i*-2.25125E-13| +| 13| -0.699526 +i* -0.714607| 1|-1.55074E-13 +i* 3.9467E-13| +| 14| 0.710653 +i* 0.703543| 1|-7.94843E-13 +i* 5.61671E-13| +| 15| -0.721591 +i* -0.69232| 1|-8.20351E-14 +i* 3.39909E-13| +| 16| 0.732366 +i* 0.680912| 1| 5.01595E-13 +i* 2.59279E-13| +| 17| -0.742946 +i* -0.669351| 1|-1.90181E-13 +i* 1.23972E-13| +| 18| 0.753358 +i* 0.657611| 1|-7.14661E-13 +i*-3.96187E-13| +| 19| -0.76357 +i* -0.645725| 1|-3.31242E-13 +i*-8.50865E-14| +| 20| 0.773609 +i* 0.633664| 1|-7.93813E-13 +i* 2.09313E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 1 +proc 0 +zone limite de 'log-exp' 1.00051 +dimgrid 2735 dimblock 256 degrePoly 700000 +proc 0, start 0 size 700160 +proc 0 start 0 size 700160 +iter : 1 Arret : 4.36089E-06 s/iter 100.538329 +iter : 2 Arret : 4.20009E-06 s/iter 100.086525 +iter : 3 Arret : 4.27261E-06 s/iter 100.410161 +iter : 4 Arret : 3.90142E-06 s/iter 100.336287 +iter : 5 Arret : 3.60563E-06 s/iter 100.308817 +iter : 6 Arret : 3.93135E-06 s/iter 100.373492 +iter : 7 Arret : 3.83714E-06 s/iter 100.283845 +iter : 8 Arret : 3.69157E-06 s/iter 100.391852 +iter : 9 Arret : 4.92428E-06 s/iter 100.459479 +iter : 10 Arret : 9.37908E-05 s/iter 100.446598 +iter : 11 Arret : 0.00213526 s/iter 100.396625 +iter : 12 Arret : 0.002542 s/iter 100.503838 +iter : 13 Arret : 0.0125219 s/iter 100.940510 +iter : 14 Arret : 0.010999 s/iter 109.789990 +iter : 15 Arret : 0.00932865 s/iter 109.205901 +iter : 16 Arret : 0.0450638 s/iter 100.884592 +iter : 17 Arret : 0.184973 s/iter 102.656255 +iter : 18 Arret : 0.0519142 s/iter 101.300314 +iter : 19 Arret : 0.0302111 s/iter 100.763046 +iter : 20 Arret : 0.0177202 s/iter 100.248985 +iter : 21 Arret : 0.00863847 s/iter 99.989614 +iter : 22 Arret : 0.00156575 s/iter 99.794924 +iter : 23 Arret : 0.000367723 s/iter 99.510307 +iter : 24 Arret : 0.000179924 s/iter 99.548317 +iter : 25 Arret : 2.80728E-05 s/iter 99.520822 +iter : 26 Arret : 9.99898E-06 s/iter 99.579748 +iter : 27 Arret : 2.46675E-08 s/iter 99.458855 +iter : 28 Arret : 9.85491E-15 s/iter 99.607347 +temps : 2827.9 seconde(s) +Nb iterations : 28 +Nb de depassements de capacite exponentielle : 0 +Precision : 7.46263E-08 +Stabilite : 9.85491E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540352 +i* 0.841439| 1| 4.39978E-13 +i* 6.25043E-13| +| 2| -0.996034 +i* 0.0889731| 1| 2.2073E-13 +i* 1.55296E-13| +| 3| 0.439836 +i* -0.898078| 1|-3.55927E-13 +i*-1.21738E-13| +| 4| 0.38266 +i* -0.923889| 1|-2.56142E-13 +i*-7.02285E-14| +| 5| -0.988496 +i* 0.15125| 1|-1.52652E-13 +i*-1.11329E-13| +| 6| 0.641421 +i* 0.767189| 1|-1.31044E-13 +i* 5.61736E-13| +| 7| 0.323979 +i* -0.946064| 1|-4.52336E-13 +i* 8.74596E-14| +| 8| -0.977067 +i* 0.212932| 1| 8.58341E-14 +i* 1.73412E-13| +| 9| 0.688262 +i* 0.725462| 1| 4.28754E-14 +i* 1.08849E-12| +| 10| 0.264022 +i* -0.964517| 1|-3.63883E-13 +i*-8.14886E-14| +| 11| -0.961793 +i* 0.273776| 1| -3.0213E-13 +i*-2.13897E-13| +| 12| 0.732395 +i* 0.68088| 1|-3.65194E-14 +i* 7.95483E-13| +| 13| 0.203027 +i* -0.979173| 1|-3.14502E-13 +i* 2.96924E-13| +| 14| -0.942735 +i* 0.333543| 1| 1.82947E-13 +i*-4.73458E-14| +| 15| 0.773646 +i* 0.633619| 1| 2.24352E-13 +i* 2.79674E-13| +| 16| 0.141232 +i* -0.989977| 1| -1.0035E-13 +i* 1.5693E-13| +| 17| -0.919967 +i* 0.391997| 1| 2.89213E-14 +i*-1.86252E-13| +| 18| 0.811852 +i* 0.583864| 1|-1.59939E-12 +i*-4.13669E-13| +| 19| 0.0788818 +i* -0.996884| 1|-2.83003E-13 +i* 1.04711E-13| +| 20| -0.893578 +i* 0.448908| 1| 4.59736E-14 +i* 1.31414E-13| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 1 +proc 0 +zone limite de 'log-exp' 1.00044 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 0, start 0 size 800000 +proc 0 start 0 size 800000 +iter : 1 Arret : 3.83515E-06 s/iter 131.128367 +iter : 2 Arret : 3.31342E-06 s/iter 130.895719 +iter : 3 Arret : 3.46185E-06 s/iter 130.774185 +iter : 4 Arret : 3.77822E-06 s/iter 130.629629 +iter : 5 Arret : 3.54151E-06 s/iter 131.099737 +iter : 6 Arret : 3.39913E-06 s/iter 130.729467 +iter : 7 Arret : 3.37038E-06 s/iter 130.632620 +iter : 8 Arret : 3.66135E-06 s/iter 130.656450 +iter : 9 Arret : 5.18164E-06 s/iter 130.618912 +iter : 10 Arret : 3.60623E-05 s/iter 130.609820 +iter : 11 Arret : 0.000919045 s/iter 130.931691 +iter : 12 Arret : 0.0269508 s/iter 130.735832 +iter : 13 Arret : 2.00753 s/iter 131.562739 +iter : 14 Arret : 0.113163 s/iter 131.675926 +iter : 15 Arret : 0.114468 s/iter 132.383980 +iter : 16 Arret : 0.0343723 s/iter 131.231628 +iter : 17 Arret : 0.0118406 s/iter 126.227547 +iter : 18 Arret : 0.00584689 s/iter 120.723541 +iter : 19 Arret : 0.00603455 s/iter 116.384134 +iter : 20 Arret : 0.00445856 s/iter 111.422234 +iter : 21 Arret : 0.00344019 s/iter 106.222631 +iter : 22 Arret : 0.000542325 s/iter 99.990260 +iter : 23 Arret : 0.00265194 s/iter 95.378338 +iter : 24 Arret : 0.00180528 s/iter 92.586290 +iter : 25 Arret : 4.07819E-06 s/iter 91.103601 +iter : 26 Arret : 1.49379E-06 s/iter 89.796006 +iter : 27 Arret : 7.96771E-09 s/iter 90.012737 +iter : 28 Arret : 1.91442E-14 s/iter 90.007579 +temps : 3326.77 seconde(s) +Nb iterations : 28 +Nb de depassements de capacite exponentielle : 0 +Precision : 6.26383E-08 +Stabilite : 1.91442E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540349 +i* 0.841441| 1|-1.16344E-13 +i* 9.55619E-13| +| 2| 0.592061 +i* 0.805893| 1|-1.57249E-13 +i*-4.43364E-13| +| 3| 0.617051 +i* 0.786923| 1|-6.42805E-13 +i*-3.49094E-13| +| 4| 0.641434 +i* 0.767178| 1| 1.00022E-12 +i*-5.90578E-13| +| 5| 0.665186 +i* 0.746678| 1|-2.53998E-14 +i*-1.14684E-12| +| 6| 0.688283 +i* 0.725442| 1|-8.68732E-13 +i* 8.52696E-13| +| 7| 0.710703 +i* 0.703493| 1| 2.02581E-13 +i* 4.54699E-13| +| 8| 0.732422 +i* 0.680851| 1|-5.22353E-13 +i*-3.99873E-13| +| 9| 0.753421 +i* 0.657538| 1| 1.23356E-13 +i*-1.05986E-12| +| 10| 0.773678 +i* 0.633579| 1|-6.75196E-13 +i* 3.60108E-13| +| 11| 0.793174 +i* 0.608995| 1| 4.43853E-13 +i*-1.42398E-12| +| 12| 0.811888 +i* 0.583813| 1|-4.10491E-13 +i*-4.46651E-13| +| 13| 0.829804 +i* 0.558055| 1| 1.30045E-12 +i* 1.12788E-13| +| 14| 0.846902 +i* 0.531748| 1|-8.09419E-13 +i* 4.98091E-13| +| 15| 0.863167 +i* 0.504918| 1| 2.98522E-13 +i* 3.81547E-13| +| 16| 0.878582 +i* 0.477591| 1|-3.06581E-13 +i*-6.95869E-13| +| 17| 0.893133 +i* 0.449793| 1| 1.24355E-13 +i* -1.3239E-12| +| 18| 0.906804 +i* 0.421553| 1|-1.23117E-12 +i*-5.57117E-13| +| 19| 0.919582 +i* 0.392898| 1|-1.03648E-12 +i* 2.90445E-14| +| 20| 0.931455 +i* 0.363856| 1|-6.42708E-13 +i*-1.50318E-12| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 1 diff --git a/Simulations/full_mpi/full_mpi_1GPU.sge b/Simulations/full_mpi/full_mpi_1GPU.sge new file mode 100644 index 0000000..fd35afa --- /dev/null +++ b/Simulations/full_mpi/full_mpi_1GPU.sge @@ -0,0 +1,25 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=1 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -V +#$ -cwd +#$ -N full_mpi_1GPU +#$ -pe mpi 1 + + +module load cuda/7.0 +module load ompi/gcc + +mpirun -np $NSLOTS ./template -r -i 60000 40000 +mpirun -np $NSLOTS ./template -r -i 150000 50000 +mpirun -np $NSLOTS ./template -r -i 250000 150000 +mpirun -np $NSLOTS ./template -r -i 350000 250000 +mpirun -np $NSLOTS ./template -r -i 500000 300000 +mpirun -np $NSLOTS ./template -r -i 600000 400000 +mpirun -np $NSLOTS ./template -r -i 700000 500000 +mpirun -np $NSLOTS ./template -r -i 800000 600000 +#mpirun -np $NSLOTS ./template -r -i 900000 700000 +#mpirun -np $NSLOTS ./template -r -i 1000000 800000 +#mpirun -np $NSLOTS ./template -r -i 1500000 500000 diff --git a/Simulations/full_mpi/full_mpi_2GPU.o140160 b/Simulations/full_mpi/full_mpi_2GPU.o140160 new file mode 100644 index 0000000..8016229 --- /dev/null +++ b/Simulations/full_mpi/full_mpi_2GPU.o140160 @@ -0,0 +1,562 @@ +REMAINING: 2 +Taking GPU #0 +Taking GPU #1 +proc 0 +proc 1 +zone limite de 'log-exp' 1.00593 +zone limite de 'log-exp' 1.00593 +dimgrid 235 dimblock 256 degrePoly 60000 +proc 1, start 30080 size 30080 +proc 1 start 30080 size 30080 +dimgrid 235 dimblock 256 degrePoly 60000 +proc 0, start 0 size 30080 +proc 0 start 0 size 30080 +iter : 1 Arret : 3.94715E-05 s/iter 0.376579 +iter : 2 Arret : 4.00498E-05 s/iter 0.376426 +iter : 3 Arret : 3.94982E-05 s/iter 0.376469 +iter : 4 Arret : 3.91196E-05 s/iter 0.376474 +iter : 5 Arret : 4.06401E-05 s/iter 0.376476 +iter : 6 Arret : 4.41482E-05 s/iter 0.376495 +iter : 7 Arret : 5.50716E-05 s/iter 0.376547 +iter : 8 Arret : 0.000118504 s/iter 0.376518 +iter : 9 Arret : 0.00115954 s/iter 0.376505 +iter : 10 Arret : 0.0219062 s/iter 0.376584 +iter : 11 Arret : 2.08077 s/iter 1.164908 +iter : 12 Arret : 0.274053 s/iter 0.376485 +iter : 13 Arret : 0.163438 s/iter 1.196444 +iter : 14 Arret : 0.0502837 s/iter 1.195663 +iter : 15 Arret : 0.0171551 s/iter 1.191447 +iter : 16 Arret : 0.00931569 s/iter 1.183639 +iter : 17 Arret : 0.00645054 s/iter 1.167546 +iter : 18 Arret : 0.00448467 s/iter 0.370707 +iter : 19 Arret : 0.00168489 s/iter 0.366051 +iter : 20 Arret : 0.00126146 s/iter 0.365448 +iter : 21 Arret : 0.0157645 s/iter 0.356946 +iter : 22 Arret : 0.00414432 s/iter 0.349791 +iter : 23 Arret : 0.0293605 s/iter 0.344674 +iter : 24 Arret : 0.000309791 s/iter 0.347406 +iter : 25 Arret : 0.000479548 s/iter 0.344763 +iter : 26 Arret : 0.000172889 s/iter 0.342501 +iter : 27 Arret : 2.54873E-05 s/iter 0.344592 +iter : 28 Arret : 6.36446E-08 s/iter 0.343705 +iter : 29 Arret : 1.95655E-12 s/iter 0.343232 +iter : 30 Arret : 1.11022E-16 s/iter 0.343867 +temps : 15.9313 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.35784E-10 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540783 +i* 0.841162| 1|-7.58456E-14 +i* 3.78031E-14| +| 2| -0.992343 +i* -0.123513| 1|-2.28637E-15 +i*-5.45917E-15| +| 3| 0.0563346 +i* 0.998412| 1| 5.70377E-15 +i* 3.3501E-14| +| 4| -0.802793 +i* -0.596258| 1| 2.03657E-15 +i* 1.01915E-14| +| 5| 0.730552 +i* -0.682857| 1|-7.48429E-14 +i* 6.77011E-14| +| 6| -0.442728 +i* 0.896656| 1|-3.77198E-14 +i*-1.89779E-15| +| 7| -0.404888 +i* -0.914366| 1| 3.20195E-14 +i* 9.65894E-15| +| 8| 0.972126 +i* -0.23446| 1| 4.02421E-14 +i*-1.54755E-14| +| 9| -0.826939 +i* 0.562292| 1| -2.4928E-14 +i*-1.59889E-14| +| 10| 0.0979895 +i* -0.995187| 1| 2.90878E-14 +i*-6.75675E-15| +| 11| 0.961513 +i* 0.27476| 1|-9.39769E-14 +i*-2.63912E-13| +| 12| -0.996627 +i* 0.0820589| 1| 2.39773E-14 +i* 1.74825E-14| +| 13| 0.575447 +i* -0.817839| 1|-3.49894E-14 +i*-7.98545E-14| +| 14| 0.701466 +i* 0.712703| 1| 7.52211E-14 +i* 1.53991E-14| +| 15| 0.259346 +i* 0.965785| 1|-2.14863E-14 +i*-2.81355E-14| +| 16| -0.907773 +i* -0.419461| 1|-3.62869E-14 +i*-9.49414E-15| +| 17| 0.903623 +i* -0.428329| 1|-1.24969E-14 +i* 7.51222E-14| +| 18| -0.249979 +i* 0.968251| 1|-1.59074E-14 +i*-1.09721E-14| +| 19| -0.583341 +i* -0.812227| 1| 1.92242E-14 +i* 2.27058E-14| +| 20| 0.997383 +i* 0.072297| 1| 2.53037E-13 +i*-5.92819E-13| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 1 +proc 1 +proc 0 +zone limite de 'log-exp' 1.00237 +zone limite de 'log-exp' 1.00237 +dimgrid 586 dimblock 256 degrePoly 150000 +proc 1, start 75008 size 75008 +dimgrid 586 dimblock 256 degrePoly 150000 +proc 0, start 0 size 75008 +proc 0 start 0 size 75008 +proc 1 start 75008 size 75008 +iter : 1 Arret : 1.60943E-05 s/iter 2.350355 +iter : 2 Arret : 1.67528E-05 s/iter 2.342992 +iter : 3 Arret : 1.68978E-05 s/iter 2.337485 +iter : 4 Arret : 1.60377E-05 s/iter 2.337553 +iter : 5 Arret : 1.62156E-05 s/iter 2.337558 +iter : 6 Arret : 1.69292E-05 s/iter 2.337450 +iter : 7 Arret : 1.84639E-05 s/iter 2.337768 +iter : 8 Arret : 2.25051E-05 s/iter 2.337545 +iter : 9 Arret : 4.76681E-05 s/iter 2.337634 +iter : 10 Arret : 0.00245562 s/iter 2.337594 +iter : 11 Arret : 0.00371283 s/iter 2.337716 +iter : 12 Arret : 0.010769 s/iter 2.910185 +iter : 13 Arret : 1.55694 s/iter 4.438167 +iter : 14 Arret : 0.116538 s/iter 2.911091 +iter : 15 Arret : 0.0585023 s/iter 3.939639 +iter : 16 Arret : 0.0321741 s/iter 3.902393 +iter : 17 Arret : 0.0186974 s/iter 3.930056 +iter : 18 Arret : 0.00687909 s/iter 3.962909 +iter : 19 Arret : 0.0214989 s/iter 2.321178 +iter : 20 Arret : 0.00865216 s/iter 3.260664 +iter : 21 Arret : 0.0168761 s/iter 3.221472 +iter : 22 Arret : 0.0147692 s/iter 4.261763 +iter : 23 Arret : 0.0125239 s/iter 2.251272 +iter : 24 Arret : 0.000664965 s/iter 2.239406 +iter : 25 Arret : 1.59841E-05 s/iter 2.245565 +iter : 26 Arret : 5.40825E-07 s/iter 2.231696 +iter : 27 Arret : 8.52059E-11 s/iter 2.240876 +iter : 28 Arret : 7.75295E-16 s/iter 2.238326 +temps : 78.4263 seconde(s) +Nb iterations : 28 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.26535E-09 +Stabilite : 7.75295E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540528 +i* 0.841326| 1| 8.68923E-14 +i* 2.2979E-13| +| 2| -0.905603 +i* -0.424127| 1| 6.50001E-14 +i* -3.0061E-14| +| 3| -0.774122 +i* 0.633037| 1|-3.89619E-14 +i*-6.71876E-14| +| 4| 0.317935 +i* -0.948113| 1| 4.656E-15 +i* 1.15645E-13| +| 5| 0.23606 +i* 0.971739| 1| 2.9924E-14 +i*-1.32854E-13| +| 6| -0.717299 +i* -0.696766| 1| 5.63785E-15 +i*-6.71685E-14| +| 7| 0.992349 +i* -0.123462| 1|-4.81056E-13 +i* 9.00335E-13| +| 8| -0.938482 +i* 0.345329| 1|-6.95555E-14 +i*-3.79159E-14| +| 9| 0.610294 +i* -0.792175| 1| -5.4852E-14 +i*-3.26232E-14| +| 10| -0.0946394 +i* 0.995512| 1|-4.73788E-14 +i*-8.10827E-14| +| 11| -0.450242 +i* -0.892906| 1| 2.41855E-14 +i*-3.23699E-15| +| 12| 0.978218 +i* 0.207583| 1|-2.84429E-13 +i* 4.69725E-13| +| 13| -0.999806 +i* 0.0197069| 1|-4.72365E-14 +i*-2.55716E-14| +| 14| 0.835648 +i* -0.549265| 1|-2.95892E-13 +i* 2.34143E-13| +| 15| -0.414707 +i* 0.909955| 1| 7.26225E-14 +i*-1.70003E-15| +| 16| -0.133754 +i* -0.991015| 1|-2.88485E-14 +i* 2.14499E-14| +| 17| 0.856687 +i* 0.515837| 1| 1.49106E-13 +i* 3.95153E-14| +| 18| -0.951361 +i* -0.308079| 1| 3.78308E-14 +i* 4.65843E-14| +| 19| 0.969257 +i* -0.24605| 1| 5.51163E-13 +i*-4.79498E-13| +| 20| -0.689285 +i* 0.724491| 1| 2.40086E-15 +i*-3.61777E-14| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 1 +proc 0 +proc 1 +zone limite de 'log-exp' 1.00142 +zone limite de 'log-exp' 1.00142 +dimgrid 977 dimblock 256 degrePoly 250000 +proc 0, start 0 size 125056 +proc 0 start 0 size 125056 +dimgrid 977 dimblock 256 degrePoly 250000 +proc 1, start 125056 size 125056 +proc 1 start 125056 size 125056 +iter : 1 Arret : 1.04122E-05 s/iter 6.893601 +iter : 2 Arret : 9.66995E-06 s/iter 6.882320 +iter : 3 Arret : 9.55261E-06 s/iter 6.898899 +iter : 4 Arret : 9.22665E-06 s/iter 6.899113 +iter : 5 Arret : 9.50477E-06 s/iter 6.894819 +iter : 6 Arret : 9.562E-06 s/iter 6.896301 +iter : 7 Arret : 9.85225E-06 s/iter 6.898079 +iter : 8 Arret : 1.00444E-05 s/iter 6.895828 +iter : 9 Arret : 1.26197E-05 s/iter 6.906197 +iter : 10 Arret : 0.000374245 s/iter 6.892279 +iter : 11 Arret : 0.000473147 s/iter 6.894504 +iter : 12 Arret : 0.00101736 s/iter 6.894983 +iter : 13 Arret : 0.00428892 s/iter 6.893815 +iter : 14 Arret : 0.0152171 s/iter 6.896640 +iter : 15 Arret : 0.00947972 s/iter 6.813081 +iter : 16 Arret : 0.00590834 s/iter 8.502086 +iter : 17 Arret : 0.0148154 s/iter 4.292037 +iter : 18 Arret : 0.303776 s/iter 4.191474 +iter : 19 Arret : 0.00212739 s/iter 4.153373 +iter : 20 Arret : 0.00703257 s/iter 3.618613 +iter : 21 Arret : 0.00722956 s/iter 5.063281 +iter : 22 Arret : 0.000539584 s/iter 3.599227 +iter : 23 Arret : 0.000175798 s/iter 3.593595 +iter : 24 Arret : 1.72224E-05 s/iter 3.538749 +iter : 25 Arret : 0.000115569 s/iter 3.554657 +iter : 26 Arret : 0.000113543 s/iter 3.546651 +iter : 27 Arret : 4.63885E-05 s/iter 3.544304 +iter : 28 Arret : 1.37358E-05 s/iter 3.565583 +iter : 29 Arret : 2.47356E-07 s/iter 3.564036 +iter : 30 Arret : 2.5459E-12 s/iter 3.540899 +iter : 31 Arret : 1.11022E-16 s/iter 3.548698 +temps : 169.022 seconde(s) +Nb iterations : 31 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.05316E-09 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540427 +i* 0.841391| 1| 9.7148E-14 +i*-1.98189E-13| +| 2| -0.997949 +i* 0.0640067| 1| 1.02696E-14 +i* 2.88415E-14| +| 3| 0.450991 +i* -0.892528| 1| 2.39739E-15 +i* 7.66835E-14| +| 4| 0.42851 +i* -0.903537| 1| 1.03733E-13 +i* 1.27433E-14| +| 5| -0.996035 +i* 0.0889649| 1| 5.1386E-14 +i* 4.21729E-14| +| 6| 0.581876 +i* 0.813277| 1| 3.29906E-13 +i* -3.5718E-15| +| 7| 0.405761 +i* -0.913979| 1| 1.69923E-13 +i*-8.86062E-14| +| 8| -0.993496 +i* 0.113867| 1| 6.34562E-14 +i* 6.04291E-14| +| 9| 0.60205 +i* 0.798458| 1| 2.39371E-13 +i* -2.2848E-13| +| 10| 0.382757 +i* -0.923849| 1| 6.36852E-14 +i* 1.1601E-13| +| 11| -0.990335 +i* 0.138698| 1| 8.32286E-14 +i* 4.57395E-14| +| 12| 0.621846 +i* 0.783139| 1| 3.5482E-14 +i*-1.57841E-13| +| 13| 0.359514 +i* -0.93314| 1| 1.00985E-13 +i*-2.52237E-13| +| 14| -0.986553 +i* 0.163442| 1| 3.24636E-14 +i* 4.58574E-14| +| 15| 0.641253 +i* 0.767329| 1| 1.79533E-13 +i* 3.03096E-13| +| 16| 0.336045 +i* -0.941846| 1| 1.38948E-13 +i*-8.14071E-14| +| 17| -0.982153 +i* 0.188084| 1| 6.94549E-14 +i* 3.09405E-14| +| 18| 0.660258 +i* 0.751039| 1| 4.21871E-13 +i* 5.02185E-14| +| 19| 0.312366 +i* -0.949962| 1|-6.37199E-14 +i*-7.39669E-14| +| 20| -0.977138 +i* 0.212608| 1|-3.80633E-14 +i* -8.4285E-14| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 1 +proc 1 +proc 0 +zone limite de 'log-exp' 1.00101 +zone limite de 'log-exp' 1.00101 +dimgrid 1368 dimblock 256 degrePoly 350000 +proc 1, start 175104 size 175104 +dimgrid 1368 dimblock 256 degrePoly 350000 +proc 0, start 0 size 175104 +proc 0 start 0 size 175104 +proc 1 start 175104 size 175104 +iter : 1 Arret : 7.23955E-06 s/iter 12.988714 +iter : 2 Arret : 8.17362E-06 s/iter 12.961404 +iter : 3 Arret : 7.81796E-06 s/iter 12.964651 +iter : 4 Arret : 7.21292E-06 s/iter 12.968827 +iter : 5 Arret : 7.55071E-06 s/iter 12.967829 +iter : 6 Arret : 7.49029E-06 s/iter 12.964916 +iter : 7 Arret : 7.62064E-06 s/iter 12.963339 +iter : 8 Arret : 7.80044E-06 s/iter 12.963493 +iter : 9 Arret : 9.75039E-06 s/iter 12.964925 +iter : 10 Arret : 0.000863071 s/iter 12.969839 +iter : 11 Arret : 0.000849607 s/iter 12.969054 +iter : 12 Arret : 0.00104766 s/iter 12.964139 +iter : 13 Arret : 0.831471 s/iter 12.972067 +iter : 14 Arret : 3.38426 s/iter 12.966001 +iter : 15 Arret : 0.107189 s/iter 12.934545 +iter : 16 Arret : 0.0542638 s/iter 16.933464 +iter : 17 Arret : 0.0319719 s/iter 16.802921 +iter : 18 Arret : 0.0123162 s/iter 17.515009 +iter : 19 Arret : 0.021246 s/iter 17.702219 +iter : 20 Arret : 0.0113278 s/iter 17.796152 +iter : 21 Arret : 0.0245772 s/iter 17.074640 +iter : 22 Arret : 0.00540155 s/iter 17.506599 +iter : 23 Arret : 0.00765026 s/iter 12.838465 +iter : 24 Arret : 0.0115831 s/iter 12.839289 +iter : 25 Arret : 0.0115203 s/iter 12.887210 +iter : 26 Arret : 0.000774924 s/iter 12.835436 +iter : 27 Arret : 0.000228102 s/iter 12.835530 +iter : 28 Arret : 0.000225979 s/iter 12.834198 +iter : 29 Arret : 2.70389E-05 s/iter 12.835221 +iter : 30 Arret : 1.29617E-05 s/iter 12.835156 +iter : 31 Arret : 1.12344E-06 s/iter 12.834214 +iter : 32 Arret : 1.60825E-09 s/iter 12.834300 +iter : 33 Arret : 5.97777E-15 s/iter 12.836140 +temps : 457.417 seconde(s) +Nb iterations : 33 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.46096E-08 +Stabilite : 5.97777E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540399 +i* 0.841409| 1| 5.12961E-13 +i*-3.37404E-15| +| 2| -0.385479 +i* 0.922716| 1| -1.616E-13 +i*-2.73566E-14| +| 3| -0.770131 +i* 0.637886| 1|-1.38431E-15 +i* 1.70921E-13| +| 4| -0.978357 +i* 0.206925| 1|-3.07393E-15 +i* 4.96131E-15| +| 5| -0.962455 +i* -0.27144| 1|-5.85088E-14 +i* 7.9714E-14| +| 6| -0.72607 +i* -0.687621| 1| -2.0612E-14 +i* 2.87948E-13| +| 7| -0.323352 +i* -0.946279| 1| 2.27159E-13 +i* 7.30891E-14| +| 8| 0.153441 +i* -0.988158| 1| 2.08479E-14 +i* 5.5551E-14| +| 9| 0.595097 +i* -0.803654| 1|-3.46265E-13 +i* 1.60098E-14| +| 10| 0.900408 +i* -0.435047| 1| 3.20081E-13 +i*-1.77827E-14| +| 11| 0.999448 +i* 0.0332229| 1|-5.70342E-13 +i* 1.21308E-12| +| 12| 0.869529 +i* 0.493882| 1| 3.01252E-14 +i* 6.11216E-13| +| 13| 0.211292 +i* 0.977423| 1|-6.97532E-14 +i* 1.23212E-13| +| 14| -0.267139 +i* 0.963658| 1|-9.26238E-14 +i*-7.20968E-14| +| 15| -0.684372 +i* 0.729133| 1| 1.64042E-13 +i*-1.89831E-14| +| 16| -0.944825 +i* 0.327574| 1| 3.70572E-14 +i*-6.84904E-14| +| 17| -0.988833 +i* -0.149027| 1|-1.41002E-13 +i* 2.02581E-14| +| 18| -0.806314 +i* -0.591488| 1| 1.24668E-13 +i*-2.62805E-13| +| 19| -0.439079 +i* -0.898448| 1|-1.76949E-13 +i*-1.05707E-13| +| 20| 0.0287415 +i* -0.999587| 1| 1.62724E-13 +i*-6.82891E-14| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 1 +proc 0 +proc 1 +zone limite de 'log-exp' 1.00071 +zone limite de 'log-exp' 1.00071 +dimgrid 1954 dimblock 256 degrePoly 500000 +proc 1, start 250112 size 250112 +proc 1 start 250112 size 250112 +dimgrid 1954 dimblock 256 degrePoly 500000 +proc 0, start 0 size 250112 +proc 0 start 0 size 250112 +iter : 1 Arret : 4.9348E-06 s/iter 26.306811 +iter : 2 Arret : 5.74497E-06 s/iter 26.125397 +iter : 3 Arret : 5.90879E-06 s/iter 26.122962 +iter : 4 Arret : 5.45965E-06 s/iter 26.117846 +iter : 5 Arret : 5.51053E-06 s/iter 26.113294 +iter : 6 Arret : 5.44166E-06 s/iter 26.107906 +iter : 7 Arret : 5.61587E-06 s/iter 26.108065 +iter : 8 Arret : 5.37769E-06 s/iter 26.112535 +iter : 9 Arret : 6.392E-06 s/iter 26.112787 +iter : 10 Arret : 0.000222412 s/iter 26.105165 +iter : 11 Arret : 0.00364174 s/iter 26.108847 +iter : 12 Arret : 0.00224664 s/iter 28.294492 +iter : 13 Arret : 0.00428508 s/iter 29.203574 +iter : 14 Arret : 0.00509531 s/iter 32.497063 +iter : 15 Arret : 0.00237252 s/iter 26.034125 +iter : 16 Arret : 0.0225054 s/iter 21.475326 +iter : 17 Arret : 1.39022 s/iter 22.775590 +iter : 18 Arret : 0.0380632 s/iter 21.509248 +iter : 19 Arret : 0.0147501 s/iter 20.099820 +iter : 20 Arret : 0.0175634 s/iter 15.352961 +iter : 21 Arret : 0.00896774 s/iter 19.613858 +iter : 22 Arret : 0.00146838 s/iter 16.233299 +iter : 23 Arret : 0.000316321 s/iter 13.214624 +iter : 24 Arret : 0.000122654 s/iter 13.000460 +iter : 25 Arret : 4.91927E-05 s/iter 12.525060 +iter : 26 Arret : 2.33271E-06 s/iter 11.550850 +iter : 27 Arret : 3.0703E-06 s/iter 11.616325 +iter : 28 Arret : 4.34623E-07 s/iter 11.570420 +iter : 29 Arret : 4.32022E-10 s/iter 11.514451 +iter : 30 Arret : 1.24127E-15 s/iter 11.583468 +temps : 637.538 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.48768E-08 +Stabilite : 1.24127E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540372 +i* 0.841426| 1|-3.05235E-13 +i* 1.38721E-13| +| 2| 0.561316 +i* 0.827602| 1|-2.60021E-13 +i* 1.9206E-13| +| 3| 0.57165 +i* 0.820497| 1|-1.83308E-13 +i* 6.15844E-14| +| 4| 0.581895 +i* 0.813264| 1| 3.05839E-13 +i* 6.52482E-14| +| 5| 0.592048 +i* 0.805902| 1|-7.14016E-13 +i*-3.98882E-14| +| 6| 0.602109 +i* 0.798414| 1| 2.66658E-13 +i*-4.75979E-13| +| 7| 0.612074 +i* 0.7908| 1| 3.16743E-13 +i*-3.40844E-13| +| 8| 0.621943 +i* 0.783062| 1| 5.64146E-13 +i*-3.14632E-13| +| 9| 0.631715 +i* 0.775201| 1|-3.83756E-14 +i* 5.41086E-13| +| 10| 0.641387 +i* 0.767218| 1| 4.00499E-13 +i*-3.71465E-13| +| 11| 0.650958 +i* 0.759114| 1| 7.58768E-15 +i*-5.54055E-13| +| 12| 0.660427 +i* 0.750891| 1| 7.47999E-13 +i* 2.73089E-13| +| 13| 0.669792 +i* 0.742549| 1| 9.40577E-13 +i* 3.39433E-14| +| 14| 0.679051 +i* 0.734091| 1| 4.34264E-13 +i*-1.04887E-13| +| 15| 0.688204 +i* 0.725517| 1|-6.26926E-13 +i*-1.86798E-13| +| 16| 0.697248 +i* 0.71683| 1| 2.2389E-13 +i*-9.46795E-14| +| 17| 0.706183 +i* 0.708029| 1| 4.79186E-13 +i* 4.75144E-13| +| 18| 0.715007 +i* 0.699117| 1| 6.39138E-13 +i* 4.95824E-13| +| 19| 0.723718 +i* 0.690096| 1| -1.2694E-13 +i* 4.44528E-13| +| 20| 0.732316 +i* 0.680965| 1|-2.76158E-13 +i* 1.17734E-13| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +proc 0 +proc 1 +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 1, start 300032 size 300032 +proc 1 start 300032 size 300032 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 0, start 0 size 300032 +proc 0 start 0 size 300032 +iter : 1 Arret : 4.75638E-06 s/iter 37.194622 +iter : 2 Arret : 4.76706E-06 s/iter 37.169379 +iter : 3 Arret : 4.56609E-06 s/iter 37.187098 +iter : 4 Arret : 4.96449E-06 s/iter 37.189698 +iter : 5 Arret : 4.6101E-06 s/iter 37.190980 +iter : 6 Arret : 4.67386E-06 s/iter 37.170837 +iter : 7 Arret : 4.4173E-06 s/iter 37.184958 +iter : 8 Arret : 4.5841E-06 s/iter 37.189119 +iter : 9 Arret : 5.81936E-06 s/iter 37.194076 +iter : 10 Arret : 9.61381E-05 s/iter 37.202796 +iter : 11 Arret : 0.00253702 s/iter 37.201994 +iter : 12 Arret : 0.00382237 s/iter 43.720161 +iter : 13 Arret : 1.98237 s/iter 37.268722 +iter : 14 Arret : 0.139529 s/iter 43.928325 +iter : 15 Arret : 0.0833681 s/iter 37.165670 +iter : 16 Arret : 0.0902433 s/iter 37.013464 +iter : 17 Arret : 0.0538083 s/iter 36.747709 +iter : 18 Arret : 0.0285517 s/iter 42.040931 +iter : 19 Arret : 0.0244232 s/iter 35.402712 +iter : 20 Arret : 0.0156356 s/iter 34.951257 +iter : 21 Arret : 0.00306159 s/iter 34.044015 +iter : 22 Arret : 0.00259881 s/iter 33.314225 +iter : 23 Arret : 0.0020894 s/iter 33.562042 +iter : 24 Arret : 0.000144328 s/iter 32.902500 +iter : 25 Arret : 4.2377E-05 s/iter 32.909701 +iter : 26 Arret : 7.50207E-06 s/iter 33.017508 +iter : 27 Arret : 4.17723E-07 s/iter 32.694117 +iter : 28 Arret : 3.57073E-10 s/iter 32.849709 +iter : 29 Arret : 1.04738E-15 s/iter 32.706464 +temps : 1055.82 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 5.38109E-08 +Stabilite : 1.57009E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540365 +i* 0.841431| 1| 4.39062E-13 +i* 5.83011E-13| +| 2| -0.553493 +i* -0.832854| 1|-5.02858E-13 +i* 3.83374E-15| +| 3| -0.579338 +i* -0.815087| 1| 4.42365E-13 +i* 2.65846E-14| +| 4| 0.592057 +i* 0.805896| 1| 2.06783E-13 +i* 1.94549E-13| +| 5| -0.604613 +i* -0.796519| 1| 2.39135E-13 +i* 2.96967E-13| +| 6| 0.617037 +i* 0.786934| 1|-3.70964E-13 +i* 2.85104E-13| +| 7| -0.629293 +i* -0.777168| 1| 3.4002E-13 +i* 1.14925E-14| +| 8| 0.641411 +i* 0.767198| 1|-6.01835E-13 +i* 5.70316E-13| +| 9| -0.653354 +i* -0.757052| 1| 3.00003E-14 +i* 4.1084E-13| +| 10| 0.665153 +i* 0.746707| 1|-9.55243E-14 +i* 7.739E-13| +| 11| -0.676773 +i* -0.736192| 1|-3.70891E-13 +i* 4.31963E-14| +| 12| 0.688242 +i* 0.725482| 1| 4.17319E-13 +i*-2.25125E-13| +| 13| -0.699526 +i* -0.714607| 1|-1.55074E-13 +i* 3.9467E-13| +| 14| 0.710653 +i* 0.703543| 1|-7.94843E-13 +i* 5.61671E-13| +| 15| -0.721591 +i* -0.69232| 1|-8.20351E-14 +i* 3.39909E-13| +| 16| 0.732366 +i* 0.680912| 1| 5.01595E-13 +i* 2.59279E-13| +| 17| -0.742946 +i* -0.669351| 1|-1.90181E-13 +i* 1.23972E-13| +| 18| 0.753358 +i* 0.657611| 1|-7.14661E-13 +i*-3.96187E-13| +| 19| -0.76357 +i* -0.645725| 1|-3.31242E-13 +i*-8.50865E-14| +| 20| 0.773609 +i* 0.633664| 1|-7.93813E-13 +i* 2.09313E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 1 +proc 0 +proc 1 +zone limite de 'log-exp' 1.00051 +zone limite de 'log-exp' 1.00051 +dimgrid 2735 dimblock 256 degrePoly 700000 +proc 1, start 350080 size 350080 +proc 1 start 350080 size 350080 +dimgrid 2735 dimblock 256 degrePoly 700000 +proc 0, start 0 size 350080 +proc 0 start 0 size 350080 +iter : 1 Arret : 4.07504E-06 s/iter 50.276924 +iter : 2 Arret : 4.14637E-06 s/iter 50.316736 +iter : 3 Arret : 3.92125E-06 s/iter 50.311941 +iter : 4 Arret : 3.96177E-06 s/iter 50.319644 +iter : 5 Arret : 3.60866E-06 s/iter 50.315146 +iter : 6 Arret : 3.73875E-06 s/iter 50.345034 +iter : 7 Arret : 3.91631E-06 s/iter 50.311163 +iter : 8 Arret : 3.82723E-06 s/iter 50.332321 +iter : 9 Arret : 4.24177E-06 s/iter 50.340320 +iter : 10 Arret : 9.18215E-05 s/iter 50.349367 +iter : 11 Arret : 0.000848166 s/iter 50.316912 +iter : 12 Arret : 0.00161125 s/iter 50.303456 +iter : 13 Arret : 0.0024668 s/iter 57.717511 +iter : 14 Arret : 0.00479788 s/iter 53.570757 +iter : 15 Arret : 0.00495555 s/iter 52.732469 +iter : 16 Arret : 0.0099658 s/iter 51.316983 +iter : 17 Arret : 0.0910784 s/iter 52.848267 +iter : 18 Arret : 0.0669533 s/iter 53.379948 +iter : 19 Arret : 0.196091 s/iter 50.742367 +iter : 20 Arret : 0.0404469 s/iter 53.773228 +iter : 21 Arret : 0.0140031 s/iter 50.742372 +iter : 22 Arret : 0.00221639 s/iter 52.968592 +iter : 23 Arret : 0.00849041 s/iter 50.251971 +iter : 24 Arret : 0.00450336 s/iter 50.017079 +iter : 25 Arret : 0.000556405 s/iter 50.012361 +iter : 26 Arret : 2.14523E-05 s/iter 50.016154 +iter : 27 Arret : 3.07624E-05 s/iter 50.035967 +iter : 28 Arret : 4.85785E-07 s/iter 49.957854 +iter : 29 Arret : 3.24294E-13 s/iter 50.017899 +temps : 1484.54 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 7.46263E-08 +Stabilite : 3.24294E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540352 +i* 0.841439| 1| 4.39978E-13 +i* 6.25043E-13| +| 2| -0.996034 +i* 0.0889731| 1| 2.2073E-13 +i* 1.55296E-13| +| 3| 0.439836 +i* -0.898078| 1|-3.55927E-13 +i*-1.21738E-13| +| 4| 0.38266 +i* -0.923889| 1|-2.56142E-13 +i*-7.02285E-14| +| 5| -0.988496 +i* 0.15125| 1|-1.52652E-13 +i*-1.11329E-13| +| 6| 0.641421 +i* 0.767189| 1|-1.31044E-13 +i* 5.61736E-13| +| 7| 0.323979 +i* -0.946064| 1|-4.52336E-13 +i* 8.74596E-14| +| 8| -0.977067 +i* 0.212932| 1| 8.58341E-14 +i* 1.73412E-13| +| 9| 0.688262 +i* 0.725462| 1| 4.28754E-14 +i* 1.08849E-12| +| 10| 0.264022 +i* -0.964517| 1|-3.63883E-13 +i*-8.14886E-14| +| 11| -0.961793 +i* 0.273776| 1| -3.0213E-13 +i*-2.13897E-13| +| 12| 0.732395 +i* 0.68088| 1|-3.65194E-14 +i* 7.95483E-13| +| 13| 0.203027 +i* -0.979173| 1|-3.14502E-13 +i* 2.96924E-13| +| 14| -0.942735 +i* 0.333543| 1| 1.82947E-13 +i*-4.73458E-14| +| 15| 0.773646 +i* 0.633619| 1| 2.24352E-13 +i* 2.79674E-13| +| 16| 0.141232 +i* -0.989977| 1| -1.0035E-13 +i* 1.5693E-13| +| 17| -0.919967 +i* 0.391997| 1| 2.89213E-14 +i*-1.86252E-13| +| 18| 0.811852 +i* 0.583864| 1|-1.59939E-12 +i*-4.13669E-13| +| 19| 0.0788818 +i* -0.996884| 1|-2.83003E-13 +i* 1.04711E-13| +| 20| -0.893578 +i* 0.448908| 1| 4.59736E-14 +i* 1.31414E-13| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 1 +proc 0 +proc 1 +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 1, start 400000 size 400000 +proc 1 start 400000 size 400000 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 0, start 0 size 400000 +proc 0 start 0 size 400000 +iter : 1 Arret : 3.43314E-06 s/iter 66.451646 +iter : 2 Arret : 3.25458E-06 s/iter 66.371208 +iter : 3 Arret : 3.1756E-06 s/iter 66.365954 +iter : 4 Arret : 3.16632E-06 s/iter 66.323972 +iter : 5 Arret : 3.35307E-06 s/iter 66.379156 +iter : 6 Arret : 3.06929E-06 s/iter 66.310093 +iter : 7 Arret : 3.05638E-06 s/iter 66.375498 +iter : 8 Arret : 3.30698E-06 s/iter 66.345679 +iter : 9 Arret : 4.07579E-06 s/iter 66.346425 +iter : 10 Arret : 1.06648E-05 s/iter 66.343012 +iter : 11 Arret : 0.00084876 s/iter 66.372100 +iter : 12 Arret : 0.00143415 s/iter 66.363225 +iter : 13 Arret : 1.46402 s/iter 66.856335 +iter : 14 Arret : 0.713405 s/iter 68.042881 +iter : 15 Arret : 2.95761 s/iter 73.478889 +iter : 16 Arret : 0.205334 s/iter 66.190886 +iter : 17 Arret : 0.294322 s/iter 63.619134 +iter : 18 Arret : 0.0487392 s/iter 60.944788 +iter : 19 Arret : 0.0248874 s/iter 62.800018 +iter : 20 Arret : 0.0170499 s/iter 62.693475 +iter : 21 Arret : 0.00846661 s/iter 60.956662 +iter : 22 Arret : 0.0198831 s/iter 55.137303 +iter : 23 Arret : 0.00364888 s/iter 51.869775 +iter : 24 Arret : 2.68554E-05 s/iter 47.810142 +iter : 25 Arret : 2.14844E-05 s/iter 46.502062 +iter : 26 Arret : 4.9054E-06 s/iter 46.126008 +iter : 27 Arret : 4.4697E-07 s/iter 45.649153 +iter : 28 Arret : 7.89107E-11 s/iter 45.613504 +iter : 29 Arret : 2.23773E-16 s/iter 45.669074 +temps : 1766.95 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 6.26383E-08 +Stabilite : 2.23773E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540349 +i* 0.841441| 1|-1.16344E-13 +i* 9.55619E-13| +| 2| 0.592061 +i* 0.805893| 1|-1.57249E-13 +i*-4.43364E-13| +| 3| 0.617051 +i* 0.786923| 1|-6.42805E-13 +i*-3.49094E-13| +| 4| 0.641434 +i* 0.767178| 1| 1.00022E-12 +i*-5.90578E-13| +| 5| 0.665186 +i* 0.746678| 1|-2.53998E-14 +i*-1.14684E-12| +| 6| 0.688283 +i* 0.725442| 1|-8.68732E-13 +i* 8.52696E-13| +| 7| 0.710703 +i* 0.703493| 1| 2.02581E-13 +i* 4.54699E-13| +| 8| 0.732422 +i* 0.680851| 1|-5.22353E-13 +i*-3.99873E-13| +| 9| 0.753421 +i* 0.657538| 1| 1.23356E-13 +i*-1.05986E-12| +| 10| 0.773678 +i* 0.633579| 1|-6.75196E-13 +i* 3.60108E-13| +| 11| 0.793174 +i* 0.608995| 1| 4.43853E-13 +i*-1.42398E-12| +| 12| 0.811888 +i* 0.583813| 1|-4.10491E-13 +i*-4.46651E-13| +| 13| 0.829804 +i* 0.558055| 1| 1.30045E-12 +i* 1.12788E-13| +| 14| 0.846902 +i* 0.531748| 1|-8.09419E-13 +i* 4.98091E-13| +| 15| 0.863167 +i* 0.504918| 1| 2.98522E-13 +i* 3.81547E-13| +| 16| 0.878582 +i* 0.477591| 1|-3.06581E-13 +i*-6.95869E-13| +| 17| 0.893133 +i* 0.449793| 1| 1.24355E-13 +i* -1.3239E-12| +| 18| 0.906804 +i* 0.421553| 1|-1.23117E-12 +i*-5.57117E-13| +| 19| 0.919582 +i* 0.392898| 1|-1.03648E-12 +i* 2.90445E-14| +| 20| 0.931455 +i* 0.363856| 1|-6.42708E-13 +i*-1.50318E-12| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 1 diff --git a/Simulations/full_mpi/full_mpi_2GPU.sge b/Simulations/full_mpi/full_mpi_2GPU.sge new file mode 100644 index 0000000..ea411bb --- /dev/null +++ b/Simulations/full_mpi/full_mpi_2GPU.sge @@ -0,0 +1,25 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=2 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -V +#$ -cwd +#$ -N full_mpi_2GPU +#$ -pe mpi 2 + + +module load cuda/7.0 +module load ompi/gcc + +mpirun -np $NSLOTS ./template -r -i 60000 40000 +mpirun -np $NSLOTS ./template -r -i 150000 50000 +mpirun -np $NSLOTS ./template -r -i 250000 150000 +mpirun -np $NSLOTS ./template -r -i 350000 250000 +mpirun -np $NSLOTS ./template -r -i 500000 300000 +mpirun -np $NSLOTS ./template -r -i 600000 400000 +mpirun -np $NSLOTS ./template -r -i 700000 500000 +mpirun -np $NSLOTS ./template -r -i 800000 600000 +#mpirun -np $NSLOTS ./template -r -i 900000 700000 +#mpirun -np $NSLOTS ./template -r -i 1000000 800000 +#mpirun -np $NSLOTS ./template -r -i 1500000 500000 diff --git a/Simulations/full_mpi/full_mpi_3GPU.o140159 b/Simulations/full_mpi/full_mpi_3GPU.o140159 new file mode 100644 index 0000000..158cd8f --- /dev/null +++ b/Simulations/full_mpi/full_mpi_3GPU.o140159 @@ -0,0 +1,604 @@ +REMAINING: 3 +Taking GPU #0 +Taking GPU #1 +Taking GPU #2 +proc 1 +proc 2 +proc 0 +zone limite de 'log-exp' 1.00593 +zone limite de 'log-exp' 1.00593 +zone limite de 'log-exp' 1.00593 +dimgrid 235 dimblock 256 degrePoly 60000 +proc 1, start 20053 size 20053 +dimgrid 235 dimblock 256 degrePoly 60000 +proc 0, start 0 size 20053 +proc 0 start 0 size 20053 +dimgrid 235 dimblock 256 degrePoly 60000 +proc 2, start 40106 size 20053 +proc 2 start 40106 size 20053 +proc 1 start 20053 size 20053 +iter : 1 Arret : 4.51053E-05 s/iter 0.366915 +iter : 2 Arret : 3.79748E-05 s/iter 0.366823 +iter : 3 Arret : 3.83563E-05 s/iter 0.366880 +iter : 4 Arret : 3.91196E-05 s/iter 0.366902 +iter : 5 Arret : 4.35007E-05 s/iter 0.366756 +iter : 6 Arret : 4.41483E-05 s/iter 0.366710 +iter : 7 Arret : 5.50718E-05 s/iter 0.366766 +iter : 8 Arret : 0.000118505 s/iter 0.366821 +iter : 9 Arret : 0.00208632 s/iter 0.366803 +iter : 10 Arret : 0.0219374 s/iter 0.366869 +iter : 11 Arret : 2.12364 s/iter 1.163790 +iter : 12 Arret : 0.290713 s/iter 0.366853 +iter : 13 Arret : 0.144909 s/iter 1.195713 +iter : 14 Arret : 0.0571799 s/iter 1.188579 +iter : 15 Arret : 0.017729 s/iter 1.192088 +iter : 16 Arret : 0.00942695 s/iter 1.186675 +iter : 17 Arret : 0.00614493 s/iter 1.170362 +iter : 18 Arret : 0.0046828 s/iter 1.012161 +iter : 19 Arret : 0.0210424 s/iter 0.356542 +iter : 20 Arret : 0.0167084 s/iter 0.355054 +iter : 21 Arret : 0.00421459 s/iter 0.348901 +iter : 22 Arret : 0.00178855 s/iter 0.342348 +iter : 23 Arret : 0.00897727 s/iter 0.340678 +iter : 24 Arret : 0.00287444 s/iter 0.336510 +iter : 25 Arret : 0.000362565 s/iter 0.336936 +iter : 26 Arret : 0.000252972 s/iter 0.337141 +iter : 27 Arret : 3.73204E-05 s/iter 0.328363 +iter : 28 Arret : 8.45973E-06 s/iter 0.334747 +iter : 29 Arret : 1.8159E-08 s/iter 0.324239 +iter : 30 Arret : 5.61914E-13 s/iter 0.337980 +temps : 16.3645 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.35784E-10 +Stabilite : 5.61914E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540783 +i* 0.841162| 1|-7.58456E-14 +i* 3.78031E-14| +| 2| -0.992343 +i* -0.123513| 1|-4.36456E-15 +i* 3.59435E-15| +| 3| 0.0563346 +i* 0.998412| 1| 5.70377E-15 +i* 3.3501E-14| +| 4| -0.802793 +i* -0.596258| 1| 2.03657E-15 +i* 1.01915E-14| +| 5| 0.730552 +i* -0.682857| 1|-7.48429E-14 +i* 6.77011E-14| +| 6| -0.442728 +i* 0.896656| 1|-3.77198E-14 +i*-1.89779E-15| +| 7| -0.404888 +i* -0.914366| 1| 3.20195E-14 +i* 9.65894E-15| +| 8| 0.972126 +i* -0.23446| 1| 4.02421E-14 +i*-1.54755E-14| +| 9| -0.826939 +i* 0.562292| 1| -2.4928E-14 +i*-1.59889E-14| +| 10| 0.0979895 +i* -0.995187| 1| 2.90878E-14 +i*-6.75675E-15| +| 11| 0.961513 +i* 0.27476| 1|-9.39769E-14 +i*-2.63912E-13| +| 12| -0.996627 +i* 0.0820589| 1| 2.39773E-14 +i* 1.74825E-14| +| 13| 0.575447 +i* -0.817839| 1|-3.49894E-14 +i*-7.98545E-14| +| 14| 0.701466 +i* 0.712703| 1| 7.52211E-14 +i* 1.53991E-14| +| 15| 0.259346 +i* 0.965785| 1|-2.14863E-14 +i*-2.81355E-14| +| 16| -0.907773 +i* -0.419461| 1|-3.62869E-14 +i*-9.49414E-15| +| 17| 0.903623 +i* -0.428329| 1|-1.24969E-14 +i* 7.51222E-14| +| 18| -0.249979 +i* 0.968251| 1|-1.59074E-14 +i*-1.09721E-14| +| 19| -0.583426 +i* -0.812166| 1| 4.94882E-14 +i*-9.16107E-15| +| 20| 0.997383 +i* 0.072297| 1| 2.53037E-13 +i*-5.92819E-13| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 1 +proc 1 +proc 2 +proc 0 +zone limite de 'log-exp' 1.00237 +zone limite de 'log-exp' 1.00237 +zone limite de 'log-exp' 1.00237 +dimgrid 586 dimblock 256 degrePoly 150000 +proc 1, start 50005 size 50005 +dimgrid 586 dimblock 256 degrePoly 150000 +proc 0, start 0 size 50005 +dimgrid 586 dimblock 256 degrePoly 150000 +proc 2, start 100010 size 50005 +proc 1 start 50005 size 50005 +proc 0 start 0 size 50005 +proc 2 start 100010 size 50005 +iter : 1 Arret : 1.83619E-05 s/iter 1.833058 +iter : 2 Arret : 1.73853E-05 s/iter 1.832458 +iter : 3 Arret : 1.70553E-05 s/iter 1.832448 +iter : 4 Arret : 1.72513E-05 s/iter 1.832684 +iter : 5 Arret : 1.69749E-05 s/iter 1.832295 +iter : 6 Arret : 1.78708E-05 s/iter 1.832450 +iter : 7 Arret : 2.02323E-05 s/iter 1.832391 +iter : 8 Arret : 2.61959E-05 s/iter 1.832666 +iter : 9 Arret : 0.000263463 s/iter 1.832325 +iter : 10 Arret : 0.00201062 s/iter 1.832469 +iter : 11 Arret : 0.0177962 s/iter 1.832459 +iter : 12 Arret : 0.00945112 s/iter 1.832643 +iter : 13 Arret : 1.13842 s/iter 3.083910 +iter : 14 Arret : 0.0340957 s/iter 3.886935 +iter : 15 Arret : 0.0812119 s/iter 1.824686 +iter : 16 Arret : 0.16371 s/iter 3.884591 +iter : 17 Arret : 0.0770217 s/iter 3.594364 +iter : 18 Arret : 0.0145081 s/iter 3.552164 +iter : 19 Arret : 0.00446866 s/iter 2.726939 +iter : 20 Arret : 0.00786537 s/iter 1.794160 +iter : 21 Arret : 0.0166355 s/iter 1.779567 +iter : 22 Arret : 0.0278383 s/iter 2.763164 +iter : 23 Arret : 0.00838616 s/iter 1.758182 +iter : 24 Arret : 0.000453907 s/iter 1.764407 +iter : 25 Arret : 3.67653E-05 s/iter 1.749282 +iter : 26 Arret : 1.55532E-05 s/iter 1.735726 +iter : 27 Arret : 9.01062E-07 s/iter 1.753730 +iter : 28 Arret : 4.37903E-10 s/iter 1.730440 +iter : 29 Arret : 3.95673E-15 s/iter 1.728429 +temps : 63.3058 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.26535E-09 +Stabilite : 3.95673E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540528 +i* 0.841326| 1| 8.68923E-14 +i* 2.2979E-13| +| 2| -0.905603 +i* -0.424127| 1| 6.50001E-14 +i* -3.0061E-14| +| 3| -0.774122 +i* 0.633037| 1|-3.89619E-14 +i*-6.71876E-14| +| 4| 0.317935 +i* -0.948113| 1| 4.656E-15 +i* 1.15645E-13| +| 5| 0.235775 +i* 0.971808| 1|-4.13627E-14 +i* -1.0803E-13| +| 6| -0.717299 +i* -0.696766| 1| 5.63785E-15 +i*-6.71685E-14| +| 7| 0.992349 +i* -0.123462| 1|-4.81056E-13 +i* 9.00335E-13| +| 8| -0.938482 +i* 0.345329| 1|-6.95555E-14 +i*-3.79159E-14| +| 9| 0.610294 +i* -0.792175| 1| -5.4852E-14 +i*-3.26232E-14| +| 10| -0.0945977 +i* 0.995516| 1| 4.45165E-14 +i* 9.42527E-14| +| 11| -0.450242 +i* -0.892906| 1| 2.41855E-14 +i*-3.23699E-15| +| 12| 0.978218 +i* 0.207583| 1|-2.84429E-13 +i* 4.69725E-13| +| 13| -0.999806 +i* 0.0197069| 1|-4.72365E-14 +i*-2.55716E-14| +| 14| 0.835648 +i* -0.549265| 1|-2.95892E-13 +i* 2.34143E-13| +| 15| -0.414707 +i* 0.909955| 1| 7.26225E-14 +i*-1.70003E-15| +| 16| -0.133754 +i* -0.991015| 1|-2.88485E-14 +i* 2.14499E-14| +| 17| 0.856687 +i* 0.515837| 1| 1.49106E-13 +i* 3.95153E-14| +| 18| -0.951361 +i* -0.308079| 1| 3.78308E-14 +i* 4.65843E-14| +| 19| 0.969257 +i* -0.24605| 1| 5.51163E-13 +i*-4.79498E-13| +| 20| -0.689285 +i* 0.724491| 1| 2.40086E-15 +i*-3.61777E-14| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 1 +proc 1 +proc 2 +proc 0 +zone limite de 'log-exp' 1.00142 +zone limite de 'log-exp' 1.00142 +zone limite de 'log-exp' 1.00142 +dimgrid 977 dimblock 256 degrePoly 250000 +proc 1, start 83370 size 83370 +dimgrid 977 dimblock 256 degrePoly 250000 +proc 2, start 166740 size 83370 +proc 2 start 166740 size 83370 +proc 1 start 83370 size 83370 +dimgrid 977 dimblock 256 degrePoly 250000 +proc 0, start 0 size 83370 +proc 0 start 0 size 83370 +iter : 1 Arret : 1.04122E-05 s/iter 4.603075 +iter : 2 Arret : 9.85149E-06 s/iter 4.604055 +iter : 3 Arret : 1.14683E-05 s/iter 4.603262 +iter : 4 Arret : 1.02226E-05 s/iter 4.602431 +iter : 5 Arret : 1.00729E-05 s/iter 4.602619 +iter : 6 Arret : 1.06838E-05 s/iter 4.601869 +iter : 7 Arret : 1.12564E-05 s/iter 4.604882 +iter : 8 Arret : 1.08854E-05 s/iter 4.602271 +iter : 9 Arret : 1.68728E-05 s/iter 4.602965 +iter : 10 Arret : 0.000908721 s/iter 4.605369 +iter : 11 Arret : 0.00208199 s/iter 4.606164 +iter : 12 Arret : 0.00236846 s/iter 4.603500 +iter : 13 Arret : 0.00395957 s/iter 4.603136 +iter : 14 Arret : 0.000973404 s/iter 4.602278 +iter : 15 Arret : 0.00182712 s/iter 4.583661 +iter : 16 Arret : 0.00194671 s/iter 3.758842 +iter : 17 Arret : 0.00719321 s/iter 2.889771 +iter : 18 Arret : 0.295953 s/iter 2.852424 +iter : 19 Arret : 0.00337128 s/iter 4.408132 +iter : 20 Arret : 0.00333381 s/iter 2.836731 +iter : 21 Arret : 0.00266677 s/iter 2.831149 +iter : 22 Arret : 0.00107544 s/iter 2.801808 +iter : 23 Arret : 0.000320605 s/iter 2.803352 +iter : 24 Arret : 0.000173629 s/iter 2.830132 +iter : 25 Arret : 0.000233464 s/iter 2.803594 +iter : 26 Arret : 0.000160813 s/iter 2.829786 +iter : 27 Arret : 0.000120024 s/iter 2.786102 +iter : 28 Arret : 9.55845E-05 s/iter 2.819982 +iter : 29 Arret : 2.30991E-05 s/iter 2.839073 +iter : 30 Arret : 9.78684E-06 s/iter 2.820049 +iter : 31 Arret : 1.81912E-06 s/iter 2.795290 +iter : 32 Arret : 6.40862E-09 s/iter 2.814603 +iter : 33 Arret : 7.74157E-15 s/iter 2.794434 +temps : 122.621 seconde(s) +Nb iterations : 33 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.05316E-09 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540427 +i* 0.841391| 1| 9.7148E-14 +i*-1.98189E-13| +| 2| -0.997949 +i* 0.0640067| 1| 1.02696E-14 +i* 2.88415E-14| +| 3| 0.450991 +i* -0.892528| 1| 2.39739E-15 +i* 7.66835E-14| +| 4| 0.42851 +i* -0.903537| 1| 1.03733E-13 +i* 1.27433E-14| +| 5| -0.996035 +i* 0.0889649| 1| 5.1386E-14 +i* 4.21729E-14| +| 6| 0.581876 +i* 0.813277| 1| 3.29906E-13 +i* -3.5718E-15| +| 7| 0.405761 +i* -0.913979| 1| 1.69923E-13 +i*-8.86062E-14| +| 8| -0.993496 +i* 0.113867| 1| 6.34562E-14 +i* 6.04291E-14| +| 9| 0.60205 +i* 0.798458| 1| 2.39371E-13 +i* -2.2848E-13| +| 10| 0.382757 +i* -0.923849| 1| 6.36852E-14 +i* 1.1601E-13| +| 11| -0.990335 +i* 0.138698| 1| 8.32286E-14 +i* 4.57395E-14| +| 12| 0.621846 +i* 0.783139| 1| 3.5482E-14 +i*-1.57841E-13| +| 13| 0.359514 +i* -0.93314| 1| 1.00985E-13 +i*-2.52237E-13| +| 14| -0.986553 +i* 0.163442| 1| 3.24636E-14 +i* 4.58574E-14| +| 15| 0.641253 +i* 0.767329| 1| 1.79533E-13 +i* 3.03096E-13| +| 16| 0.336045 +i* -0.941846| 1| 1.38948E-13 +i*-8.14071E-14| +| 17| -0.982153 +i* 0.188084| 1| 6.94549E-14 +i* 3.09405E-14| +| 18| 0.660258 +i* 0.751039| 1| 4.21871E-13 +i* 5.02185E-14| +| 19| 0.312366 +i* -0.949962| 1|-6.37199E-14 +i*-7.39669E-14| +| 20| -0.977138 +i* 0.212608| 1|-3.80633E-14 +i* -8.4285E-14| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 1 +proc 1 +proc 2 +proc 0 +zone limite de 'log-exp' 1.00101 +zone limite de 'log-exp' 1.00101 +zone limite de 'log-exp' 1.00101 +dimgrid 1368 dimblock 256 degrePoly 350000 +proc 1, start 116736 size 116736 +dimgrid 1368 dimblock 256 degrePoly 350000 +proc 2, start 233472 size 116736 +dimgrid 1368 dimblock 256 degrePoly 350000 +proc 0, start 0 size 116736 +proc 0 start 0 size 116736 +proc 1 start 116736 size 116736 +proc 2 start 233472 size 116736 +iter : 1 Arret : 7.25108E-06 s/iter 8.701598 +iter : 2 Arret : 7.01169E-06 s/iter 8.695411 +iter : 3 Arret : 7.08063E-06 s/iter 8.691498 +iter : 4 Arret : 6.71613E-06 s/iter 8.696067 +iter : 5 Arret : 8.00231E-06 s/iter 8.693456 +iter : 6 Arret : 6.92129E-06 s/iter 8.693906 +iter : 7 Arret : 7.08909E-06 s/iter 8.691731 +iter : 8 Arret : 7.80014E-06 s/iter 8.689556 +iter : 9 Arret : 1.05064E-05 s/iter 8.687045 +iter : 10 Arret : 0.000743236 s/iter 8.683404 +iter : 11 Arret : 0.000665165 s/iter 8.679771 +iter : 12 Arret : 0.00104331 s/iter 8.679382 +iter : 13 Arret : 0.820946 s/iter 8.680273 +iter : 14 Arret : 3.39143 s/iter 10.141868 +iter : 15 Arret : 0.124079 s/iter 10.120875 +iter : 16 Arret : 0.060865 s/iter 10.097925 +iter : 17 Arret : 0.0362188 s/iter 10.080714 +iter : 18 Arret : 0.0235232 s/iter 13.316578 +iter : 19 Arret : 0.019308 s/iter 10.793160 +iter : 20 Arret : 0.0181476 s/iter 10.220050 +iter : 21 Arret : 0.0341411 s/iter 13.317077 +iter : 22 Arret : 0.0238257 s/iter 13.520573 +iter : 23 Arret : 0.0622072 s/iter 13.384251 +iter : 24 Arret : 0.0384535 s/iter 13.405236 +iter : 25 Arret : 0.0315007 s/iter 13.389625 +iter : 26 Arret : 0.0793407 s/iter 13.377513 +iter : 27 Arret : 0.00511819 s/iter 13.311241 +iter : 28 Arret : 0.000404404 s/iter 8.624483 +iter : 29 Arret : 8.29183E-05 s/iter 8.623864 +iter : 30 Arret : 0.000107024 s/iter 8.624427 +iter : 31 Arret : 1.83455E-05 s/iter 8.626520 +iter : 32 Arret : 9.95568E-06 s/iter 8.624102 +iter : 33 Arret : 3.50874E-06 s/iter 8.630894 +iter : 34 Arret : 3.09608E-08 s/iter 8.626743 +iter : 35 Arret : 1.44506E-13 s/iter 8.626785 +temps : 350.829 seconde(s) +Nb iterations : 35 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.46096E-08 +Stabilite : 1.11023E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540399 +i* 0.841409| 1| 5.12961E-13 +i*-3.37404E-15| +| 2| -0.385479 +i* 0.922716| 1| -1.616E-13 +i*-2.73566E-14| +| 3| -0.770131 +i* 0.637886| 1|-1.38431E-15 +i* 1.70921E-13| +| 4| -0.978357 +i* 0.206925| 1|-3.07393E-15 +i* 4.96131E-15| +| 5| -0.962455 +i* -0.27144| 1|-5.85088E-14 +i* 7.9714E-14| +| 6| -0.72607 +i* -0.687621| 1| -2.0612E-14 +i* 2.87948E-13| +| 7| -0.323352 +i* -0.946279| 1| 2.27159E-13 +i* 7.30891E-14| +| 8| 0.153459 +i* -0.988155| 1| 4.60049E-15 +i*-2.43555E-14| +| 9| 0.595097 +i* -0.803654| 1|-3.46265E-13 +i* 1.60098E-14| +| 10| 0.900408 +i* -0.435047| 1| 3.20081E-13 +i*-1.77827E-14| +| 11| 0.999448 +i* 0.0332229| 1|-5.70342E-13 +i* 1.21308E-12| +| 12| 0.869529 +i* 0.493882| 1| 3.01252E-14 +i* 6.11216E-13| +| 13| 0.211292 +i* 0.977423| 1|-6.97532E-14 +i* 1.23212E-13| +| 14| -0.267139 +i* 0.963658| 1|-9.26238E-14 +i*-7.20968E-14| +| 15| -0.684372 +i* 0.729133| 1| 1.64042E-13 +i*-1.89831E-14| +| 16| -0.944825 +i* 0.327574| 1| 3.70572E-14 +i*-6.84904E-14| +| 17| -0.988833 +i* -0.149027| 1|-1.41002E-13 +i* 2.02581E-14| +| 18| -0.806314 +i* -0.591488| 1| 1.24668E-13 +i*-2.62805E-13| +| 19| -0.439079 +i* -0.898448| 1|-1.76949E-13 +i*-1.05707E-13| +| 20| 0.0287415 +i* -0.999587| 1| 1.62724E-13 +i*-6.82891E-14| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 1 +proc 1 +proc 2 +proc 0 +zone limite de 'log-exp' 1.00071 +zone limite de 'log-exp' 1.00071 +zone limite de 'log-exp' 1.00071 +dimgrid 1954 dimblock 256 degrePoly 500000 +proc 2, start 333482 size 166741 +dimgrid 1954 dimblock 256 degrePoly 500000 +proc 1, start 166741 size 166741 +dimgrid 1954 dimblock 256 degrePoly 500000 +proc 0, start 0 size 166741 +proc 0 start 0 size 166741 +proc 1 start 166741 size 166741 +proc 2 start 333482 size 166741 +iter : 1 Arret : 5.44829E-06 s/iter 17.188421 +iter : 2 Arret : 5.42874E-06 s/iter 17.137695 +iter : 3 Arret : 5.23492E-06 s/iter 17.123244 +iter : 4 Arret : 5.51556E-06 s/iter 17.128160 +iter : 5 Arret : 5.22118E-06 s/iter 17.122102 +iter : 6 Arret : 5.01816E-06 s/iter 17.123783 +iter : 7 Arret : 5.0087E-06 s/iter 17.115281 +iter : 8 Arret : 5.28527E-06 s/iter 17.120375 +iter : 9 Arret : 6.38913E-06 s/iter 17.121394 +iter : 10 Arret : 2.99276E-05 s/iter 17.125175 +iter : 11 Arret : 0.000916092 s/iter 17.123111 +iter : 12 Arret : 0.00112622 s/iter 17.129686 +iter : 13 Arret : 0.00199901 s/iter 18.785503 +iter : 14 Arret : 0.00536103 s/iter 17.609054 +iter : 15 Arret : 0.00620338 s/iter 18.429826 +iter : 16 Arret : 0.00463214 s/iter 16.044795 +iter : 17 Arret : 1.5572 s/iter 16.371044 +iter : 18 Arret : 0.084601 s/iter 14.529226 +iter : 19 Arret : 0.0115579 s/iter 15.452523 +iter : 20 Arret : 0.00599505 s/iter 14.669002 +iter : 21 Arret : 0.00192484 s/iter 10.219969 +iter : 22 Arret : 0.0109349 s/iter 10.105479 +iter : 23 Arret : 0.00351895 s/iter 9.786904 +iter : 24 Arret : 8.50621E-05 s/iter 8.935303 +iter : 25 Arret : 3.28381E-05 s/iter 8.653848 +iter : 26 Arret : 4.45938E-06 s/iter 8.532165 +iter : 27 Arret : 1.46328E-08 s/iter 8.457670 +iter : 28 Arret : 4.31796E-14 s/iter 8.370340 +temps : 410.952 seconde(s) +Nb iterations : 28 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.48768E-08 +Stabilite : 1.44695E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540372 +i* 0.841426| 1|-3.05235E-13 +i* 1.38721E-13| +| 2| 0.561316 +i* 0.827602| 1|-2.60021E-13 +i* 1.9206E-13| +| 3| 0.57165 +i* 0.820497| 1|-1.83308E-13 +i* 6.15844E-14| +| 4| 0.581895 +i* 0.813264| 1| 3.05839E-13 +i* 6.52482E-14| +| 5| 0.592048 +i* 0.805902| 1|-7.14016E-13 +i*-3.98882E-14| +| 6| 0.602109 +i* 0.798414| 1| 2.66658E-13 +i*-4.75979E-13| +| 7| 0.612074 +i* 0.7908| 1| 3.16743E-13 +i*-3.40844E-13| +| 8| 0.621943 +i* 0.783062| 1| 5.64146E-13 +i*-3.14632E-13| +| 9| 0.631715 +i* 0.775201| 1|-3.83756E-14 +i* 5.41086E-13| +| 10| 0.641387 +i* 0.767218| 1| 4.00499E-13 +i*-3.71465E-13| +| 11| 0.650958 +i* 0.759114| 1| 7.58768E-15 +i*-5.54055E-13| +| 12| 0.660427 +i* 0.750891| 1| 7.47999E-13 +i* 2.73089E-13| +| 13| 0.669792 +i* 0.742549| 1| 9.40577E-13 +i* 3.39433E-14| +| 14| 0.679051 +i* 0.734091| 1| 4.34264E-13 +i*-1.04887E-13| +| 15| 0.688204 +i* 0.725517| 1|-6.26926E-13 +i*-1.86798E-13| +| 16| 0.697248 +i* 0.71683| 1| 2.2389E-13 +i*-9.46795E-14| +| 17| 0.706183 +i* 0.708029| 1| 4.79186E-13 +i* 4.75144E-13| +| 18| 0.715007 +i* 0.699117| 1| 6.39138E-13 +i* 4.95824E-13| +| 19| 0.723718 +i* 0.690096| 1| -1.2694E-13 +i* 4.44528E-13| +| 20| 0.732316 +i* 0.680965| 1|-2.76158E-13 +i* 1.17734E-13| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +proc 0 +proc 1 +proc 2 +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 1, start 200021 size 200021 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 2, start 400042 size 200021 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 0, start 0 size 200021 +proc 0 start 0 size 200021 +proc 2 start 400042 size 200021 +proc 1 start 200021 size 200021 +iter : 1 Arret : 4.17374E-06 s/iter 25.553089 +iter : 2 Arret : 4.24471E-06 s/iter 25.497354 +iter : 3 Arret : 4.02926E-06 s/iter 25.510295 +iter : 4 Arret : 3.90309E-06 s/iter 25.498014 +iter : 5 Arret : 4.14737E-06 s/iter 25.505852 +iter : 6 Arret : 4.14451E-06 s/iter 25.510250 +iter : 7 Arret : 4.54952E-06 s/iter 25.534869 +iter : 8 Arret : 4.39097E-06 s/iter 25.519822 +iter : 9 Arret : 5.39778E-06 s/iter 25.501601 +iter : 10 Arret : 1.06277E-05 s/iter 25.514311 +iter : 11 Arret : 0.000466846 s/iter 25.483886 +iter : 12 Arret : 0.00147408 s/iter 25.506990 +iter : 13 Arret : 0.917202 s/iter 25.532816 +iter : 14 Arret : 0.738772 s/iter 25.543670 +iter : 15 Arret : 1.09406 s/iter 33.427707 +iter : 16 Arret : 0.0147818 s/iter 30.484631 +iter : 17 Arret : 0.00982586 s/iter 27.428111 +iter : 18 Arret : 0.00305155 s/iter 23.911742 +iter : 19 Arret : 0.00879189 s/iter 27.378373 +iter : 20 Arret : 0.0148466 s/iter 27.330975 +iter : 21 Arret : 0.00541507 s/iter 27.053957 +iter : 22 Arret : 0.00917579 s/iter 22.028199 +iter : 23 Arret : 0.00176967 s/iter 24.447698 +iter : 24 Arret : 0.000776941 s/iter 21.846447 +iter : 25 Arret : 1.85979E-05 s/iter 21.763637 +iter : 26 Arret : 5.99112E-08 s/iter 21.943537 +iter : 27 Arret : 6.36688E-13 s/iter 21.839783 +temps : 688.615 seconde(s) +Nb iterations : 27 +Nb de depassements de capacite exponentielle : 0 +Precision : 5.38109E-08 +Stabilite : 1.72079E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540365 +i* 0.841431| 1| 4.39062E-13 +i* 5.83011E-13| +| 2| -0.553493 +i* -0.832854| 1|-5.02858E-13 +i* 3.83374E-15| +| 3| -0.579338 +i* -0.815087| 1| 4.42365E-13 +i* 2.65846E-14| +| 4| 0.592057 +i* 0.805896| 1| 2.06783E-13 +i* 1.94549E-13| +| 5| -0.604613 +i* -0.796519| 1| 2.39135E-13 +i* 2.96967E-13| +| 6| 0.617037 +i* 0.786934| 1|-3.70964E-13 +i* 2.85104E-13| +| 7| -0.629293 +i* -0.777168| 1| 3.4002E-13 +i* 1.14925E-14| +| 8| 0.641411 +i* 0.767198| 1|-6.01835E-13 +i* 5.70316E-13| +| 9| -0.653354 +i* -0.757052| 1| 3.00003E-14 +i* 4.1084E-13| +| 10| 0.665153 +i* 0.746707| 1|-9.55243E-14 +i* 7.739E-13| +| 11| -0.676773 +i* -0.736192| 1|-3.70891E-13 +i* 4.31963E-14| +| 12| 0.688242 +i* 0.725482| 1| 4.17319E-13 +i*-2.25125E-13| +| 13| -0.699526 +i* -0.714607| 1|-1.55074E-13 +i* 3.9467E-13| +| 14| 0.710653 +i* 0.703543| 1|-7.94843E-13 +i* 5.61671E-13| +| 15| -0.721591 +i* -0.69232| 1|-8.20351E-14 +i* 3.39909E-13| +| 16| 0.732366 +i* 0.680912| 1| 5.01595E-13 +i* 2.59279E-13| +| 17| -0.742946 +i* -0.669351| 1|-1.90181E-13 +i* 1.23972E-13| +| 18| 0.753358 +i* 0.657611| 1|-7.14661E-13 +i*-3.96187E-13| +| 19| -0.76357 +i* -0.645725| 1|-3.31242E-13 +i*-8.50865E-14| +| 20| 0.773609 +i* 0.633664| 1|-7.93813E-13 +i* 2.09313E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 1 +proc 1 +proc 2 +proc 0 +zone limite de 'log-exp' 1.00051 +zone limite de 'log-exp' 1.00051 +zone limite de 'log-exp' 1.00051 +dimgrid 2735 dimblock 256 degrePoly 700000 +proc 2, start 466772 size 233386 +dimgrid 2735 dimblock 256 degrePoly 700000 +proc 1, start 233386 size 233386 +proc 2 start 466772 size 233386 +dimgrid 2735 dimblock 256 degrePoly 700000 +proc 0, start 0 size 233386 +proc 0 start 0 size 233386 +proc 1 start 233386 size 233386 +iter : 1 Arret : 3.63067E-06 s/iter 34.355771 +iter : 2 Arret : 3.51666E-06 s/iter 34.313476 +iter : 3 Arret : 3.37718E-06 s/iter 34.302244 +iter : 4 Arret : 3.51452E-06 s/iter 34.331891 +iter : 5 Arret : 3.53495E-06 s/iter 34.305875 +iter : 6 Arret : 3.54533E-06 s/iter 34.270154 +iter : 7 Arret : 3.57791E-06 s/iter 34.269601 +iter : 8 Arret : 3.49843E-06 s/iter 34.269532 +iter : 9 Arret : 3.56279E-06 s/iter 34.267016 +iter : 10 Arret : 6.70933E-06 s/iter 34.264316 +iter : 11 Arret : 0.000744895 s/iter 34.272504 +iter : 12 Arret : 0.0168677 s/iter 34.261719 +iter : 13 Arret : 0.0132741 s/iter 41.631459 +iter : 14 Arret : 0.0144504 s/iter 34.370399 +iter : 15 Arret : 0.0148871 s/iter 34.380936 +iter : 16 Arret : 0.117079 s/iter 42.029927 +iter : 17 Arret : 0.125622 s/iter 35.777828 +iter : 18 Arret : 0.0338842 s/iter 34.659887 +iter : 19 Arret : 0.0255305 s/iter 34.785339 +iter : 20 Arret : 0.0303666 s/iter 35.462034 +iter : 21 Arret : 0.0337579 s/iter 34.650721 +iter : 22 Arret : 0.0214608 s/iter 34.657778 +iter : 23 Arret : 0.00401409 s/iter 37.611052 +iter : 24 Arret : 0.00127792 s/iter 34.577885 +iter : 25 Arret : 0.000708122 s/iter 34.760828 +iter : 26 Arret : 1.94192E-06 s/iter 34.694471 +iter : 27 Arret : 3.18954E-08 s/iter 34.634308 +iter : 28 Arret : 1.15496E-13 s/iter 34.588120 +temps : 985.364 seconde(s) +Nb iterations : 28 +Nb de depassements de capacite exponentielle : 0 +Precision : 7.46263E-08 +Stabilite : 1.15496E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540352 +i* 0.841439| 1| 4.39978E-13 +i* 6.25043E-13| +| 2| -0.996034 +i* 0.0889731| 1| 2.2073E-13 +i* 1.55296E-13| +| 3| 0.439836 +i* -0.898078| 1|-3.55927E-13 +i*-1.21738E-13| +| 4| 0.38266 +i* -0.923889| 1|-2.56142E-13 +i*-7.02285E-14| +| 5| -0.988496 +i* 0.15125| 1|-1.52652E-13 +i*-1.11329E-13| +| 6| 0.641421 +i* 0.767189| 1|-1.31044E-13 +i* 5.61736E-13| +| 7| 0.323979 +i* -0.946064| 1|-4.52336E-13 +i* 8.74596E-14| +| 8| -0.977067 +i* 0.212932| 1| 8.58341E-14 +i* 1.73412E-13| +| 9| 0.688262 +i* 0.725462| 1| 4.28754E-14 +i* 1.08849E-12| +| 10| 0.264022 +i* -0.964517| 1|-3.63883E-13 +i*-8.14886E-14| +| 11| -0.961793 +i* 0.273776| 1| -3.0213E-13 +i*-2.13897E-13| +| 12| 0.732395 +i* 0.68088| 1|-3.65194E-14 +i* 7.95483E-13| +| 13| 0.203027 +i* -0.979173| 1|-3.14502E-13 +i* 2.96924E-13| +| 14| -0.942735 +i* 0.333543| 1| 1.82947E-13 +i*-4.73458E-14| +| 15| 0.773646 +i* 0.633619| 1| 2.24352E-13 +i* 2.79674E-13| +| 16| 0.141232 +i* -0.989977| 1| -1.0035E-13 +i* 1.5693E-13| +| 17| -0.919967 +i* 0.391997| 1| 2.89213E-14 +i*-1.86252E-13| +| 18| 0.811852 +i* 0.583864| 1|-1.59939E-12 +i*-4.13669E-13| +| 19| 0.0788818 +i* -0.996884| 1|-2.83003E-13 +i* 1.04711E-13| +| 20| -0.893578 +i* 0.448908| 1| 4.59736E-14 +i* 1.31414E-13| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 1 +proc 1 +proc 2 +proc 0 +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 2, start 533332 size 266666 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 0, start 0 size 266666 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 1, start 266666 size 266666 +proc 1 start 266666 size 266666 +proc 2 start 533332 size 266666 +proc 0 start 0 size 266666 +iter : 1 Arret : 3.65034E-06 s/iter 44.298468 +iter : 2 Arret : 3.20717E-06 s/iter 44.362840 +iter : 3 Arret : 3.28214E-06 s/iter 44.348033 +iter : 4 Arret : 3.53473E-06 s/iter 44.372779 +iter : 5 Arret : 3.64435E-06 s/iter 44.339393 +iter : 6 Arret : 3.48715E-06 s/iter 44.311216 +iter : 7 Arret : 3.20236E-06 s/iter 44.195501 +iter : 8 Arret : 3.46765E-06 s/iter 44.337231 +iter : 9 Arret : 4.55782E-06 s/iter 44.336266 +iter : 10 Arret : 3.03387E-05 s/iter 44.344481 +iter : 11 Arret : 0.000895058 s/iter 44.372449 +iter : 12 Arret : 0.00155707 s/iter 51.112648 +iter : 13 Arret : 1.43645 s/iter 52.743256 +iter : 14 Arret : 1.09102 s/iter 44.524633 +iter : 15 Arret : 0.0755624 s/iter 44.574228 +iter : 16 Arret : 0.0191023 s/iter 48.607142 +iter : 17 Arret : 0.0113021 s/iter 49.878872 +iter : 18 Arret : 0.0136773 s/iter 47.858875 +iter : 19 Arret : 0.0252439 s/iter 39.188313 +iter : 20 Arret : 0.034702 s/iter 39.327917 +iter : 21 Arret : 0.0204901 s/iter 41.570418 +iter : 22 Arret : 0.00860925 s/iter 42.424027 +iter : 23 Arret : 0.0024318 s/iter 40.816516 +iter : 24 Arret : 0.000206468 s/iter 32.760844 +iter : 25 Arret : 0.000152172 s/iter 31.523865 +iter : 26 Arret : 0.000466464 s/iter 30.993628 +iter : 27 Arret : 7.31094E-05 s/iter 30.855992 +iter : 28 Arret : 3.56766E-10 s/iter 31.007972 +iter : 29 Arret : 8.9509E-16 s/iter 30.809036 +temps : 1218.9 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 0.0233219 +Stabilite : 1.57009E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540349 +i* 0.841441| 1|-1.16344E-13 +i* 9.55619E-13| +| 2| 0.592061 +i* 0.805893| 1|-1.57249E-13 +i*-4.43364E-13| +| 3| 0.617051 +i* 0.786923| 1|-6.42805E-13 +i*-3.49094E-13| +| 4| 0.641434 +i* 0.767178| 1| 1.00022E-12 +i*-5.90578E-13| +| 5| 0.665186 +i* 0.746678| 1|-2.53998E-14 +i*-1.14684E-12| +| 6| 0.688283 +i* 0.725442| 1|-8.68732E-13 +i* 8.52696E-13| +| 7| 0.710703 +i* 0.703493| 1| 2.02581E-13 +i* 4.54699E-13| +| 8| 0.732422 +i* 0.680851| 1|-5.22353E-13 +i*-3.99873E-13| +| 9| 0.753421 +i* 0.657538| 1| 1.23356E-13 +i*-1.05986E-12| +| 10| 0.773678 +i* 0.633579| 1|-6.75196E-13 +i* 3.60108E-13| +| 11| 0.793174 +i* 0.608995| 1| 4.43853E-13 +i*-1.42398E-12| +| 12| 0.811888 +i* 0.583813| 1|-4.10491E-13 +i*-4.46651E-13| +| 13| 0.829804 +i* 0.558055| 1| 1.30045E-12 +i* 1.12788E-13| +| 14| 0.846902 +i* 0.531748| 1|-8.09419E-13 +i* 4.98091E-13| +| 15| 0.863167 +i* 0.504918| 1| 2.98522E-13 +i* 3.81547E-13| +| 16| 0.878582 +i* 0.477591| 1|-3.06581E-13 +i*-6.95869E-13| +| 17| 0.893133 +i* 0.449793| 1| 1.24355E-13 +i* -1.3239E-12| +| 18| 0.906804 +i* 0.421553| 1|-1.23117E-12 +i*-5.57117E-13| +| 19| 0.919582 +i* 0.392898| 1|-1.03648E-12 +i* 2.90445E-14| +| 20| 0.931455 +i* 0.363856| 1|-6.42708E-13 +i*-1.50318E-12| ++---+----------------------------+------------+----------------------------+ +799998 racines de module = 1 + 2 racines de module = 0.999973 diff --git a/Simulations/full_mpi/full_mpi_3GPU.sge b/Simulations/full_mpi/full_mpi_3GPU.sge new file mode 100644 index 0000000..53261fe --- /dev/null +++ b/Simulations/full_mpi/full_mpi_3GPU.sge @@ -0,0 +1,25 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=3 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -V +#$ -cwd +#$ -N full_mpi_3GPU +#$ -pe mpi 3 + + +module load cuda/7.0 +module load ompi/gcc + +mpirun -np $NSLOTS ./template -r -i 60000 40000 +mpirun -np $NSLOTS ./template -r -i 150000 50000 +mpirun -np $NSLOTS ./template -r -i 250000 150000 +mpirun -np $NSLOTS ./template -r -i 350000 250000 +mpirun -np $NSLOTS ./template -r -i 500000 300000 +mpirun -np $NSLOTS ./template -r -i 600000 400000 +mpirun -np $NSLOTS ./template -r -i 700000 500000 +mpirun -np $NSLOTS ./template -r -i 800000 600000 +#mpirun -np $NSLOTS ./template -r -i 900000 700000 +#mpirun -np $NSLOTS ./template -r -i 1000000 800000 +#mpirun -np $NSLOTS ./template -r -i 1500000 500000 diff --git a/Simulations/full_mpi/full_mpi_4GPU.o140132 b/Simulations/full_mpi/full_mpi_4GPU.o140132 new file mode 100644 index 0000000..2c3dc2a --- /dev/null +++ b/Simulations/full_mpi/full_mpi_4GPU.o140132 @@ -0,0 +1,622 @@ +REMAINING: 4 +Taking GPU #0 +Taking GPU #1 +Taking GPU #2 +Taking GPU #3 +proc 1 +proc 2 +proc 3 +proc 0 +zone limite de 'log-exp' 1.00593 +zone limite de 'log-exp' 1.00593 +zone limite de 'log-exp' 1.00593 +zone limite de 'log-exp' 1.00593 +dimgrid 235 dimblock 256 degrePoly 60000 +proc 1, start 15040 size 15040 +dimgrid 235 dimblock 256 degrePoly 60000 +proc 3, start 45120 size 15040 +dimgrid 235 dimblock 256 degrePoly 60000 +proc 0, start 0 size 15040 +proc 1 start 15040 size 15040 +proc 3 start 45120 size 15040 +proc 0 start 0 size 15040 +dimgrid 235 dimblock 256 degrePoly 60000 +proc 2, start 30080 size 15040 +proc 2 start 30080 size 15040 +iter : 1 Arret : 4.54253E-05 s/iter 0.190120 +iter : 2 Arret : 4.02349E-05 s/iter 0.189998 +iter : 3 Arret : 4.05851E-05 s/iter 0.190002 +iter : 4 Arret : 3.90123E-05 s/iter 0.189988 +iter : 5 Arret : 4.05115E-05 s/iter 0.189940 +iter : 6 Arret : 4.39547E-05 s/iter 0.189985 +iter : 7 Arret : 5.458E-05 s/iter 0.189984 +iter : 8 Arret : 0.000119494 s/iter 0.189981 +iter : 9 Arret : 0.00168327 s/iter 0.189962 +iter : 10 Arret : 0.0030417 s/iter 0.189891 +iter : 11 Arret : 2.15612 s/iter 0.189972 +iter : 12 Arret : 0.346227 s/iter 0.190014 +iter : 13 Arret : 0.126669 s/iter 1.018201 +iter : 14 Arret : 0.0535949 s/iter 1.016001 +iter : 15 Arret : 0.0185974 s/iter 1.012376 +iter : 16 Arret : 0.0101783 s/iter 1.010000 +iter : 17 Arret : 0.00628304 s/iter 1.004893 +iter : 18 Arret : 0.00442205 s/iter 0.867780 +iter : 19 Arret : 0.00334052 s/iter 0.850989 +iter : 20 Arret : 0.166672 s/iter 0.833688 +iter : 21 Arret : 0.154722 s/iter 0.185018 +iter : 22 Arret : 0.0369513 s/iter 0.857692 +iter : 23 Arret : 0.00795041 s/iter 0.183896 +iter : 24 Arret : 0.00113436 s/iter 0.179252 +iter : 25 Arret : 0.000916314 s/iter 0.179162 +iter : 26 Arret : 0.000437934 s/iter 0.173024 +iter : 27 Arret : 0.000164013 s/iter 0.173156 +iter : 28 Arret : 0.000120343 s/iter 0.173113 +iter : 29 Arret : 0.000163904 s/iter 0.173138 +iter : 30 Arret : 9.69458E-05 s/iter 0.173072 +iter : 31 Arret : 8.66273E-06 s/iter 0.172998 +iter : 32 Arret : 2.89696E-08 s/iter 0.173059 +iter : 33 Arret : 8.96067E-13 s/iter 0.173085 +temps : 13.0123 seconde(s) +Nb iterations : 33 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.35784E-10 +Stabilite : 8.96067E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540783 +i* 0.841162| 1|-7.58456E-14 +i* 3.78031E-14| +| 2| -0.992343 +i* -0.123513| 1|-2.28637E-15 +i*-5.45917E-15| +| 3| 0.0563346 +i* 0.998412| 1| 5.70377E-15 +i* 3.3501E-14| +| 4| -0.802793 +i* -0.596258| 1| 2.03657E-15 +i* 1.01915E-14| +| 5| 0.730552 +i* -0.682857| 1|-7.48429E-14 +i* 6.77011E-14| +| 6| -0.442728 +i* 0.896656| 1|-3.77198E-14 +i*-1.89779E-15| +| 7| -0.404888 +i* -0.914366| 1| 3.20195E-14 +i* 9.65894E-15| +| 8| 0.972126 +i* -0.23446| 1| 4.02421E-14 +i*-1.54755E-14| +| 9| -0.826939 +i* 0.562292| 1| -2.4928E-14 +i*-1.59889E-14| +| 10| 0.0979895 +i* -0.995187| 1| 2.90878E-14 +i*-6.75675E-15| +| 11| 0.961513 +i* 0.27476| 1|-9.39769E-14 +i*-2.63912E-13| +| 12| -0.996627 +i* 0.0820589| 1| 2.39773E-14 +i* 1.74825E-14| +| 13| 0.575447 +i* -0.817839| 1|-3.49894E-14 +i*-7.98545E-14| +| 14| 0.701466 +i* 0.712703| 1| 7.52211E-14 +i* 1.53991E-14| +| 15| 0.259346 +i* 0.965785| 1|-2.14863E-14 +i*-2.81355E-14| +| 16| -0.907773 +i* -0.419461| 1|-3.62869E-14 +i*-9.49414E-15| +| 17| 0.903623 +i* -0.428329| 1|-1.24969E-14 +i* 7.51222E-14| +| 18| -0.249979 +i* 0.968251| 1|-1.59074E-14 +i*-1.09721E-14| +| 19| -0.584107 +i* -0.811677| 1| 1.93838E-14 +i* -1.0613E-14| +| 20| 0.997383 +i* 0.072297| 1| 2.53037E-13 +i*-5.92819E-13| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 1 +proc 2 +proc 3 +proc 0 +proc 1 +zone limite de 'log-exp' 1.00237 +zone limite de 'log-exp' 1.00237 +zone limite de 'log-exp' 1.00237 +zone limite de 'log-exp' 1.00237 +dimgrid 586 dimblock 256 degrePoly 150000 +proc 0, start 0 size 37504 +dimgrid 586 dimblock 256 degrePoly 150000 +proc 3, start 112512 size 37504 +dimgrid 586 dimblock 256 degrePoly 150000 +proc 1, start 37504 size 37504 +dimgrid 586 dimblock 256 degrePoly 150000 +proc 2, start 75008 size 37504 +proc 2 start 75008 size 37504 +proc 0 start 0 size 37504 +proc 3 start 112512 size 37504 +proc 1 start 37504 size 37504 +iter : 1 Arret : 1.61155E-05 s/iter 1.388910 +iter : 2 Arret : 1.5292E-05 s/iter 1.388566 +iter : 3 Arret : 1.53382E-05 s/iter 1.388256 +iter : 4 Arret : 1.53436E-05 s/iter 1.388459 +iter : 5 Arret : 1.56797E-05 s/iter 1.388267 +iter : 6 Arret : 1.62943E-05 s/iter 1.388223 +iter : 7 Arret : 1.78031E-05 s/iter 1.388438 +iter : 8 Arret : 2.07609E-05 s/iter 1.388272 +iter : 9 Arret : 4.52349E-05 s/iter 1.388452 +iter : 10 Arret : 0.00148307 s/iter 1.388277 +iter : 11 Arret : 0.00381365 s/iter 1.388380 +iter : 12 Arret : 0.00454231 s/iter 2.679420 +iter : 13 Arret : 0.017103 s/iter 2.976033 +iter : 14 Arret : 1.38869 s/iter 1.383510 +iter : 15 Arret : 0.0597475 s/iter 1.384033 +iter : 16 Arret : 0.0363329 s/iter 2.973069 +iter : 17 Arret : 0.0127731 s/iter 3.418217 +iter : 18 Arret : 0.0103682 s/iter 3.020991 +iter : 19 Arret : 0.00840855 s/iter 2.969344 +iter : 20 Arret : 0.00415465 s/iter 3.306301 +iter : 21 Arret : 0.00116781 s/iter 1.346551 +iter : 22 Arret : 0.00222874 s/iter 1.341294 +iter : 23 Arret : 0.00230842 s/iter 1.334988 +iter : 24 Arret : 0.00269266 s/iter 1.337748 +iter : 25 Arret : 0.000589182 s/iter 1.335027 +iter : 26 Arret : 1.15656E-05 s/iter 1.331811 +iter : 27 Arret : 2.039E-06 s/iter 1.328004 +iter : 28 Arret : 3.02093E-09 s/iter 1.343235 +iter : 29 Arret : 2.75813E-14 s/iter 1.332966 +temps : 51.6331 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.26507E-09 +Stabilite : 2.75813E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540528 +i* 0.841326| 1| 8.68923E-14 +i* 2.2979E-13| +| 2| -0.905603 +i* -0.424127| 1| 6.50001E-14 +i* -3.0061E-14| +| 3| -0.774122 +i* 0.633037| 1|-3.89619E-14 +i*-6.71876E-14| +| 4| 0.317935 +i* -0.948113| 1| 4.656E-15 +i* 1.15645E-13| +| 5| 0.235978 +i* 0.971758| 1|-2.91295E-14 +i*-3.06716E-14| +| 6| -0.717299 +i* -0.696766| 1| 5.63785E-15 +i*-6.71685E-14| +| 7| 0.992349 +i* -0.123462| 1|-4.81056E-13 +i* 9.00335E-13| +| 8| -0.938482 +i* 0.345329| 1|-6.95555E-14 +i*-3.79159E-14| +| 9| 0.610294 +i* -0.792175| 1| -5.4852E-14 +i*-3.26232E-14| +| 10| -0.0946394 +i* 0.995512| 1|-4.73788E-14 +i*-8.10827E-14| +| 11| -0.450242 +i* -0.892906| 1| 2.41855E-14 +i*-3.23699E-15| +| 12| 0.978218 +i* 0.207583| 1|-2.84429E-13 +i* 4.69725E-13| +| 13| -0.999806 +i* 0.0197069| 1|-4.72365E-14 +i*-2.55716E-14| +| 14| 0.835648 +i* -0.549265| 1|-2.95892E-13 +i* 2.34143E-13| +| 15| -0.414707 +i* 0.909955| 1| 7.26225E-14 +i*-1.70003E-15| +| 16| -0.133754 +i* -0.991015| 1|-2.88485E-14 +i* 2.14499E-14| +| 17| 0.856687 +i* 0.515837| 1| 1.49106E-13 +i* 3.95153E-14| +| 18| -0.951361 +i* -0.308079| 1| 3.78308E-14 +i* 4.65843E-14| +| 19| 0.969257 +i* -0.24605| 1| 5.51163E-13 +i*-4.79498E-13| +| 20| -0.689285 +i* 0.724491| 1| 2.40086E-15 +i*-3.61777E-14| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 1 +proc 1 +proc 2 +proc 3 +proc 0 +zone limite de 'log-exp' 1.00142 +zone limite de 'log-exp' 1.00142 +zone limite de 'log-exp' 1.00142 +zone limite de 'log-exp' 1.00142 +dimgrid 977 dimblock 256 degrePoly 250000 +proc 2, start 125056 size 62528 +dimgrid 977 dimblock 256 degrePoly 250000 +proc 0, start 0 size 62528 +dimgrid 977 dimblock 256 degrePoly 250000 +proc 3, start 187584 size 62528 +proc 3 start 187584 size 62528 +proc 2 start 125056 size 62528 +proc 0 start 0 size 62528 +dimgrid 977 dimblock 256 degrePoly 250000 +proc 1, start 62528 size 62528 +proc 1 start 62528 size 62528 +iter : 1 Arret : 1.11968E-05 s/iter 3.825242 +iter : 2 Arret : 1.00799E-05 s/iter 3.807837 +iter : 3 Arret : 9.41078E-06 s/iter 3.813149 +iter : 4 Arret : 9.26536E-06 s/iter 3.814952 +iter : 5 Arret : 9.34813E-06 s/iter 3.812300 +iter : 6 Arret : 9.56148E-06 s/iter 3.818827 +iter : 7 Arret : 9.85158E-06 s/iter 3.809789 +iter : 8 Arret : 1.00436E-05 s/iter 3.817985 +iter : 9 Arret : 3.01654E-05 s/iter 3.810639 +iter : 10 Arret : 0.000664555 s/iter 3.818425 +iter : 11 Arret : 0.000737975 s/iter 3.818479 +iter : 12 Arret : 0.000983341 s/iter 3.816886 +iter : 13 Arret : 0.00169178 s/iter 3.818781 +iter : 14 Arret : 0.00246696 s/iter 3.818401 +iter : 15 Arret : 0.00246605 s/iter 3.779944 +iter : 16 Arret : 0.00658304 s/iter 2.977729 +iter : 17 Arret : 0.00690937 s/iter 5.004823 +iter : 18 Arret : 0.300013 s/iter 4.828460 +iter : 19 Arret : 0.0468449 s/iter 4.960936 +iter : 20 Arret : 0.00243593 s/iter 2.120119 +iter : 21 Arret : 0.000654892 s/iter 2.126485 +iter : 22 Arret : 0.00213423 s/iter 2.116250 +iter : 23 Arret : 0.000510708 s/iter 2.110308 +iter : 24 Arret : 0.00102843 s/iter 2.108799 +iter : 25 Arret : 0.000140837 s/iter 2.110467 +iter : 26 Arret : 9.44179E-05 s/iter 2.106952 +iter : 27 Arret : 2.22669E-05 s/iter 2.108487 +iter : 28 Arret : 1.36769E-06 s/iter 2.108960 +iter : 29 Arret : 2.186E-10 s/iter 2.111770 +iter : 30 Arret : 2.77556E-16 s/iter 2.094068 +temps : 98.5095 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.05316E-09 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540427 +i* 0.841391| 1| 9.7148E-14 +i*-1.98189E-13| +| 2| -0.997949 +i* 0.0640067| 1| 1.02696E-14 +i* 2.88415E-14| +| 3| 0.450991 +i* -0.892528| 1| 2.39739E-15 +i* 7.66835E-14| +| 4| 0.42851 +i* -0.903537| 1| 1.03733E-13 +i* 1.27433E-14| +| 5| -0.996035 +i* 0.0889649| 1| 5.1386E-14 +i* 4.21729E-14| +| 6| 0.581876 +i* 0.813277| 1| 3.29906E-13 +i* -3.5718E-15| +| 7| 0.405761 +i* -0.913979| 1| 1.69923E-13 +i*-8.86062E-14| +| 8| -0.993496 +i* 0.113867| 1| 6.34562E-14 +i* 6.04291E-14| +| 9| 0.60205 +i* 0.798458| 1| 2.39371E-13 +i* -2.2848E-13| +| 10| 0.382757 +i* -0.923849| 1| 6.36852E-14 +i* 1.1601E-13| +| 11| -0.990335 +i* 0.138698| 1| 8.32286E-14 +i* 4.57395E-14| +| 12| 0.621846 +i* 0.783139| 1| 3.5482E-14 +i*-1.57841E-13| +| 13| 0.359514 +i* -0.93314| 1| 1.00985E-13 +i*-2.52237E-13| +| 14| -0.986553 +i* 0.163442| 1| 3.24636E-14 +i* 4.58574E-14| +| 15| 0.641253 +i* 0.767329| 1| 1.79533E-13 +i* 3.03096E-13| +| 16| 0.336045 +i* -0.941846| 1| 1.38948E-13 +i*-8.14071E-14| +| 17| -0.982153 +i* 0.188084| 1| 6.94549E-14 +i* 3.09405E-14| +| 18| 0.660258 +i* 0.751039| 1| 4.21871E-13 +i* 5.02185E-14| +| 19| 0.312366 +i* -0.949962| 1|-6.37199E-14 +i*-7.39669E-14| +| 20| -0.977138 +i* 0.212608| 1|-3.80633E-14 +i* -8.4285E-14| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 1 +proc 0 +proc 1 +proc 2 +proc 3 +zone limite de 'log-exp' 1.00101 +zone limite de 'log-exp' 1.00101 +zone limite de 'log-exp' 1.00101 +zone limite de 'log-exp' 1.00101 +dimgrid 1368 dimblock 256 degrePoly 350000 +proc 3, start 262656 size 87552 +dimgrid 1368 dimblock 256 degrePoly 350000 +proc 1, start 87552 size 87552 +dimgrid 1368 dimblock 256 degrePoly 350000 +proc 2, start 175104 size 87552 +proc 1 start 87552 size 87552 +dimgrid 1368 dimblock 256 degrePoly 350000 +proc 0, start 0 size 87552 +proc 0 start 0 size 87552 +proc 3 start 262656 size 87552 +proc 2 start 175104 size 87552 +iter : 1 Arret : 7.37223E-06 s/iter 6.537086 +iter : 2 Arret : 6.87852E-06 s/iter 6.540337 +iter : 3 Arret : 6.62662E-06 s/iter 6.539807 +iter : 4 Arret : 6.78716E-06 s/iter 6.537314 +iter : 5 Arret : 6.73158E-06 s/iter 6.543333 +iter : 6 Arret : 7.46053E-06 s/iter 6.536618 +iter : 7 Arret : 7.08865E-06 s/iter 6.536382 +iter : 8 Arret : 7.79945E-06 s/iter 6.534593 +iter : 9 Arret : 9.74861E-06 s/iter 6.536504 +iter : 10 Arret : 0.000745782 s/iter 6.537362 +iter : 11 Arret : 0.000455744 s/iter 6.535194 +iter : 12 Arret : 0.00342228 s/iter 6.534104 +iter : 13 Arret : 0.810408 s/iter 6.536777 +iter : 14 Arret : 3.37422 s/iter 10.380895 +iter : 15 Arret : 0.136557 s/iter 11.212541 +iter : 16 Arret : 0.0661427 s/iter 9.571236 +iter : 17 Arret : 0.0390301 s/iter 11.168500 +iter : 18 Arret : 0.056921 s/iter 11.419060 +iter : 19 Arret : 0.0851919 s/iter 11.272764 +iter : 20 Arret : 0.0308655 s/iter 11.252338 +iter : 21 Arret : 0.0183277 s/iter 11.252867 +iter : 22 Arret : 0.0401954 s/iter 10.205076 +iter : 23 Arret : 0.0540968 s/iter 11.305983 +iter : 24 Arret : 0.0434344 s/iter 10.978858 +iter : 25 Arret : 0.0335517 s/iter 11.237082 +iter : 26 Arret : 0.115944 s/iter 11.039900 +iter : 27 Arret : 0.0492573 s/iter 8.777420 +iter : 28 Arret : 0.0191575 s/iter 6.485398 +iter : 29 Arret : 0.0184729 s/iter 7.151590 +iter : 30 Arret : 0.00124008 s/iter 6.484897 +iter : 31 Arret : 6.47966E-05 s/iter 6.485006 +iter : 32 Arret : 4.59568E-05 s/iter 6.485609 +iter : 33 Arret : 3.27878E-06 s/iter 6.484358 +iter : 34 Arret : 2.62749E-10 s/iter 6.485211 +iter : 35 Arret : 1.0339E-15 s/iter 6.482394 +temps : 289.016 seconde(s) +Nb iterations : 35 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.46096E-08 +Stabilite : 1.11023E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540399 +i* 0.841409| 1| 5.12961E-13 +i*-3.37404E-15| +| 2| -0.385479 +i* 0.922716| 1| -1.616E-13 +i*-2.73566E-14| +| 3| -0.770131 +i* 0.637886| 1|-1.38431E-15 +i* 1.70921E-13| +| 4| -0.978357 +i* 0.206925| 1|-3.07393E-15 +i* 4.96131E-15| +| 5| -0.962455 +i* -0.27144| 1|-5.85088E-14 +i* 7.9714E-14| +| 6| -0.72607 +i* -0.687621| 1| -2.0612E-14 +i* 2.87948E-13| +| 7| -0.323352 +i* -0.946279| 1| 2.27159E-13 +i* 7.30891E-14| +| 8| 0.153459 +i* -0.988155| 1| 4.60049E-15 +i*-2.43555E-14| +| 9| 0.595097 +i* -0.803654| 1|-3.46265E-13 +i* 1.60098E-14| +| 10| 0.900408 +i* -0.435047| 1| 3.20081E-13 +i*-1.77827E-14| +| 11| 0.999448 +i* 0.0332229| 1|-5.70342E-13 +i* 1.21308E-12| +| 12| 0.869529 +i* 0.493882| 1| 3.01252E-14 +i* 6.11216E-13| +| 13| 0.211292 +i* 0.977423| 1|-6.97532E-14 +i* 1.23212E-13| +| 14| -0.267139 +i* 0.963658| 1|-9.26238E-14 +i*-7.20968E-14| +| 15| -0.684372 +i* 0.729133| 1| 1.64042E-13 +i*-1.89831E-14| +| 16| -0.944825 +i* 0.327574| 1| 3.70572E-14 +i*-6.84904E-14| +| 17| -0.988833 +i* -0.149027| 1|-1.41002E-13 +i* 2.02581E-14| +| 18| -0.806314 +i* -0.591488| 1| 1.24668E-13 +i*-2.62805E-13| +| 19| -0.439079 +i* -0.898448| 1|-1.76949E-13 +i*-1.05707E-13| +| 20| 0.0287595 +i* -0.999586| 1| 4.76598E-14 +i*-1.43895E-14| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 1 +proc 0 +proc 1 +proc 2 +proc 3 +zone limite de 'log-exp' 1.00071 +zone limite de 'log-exp' 1.00071 +zone limite de 'log-exp' 1.00071 +zone limite de 'log-exp' 1.00071 +dimgrid 1954 dimblock 256 degrePoly 500000 +proc 3, start 375168 size 125056 +dimgrid 1954 dimblock 256 degrePoly 500000 +proc 1, start 125056 size 125056 +dimgrid 1954 dimblock 256 degrePoly 500000 +proc 2, start 250112 size 125056 +proc 1 start 125056 size 125056 +dimgrid 1954 dimblock 256 degrePoly 500000 +proc 0, start 0 size 125056 +proc 0 start 0 size 125056 +proc 3 start 375168 size 125056 +proc 2 start 250112 size 125056 +iter : 1 Arret : 5.43999E-06 s/iter 13.794000 +iter : 2 Arret : 4.91286E-06 s/iter 13.791136 +iter : 3 Arret : 4.80927E-06 s/iter 13.796273 +iter : 4 Arret : 4.84881E-06 s/iter 13.800496 +iter : 5 Arret : 4.97591E-06 s/iter 13.796980 +iter : 6 Arret : 4.79153E-06 s/iter 13.804318 +iter : 7 Arret : 4.83022E-06 s/iter 13.810851 +iter : 8 Arret : 5.21278E-06 s/iter 13.801380 +iter : 9 Arret : 6.23421E-06 s/iter 13.799572 +iter : 10 Arret : 6.92488E-05 s/iter 13.809235 +iter : 11 Arret : 0.00410439 s/iter 13.803771 +iter : 12 Arret : 0.00309009 s/iter 13.812651 +iter : 13 Arret : 0.0029815 s/iter 18.000127 +iter : 14 Arret : 0.00820943 s/iter 19.596298 +iter : 15 Arret : 0.0062262 s/iter 19.403564 +iter : 16 Arret : 1.4696 s/iter 14.578745 +iter : 17 Arret : 0.0225548 s/iter 15.759602 +iter : 18 Arret : 0.00265918 s/iter 11.703397 +iter : 19 Arret : 0.0066924 s/iter 8.696998 +iter : 20 Arret : 0.00187233 s/iter 14.112555 +iter : 21 Arret : 0.00910475 s/iter 8.336565 +iter : 22 Arret : 0.0385392 s/iter 8.037996 +iter : 23 Arret : 0.0216755 s/iter 9.237626 +iter : 24 Arret : 0.0024009 s/iter 7.207663 +iter : 25 Arret : 0.00123955 s/iter 6.955790 +iter : 26 Arret : 3.53765E-05 s/iter 6.696812 +iter : 27 Arret : 7.34783E-06 s/iter 6.014489 +iter : 28 Arret : 1.71411E-07 s/iter 5.956492 +iter : 29 Arret : 3.11637E-12 s/iter 5.922541 +iter : 30 Arret : 1.57009E-16 s/iter 5.957097 +temps : 358.278 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.48768E-08 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540372 +i* 0.841426| 1|-3.05235E-13 +i* 1.38721E-13| +| 2| 0.561316 +i* 0.827602| 1|-2.60021E-13 +i* 1.9206E-13| +| 3| 0.57165 +i* 0.820497| 1|-1.83308E-13 +i* 6.15844E-14| +| 4| 0.581895 +i* 0.813264| 1| 3.05839E-13 +i* 6.52482E-14| +| 5| 0.592048 +i* 0.805902| 1|-7.14016E-13 +i*-3.98882E-14| +| 6| 0.602109 +i* 0.798414| 1| 2.66658E-13 +i*-4.75979E-13| +| 7| 0.612074 +i* 0.7908| 1| 3.16743E-13 +i*-3.40844E-13| +| 8| 0.621943 +i* 0.783062| 1| 5.64146E-13 +i*-3.14632E-13| +| 9| 0.631715 +i* 0.775201| 1|-3.83756E-14 +i* 5.41086E-13| +| 10| 0.641387 +i* 0.767218| 1| 4.00499E-13 +i*-3.71465E-13| +| 11| 0.650958 +i* 0.759114| 1| 7.58768E-15 +i*-5.54055E-13| +| 12| 0.660427 +i* 0.750891| 1| 7.47999E-13 +i* 2.73089E-13| +| 13| 0.669792 +i* 0.742549| 1| 9.40577E-13 +i* 3.39433E-14| +| 14| 0.679051 +i* 0.734091| 1| 4.34264E-13 +i*-1.04887E-13| +| 15| 0.688204 +i* 0.725517| 1|-6.26926E-13 +i*-1.86798E-13| +| 16| 0.697248 +i* 0.71683| 1| 2.2389E-13 +i*-9.46795E-14| +| 17| 0.706183 +i* 0.708029| 1| 4.79186E-13 +i* 4.75144E-13| +| 18| 0.715007 +i* 0.699117| 1| 6.39138E-13 +i* 4.95824E-13| +| 19| 0.723718 +i* 0.690096| 1| -1.2694E-13 +i* 4.44528E-13| +| 20| 0.732316 +i* 0.680965| 1|-2.76158E-13 +i* 1.17734E-13| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +proc 2 +proc 3 +proc 0 +proc 1 +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 1, start 150016 size 150016 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 3, start 450048 size 150016 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 2, start 300032 size 150016 +proc 1 start 150016 size 150016 +proc 3 start 450048 size 150016 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 0, start 0 size 150016 +proc 0 start 0 size 150016 +proc 2 start 300032 size 150016 +iter : 1 Arret : 4.20321E-06 s/iter 18.775985 +iter : 2 Arret : 4.09855E-06 s/iter 18.747734 +iter : 3 Arret : 3.93391E-06 s/iter 18.730793 +iter : 4 Arret : 4.03193E-06 s/iter 18.732680 +iter : 5 Arret : 4.10736E-06 s/iter 18.735318 +iter : 6 Arret : 4.01386E-06 s/iter 18.743326 +iter : 7 Arret : 4.19451E-06 s/iter 18.739337 +iter : 8 Arret : 4.62309E-06 s/iter 18.741333 +iter : 9 Arret : 6.05422E-06 s/iter 18.740129 +iter : 10 Arret : 4.11892E-05 s/iter 18.733834 +iter : 11 Arret : 0.000517404 s/iter 18.736838 +iter : 12 Arret : 0.00114025 s/iter 18.735603 +iter : 13 Arret : 0.00285906 s/iter 18.781157 +iter : 14 Arret : 1.38645 s/iter 26.334716 +iter : 15 Arret : 0.623951 s/iter 22.498967 +iter : 16 Arret : 0.011785 s/iter 22.383771 +iter : 17 Arret : 0.0286509 s/iter 18.675149 +iter : 18 Arret : 0.0199337 s/iter 21.455577 +iter : 19 Arret : 0.00279992 s/iter 23.472538 +iter : 20 Arret : 0.00154477 s/iter 24.299102 +iter : 21 Arret : 0.000859833 s/iter 17.698308 +iter : 22 Arret : 0.000296794 s/iter 17.754719 +iter : 23 Arret : 3.50155E-05 s/iter 17.796812 +iter : 24 Arret : 1.46092E-05 s/iter 16.575301 +iter : 25 Arret : 1.13486E-05 s/iter 16.409288 +iter : 26 Arret : 2.08371E-06 s/iter 16.504363 +iter : 27 Arret : 4.3351E-08 s/iter 16.502863 +iter : 28 Arret : 1.78892E-13 s/iter 17.369262 +temps : 539.966 seconde(s) +Nb iterations : 28 +Nb de depassements de capacite exponentielle : 0 +Precision : 5.38109E-08 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540365 +i* 0.841431| 1| 4.39062E-13 +i* 5.83011E-13| +| 2| -0.553493 +i* -0.832854| 1|-5.02858E-13 +i* 3.83374E-15| +| 3| -0.579338 +i* -0.815087| 1| 4.42365E-13 +i* 2.65846E-14| +| 4| 0.592057 +i* 0.805896| 1| 2.06783E-13 +i* 1.94549E-13| +| 5| -0.604613 +i* -0.796519| 1| 2.39135E-13 +i* 2.96967E-13| +| 6| 0.617037 +i* 0.786934| 1|-3.70964E-13 +i* 2.85104E-13| +| 7| -0.629293 +i* -0.777168| 1| 3.4002E-13 +i* 1.14925E-14| +| 8| 0.641411 +i* 0.767198| 1|-6.01835E-13 +i* 5.70316E-13| +| 9| -0.653354 +i* -0.757052| 1| 3.00003E-14 +i* 4.1084E-13| +| 10| 0.665153 +i* 0.746707| 1|-9.55243E-14 +i* 7.739E-13| +| 11| -0.676773 +i* -0.736192| 1|-3.70891E-13 +i* 4.31963E-14| +| 12| 0.688242 +i* 0.725482| 1| 4.17319E-13 +i*-2.25125E-13| +| 13| -0.699526 +i* -0.714607| 1|-1.55074E-13 +i* 3.9467E-13| +| 14| 0.710653 +i* 0.703543| 1|-7.94843E-13 +i* 5.61671E-13| +| 15| -0.721591 +i* -0.69232| 1|-8.20351E-14 +i* 3.39909E-13| +| 16| 0.732366 +i* 0.680912| 1| 5.01595E-13 +i* 2.59279E-13| +| 17| -0.742946 +i* -0.669351| 1|-1.90181E-13 +i* 1.23972E-13| +| 18| 0.753358 +i* 0.657611| 1|-7.14661E-13 +i*-3.96187E-13| +| 19| -0.76357 +i* -0.645725| 1|-3.31242E-13 +i*-8.50865E-14| +| 20| 0.773609 +i* 0.633664| 1|-7.93813E-13 +i* 2.09313E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 1 +proc 2 +proc 3 +proc 0 +proc 1 +zone limite de 'log-exp' 1.00051 +zone limite de 'log-exp' 1.00051 +zone limite de 'log-exp' 1.00051 +zone limite de 'log-exp' 1.00051 +dimgrid 2735 dimblock 256 degrePoly 700000 +proc 2, start 350080 size 175040 +dimgrid 2735 dimblock 256 degrePoly 700000 +proc 1, start 175040 size 175040 +dimgrid 2735 dimblock 256 degrePoly 700000 +proc 3, start 525120 size 175040 +proc 3 start 525120 size 175040 +dimgrid 2735 dimblock 256 degrePoly 700000 +proc 0, start 0 size 175040 +proc 0 start 0 size 175040 +proc 2 start 350080 size 175040 +proc 1 start 175040 size 175040 +iter : 1 Arret : 4.05426E-06 s/iter 26.055375 +iter : 2 Arret : 3.62462E-06 s/iter 26.017320 +iter : 3 Arret : 3.57426E-06 s/iter 26.031338 +iter : 4 Arret : 3.57393E-06 s/iter 26.019895 +iter : 5 Arret : 3.53387E-06 s/iter 26.031664 +iter : 6 Arret : 3.57381E-06 s/iter 26.022006 +iter : 7 Arret : 4.05236E-06 s/iter 26.018695 +iter : 8 Arret : 3.5632E-06 s/iter 26.018506 +iter : 9 Arret : 3.74898E-06 s/iter 26.036369 +iter : 10 Arret : 1.82635E-05 s/iter 26.019377 +iter : 11 Arret : 0.0017458 s/iter 26.032260 +iter : 12 Arret : 0.00155961 s/iter 33.564621 +iter : 13 Arret : 0.00513024 s/iter 27.283039 +iter : 14 Arret : 0.00473339 s/iter 33.669836 +iter : 15 Arret : 0.00281261 s/iter 31.946913 +iter : 16 Arret : 0.00468659 s/iter 28.606391 +iter : 17 Arret : 0.0122921 s/iter 30.427694 +iter : 18 Arret : 0.0156527 s/iter 31.617517 +iter : 19 Arret : 0.0320085 s/iter 25.851204 +iter : 20 Arret : 0.22003 s/iter 25.842946 +iter : 21 Arret : 0.012535 s/iter 28.965802 +iter : 22 Arret : 0.00376424 s/iter 28.796070 +iter : 23 Arret : 0.00220948 s/iter 25.734592 +iter : 24 Arret : 0.00248624 s/iter 25.743976 +iter : 25 Arret : 0.000364428 s/iter 25.732814 +iter : 26 Arret : 0.000719089 s/iter 25.747749 +iter : 27 Arret : 0.000438507 s/iter 25.790591 +iter : 28 Arret : 1.26042E-05 s/iter 25.738843 +iter : 29 Arret : 3.25839E-06 s/iter 25.855423 +iter : 30 Arret : 1.74243E-07 s/iter 25.753106 +iter : 31 Arret : 3.09364E-11 s/iter 25.736769 +iter : 32 Arret : 1.57009E-16 s/iter 25.740011 +temps : 871.12 seconde(s) +Nb iterations : 32 +Nb de depassements de capacite exponentielle : 0 +Precision : 7.46262E-08 +Stabilite : 1.57009E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540352 +i* 0.841439| 1| 4.39978E-13 +i* 6.25043E-13| +| 2| -0.996034 +i* 0.0889731| 1| 2.2073E-13 +i* 1.55296E-13| +| 3| 0.439836 +i* -0.898078| 1|-3.55927E-13 +i*-1.21738E-13| +| 4| 0.38266 +i* -0.923889| 1|-2.56142E-13 +i*-7.02285E-14| +| 5| -0.988496 +i* 0.15125| 1|-1.52652E-13 +i*-1.11329E-13| +| 6| 0.641421 +i* 0.767189| 1|-1.31044E-13 +i* 5.61736E-13| +| 7| 0.323979 +i* -0.946064| 1|-4.52336E-13 +i* 8.74596E-14| +| 8| -0.977067 +i* 0.212932| 1| 8.58341E-14 +i* 1.73412E-13| +| 9| 0.688262 +i* 0.725462| 1| 4.28754E-14 +i* 1.08849E-12| +| 10| 0.264022 +i* -0.964517| 1|-3.63883E-13 +i*-8.14886E-14| +| 11| -0.961793 +i* 0.273776| 1| -3.0213E-13 +i*-2.13897E-13| +| 12| 0.732395 +i* 0.68088| 1|-3.65194E-14 +i* 7.95483E-13| +| 13| 0.203027 +i* -0.979173| 1|-3.14502E-13 +i* 2.96924E-13| +| 14| -0.942735 +i* 0.333543| 1| 1.82947E-13 +i*-4.73458E-14| +| 15| 0.773646 +i* 0.633619| 1| 2.24352E-13 +i* 2.79674E-13| +| 16| 0.141232 +i* -0.989977| 1| -1.0035E-13 +i* 1.5693E-13| +| 17| -0.919967 +i* 0.391997| 1| 2.89213E-14 +i*-1.86252E-13| +| 18| 0.811852 +i* 0.583864| 1|-1.59939E-12 +i*-4.13669E-13| +| 19| 0.0788818 +i* -0.996884| 1|-2.83003E-13 +i* 1.04711E-13| +| 20| -0.893578 +i* 0.448908| 1| 4.59736E-14 +i* 1.31414E-13| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 1 +proc 0 +proc 1 +proc 2 +proc 3 +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 3, start 600000 size 200000 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 1, start 200000 size 200000 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 2, start 400000 size 200000 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 0, start 0 size 200000 +proc 1 start 200000 size 200000 +proc 2 start 400000 size 200000 +proc 3 start 600000 size 200000 +proc 0 start 0 size 200000 +iter : 1 Arret : 3.03518E-06 s/iter 34.128856 +iter : 2 Arret : 3.06784E-06 s/iter 34.090727 +iter : 3 Arret : 3.06891E-06 s/iter 34.094241 +iter : 4 Arret : 2.95036E-06 s/iter 34.084829 +iter : 5 Arret : 2.99138E-06 s/iter 34.097352 +iter : 6 Arret : 3.04517E-06 s/iter 34.105084 +iter : 7 Arret : 3.18905E-06 s/iter 34.137020 +iter : 8 Arret : 3.30369E-06 s/iter 34.092524 +iter : 9 Arret : 4.0676E-06 s/iter 34.099620 +iter : 10 Arret : 8.80539E-06 s/iter 34.123961 +iter : 11 Arret : 0.000853991 s/iter 34.124027 +iter : 12 Arret : 0.000833381 s/iter 39.333820 +iter : 13 Arret : 2.00076 s/iter 34.135418 +iter : 14 Arret : 1.04464 s/iter 39.211608 +iter : 15 Arret : 0.956436 s/iter 35.763699 +iter : 16 Arret : 1.05412 s/iter 34.269226 +iter : 17 Arret : 0.887869 s/iter 32.651104 +iter : 18 Arret : 2.49443 s/iter 39.662531 +iter : 19 Arret : 0.0130108 s/iter 30.564624 +iter : 20 Arret : 0.0127308 s/iter 29.378733 +iter : 21 Arret : 0.00448902 s/iter 28.875435 +iter : 22 Arret : 0.0025421 s/iter 27.743883 +iter : 23 Arret : 0.000929422 s/iter 25.969572 +iter : 24 Arret : 4.42165E-05 s/iter 25.190779 +iter : 25 Arret : 1.79364E-05 s/iter 23.938702 +iter : 26 Arret : 5.68442E-06 s/iter 23.601870 +iter : 27 Arret : 4.0515E-07 s/iter 23.613905 +iter : 28 Arret : 2.68075E-10 s/iter 23.702620 +iter : 29 Arret : 6.86635E-16 s/iter 23.681104 +temps : 917.174 seconde(s) diff --git a/Simulations/full_mpi/full_mpi_4GPU.sge b/Simulations/full_mpi/full_mpi_4GPU.sge new file mode 100644 index 0000000..dafa0cf --- /dev/null +++ b/Simulations/full_mpi/full_mpi_4GPU.sge @@ -0,0 +1,25 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=4 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -V +#$ -cwd +#$ -N full_mpi_4GPU +#$ -pe mpi 4 + + +module load cuda/7.0 +module load ompi/gcc + +mpirun -np $NSLOTS ./template -r -i 60000 40000 +mpirun -np $NSLOTS ./template -r -i 150000 50000 +mpirun -np $NSLOTS ./template -r -i 250000 150000 +mpirun -np $NSLOTS ./template -r -i 350000 250000 +mpirun -np $NSLOTS ./template -r -i 500000 300000 +mpirun -np $NSLOTS ./template -r -i 600000 400000 +mpirun -np $NSLOTS ./template -r -i 700000 500000 +mpirun -np $NSLOTS ./template -r -i 800000 600000 +mpirun -np $NSLOTS ./template -r -i 900000 700000 +mpirun -np $NSLOTS ./template -r -i 1000000 800000 +mpirun -np $NSLOTS ./template -r -i 1500000 500000 diff --git a/Simulations/full_openmp/full_openmp_1GPU.o140165 b/Simulations/full_openmp/full_openmp_1GPU.o140165 new file mode 100644 index 0000000..84aa3b6 --- /dev/null +++ b/Simulations/full_openmp/full_openmp_1GPU.o140165 @@ -0,0 +1,511 @@ +REMAINING: 1 +Taking GPU #3 +zone limite de 'log-exp' 1.00593 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 235 dimblock 256 degrePoly 60000 +gpu 0 dimgrid2 235 start 0 size 60160 +gpu 0 iter : 1 Arret : 5.01505E-05 s/iter 0.752555 +gpu 0 iter : 2 Arret : 4.32789E-05 s/iter 0.752365 +gpu 0 iter : 3 Arret : 4.45615E-05 s/iter 0.752417 +gpu 0 iter : 4 Arret : 4.42697E-05 s/iter 0.752431 +gpu 0 iter : 5 Arret : 4.06411E-05 s/iter 0.752415 +gpu 0 iter : 6 Arret : 4.41499E-05 s/iter 0.752420 +gpu 0 iter : 7 Arret : 5.50757E-05 s/iter 0.752345 +gpu 0 iter : 8 Arret : 0.000694531 s/iter 0.752443 +gpu 0 iter : 9 Arret : 0.00117193 s/iter 0.752305 +gpu 0 iter : 10 Arret : 0.0225506 s/iter 0.752371 +gpu 0 iter : 11 Arret : 1.92499 s/iter 1.259044 +gpu 0 iter : 12 Arret : 0.0745471 s/iter 0.752271 +gpu 0 iter : 13 Arret : 0.0973834 s/iter 0.752268 +gpu 0 iter : 14 Arret : 0.106004 s/iter 1.275597 +gpu 0 iter : 15 Arret : 0.0165737 s/iter 1.272023 +gpu 0 iter : 16 Arret : 0.00779384 s/iter 1.273056 +gpu 0 iter : 17 Arret : 0.00519845 s/iter 1.250155 +gpu 0 iter : 18 Arret : 0.00892143 s/iter 0.736177 +gpu 0 iter : 19 Arret : 0.00448482 s/iter 0.708562 +gpu 0 iter : 20 Arret : 0.020935 s/iter 0.700305 +gpu 0 iter : 21 Arret : 0.0174876 s/iter 0.906835 +gpu 0 iter : 22 Arret : 0.00111891 s/iter 0.676895 +gpu 0 iter : 23 Arret : 0.000389286 s/iter 0.656019 +gpu 0 iter : 24 Arret : 0.00124195 s/iter 0.661695 +gpu 0 iter : 25 Arret : 0.00324262 s/iter 0.649796 +gpu 0 iter : 26 Arret : 6.61927E-05 s/iter 0.524316 +gpu 0 iter : 27 Arret : 2.71425E-05 s/iter 0.519333 +gpu 0 iter : 28 Arret : 9.63588E-07 s/iter 0.525346 +gpu 0 iter : 29 Arret : 1.01411E-10 s/iter 0.521530 +gpu 0 iter : 30 Arret : 3.15975E-15 s/iter 0.517480 +temps : 24.3248 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.35784E-10 +Stabilite : 3.15975E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540783 +i* 0.841162| 1|-7.58456E-14 +i* 3.78031E-14| +| 2| -0.992343 +i* -0.123513| 1|-4.36456E-15 +i* 3.59435E-15| +| 3| 0.0563346 +i* 0.998412| 1| 5.70377E-15 +i* 3.3501E-14| +| 4| -0.80273 +i* -0.596342| 1|-1.96995E-14 +i* -2.6033E-14| +| 5| 0.730552 +i* -0.682857| 1|-7.48429E-14 +i* 6.77011E-14| +| 6| -0.442728 +i* 0.896656| 1|-3.77198E-14 +i*-1.89779E-15| +| 7| -0.404888 +i* -0.914366| 1| 3.20195E-14 +i* 9.65894E-15| +| 8| 0.972126 +i* -0.23446| 1| 4.02421E-14 +i*-1.54755E-14| +| 9| -0.826939 +i* 0.562292| 1| -2.4928E-14 +i*-1.59889E-14| +| 10| 0.0979895 +i* -0.995187| 1| 2.27804E-14 +i*-1.97481E-14| +| 11| 0.961513 +i* 0.27476| 1|-9.39769E-14 +i*-2.63912E-13| +| 12| -0.996627 +i* 0.0820589| 1| 2.39773E-14 +i* 1.74825E-14| +| 13| 0.575447 +i* -0.817839| 1|-3.49894E-14 +i*-7.98545E-14| +| 14| 0.701466 +i* 0.712703| 1| 7.52211E-14 +i* 1.53991E-14| +| 15| 0.259346 +i* 0.965785| 1|-2.14863E-14 +i*-2.81355E-14| +| 16| -0.907773 +i* -0.419461| 1|-3.62869E-14 +i*-9.49414E-15| +| 17| 0.903623 +i* -0.428329| 1|-1.24969E-14 +i* 7.51222E-14| +| 18| -0.249979 +i* 0.968251| 1|-1.59074E-14 +i*-1.09721E-14| +| 19| -0.583256 +i* -0.812288| 1|-6.17215E-15 +i* 4.85358E-14| +| 20| 0.997383 +i* 0.072297| 1| 2.53037E-13 +i*-5.92819E-13| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 1 +zone limite de 'log-exp' 1.00237 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 586 dimblock 256 degrePoly 150000 +gpu 0 dimgrid2 586 start 0 size 150016 +gpu 0 iter : 1 Arret : 1.63964E-05 s/iter 4.677497 +gpu 0 iter : 2 Arret : 1.6127E-05 s/iter 4.675437 +gpu 0 iter : 3 Arret : 1.62587E-05 s/iter 4.673977 +gpu 0 iter : 4 Arret : 1.57168E-05 s/iter 4.675710 +gpu 0 iter : 5 Arret : 1.60975E-05 s/iter 4.675592 +gpu 0 iter : 6 Arret : 1.68058E-05 s/iter 4.675951 +gpu 0 iter : 7 Arret : 1.83433E-05 s/iter 4.674129 +gpu 0 iter : 8 Arret : 2.23201E-05 s/iter 4.676196 +gpu 0 iter : 9 Arret : 0.000120962 s/iter 4.674233 +gpu 0 iter : 10 Arret : 0.0050599 s/iter 4.675473 +gpu 0 iter : 11 Arret : 0.00201552 s/iter 4.674922 +gpu 0 iter : 12 Arret : 0.00812397 s/iter 4.675066 +gpu 0 iter : 13 Arret : 1.49892 s/iter 6.735627 +gpu 0 iter : 14 Arret : 0.0726739 s/iter 4.672589 +gpu 0 iter : 15 Arret : 0.0439834 s/iter 6.675641 +gpu 0 iter : 16 Arret : 0.0237516 s/iter 4.667633 +gpu 0 iter : 17 Arret : 0.0164273 s/iter 6.591866 +gpu 0 iter : 18 Arret : 0.0544284 s/iter 6.683422 +gpu 0 iter : 19 Arret : 0.0693187 s/iter 5.846457 +gpu 0 iter : 20 Arret : 0.0244663 s/iter 6.575941 +gpu 0 iter : 21 Arret : 0.0170064 s/iter 5.851392 +gpu 0 iter : 22 Arret : 0.0132914 s/iter 4.512540 +gpu 0 iter : 23 Arret : 0.000340596 s/iter 4.492501 +gpu 0 iter : 24 Arret : 0.000818373 s/iter 4.462503 +gpu 0 iter : 25 Arret : 0.000816806 s/iter 4.471482 +gpu 0 iter : 26 Arret : 2.75366E-05 s/iter 4.467418 +gpu 0 iter : 27 Arret : 1.11905E-05 s/iter 4.471479 +gpu 0 iter : 28 Arret : 1.25333E-07 s/iter 4.486611 +gpu 0 iter : 29 Arret : 1.10046E-12 s/iter 4.460078 +gpu 0 iter : 30 Arret : 1.11022E-16 s/iter 4.443078 +temps : 151.38 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.26535E-09 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540528 +i* 0.841326| 1| 8.68923E-14 +i* 2.2979E-13| +| 2| -0.905603 +i* -0.424127| 1| 6.50001E-14 +i* -3.0061E-14| +| 3| -0.774122 +i* 0.633037| 1|-3.89619E-14 +i*-6.71876E-14| +| 4| 0.317935 +i* -0.948113| 1| 4.656E-15 +i* 1.15645E-13| +| 5| 0.235897 +i* 0.971778| 1|-3.15963E-14 +i*-8.88994E-14| +| 6| -0.717299 +i* -0.696766| 1| 5.63785E-15 +i*-6.71685E-14| +| 7| 0.992349 +i* -0.123462| 1|-4.81056E-13 +i* 9.00335E-13| +| 8| -0.938482 +i* 0.345329| 1|-6.95555E-14 +i*-3.79159E-14| +| 9| 0.610294 +i* -0.792175| 1| -5.4852E-14 +i*-3.26232E-14| +| 10| -0.0945977 +i* 0.995516| 1| 4.45165E-14 +i* 9.42527E-14| +| 11| -0.450242 +i* -0.892906| 1| 2.41855E-14 +i*-3.23699E-15| +| 12| 0.978218 +i* 0.207583| 1|-2.84429E-13 +i* 4.69725E-13| +| 13| -0.999806 +i* 0.0197069| 1|-4.72365E-14 +i*-2.55716E-14| +| 14| 0.835648 +i* -0.549265| 1|-2.95892E-13 +i* 2.34143E-13| +| 15| -0.414707 +i* 0.909955| 1| 7.26225E-14 +i*-1.70003E-15| +| 16| -0.133754 +i* -0.991015| 1|-2.88485E-14 +i* 2.14499E-14| +| 17| 0.856687 +i* 0.515837| 1| 1.49106E-13 +i* 3.95153E-14| +| 18| -0.951361 +i* -0.308079| 1| 3.78308E-14 +i* 4.65843E-14| +| 19| 0.969257 +i* -0.24605| 1| 5.51163E-13 +i*-4.79498E-13| +| 20| -0.689285 +i* 0.724491| 1| 2.40086E-15 +i*-3.61777E-14| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 1 +zone limite de 'log-exp' 1.00142 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 977 dimblock 256 degrePoly 250000 +gpu 0 dimgrid2 977 start 0 size 250112 +gpu 0 iter : 1 Arret : 1.15543E-05 s/iter 13.064328 +gpu 0 iter : 2 Arret : 1.05743E-05 s/iter 13.099577 +gpu 0 iter : 3 Arret : 1.00182E-05 s/iter 13.092478 +gpu 0 iter : 4 Arret : 9.77217E-06 s/iter 13.098796 +gpu 0 iter : 5 Arret : 1.10944E-05 s/iter 13.096321 +gpu 0 iter : 6 Arret : 1.15644E-05 s/iter 13.098761 +gpu 0 iter : 7 Arret : 9.85482E-06 s/iter 13.095612 +gpu 0 iter : 8 Arret : 1.06459E-05 s/iter 13.079031 +gpu 0 iter : 9 Arret : 2.17082E-05 s/iter 13.095096 +gpu 0 iter : 10 Arret : 0.00106372 s/iter 13.097410 +gpu 0 iter : 11 Arret : 0.00274403 s/iter 13.098142 +gpu 0 iter : 12 Arret : 0.00233621 s/iter 15.172668 +gpu 0 iter : 13 Arret : 0.00104775 s/iter 13.090864 +gpu 0 iter : 14 Arret : 0.00142817 s/iter 13.093375 +gpu 0 iter : 15 Arret : 0.00192709 s/iter 13.017860 +gpu 0 iter : 16 Arret : 0.0176279 s/iter 11.468330 +gpu 0 iter : 17 Arret : 0.0577522 s/iter 7.983525 +gpu 0 iter : 18 Arret : 0.0271883 s/iter 9.498511 +gpu 0 iter : 19 Arret : 0.32067 s/iter 9.329063 +gpu 0 iter : 20 Arret : 0.0289407 s/iter 9.296524 +gpu 0 iter : 21 Arret : 0.00140766 s/iter 7.142933 +gpu 0 iter : 22 Arret : 0.000475428 s/iter 7.123373 +gpu 0 iter : 23 Arret : 0.000240166 s/iter 7.094510 +gpu 0 iter : 24 Arret : 1.51927E-05 s/iter 7.077023 +gpu 0 iter : 25 Arret : 1.77863E-06 s/iter 7.010421 +gpu 0 iter : 26 Arret : 8.08854E-10 s/iter 7.130576 +gpu 0 iter : 27 Arret : 1.00074E-15 s/iter 7.048493 +temps : 296.321 seconde(s) +Nb iterations : 27 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.05316E-09 +Stabilite : 1.00074E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540427 +i* 0.841391| 1| 9.7148E-14 +i*-1.98189E-13| +| 2| -0.997949 +i* 0.0640067| 1| 1.02696E-14 +i* 2.88415E-14| +| 3| 0.450991 +i* -0.892528| 1| 2.39739E-15 +i* 7.66835E-14| +| 4| 0.42851 +i* -0.903537| 1| 1.03733E-13 +i* 1.27433E-14| +| 5| -0.996035 +i* 0.0889649| 1| 5.1386E-14 +i* 4.21729E-14| +| 6| 0.581876 +i* 0.813277| 1| 3.29906E-13 +i* -3.5718E-15| +| 7| 0.405761 +i* -0.913979| 1| 1.69923E-13 +i*-8.86062E-14| +| 8| -0.993496 +i* 0.113867| 1| 6.34562E-14 +i* 6.04291E-14| +| 9| 0.60205 +i* 0.798458| 1| 2.39371E-13 +i* -2.2848E-13| +| 10| 0.382757 +i* -0.923849| 1| 6.36852E-14 +i* 1.1601E-13| +| 11| -0.990335 +i* 0.138698| 1| 8.32286E-14 +i* 4.57395E-14| +| 12| 0.621846 +i* 0.783139| 1| 3.5482E-14 +i*-1.57841E-13| +| 13| 0.359514 +i* -0.93314| 1| 1.00985E-13 +i*-2.52237E-13| +| 14| -0.986553 +i* 0.163442| 1| 3.24636E-14 +i* 4.58574E-14| +| 15| 0.641253 +i* 0.767329| 1| 1.79533E-13 +i* 3.03096E-13| +| 16| 0.336045 +i* -0.941846| 1| 1.38948E-13 +i*-8.14071E-14| +| 17| -0.982153 +i* 0.188084| 1| 6.94549E-14 +i* 3.09405E-14| +| 18| 0.660258 +i* 0.751039| 1| 4.21871E-13 +i* 5.02185E-14| +| 19| 0.312366 +i* -0.949962| 1|-6.37199E-14 +i*-7.39669E-14| +| 20| -0.977138 +i* 0.212608| 1|-3.80633E-14 +i* -8.4285E-14| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 1 +zone limite de 'log-exp' 1.00101 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 1368 dimblock 256 degrePoly 350000 +gpu 0 dimgrid2 1368 start 0 size 350208 +gpu 0 iter : 1 Arret : 8.60936E-06 s/iter 25.332348 +gpu 0 iter : 2 Arret : 7.40646E-06 s/iter 25.331263 +gpu 0 iter : 3 Arret : 7.97813E-06 s/iter 25.297466 +gpu 0 iter : 4 Arret : 7.23099E-06 s/iter 25.306792 +gpu 0 iter : 5 Arret : 6.85143E-06 s/iter 25.280568 +gpu 0 iter : 6 Arret : 6.79155E-06 s/iter 25.305357 +gpu 0 iter : 7 Arret : 7.08999E-06 s/iter 25.314962 +gpu 0 iter : 8 Arret : 7.80158E-06 s/iter 25.279543 +gpu 0 iter : 9 Arret : 2.6561E-05 s/iter 25.267836 +gpu 0 iter : 10 Arret : 0.00102009 s/iter 25.308796 +gpu 0 iter : 11 Arret : 0.00106765 s/iter 25.285841 +gpu 0 iter : 12 Arret : 0.00106457 s/iter 25.305366 +gpu 0 iter : 13 Arret : 0.857755 s/iter 25.292478 +gpu 0 iter : 14 Arret : 3.15407 s/iter 25.495050 +gpu 0 iter : 15 Arret : 0.0928667 s/iter 25.354315 +gpu 0 iter : 16 Arret : 0.0413768 s/iter 25.910028 +gpu 0 iter : 17 Arret : 0.0497463 s/iter 25.748876 +gpu 0 iter : 18 Arret : 0.0497904 s/iter 25.748583 +gpu 0 iter : 19 Arret : 0.0354662 s/iter 25.596173 +gpu 0 iter : 20 Arret : 0.0431719 s/iter 25.648011 +gpu 0 iter : 21 Arret : 0.0230133 s/iter 25.155342 +gpu 0 iter : 22 Arret : 0.00525789 s/iter 25.160092 +gpu 0 iter : 23 Arret : 0.00203657 s/iter 24.929404 +gpu 0 iter : 24 Arret : 0.000600149 s/iter 24.929483 +gpu 0 iter : 25 Arret : 0.00016638 s/iter 24.931502 +gpu 0 iter : 26 Arret : 0.000154787 s/iter 24.957389 +gpu 0 iter : 27 Arret : 0.000302699 s/iter 24.917011 +gpu 0 iter : 28 Arret : 2.13113E-05 s/iter 24.916750 +gpu 0 iter : 29 Arret : 1.51643E-05 s/iter 24.917954 +gpu 0 iter : 30 Arret : 3.76262E-06 s/iter 24.943057 +gpu 0 iter : 31 Arret : 1.29245E-07 s/iter 24.913031 +gpu 0 iter : 32 Arret : 6.35329E-12 s/iter 24.917417 +gpu 0 iter : 33 Arret : 1.24127E-16 s/iter 24.950893 +temps : 833.807 seconde(s) +Nb iterations : 33 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.46096E-08 +Stabilite : 1.24127E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540399 +i* 0.841409| 1| 5.12961E-13 +i*-3.37404E-15| +| 2| -0.385479 +i* 0.922716| 1| -1.616E-13 +i*-2.73566E-14| +| 3| -0.770131 +i* 0.637886| 1|-1.38431E-15 +i* 1.70921E-13| +| 4| -0.978357 +i* 0.206925| 1|-3.07393E-15 +i* 4.96131E-15| +| 5| -0.962455 +i* -0.27144| 1|-5.85088E-14 +i* 7.9714E-14| +| 6| -0.72607 +i* -0.687621| 1| -2.0612E-14 +i* 2.87948E-13| +| 7| -0.323352 +i* -0.946279| 1| 2.27159E-13 +i* 7.30891E-14| +| 8| 0.153459 +i* -0.988155| 1| 4.60049E-15 +i*-2.43555E-14| +| 9| 0.595097 +i* -0.803654| 1|-3.46265E-13 +i* 1.60098E-14| +| 10| 0.900408 +i* -0.435047| 1| 3.20081E-13 +i*-1.77827E-14| +| 11| 0.999448 +i* 0.0332229| 1|-5.70342E-13 +i* 1.21308E-12| +| 12| 0.869529 +i* 0.493882| 1| 3.01252E-14 +i* 6.11216E-13| +| 13| 0.211292 +i* 0.977423| 1|-6.97532E-14 +i* 1.23212E-13| +| 14| -0.267139 +i* 0.963658| 1|-9.26238E-14 +i*-7.20968E-14| +| 15| -0.684372 +i* 0.729133| 1| 1.64042E-13 +i*-1.89831E-14| +| 16| -0.944825 +i* 0.327574| 1| 3.70572E-14 +i*-6.84904E-14| +| 17| -0.988833 +i* -0.149027| 1|-1.41002E-13 +i* 2.02581E-14| +| 18| -0.806314 +i* -0.591488| 1| 1.24668E-13 +i*-2.62805E-13| +| 19| -0.439079 +i* -0.898448| 1|-1.76949E-13 +i*-1.05707E-13| +| 20| 0.0287415 +i* -0.999587| 1| 1.62724E-13 +i*-6.82891E-14| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 1 +zone limite de 'log-exp' 1.00071 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 1954 dimblock 256 degrePoly 500000 +gpu 0 dimgrid2 1954 start 0 size 500224 +gpu 0 iter : 1 Arret : 6.12242E-06 s/iter 51.505107 +gpu 0 iter : 2 Arret : 6.31918E-06 s/iter 51.453063 +gpu 0 iter : 3 Arret : 5.33763E-06 s/iter 51.408046 +gpu 0 iter : 4 Arret : 5.41422E-06 s/iter 51.400436 +gpu 0 iter : 5 Arret : 5.39348E-06 s/iter 51.382269 +gpu 0 iter : 6 Arret : 5.60111E-06 s/iter 51.438183 +gpu 0 iter : 7 Arret : 5.01475E-06 s/iter 51.488070 +gpu 0 iter : 8 Arret : 5.29744E-06 s/iter 51.358997 +gpu 0 iter : 9 Arret : 6.66838E-06 s/iter 51.085502 +gpu 0 iter : 10 Arret : 6.73287E-05 s/iter 51.335479 +gpu 0 iter : 11 Arret : 0.00990101 s/iter 51.464874 +gpu 0 iter : 12 Arret : 0.00823435 s/iter 51.403521 +gpu 0 iter : 13 Arret : 0.0131909 s/iter 51.825163 +gpu 0 iter : 14 Arret : 0.00701993 s/iter 52.176993 +gpu 0 iter : 15 Arret : 0.0153428 s/iter 47.885546 +gpu 0 iter : 16 Arret : 1.40554 s/iter 37.523257 +gpu 0 iter : 17 Arret : 0.017993 s/iter 33.363730 +gpu 0 iter : 18 Arret : 0.0130545 s/iter 31.485423 +gpu 0 iter : 19 Arret : 0.00840726 s/iter 29.781113 +gpu 0 iter : 20 Arret : 0.0195837 s/iter 30.113452 +gpu 0 iter : 21 Arret : 0.0204301 s/iter 30.982105 +gpu 0 iter : 22 Arret : 0.0051956 s/iter 26.750718 +gpu 0 iter : 23 Arret : 0.000187857 s/iter 25.344565 +gpu 0 iter : 24 Arret : 9.72305E-05 s/iter 24.719137 +gpu 0 iter : 25 Arret : 3.47336E-05 s/iter 23.203467 +gpu 0 iter : 26 Arret : 1.4149E-05 s/iter 22.255267 +gpu 0 iter : 27 Arret : 9.26981E-06 s/iter 22.153239 +gpu 0 iter : 28 Arret : 2.81196E-06 s/iter 22.023657 +gpu 0 iter : 29 Arret : 1.36843E-07 s/iter 21.837417 +gpu 0 iter : 30 Arret : 1.32082E-11 s/iter 21.847546 +gpu 0 iter : 31 Arret : 1.11022E-16 s/iter 21.866344 +temps : 1194.76 seconde(s) +Nb iterations : 31 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.48768E-08 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540372 +i* 0.841426| 1|-3.05235E-13 +i* 1.38721E-13| +| 2| 0.561316 +i* 0.827602| 1|-2.60021E-13 +i* 1.9206E-13| +| 3| 0.57165 +i* 0.820497| 1|-1.83308E-13 +i* 6.15844E-14| +| 4| 0.581895 +i* 0.813264| 1| 3.05839E-13 +i* 6.52482E-14| +| 5| 0.592048 +i* 0.805902| 1|-7.14016E-13 +i*-3.98882E-14| +| 6| 0.602109 +i* 0.798414| 1| 2.66658E-13 +i*-4.75979E-13| +| 7| 0.612074 +i* 0.7908| 1| 3.16743E-13 +i*-3.40844E-13| +| 8| 0.621943 +i* 0.783062| 1| 5.64146E-13 +i*-3.14632E-13| +| 9| 0.631715 +i* 0.775201| 1|-3.83756E-14 +i* 5.41086E-13| +| 10| 0.641387 +i* 0.767218| 1| 4.00499E-13 +i*-3.71465E-13| +| 11| 0.650958 +i* 0.759114| 1| 7.58768E-15 +i*-5.54055E-13| +| 12| 0.660427 +i* 0.750891| 1| 7.47999E-13 +i* 2.73089E-13| +| 13| 0.669792 +i* 0.742549| 1| 9.40577E-13 +i* 3.39433E-14| +| 14| 0.679051 +i* 0.734091| 1| 4.34264E-13 +i*-1.04887E-13| +| 15| 0.688204 +i* 0.725517| 1|-6.26926E-13 +i*-1.86798E-13| +| 16| 0.697248 +i* 0.71683| 1| 2.2389E-13 +i*-9.46795E-14| +| 17| 0.706183 +i* 0.708029| 1| 4.79186E-13 +i* 4.75144E-13| +| 18| 0.715007 +i* 0.699117| 1| 6.39138E-13 +i* 4.95824E-13| +| 19| 0.723718 +i* 0.690096| 1| -1.2694E-13 +i* 4.44528E-13| +| 20| 0.732316 +i* 0.680965| 1|-2.76158E-13 +i* 1.17734E-13| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +zone limite de 'log-exp' 1.00059 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 0 dimgrid2 2344 start 0 size 600064 +gpu 0 iter : 1 Arret : 5.11012E-06 s/iter 73.756595 +gpu 0 iter : 2 Arret : 5.49594E-06 s/iter 74.121359 +gpu 0 iter : 3 Arret : 4.95278E-06 s/iter 74.139359 +gpu 0 iter : 4 Arret : 4.31967E-06 s/iter 74.012268 +gpu 0 iter : 5 Arret : 4.586E-06 s/iter 74.059945 +gpu 0 iter : 6 Arret : 4.28143E-06 s/iter 74.091814 +gpu 0 iter : 7 Arret : 4.14913E-06 s/iter 74.022009 +gpu 0 iter : 8 Arret : 4.768E-06 s/iter 74.045411 +gpu 0 iter : 9 Arret : 6.32809E-06 s/iter 74.020498 +gpu 0 iter : 10 Arret : 0.000551734 s/iter 74.008861 +gpu 0 iter : 11 Arret : 0.000854623 s/iter 74.075006 +gpu 0 iter : 12 Arret : 0.00526383 s/iter 74.351997 +gpu 0 iter : 13 Arret : 1.86671 s/iter 74.338451 +gpu 0 iter : 14 Arret : 0.044381 s/iter 74.401470 +gpu 0 iter : 15 Arret : 0.0449663 s/iter 77.708059 +gpu 0 iter : 16 Arret : 0.0459647 s/iter 73.860654 +gpu 0 iter : 17 Arret : 0.0457241 s/iter 72.117134 +gpu 0 iter : 18 Arret : 0.0378989 s/iter 71.687519 +gpu 0 iter : 19 Arret : 0.0321851 s/iter 69.198666 +gpu 0 iter : 20 Arret : 0.0124933 s/iter 68.613221 +gpu 0 iter : 21 Arret : 0.00730326 s/iter 67.130299 +gpu 0 iter : 22 Arret : 0.00446236 s/iter 65.916847 +gpu 0 iter : 23 Arret : 0.000497812 s/iter 65.967574 +gpu 0 iter : 24 Arret : 0.000892713 s/iter 65.658481 +gpu 0 iter : 25 Arret : 4.7836E-06 s/iter 64.891775 +gpu 0 iter : 26 Arret : 1.04505E-09 s/iter 65.003588 +gpu 0 iter : 27 Arret : 3.1578E-15 s/iter 65.348519 +temps : 1931.46 seconde(s) +Nb iterations : 27 +Nb de depassements de capacite exponentielle : 0 +Precision : 5.38109E-08 +Stabilite : 3.1578E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540365 +i* 0.841431| 1| 4.39062E-13 +i* 5.83011E-13| +| 2| -0.553493 +i* -0.832854| 1|-5.02858E-13 +i* 3.83374E-15| +| 3| -0.579338 +i* -0.815087| 1| 4.42365E-13 +i* 2.65846E-14| +| 4| 0.592057 +i* 0.805896| 1| 2.06783E-13 +i* 1.94549E-13| +| 5| -0.604613 +i* -0.796519| 1| 2.39135E-13 +i* 2.96967E-13| +| 6| 0.617037 +i* 0.786934| 1|-3.70964E-13 +i* 2.85104E-13| +| 7| -0.629293 +i* -0.777168| 1| 3.4002E-13 +i* 1.14925E-14| +| 8| 0.641411 +i* 0.767198| 1|-6.01835E-13 +i* 5.70316E-13| +| 9| -0.653354 +i* -0.757052| 1| 3.00003E-14 +i* 4.1084E-13| +| 10| 0.665153 +i* 0.746707| 1|-9.55243E-14 +i* 7.739E-13| +| 11| -0.676773 +i* -0.736192| 1|-3.70891E-13 +i* 4.31963E-14| +| 12| 0.688242 +i* 0.725482| 1| 4.17319E-13 +i*-2.25125E-13| +| 13| -0.699526 +i* -0.714607| 1|-1.55074E-13 +i* 3.9467E-13| +| 14| 0.710653 +i* 0.703543| 1|-7.94843E-13 +i* 5.61671E-13| +| 15| -0.721591 +i* -0.69232| 1|-8.20351E-14 +i* 3.39909E-13| +| 16| 0.732366 +i* 0.680912| 1| 5.01595E-13 +i* 2.59279E-13| +| 17| -0.742946 +i* -0.669351| 1|-1.90181E-13 +i* 1.23972E-13| +| 18| 0.753358 +i* 0.657611| 1|-7.14661E-13 +i*-3.96187E-13| +| 19| -0.76357 +i* -0.645725| 1|-3.31242E-13 +i*-8.50865E-14| +| 20| 0.773609 +i* 0.633664| 1|-7.93813E-13 +i* 2.09313E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 1 +zone limite de 'log-exp' 1.00051 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 2735 dimblock 256 degrePoly 700000 +gpu 0 dimgrid2 2735 start 0 size 700160 +gpu 0 iter : 1 Arret : 4.40509E-06 s/iter 100.694769 +gpu 0 iter : 2 Arret : 4.14157E-06 s/iter 100.469337 +gpu 0 iter : 3 Arret : 4.41135E-06 s/iter 100.605636 +gpu 0 iter : 4 Arret : 3.77329E-06 s/iter 100.474382 +gpu 0 iter : 5 Arret : 3.66086E-06 s/iter 100.585159 +gpu 0 iter : 6 Arret : 3.72953E-06 s/iter 100.453144 +gpu 0 iter : 7 Arret : 3.69827E-06 s/iter 100.534472 +gpu 0 iter : 8 Arret : 4.0146E-06 s/iter 100.527939 +gpu 0 iter : 9 Arret : 4.40501E-06 s/iter 100.506852 +gpu 0 iter : 10 Arret : 0.000145438 s/iter 100.425934 +gpu 0 iter : 11 Arret : 0.000853238 s/iter 100.356423 +gpu 0 iter : 12 Arret : 0.00173408 s/iter 100.698172 +gpu 0 iter : 13 Arret : 0.00406782 s/iter 102.669605 +gpu 0 iter : 14 Arret : 0.00525798 s/iter 100.740660 +gpu 0 iter : 15 Arret : 0.00912631 s/iter 101.481624 +gpu 0 iter : 16 Arret : 0.0564377 s/iter 100.156723 +gpu 0 iter : 17 Arret : 0.173647 s/iter 101.052747 +gpu 0 iter : 18 Arret : 0.0415567 s/iter 103.159864 +gpu 0 iter : 19 Arret : 0.0291844 s/iter 101.678094 +gpu 0 iter : 20 Arret : 0.0193248 s/iter 101.283426 +gpu 0 iter : 21 Arret : 0.00828239 s/iter 100.513861 +gpu 0 iter : 22 Arret : 0.00218532 s/iter 99.669534 +gpu 0 iter : 23 Arret : 0.00038288 s/iter 99.672435 +gpu 0 iter : 24 Arret : 0.00053382 s/iter 99.680679 +gpu 0 iter : 25 Arret : 0.000180417 s/iter 99.792193 +gpu 0 iter : 26 Arret : 6.23119E-05 s/iter 99.656799 +gpu 0 iter : 27 Arret : 1.31328E-05 s/iter 99.708395 +gpu 0 iter : 28 Arret : 1.46741E-06 s/iter 99.655086 +gpu 0 iter : 29 Arret : 1.39344E-08 s/iter 99.775734 +gpu 0 iter : 30 Arret : 6.13969E-15 s/iter 99.639756 +temps : 3017.33 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 7.46262E-08 +Stabilite : 6.13969E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540352 +i* 0.841439| 1| 4.39978E-13 +i* 6.25043E-13| +| 2| -0.996034 +i* 0.0889731| 1| 2.2073E-13 +i* 1.55296E-13| +| 3| 0.439836 +i* -0.898078| 1|-3.55927E-13 +i*-1.21738E-13| +| 4| 0.38266 +i* -0.923889| 1|-2.56142E-13 +i*-7.02285E-14| +| 5| -0.988496 +i* 0.15125| 1|-1.52652E-13 +i*-1.11329E-13| +| 6| 0.641421 +i* 0.767189| 1|-1.31044E-13 +i* 5.61736E-13| +| 7| 0.323979 +i* -0.946064| 1|-4.52336E-13 +i* 8.74596E-14| +| 8| -0.977067 +i* 0.212932| 1| 8.58341E-14 +i* 1.73412E-13| +| 9| 0.688262 +i* 0.725462| 1| 4.28754E-14 +i* 1.08849E-12| +| 10| 0.264022 +i* -0.964517| 1|-3.63883E-13 +i*-8.14886E-14| +| 11| -0.961793 +i* 0.273776| 1| -3.0213E-13 +i*-2.13897E-13| +| 12| 0.732395 +i* 0.68088| 1|-3.65194E-14 +i* 7.95483E-13| +| 13| 0.203027 +i* -0.979173| 1|-3.14502E-13 +i* 2.96924E-13| +| 14| -0.942735 +i* 0.333543| 1| 1.82947E-13 +i*-4.73458E-14| +| 15| 0.773646 +i* 0.633619| 1| 2.24352E-13 +i* 2.79674E-13| +| 16| 0.141232 +i* -0.989977| 1| -1.0035E-13 +i* 1.5693E-13| +| 17| -0.919967 +i* 0.391997| 1| 2.89213E-14 +i*-1.86252E-13| +| 18| 0.811852 +i* 0.583864| 1|-1.59939E-12 +i*-4.13669E-13| +| 19| 0.0788818 +i* -0.996884| 1|-2.83003E-13 +i* 1.04711E-13| +| 20| -0.893578 +i* 0.448908| 1| 4.59736E-14 +i* 1.31414E-13| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 1 +zone limite de 'log-exp' 1.00044 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 0 dimgrid2 3125 start 0 size 800000 +gpu 0 iter : 1 Arret : 3.74909E-06 s/iter 131.738179 +gpu 0 iter : 2 Arret : 3.49254E-06 s/iter 131.503382 +gpu 0 iter : 3 Arret : 3.79247E-06 s/iter 130.862896 +gpu 0 iter : 4 Arret : 3.40119E-06 s/iter 130.832910 +gpu 0 iter : 5 Arret : 3.64216E-06 s/iter 131.517237 +gpu 0 iter : 6 Arret : 3.50994E-06 s/iter 131.403093 +gpu 0 iter : 7 Arret : 3.54522E-06 s/iter 131.315477 +gpu 0 iter : 8 Arret : 3.57706E-06 s/iter 131.206471 +gpu 0 iter : 9 Arret : 4.78249E-06 s/iter 131.242355 +gpu 0 iter : 10 Arret : 0.000445854 s/iter 131.325342 +gpu 0 iter : 11 Arret : 0.00106438 s/iter 131.005859 +gpu 0 iter : 12 Arret : 0.0159228 s/iter 130.855281 +gpu 0 iter : 13 Arret : 1.96586 s/iter 131.580736 +gpu 0 iter : 14 Arret : 0.0310235 s/iter 139.161956 +gpu 0 iter : 15 Arret : 0.288368 s/iter 132.380708 +gpu 0 iter : 16 Arret : 0.268505 s/iter 131.753751 +gpu 0 iter : 17 Arret : 0.055019 s/iter 130.693875 +gpu 0 iter : 18 Arret : 0.0095986 s/iter 120.836692 +gpu 0 iter : 19 Arret : 0.0067465 s/iter 121.133462 +gpu 0 iter : 20 Arret : 0.00486301 s/iter 111.958685 +gpu 0 iter : 21 Arret : 0.00150462 s/iter 106.824156 +gpu 0 iter : 22 Arret : 0.00367623 s/iter 100.023867 +gpu 0 iter : 23 Arret : 0.000649555 s/iter 95.844251 +gpu 0 iter : 24 Arret : 1.61661E-05 s/iter 92.179310 +gpu 0 iter : 25 Arret : 1.57748E-05 s/iter 90.746510 +gpu 0 iter : 26 Arret : 2.71821E-06 s/iter 90.684064 +gpu 0 iter : 27 Arret : 5.01324E-07 s/iter 90.550543 +gpu 0 iter : 28 Arret : 6.04245E-10 s/iter 90.007638 +gpu 0 iter : 29 Arret : 1.57426E-15 s/iter 90.215782 +temps : 3442.42 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 6.26383E-08 +Stabilite : 1.57426E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540349 +i* 0.841441| 1|-1.16344E-13 +i* 9.55619E-13| +| 2| 0.592061 +i* 0.805893| 1|-1.57249E-13 +i*-4.43364E-13| +| 3| 0.617051 +i* 0.786923| 1|-6.42805E-13 +i*-3.49094E-13| +| 4| 0.641434 +i* 0.767178| 1| 1.00022E-12 +i*-5.90578E-13| +| 5| 0.665186 +i* 0.746678| 1|-2.53998E-14 +i*-1.14684E-12| +| 6| 0.688283 +i* 0.725442| 1|-8.68732E-13 +i* 8.52696E-13| +| 7| 0.710703 +i* 0.703493| 1| 2.02581E-13 +i* 4.54699E-13| +| 8| 0.732422 +i* 0.680851| 1|-5.22353E-13 +i*-3.99873E-13| +| 9| 0.753421 +i* 0.657538| 1| 1.23356E-13 +i*-1.05986E-12| +| 10| 0.773678 +i* 0.633579| 1|-6.75196E-13 +i* 3.60108E-13| +| 11| 0.793174 +i* 0.608995| 1| 4.43853E-13 +i*-1.42398E-12| +| 12| 0.811888 +i* 0.583813| 1|-4.10491E-13 +i*-4.46651E-13| +| 13| 0.829804 +i* 0.558055| 1| 1.30045E-12 +i* 1.12788E-13| +| 14| 0.846902 +i* 0.531748| 1|-8.09419E-13 +i* 4.98091E-13| +| 15| 0.863167 +i* 0.504918| 1| 2.98522E-13 +i* 3.81547E-13| +| 16| 0.878582 +i* 0.477591| 1|-3.06581E-13 +i*-6.95869E-13| +| 17| 0.893133 +i* 0.449793| 1| 1.24355E-13 +i* -1.3239E-12| +| 18| 0.906804 +i* 0.421553| 1|-1.23117E-12 +i*-5.57117E-13| +| 19| 0.919582 +i* 0.392898| 1|-1.03648E-12 +i* 2.90445E-14| +| 20| 0.931455 +i* 0.363856| 1|-6.42708E-13 +i*-1.50318E-12| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 1 diff --git a/Simulations/full_openmp/full_openmp_1GPU.sge b/Simulations/full_openmp/full_openmp_1GPU.sge new file mode 100644 index 0000000..038b92b --- /dev/null +++ b/Simulations/full_openmp/full_openmp_1GPU.sge @@ -0,0 +1,27 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=1 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -pe openmp 1 +#$ -V +#$ -cwd +#$ -N full_openmp_1GPU + +module load gcc/4.9.0 +module load cuda/7.0 +export OMP_NUM_THREADS=1 + +./template -r -i 60000 40000 +./template -r -i 150000 50000 +./template -r -i 250000 150000 +./template -r -i 350000 250000 +./template -r -i 500000 300000 +./template -r -i 600000 400000 +./template -r -i 700000 500000 +./template -r -i 800000 600000 +#./template -r -i 900000 700000 +#./template -r -i 1000000 800000 +#./template -r -i 1500000 500000 + + diff --git a/Simulations/full_openmp/full_openmp_2GPU.o140164 b/Simulations/full_openmp/full_openmp_2GPU.o140164 new file mode 100644 index 0000000..09208b1 --- /dev/null +++ b/Simulations/full_openmp/full_openmp_2GPU.o140164 @@ -0,0 +1,540 @@ +REMAINING: 2 +Taking GPU #2 +Taking GPU #3 +zone limite de 'log-exp' 1.00593 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 0 dimgrid 235 dimblock 256 degrePoly 60000 +gpu 0 dimgrid2 118 start 0 size 30080 +gpu 1 dimgrid 235 dimblock 256 degrePoly 60000 +gpu 1 dimgrid2 118 start 30080 size 30080 +gpu 0 iter : 1 Arret : 4.09766E-05 s/iter 0.377749 +gpu 0 iter : 2 Arret : 3.79749E-05 s/iter 0.377727 +gpu 0 iter : 3 Arret : 3.85767E-05 s/iter 0.377765 +gpu 0 iter : 4 Arret : 3.91197E-05 s/iter 0.377744 +gpu 0 iter : 5 Arret : 4.06402E-05 s/iter 0.377742 +gpu 0 iter : 6 Arret : 4.41484E-05 s/iter 0.377649 +gpu 0 iter : 7 Arret : 5.50721E-05 s/iter 0.377635 +gpu 0 iter : 8 Arret : 0.000118507 s/iter 0.377582 +gpu 0 iter : 9 Arret : 0.00116121 s/iter 0.377567 +gpu 0 iter : 10 Arret : 0.0219727 s/iter 0.377659 +gpu 0 iter : 11 Arret : 2.07933 s/iter 1.180745 +gpu 0 iter : 12 Arret : 0.27049 s/iter 0.377586 +gpu 0 iter : 13 Arret : 0.1554 s/iter 1.212301 +gpu 0 iter : 14 Arret : 0.0487107 s/iter 1.213253 +gpu 0 iter : 15 Arret : 0.0169372 s/iter 1.208391 +gpu 0 iter : 16 Arret : 0.00924961 s/iter 1.200600 +gpu 0 iter : 17 Arret : 0.00644126 s/iter 1.173874 +gpu 0 iter : 18 Arret : 0.00441137 s/iter 0.370745 +gpu 0 iter : 19 Arret : 0.00203274 s/iter 0.364311 +gpu 0 iter : 20 Arret : 0.00318275 s/iter 0.364538 +gpu 0 iter : 21 Arret : 0.009373 s/iter 0.355906 +gpu 0 iter : 22 Arret : 0.0125472 s/iter 0.351740 +gpu 0 iter : 23 Arret : 0.0298136 s/iter 0.350290 +gpu 0 iter : 24 Arret : 0.00227002 s/iter 0.351832 +gpu 0 iter : 25 Arret : 0.000622083 s/iter 0.342077 +gpu 0 iter : 26 Arret : 0.000137321 s/iter 0.346191 +gpu 0 iter : 27 Arret : 4.34709E-05 s/iter 0.348120 +gpu 0 iter : 28 Arret : 3.54366E-06 s/iter 0.343417 +gpu 0 iter : 29 Arret : 2.7858E-09 s/iter 0.341845 +gpu 0 iter : 30 Arret : 8.62089E-14 s/iter 0.341833 +temps : 16.8078 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.35784E-10 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540783 +i* 0.841162| 1|-7.58456E-14 +i* 3.78031E-14| +| 2| -0.992343 +i* -0.123513| 1|-2.28637E-15 +i*-5.45917E-15| +| 3| 0.0563346 +i* 0.998412| 1| 5.70377E-15 +i* 3.3501E-14| +| 4| -0.802793 +i* -0.596258| 1| 2.03657E-15 +i* 1.01915E-14| +| 5| 0.730552 +i* -0.682857| 1|-7.48429E-14 +i* 6.77011E-14| +| 6| -0.442728 +i* 0.896656| 1|-3.77198E-14 +i*-1.89779E-15| +| 7| -0.404888 +i* -0.914366| 1| 3.20195E-14 +i* 9.65894E-15| +| 8| 0.972126 +i* -0.23446| 1| 4.02421E-14 +i*-1.54755E-14| +| 9| -0.826939 +i* 0.562292| 1| -2.4928E-14 +i*-1.59889E-14| +| 10| 0.0979895 +i* -0.995187| 1| 2.90878E-14 +i*-6.75675E-15| +| 11| 0.961513 +i* 0.27476| 1|-9.39769E-14 +i*-2.63912E-13| +| 12| -0.996627 +i* 0.0820589| 1| 2.39773E-14 +i* 1.74825E-14| +| 13| 0.575447 +i* -0.817839| 1|-3.49894E-14 +i*-7.98545E-14| +| 14| 0.701466 +i* 0.712703| 1| 7.52211E-14 +i* 1.53991E-14| +| 15| 0.259346 +i* 0.965785| 1|-2.14863E-14 +i*-2.81355E-14| +| 16| -0.907773 +i* -0.419461| 1|-3.62869E-14 +i*-9.49414E-15| +| 17| 0.903623 +i* -0.428329| 1|-1.24969E-14 +i* 7.51222E-14| +| 18| -0.249979 +i* 0.968251| 1|-1.59074E-14 +i*-1.09721E-14| +| 19| -0.583341 +i* -0.812227| 1| 1.92242E-14 +i* 2.27058E-14| +| 20| 0.997383 +i* 0.072297| 1| 2.53037E-13 +i*-5.92819E-13| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 1 +zone limite de 'log-exp' 1.00237 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 0 dimgrid 586 dimblock 256 degrePoly 150000 +gpu 0 dimgrid2 293 start 0 size 75008 +gpu 1 dimgrid 586 dimblock 256 degrePoly 150000 +gpu 1 dimgrid2 293 start 75008 size 75008 +gpu 0 iter : 1 Arret : 1.60819E-05 s/iter 2.345593 +gpu 0 iter : 2 Arret : 1.52654E-05 s/iter 2.345397 +gpu 0 iter : 3 Arret : 1.58146E-05 s/iter 2.345455 +gpu 0 iter : 4 Arret : 1.54189E-05 s/iter 2.345151 +gpu 0 iter : 5 Arret : 1.57815E-05 s/iter 2.345049 +gpu 0 iter : 6 Arret : 1.6413E-05 s/iter 2.345470 +gpu 0 iter : 7 Arret : 1.77314E-05 s/iter 2.345388 +gpu 0 iter : 8 Arret : 2.1072E-05 s/iter 2.345347 +gpu 0 iter : 9 Arret : 4.09887E-05 s/iter 2.344913 +gpu 0 iter : 10 Arret : 0.00231734 s/iter 2.344920 +gpu 0 iter : 11 Arret : 0.00364869 s/iter 2.344545 +gpu 0 iter : 12 Arret : 0.00595916 s/iter 2.901608 +gpu 0 iter : 13 Arret : 0.433645 s/iter 2.901110 +gpu 0 iter : 14 Arret : 2.16599 s/iter 4.403684 +gpu 0 iter : 15 Arret : 0.0451248 s/iter 2.331735 +gpu 0 iter : 16 Arret : 0.0269953 s/iter 4.010657 +gpu 0 iter : 17 Arret : 0.0143832 s/iter 2.323230 +gpu 0 iter : 18 Arret : 0.0101457 s/iter 4.336764 +gpu 0 iter : 19 Arret : 0.00443502 s/iter 3.973966 +gpu 0 iter : 20 Arret : 0.00482918 s/iter 2.285743 +gpu 0 iter : 21 Arret : 0.00559571 s/iter 3.957234 +gpu 0 iter : 22 Arret : 0.00102978 s/iter 2.262199 +gpu 0 iter : 23 Arret : 0.000982733 s/iter 2.250995 +gpu 0 iter : 24 Arret : 0.000314964 s/iter 2.256563 +gpu 0 iter : 25 Arret : 9.62593E-05 s/iter 2.257743 +gpu 0 iter : 26 Arret : 2.22765E-05 s/iter 2.274003 +gpu 0 iter : 27 Arret : 3.08519E-05 s/iter 2.262628 +gpu 0 iter : 28 Arret : 9.19951E-06 s/iter 2.243517 +gpu 0 iter : 29 Arret : 5.62649E-07 s/iter 2.241072 +gpu 0 iter : 30 Arret : 9.17827E-11 s/iter 2.245254 +gpu 0 iter : 31 Arret : 8.04912E-16 s/iter 2.239630 +temps : 82.6744 seconde(s) +Nb iterations : 31 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.26507E-09 +Stabilite : 8.04912E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540528 +i* 0.841326| 1| 8.68923E-14 +i* 2.2979E-13| +| 2| -0.905603 +i* -0.424127| 1| 6.50001E-14 +i* -3.0061E-14| +| 3| -0.774122 +i* 0.633037| 1|-3.89619E-14 +i*-6.71876E-14| +| 4| 0.317935 +i* -0.948113| 1| 4.656E-15 +i* 1.15645E-13| +| 5| 0.23606 +i* 0.971739| 1| 2.9924E-14 +i*-1.32854E-13| +| 6| -0.717299 +i* -0.696766| 1| 5.63785E-15 +i*-6.71685E-14| +| 7| 0.992349 +i* -0.123462| 1|-4.81056E-13 +i* 9.00335E-13| +| 8| -0.938482 +i* 0.345329| 1|-6.95555E-14 +i*-3.79159E-14| +| 9| 0.610294 +i* -0.792175| 1| -5.4852E-14 +i*-3.26232E-14| +| 10| -0.0946394 +i* 0.995512| 1|-4.73788E-14 +i*-8.10827E-14| +| 11| -0.450242 +i* -0.892906| 1| 2.41855E-14 +i*-3.23699E-15| +| 12| 0.978218 +i* 0.207583| 1|-2.84429E-13 +i* 4.69725E-13| +| 13| -0.999806 +i* 0.0197069| 1|-4.72365E-14 +i*-2.55716E-14| +| 14| 0.835648 +i* -0.549265| 1|-2.95892E-13 +i* 2.34143E-13| +| 15| -0.414707 +i* 0.909955| 1| 7.26225E-14 +i*-1.70003E-15| +| 16| -0.133754 +i* -0.991015| 1|-2.88485E-14 +i* 2.14499E-14| +| 17| 0.856687 +i* 0.515837| 1| 1.49106E-13 +i* 3.95153E-14| +| 18| -0.951361 +i* -0.308079| 1| 3.78308E-14 +i* 4.65843E-14| +| 19| 0.969257 +i* -0.24605| 1| 5.51163E-13 +i*-4.79498E-13| +| 20| -0.689285 +i* 0.724491| 1| 2.40086E-15 +i*-3.61777E-14| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 1 +zone limite de 'log-exp' 1.00142 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 0 dimgrid 977 dimblock 256 degrePoly 250000 +gpu 0 dimgrid2 489 start 0 size 125056 +gpu 1 dimgrid 977 dimblock 256 degrePoly 250000 +gpu 1 dimgrid2 489 start 125056 size 125056 +gpu 0 iter : 1 Arret : 1.04122E-05 s/iter 6.895757 +gpu 0 iter : 2 Arret : 9.66998E-06 s/iter 6.877326 +gpu 0 iter : 3 Arret : 9.65609E-06 s/iter 6.885434 +gpu 0 iter : 4 Arret : 1.03183E-05 s/iter 6.886343 +gpu 0 iter : 5 Arret : 9.75367E-06 s/iter 6.875198 +gpu 0 iter : 6 Arret : 9.56197E-06 s/iter 6.877253 +gpu 0 iter : 7 Arret : 9.85222E-06 s/iter 6.888180 +gpu 0 iter : 8 Arret : 1.00444E-05 s/iter 6.876080 +gpu 0 iter : 9 Arret : 1.14954E-05 s/iter 6.871764 +gpu 0 iter : 10 Arret : 0.00617074 s/iter 6.872061 +gpu 0 iter : 11 Arret : 0.00502727 s/iter 9.108306 +gpu 0 iter : 12 Arret : 0.00709612 s/iter 6.884838 +gpu 0 iter : 13 Arret : 0.00636365 s/iter 9.133645 +gpu 0 iter : 14 Arret : 0.000962158 s/iter 6.881477 +gpu 0 iter : 15 Arret : 0.00515317 s/iter 6.879637 +gpu 0 iter : 16 Arret : 0.00489618 s/iter 7.799484 +gpu 0 iter : 17 Arret : 0.0126101 s/iter 6.409073 +gpu 0 iter : 18 Arret : 0.306794 s/iter 4.221095 +gpu 0 iter : 19 Arret : 0.00788796 s/iter 5.229623 +gpu 0 iter : 20 Arret : 0.000261124 s/iter 4.114536 +gpu 0 iter : 21 Arret : 0.000181317 s/iter 3.590034 +gpu 0 iter : 22 Arret : 0.000215766 s/iter 3.589880 +gpu 0 iter : 23 Arret : 0.000292282 s/iter 3.567063 +gpu 0 iter : 24 Arret : 7.59488E-05 s/iter 3.557992 +gpu 0 iter : 25 Arret : 8.78575E-06 s/iter 3.569234 +gpu 0 iter : 26 Arret : 1.71E-07 s/iter 3.545083 +gpu 0 iter : 27 Arret : 3.25965E-13 s/iter 3.556937 +temps : 161.369 seconde(s) +Nb iterations : 27 +Nb de depassements de capacite exponentielle : 0 +Precision : 6.32861E-09 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540427 +i* 0.841391| 1| 9.7148E-14 +i*-1.98189E-13| +| 2| -0.997949 +i* 0.0640067| 1| 1.02696E-14 +i* 2.88415E-14| +| 3| 0.450991 +i* -0.892528| 1| 2.39739E-15 +i* 7.66835E-14| +| 4| 0.42851 +i* -0.903537| 1| 1.03733E-13 +i* 1.27433E-14| +| 5| -0.996035 +i* 0.0889649| 1| 5.1386E-14 +i* 4.21729E-14| +| 6| 0.581876 +i* 0.813277| 1| 3.29906E-13 +i* -3.5718E-15| +| 7| 0.405761 +i* -0.913979| 1| 1.69923E-13 +i*-8.86062E-14| +| 8| -0.993496 +i* 0.113867| 1| 6.34562E-14 +i* 6.04291E-14| +| 9| 0.60205 +i* 0.798458| 1| 2.39371E-13 +i* -2.2848E-13| +| 10| 0.382757 +i* -0.923849| 1| 6.36852E-14 +i* 1.1601E-13| +| 11| -0.990335 +i* 0.138698| 1| 8.32286E-14 +i* 4.57395E-14| +| 12| 0.621846 +i* 0.783139| 1| 3.5482E-14 +i*-1.57841E-13| +| 13| 0.359514 +i* -0.93314| 1| 1.00985E-13 +i*-2.52237E-13| +| 14| -0.986553 +i* 0.163442| 1| 3.24636E-14 +i* 4.58574E-14| +| 15| 0.641253 +i* 0.767329| 1| 1.79533E-13 +i* 3.03096E-13| +| 16| 0.336045 +i* -0.941846| 1| 1.38948E-13 +i*-8.14071E-14| +| 17| -0.982153 +i* 0.188084| 1| 6.94549E-14 +i* 3.09405E-14| +| 18| 0.660258 +i* 0.751039| 1| 4.21871E-13 +i* 5.02185E-14| +| 19| 0.312366 +i* -0.949962| 1|-6.37199E-14 +i*-7.39669E-14| +| 20| -0.977138 +i* 0.212608| 1|-3.80633E-14 +i* -8.4285E-14| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 1 +zone limite de 'log-exp' 1.00101 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 1 dimgrid 1368 dimblock 256 degrePoly 350000 +gpu 1 dimgrid2 684 start 175104 size 175104 +gpu 0 dimgrid 1368 dimblock 256 degrePoly 350000 +gpu 0 dimgrid2 684 start 0 size 175104 +gpu 0 iter : 1 Arret : 7.32344E-06 s/iter 12.954303 +gpu 0 iter : 2 Arret : 7.07863E-06 s/iter 12.981308 +gpu 0 iter : 3 Arret : 6.90431E-06 s/iter 12.986614 +gpu 0 iter : 4 Arret : 7.26859E-06 s/iter 12.992632 +gpu 0 iter : 5 Arret : 6.9268E-06 s/iter 13.005304 +gpu 0 iter : 6 Arret : 6.766E-06 s/iter 12.980752 +gpu 0 iter : 7 Arret : 7.08928E-06 s/iter 12.936596 +gpu 0 iter : 8 Arret : 7.80045E-06 s/iter 12.948599 +gpu 0 iter : 9 Arret : 9.75059E-06 s/iter 12.933171 +gpu 0 iter : 10 Arret : 0.000389813 s/iter 12.982388 +gpu 0 iter : 11 Arret : 0.00168924 s/iter 12.933771 +gpu 0 iter : 12 Arret : 0.00163024 s/iter 16.015025 +gpu 0 iter : 13 Arret : 0.831287 s/iter 12.991337 +gpu 0 iter : 14 Arret : 3.41318 s/iter 13.007981 +gpu 0 iter : 15 Arret : 0.111579 s/iter 13.648097 +gpu 0 iter : 16 Arret : 0.0536558 s/iter 13.532104 +gpu 0 iter : 17 Arret : 0.0316379 s/iter 12.902939 +gpu 0 iter : 18 Arret : 0.0221392 s/iter 15.777843 +gpu 0 iter : 19 Arret : 0.023782 s/iter 13.053666 +gpu 0 iter : 20 Arret : 0.0188987 s/iter 16.564822 +gpu 0 iter : 21 Arret : 0.0391672 s/iter 17.699510 +gpu 0 iter : 22 Arret : 0.0433525 s/iter 14.316996 +gpu 0 iter : 23 Arret : 0.0310573 s/iter 12.886593 +gpu 0 iter : 24 Arret : 0.0130632 s/iter 14.221913 +gpu 0 iter : 25 Arret : 0.00228986 s/iter 12.848043 +gpu 0 iter : 26 Arret : 0.00142186 s/iter 12.844861 +gpu 0 iter : 27 Arret : 0.000342562 s/iter 12.846961 +gpu 0 iter : 28 Arret : 7.29744E-05 s/iter 12.848477 +gpu 0 iter : 29 Arret : 6.11624E-06 s/iter 12.846333 +gpu 0 iter : 30 Arret : 1.04055E-05 s/iter 12.845798 +gpu 0 iter : 31 Arret : 8.14262E-06 s/iter 12.846716 +gpu 0 iter : 32 Arret : 2.39311E-06 s/iter 12.848384 +gpu 0 iter : 33 Arret : 1.15675E-08 s/iter 12.847822 +gpu 0 iter : 34 Arret : 4.74404E-14 s/iter 12.843750 +temps : 458.792 seconde(s) +Nb iterations : 34 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.46096E-08 +Stabilite : 1.14439E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540399 +i* 0.841409| 1| 5.12961E-13 +i*-3.37404E-15| +| 2| -0.385479 +i* 0.922716| 1| -1.616E-13 +i*-2.73566E-14| +| 3| -0.770131 +i* 0.637886| 1|-1.38431E-15 +i* 1.70921E-13| +| 4| -0.978357 +i* 0.206925| 1|-3.07393E-15 +i* 4.96131E-15| +| 5| -0.962455 +i* -0.27144| 1|-5.85088E-14 +i* 7.9714E-14| +| 6| -0.72607 +i* -0.687621| 1| -2.0612E-14 +i* 2.87948E-13| +| 7| -0.323352 +i* -0.946279| 1| 2.27159E-13 +i* 7.30891E-14| +| 8| 0.153459 +i* -0.988155| 1| 4.60049E-15 +i*-2.43555E-14| +| 9| 0.595097 +i* -0.803654| 1|-3.46265E-13 +i* 1.60098E-14| +| 10| 0.900408 +i* -0.435047| 1| 3.20081E-13 +i*-1.77827E-14| +| 11| 0.999448 +i* 0.0332229| 1|-5.70342E-13 +i* 1.21308E-12| +| 12| 0.869529 +i* 0.493882| 1| 3.01252E-14 +i* 6.11216E-13| +| 13| 0.211292 +i* 0.977423| 1|-6.97532E-14 +i* 1.23212E-13| +| 14| -0.267139 +i* 0.963658| 1|-9.26238E-14 +i*-7.20968E-14| +| 15| -0.684372 +i* 0.729133| 1| 1.64042E-13 +i*-1.89831E-14| +| 16| -0.944825 +i* 0.327574| 1| 3.70572E-14 +i*-6.84904E-14| +| 17| -0.988833 +i* -0.149027| 1|-1.41002E-13 +i* 2.02581E-14| +| 18| -0.806314 +i* -0.591488| 1| 1.24668E-13 +i*-2.62805E-13| +| 19| -0.439079 +i* -0.898448| 1|-1.76949E-13 +i*-1.05707E-13| +| 20| 0.0287595 +i* -0.999586| 1| 4.76598E-14 +i*-1.43895E-14| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 1 +zone limite de 'log-exp' 1.00071 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 1 dimgrid 1954 dimblock 256 degrePoly 500000 +gpu 1 dimgrid2 977 start 250112 size 250112 +gpu 0 dimgrid 1954 dimblock 256 degrePoly 500000 +gpu 0 dimgrid2 977 start 0 size 250112 +gpu 0 iter : 1 Arret : 5.66981E-06 s/iter 26.243500 +gpu 0 iter : 2 Arret : 4.82614E-06 s/iter 26.155609 +gpu 0 iter : 3 Arret : 5.08487E-06 s/iter 26.220032 +gpu 0 iter : 4 Arret : 4.81813E-06 s/iter 26.206135 +gpu 0 iter : 5 Arret : 5.52439E-06 s/iter 26.225948 +gpu 0 iter : 6 Arret : 4.73134E-06 s/iter 26.199860 +gpu 0 iter : 7 Arret : 4.95057E-06 s/iter 26.197320 +gpu 0 iter : 8 Arret : 5.2867E-06 s/iter 26.218407 +gpu 0 iter : 9 Arret : 6.39202E-06 s/iter 26.195373 +gpu 0 iter : 10 Arret : 5.44877E-05 s/iter 26.194619 +gpu 0 iter : 11 Arret : 0.00113955 s/iter 26.198648 +gpu 0 iter : 12 Arret : 0.00233295 s/iter 26.205898 +gpu 0 iter : 13 Arret : 0.00269137 s/iter 26.219943 +gpu 0 iter : 14 Arret : 0.00436419 s/iter 26.210349 +gpu 0 iter : 15 Arret : 0.0325608 s/iter 26.028106 +gpu 0 iter : 16 Arret : 0.0458093 s/iter 20.473858 +gpu 0 iter : 17 Arret : 1.39035 s/iter 21.967251 +gpu 0 iter : 18 Arret : 0.0686378 s/iter 22.648105 +gpu 0 iter : 19 Arret : 0.0167258 s/iter 19.073745 +gpu 0 iter : 20 Arret : 0.0073255 s/iter 18.809805 +gpu 0 iter : 21 Arret : 0.00825181 s/iter 16.400626 +gpu 0 iter : 22 Arret : 0.00369807 s/iter 17.676396 +gpu 0 iter : 23 Arret : 0.00143206 s/iter 14.057186 +gpu 0 iter : 24 Arret : 0.000362864 s/iter 12.988505 +gpu 0 iter : 25 Arret : 5.99505E-05 s/iter 12.740882 +gpu 0 iter : 26 Arret : 1.38177E-05 s/iter 11.720352 +gpu 0 iter : 27 Arret : 7.95915E-06 s/iter 11.636867 +gpu 0 iter : 28 Arret : 2.45128E-06 s/iter 11.537776 +gpu 0 iter : 29 Arret : 4.00503E-08 s/iter 11.539953 +gpu 0 iter : 30 Arret : 2.18749E-13 s/iter 11.544507 +temps : 628.842 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.48768E-08 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540372 +i* 0.841426| 1|-3.05235E-13 +i* 1.38721E-13| +| 2| 0.561316 +i* 0.827602| 1|-2.60021E-13 +i* 1.9206E-13| +| 3| 0.57165 +i* 0.820497| 1|-1.83308E-13 +i* 6.15844E-14| +| 4| 0.581895 +i* 0.813264| 1| 3.05839E-13 +i* 6.52482E-14| +| 5| 0.592048 +i* 0.805902| 1|-7.14016E-13 +i*-3.98882E-14| +| 6| 0.602109 +i* 0.798414| 1| 2.66658E-13 +i*-4.75979E-13| +| 7| 0.612074 +i* 0.7908| 1| 3.16743E-13 +i*-3.40844E-13| +| 8| 0.621943 +i* 0.783062| 1| 5.64146E-13 +i*-3.14632E-13| +| 9| 0.631715 +i* 0.775201| 1|-3.83756E-14 +i* 5.41086E-13| +| 10| 0.641387 +i* 0.767218| 1| 4.00499E-13 +i*-3.71465E-13| +| 11| 0.650958 +i* 0.759114| 1| 7.58768E-15 +i*-5.54055E-13| +| 12| 0.660427 +i* 0.750891| 1| 7.47999E-13 +i* 2.73089E-13| +| 13| 0.669792 +i* 0.742549| 1| 9.40577E-13 +i* 3.39433E-14| +| 14| 0.679051 +i* 0.734091| 1| 4.34264E-13 +i*-1.04887E-13| +| 15| 0.688204 +i* 0.725517| 1|-6.26926E-13 +i*-1.86798E-13| +| 16| 0.697248 +i* 0.71683| 1| 2.2389E-13 +i*-9.46795E-14| +| 17| 0.706183 +i* 0.708029| 1| 4.79186E-13 +i* 4.75144E-13| +| 18| 0.715007 +i* 0.699117| 1| 6.39138E-13 +i* 4.95824E-13| +| 19| 0.723718 +i* 0.690096| 1| -1.2694E-13 +i* 4.44528E-13| +| 20| 0.732316 +i* 0.680965| 1|-2.76158E-13 +i* 1.17734E-13| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +zone limite de 'log-exp' 1.00059 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 0 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 0 dimgrid2 1172 start 0 size 300032 +gpu 1 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 1 dimgrid2 1172 start 300032 size 300032 +gpu 0 iter : 1 Arret : 4.27998E-06 s/iter 37.322864 +gpu 0 iter : 2 Arret : 4.10617E-06 s/iter 37.241818 +gpu 0 iter : 3 Arret : 4.53518E-06 s/iter 37.266422 +gpu 0 iter : 4 Arret : 4.06183E-06 s/iter 37.257521 +gpu 0 iter : 5 Arret : 4.08957E-06 s/iter 37.242975 +gpu 0 iter : 6 Arret : 4.1063E-06 s/iter 37.243477 +gpu 0 iter : 7 Arret : 4.11679E-06 s/iter 37.260449 +gpu 0 iter : 8 Arret : 4.55908E-06 s/iter 37.268788 +gpu 0 iter : 9 Arret : 5.63978E-06 s/iter 37.274568 +gpu 0 iter : 10 Arret : 3.12352E-05 s/iter 37.263840 +gpu 0 iter : 11 Arret : 0.000760143 s/iter 37.275869 +gpu 0 iter : 12 Arret : 0.00101593 s/iter 37.272537 +gpu 0 iter : 13 Arret : 2.01147 s/iter 45.273128 +gpu 0 iter : 14 Arret : 0.399191 s/iter 37.620123 +gpu 0 iter : 15 Arret : 0.349288 s/iter 37.631719 +gpu 0 iter : 16 Arret : 0.208253 s/iter 39.378074 +gpu 0 iter : 17 Arret : 0.0357115 s/iter 36.777203 +gpu 0 iter : 18 Arret : 0.00764262 s/iter 36.020848 +gpu 0 iter : 19 Arret : 0.00870865 s/iter 35.507205 +gpu 0 iter : 20 Arret : 0.00636133 s/iter 36.016380 +gpu 0 iter : 21 Arret : 0.00247744 s/iter 34.115098 +gpu 0 iter : 22 Arret : 0.00232921 s/iter 33.193981 +gpu 0 iter : 23 Arret : 0.000237628 s/iter 33.032645 +gpu 0 iter : 24 Arret : 2.29813E-05 s/iter 32.946598 +gpu 0 iter : 25 Arret : 2.02338E-05 s/iter 32.928243 +gpu 0 iter : 26 Arret : 2.55188E-05 s/iter 32.809567 +gpu 0 iter : 27 Arret : 5.88928E-06 s/iter 32.589015 +gpu 0 iter : 28 Arret : 5.50518E-09 s/iter 32.619895 +gpu 0 iter : 29 Arret : 1.64317E-14 s/iter 32.704855 +temps : 1049.55 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 5.38109E-08 +Stabilite : 1.57009E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540365 +i* 0.841431| 1| 4.39062E-13 +i* 5.83011E-13| +| 2| -0.553493 +i* -0.832854| 1|-5.02858E-13 +i* 3.83374E-15| +| 3| -0.579338 +i* -0.815087| 1| 4.42365E-13 +i* 2.65846E-14| +| 4| 0.592057 +i* 0.805896| 1| 2.06783E-13 +i* 1.94549E-13| +| 5| -0.604613 +i* -0.796519| 1| 2.39135E-13 +i* 2.96967E-13| +| 6| 0.617037 +i* 0.786934| 1|-3.70964E-13 +i* 2.85104E-13| +| 7| -0.629293 +i* -0.777168| 1| 3.4002E-13 +i* 1.14925E-14| +| 8| 0.641411 +i* 0.767198| 1|-6.01835E-13 +i* 5.70316E-13| +| 9| -0.653354 +i* -0.757052| 1| 3.00003E-14 +i* 4.1084E-13| +| 10| 0.665153 +i* 0.746707| 1|-9.55243E-14 +i* 7.739E-13| +| 11| -0.676773 +i* -0.736192| 1|-3.70891E-13 +i* 4.31963E-14| +| 12| 0.688242 +i* 0.725482| 1| 4.17319E-13 +i*-2.25125E-13| +| 13| -0.699526 +i* -0.714607| 1|-1.55074E-13 +i* 3.9467E-13| +| 14| 0.710653 +i* 0.703543| 1|-7.94843E-13 +i* 5.61671E-13| +| 15| -0.721591 +i* -0.69232| 1|-8.20351E-14 +i* 3.39909E-13| +| 16| 0.732366 +i* 0.680912| 1| 5.01595E-13 +i* 2.59279E-13| +| 17| -0.742946 +i* -0.669351| 1|-1.90181E-13 +i* 1.23972E-13| +| 18| 0.753358 +i* 0.657611| 1|-7.14661E-13 +i*-3.96187E-13| +| 19| -0.76357 +i* -0.645725| 1|-3.31242E-13 +i*-8.50865E-14| +| 20| 0.773609 +i* 0.633664| 1|-7.93813E-13 +i* 2.09313E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 1 +zone limite de 'log-exp' 1.00051 +CPU thread 1 (of 2) uses CUDA device 1 +CPU thread 0 (of 2) uses CUDA device 0 +gpu 1 dimgrid 2735 dimblock 256 degrePoly 700000 +gpu 1 dimgrid2 1368 start 350080 size 350080 +gpu 0 dimgrid 2735 dimblock 256 degrePoly 700000 +gpu 0 dimgrid2 1368 start 0 size 350080 +gpu 0 iter : 1 Arret : 3.85506E-06 s/iter 50.537882 +gpu 0 iter : 2 Arret : 3.66998E-06 s/iter 50.446787 +gpu 0 iter : 3 Arret : 3.5726E-06 s/iter 50.500062 +gpu 0 iter : 4 Arret : 3.62569E-06 s/iter 50.536621 +gpu 0 iter : 5 Arret : 3.53038E-06 s/iter 50.517457 +gpu 0 iter : 6 Arret : 3.56934E-06 s/iter 50.509400 +gpu 0 iter : 7 Arret : 3.64216E-06 s/iter 50.424296 +gpu 0 iter : 8 Arret : 3.67185E-06 s/iter 50.440541 +gpu 0 iter : 9 Arret : 3.63502E-06 s/iter 50.438151 +gpu 0 iter : 10 Arret : 9.16823E-06 s/iter 50.456984 +gpu 0 iter : 11 Arret : 0.000775983 s/iter 50.442631 +gpu 0 iter : 12 Arret : 0.00172532 s/iter 50.492134 +gpu 0 iter : 13 Arret : 0.00299803 s/iter 51.124560 +gpu 0 iter : 14 Arret : 0.00358296 s/iter 56.913865 +gpu 0 iter : 15 Arret : 0.00444746 s/iter 51.832479 +gpu 0 iter : 16 Arret : 0.0771326 s/iter 55.051554 +gpu 0 iter : 17 Arret : 0.187135 s/iter 50.619418 +gpu 0 iter : 18 Arret : 0.0318843 s/iter 52.931554 +gpu 0 iter : 19 Arret : 0.0152072 s/iter 50.308926 +gpu 0 iter : 20 Arret : 0.0163219 s/iter 56.692462 +gpu 0 iter : 21 Arret : 0.00872806 s/iter 57.177894 +gpu 0 iter : 22 Arret : 0.0115686 s/iter 50.015870 +gpu 0 iter : 23 Arret : 0.0199021 s/iter 50.011047 +gpu 0 iter : 24 Arret : 0.00353983 s/iter 50.010630 +gpu 0 iter : 25 Arret : 0.000449015 s/iter 50.024349 +gpu 0 iter : 26 Arret : 0.000359858 s/iter 50.022460 +gpu 0 iter : 27 Arret : 0.000264692 s/iter 50.007880 +gpu 0 iter : 28 Arret : 9.80473E-05 s/iter 50.011312 +gpu 0 iter : 29 Arret : 1.12945E-05 s/iter 50.013302 +gpu 0 iter : 30 Arret : 1.06056E-08 s/iter 49.925806 +gpu 0 iter : 31 Arret : 5.50569E-15 s/iter 49.926960 +temps : 1589.66 seconde(s) +Nb iterations : 31 +Nb de depassements de capacite exponentielle : 0 +Precision : 7.46262E-08 +Stabilite : 5.50569E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540352 +i* 0.841439| 1| 4.39978E-13 +i* 6.25043E-13| +| 2| -0.996034 +i* 0.0889731| 1| 2.2073E-13 +i* 1.55296E-13| +| 3| 0.439836 +i* -0.898078| 1|-3.55927E-13 +i*-1.21738E-13| +| 4| 0.38266 +i* -0.923889| 1|-2.56142E-13 +i*-7.02285E-14| +| 5| -0.988496 +i* 0.15125| 1|-1.52652E-13 +i*-1.11329E-13| +| 6| 0.641421 +i* 0.767189| 1|-1.31044E-13 +i* 5.61736E-13| +| 7| 0.323979 +i* -0.946064| 1|-4.52336E-13 +i* 8.74596E-14| +| 8| -0.977067 +i* 0.212932| 1| 8.58341E-14 +i* 1.73412E-13| +| 9| 0.688262 +i* 0.725462| 1| 4.28754E-14 +i* 1.08849E-12| +| 10| 0.264022 +i* -0.964517| 1|-3.63883E-13 +i*-8.14886E-14| +| 11| -0.961793 +i* 0.273776| 1| -3.0213E-13 +i*-2.13897E-13| +| 12| 0.732395 +i* 0.68088| 1|-3.65194E-14 +i* 7.95483E-13| +| 13| 0.203027 +i* -0.979173| 1|-3.14502E-13 +i* 2.96924E-13| +| 14| -0.942735 +i* 0.333543| 1| 1.82947E-13 +i*-4.73458E-14| +| 15| 0.773646 +i* 0.633619| 1| 2.24352E-13 +i* 2.79674E-13| +| 16| 0.141232 +i* -0.989977| 1| -1.0035E-13 +i* 1.5693E-13| +| 17| -0.919967 +i* 0.391997| 1| 2.89213E-14 +i*-1.86252E-13| +| 18| 0.811852 +i* 0.583864| 1|-1.59939E-12 +i*-4.13669E-13| +| 19| 0.0788818 +i* -0.996884| 1|-2.83003E-13 +i* 1.04711E-13| +| 20| -0.893578 +i* 0.448908| 1| 4.59736E-14 +i* 1.31414E-13| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 1 +zone limite de 'log-exp' 1.00044 +CPU thread 1 (of 2) uses CUDA device 1 +CPU thread 0 (of 2) uses CUDA device 0 +gpu 0 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 0 dimgrid2 1563 start 0 size 400000 +gpu 1 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 1 dimgrid2 1563 start 400000 size 400000 +gpu 0 iter : 1 Arret : 3.10089E-06 s/iter 66.233735 +gpu 0 iter : 2 Arret : 3.0838E-06 s/iter 65.987108 +gpu 0 iter : 3 Arret : 3.06149E-06 s/iter 66.189454 +gpu 0 iter : 4 Arret : 3.0062E-06 s/iter 65.996849 +gpu 0 iter : 5 Arret : 3.0175E-06 s/iter 65.939646 +gpu 0 iter : 6 Arret : 3.04713E-06 s/iter 65.973994 +gpu 0 iter : 7 Arret : 3.05645E-06 s/iter 66.066266 +gpu 0 iter : 8 Arret : 3.30702E-06 s/iter 65.988454 +gpu 0 iter : 9 Arret : 4.07591E-06 s/iter 65.937363 +gpu 0 iter : 10 Arret : 8.87751E-06 s/iter 65.957225 +gpu 0 iter : 11 Arret : 0.00223658 s/iter 66.065550 +gpu 0 iter : 12 Arret : 0.00280193 s/iter 66.350461 +gpu 0 iter : 13 Arret : 2.16738 s/iter 71.352901 +gpu 0 iter : 14 Arret : 0.942103 s/iter 66.359607 +gpu 0 iter : 15 Arret : 4.73642 s/iter 71.197413 +gpu 0 iter : 16 Arret : 0.106528 s/iter 66.581428 +gpu 0 iter : 17 Arret : 0.126902 s/iter 68.405076 +gpu 0 iter : 18 Arret : 0.0671442 s/iter 65.117577 +gpu 0 iter : 19 Arret : 0.0842362 s/iter 64.328947 +gpu 0 iter : 20 Arret : 0.06511 s/iter 58.256373 +gpu 0 iter : 21 Arret : 0.0412827 s/iter 62.163236 +gpu 0 iter : 22 Arret : 0.0193263 s/iter 56.316208 +gpu 0 iter : 23 Arret : 0.0142222 s/iter 56.754546 +gpu 0 iter : 24 Arret : 0.00245535 s/iter 47.889436 +gpu 0 iter : 25 Arret : 0.000939196 s/iter 46.695509 +gpu 0 iter : 26 Arret : 2.31722E-05 s/iter 46.175563 +gpu 0 iter : 27 Arret : 1.05871E-06 s/iter 45.766439 +gpu 0 iter : 28 Arret : 1.17662E-11 s/iter 45.536542 +gpu 0 iter : 29 Arret : 1.57009E-16 s/iter 45.801905 +temps : 1778.69 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 6.26383E-08 +Stabilite : 1.57009E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540349 +i* 0.841441| 1|-1.16344E-13 +i* 9.55619E-13| +| 2| 0.592061 +i* 0.805893| 1|-1.57249E-13 +i*-4.43364E-13| +| 3| 0.617051 +i* 0.786923| 1|-6.42805E-13 +i*-3.49094E-13| +| 4| 0.641434 +i* 0.767178| 1| 1.00022E-12 +i*-5.90578E-13| +| 5| 0.665186 +i* 0.746678| 1|-2.53998E-14 +i*-1.14684E-12| +| 6| 0.688283 +i* 0.725442| 1|-8.68732E-13 +i* 8.52696E-13| +| 7| 0.710703 +i* 0.703493| 1| 2.02581E-13 +i* 4.54699E-13| +| 8| 0.732422 +i* 0.680851| 1|-5.22353E-13 +i*-3.99873E-13| +| 9| 0.753421 +i* 0.657538| 1| 1.23356E-13 +i*-1.05986E-12| +| 10| 0.773678 +i* 0.633579| 1|-6.75196E-13 +i* 3.60108E-13| +| 11| 0.793174 +i* 0.608995| 1| 4.43853E-13 +i*-1.42398E-12| +| 12| 0.811888 +i* 0.583813| 1|-4.10491E-13 +i*-4.46651E-13| +| 13| 0.829804 +i* 0.558055| 1| 1.30045E-12 +i* 1.12788E-13| +| 14| 0.846902 +i* 0.531748| 1|-8.09419E-13 +i* 4.98091E-13| +| 15| 0.863167 +i* 0.504918| 1| 2.98522E-13 +i* 3.81547E-13| +| 16| 0.878582 +i* 0.477591| 1|-3.06581E-13 +i*-6.95869E-13| +| 17| 0.893133 +i* 0.449793| 1| 1.24355E-13 +i* -1.3239E-12| +| 18| 0.906804 +i* 0.421553| 1|-1.23117E-12 +i*-5.57117E-13| +| 19| 0.919582 +i* 0.392898| 1|-1.03648E-12 +i* 2.90445E-14| +| 20| 0.931455 +i* 0.363856| 1|-6.42708E-13 +i*-1.50318E-12| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 1 diff --git a/Simulations/full_openmp/full_openmp_2GPU.sge b/Simulations/full_openmp/full_openmp_2GPU.sge new file mode 100644 index 0000000..82276b2 --- /dev/null +++ b/Simulations/full_openmp/full_openmp_2GPU.sge @@ -0,0 +1,27 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=2 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -pe openmp 2 +#$ -V +#$ -cwd +#$ -N full_openmp_2GPU + +module load gcc/4.9.0 +module load cuda/7.0 +export OMP_NUM_THREADS=2 + +./template -r -i 60000 40000 +./template -r -i 150000 50000 +./template -r -i 250000 150000 +./template -r -i 350000 250000 +./template -r -i 500000 300000 +./template -r -i 600000 400000 +./template -r -i 700000 500000 +./template -r -i 800000 600000 +#./template -r -i 900000 700000 +#./template -r -i 1000000 800000 +#./template -r -i 1500000 500000 + + diff --git a/Simulations/full_openmp/full_openmp_3GPU.o140163 b/Simulations/full_openmp/full_openmp_3GPU.o140163 new file mode 100644 index 0000000..693fb02 --- /dev/null +++ b/Simulations/full_openmp/full_openmp_3GPU.o140163 @@ -0,0 +1,565 @@ +REMAINING: 3 +Taking GPU #0 +Taking GPU #1 +Taking GPU #2 +zone limite de 'log-exp' 1.00593 +CPU thread 1 (of 3) uses CUDA device 1 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 0 (of 3) uses CUDA device 0 +gpu 1 dimgrid 235 dimblock 256 degrePoly 60000 +gpu 1 dimgrid2 79 start 20053 size 20053 +gpu 2 dimgrid 235 dimblock 256 degrePoly 60000 +gpu 0 dimgrid 235 dimblock 256 degrePoly 60000 +gpu 0 dimgrid2 79 start 0 size 20053 +gpu 2 dimgrid2 79 start 40106 size 20053 +gpu 0 iter : 1 Arret : 4.45023E-05 s/iter 0.365910 +gpu 0 iter : 2 Arret : 3.97664E-05 s/iter 0.365783 +gpu 0 iter : 3 Arret : 3.83563E-05 s/iter 0.365808 +gpu 0 iter : 4 Arret : 4.09098E-05 s/iter 0.365792 +gpu 0 iter : 5 Arret : 4.06402E-05 s/iter 0.365790 +gpu 0 iter : 6 Arret : 4.41483E-05 s/iter 0.365795 +gpu 0 iter : 7 Arret : 5.50719E-05 s/iter 0.365797 +gpu 0 iter : 8 Arret : 0.000118506 s/iter 0.365824 +gpu 0 iter : 9 Arret : 0.00173508 s/iter 0.365741 +gpu 0 iter : 10 Arret : 0.0219619 s/iter 0.365806 +gpu 0 iter : 11 Arret : 2.12669 s/iter 1.163297 +gpu 0 iter : 12 Arret : 0.293659 s/iter 0.365830 +gpu 0 iter : 13 Arret : 0.150913 s/iter 1.192984 +gpu 0 iter : 14 Arret : 0.0525383 s/iter 1.193344 +gpu 0 iter : 15 Arret : 0.017941 s/iter 1.188756 +gpu 0 iter : 16 Arret : 0.00949223 s/iter 1.183377 +gpu 0 iter : 17 Arret : 0.00618922 s/iter 1.174720 +gpu 0 iter : 18 Arret : 0.00478541 s/iter 1.021119 +gpu 0 iter : 19 Arret : 0.0209781 s/iter 0.355703 +gpu 0 iter : 20 Arret : 0.00277186 s/iter 0.354432 +gpu 0 iter : 21 Arret : 0.00126164 s/iter 0.350947 +gpu 0 iter : 22 Arret : 0.0813 s/iter 0.342869 +gpu 0 iter : 23 Arret : 0.0695633 s/iter 0.341054 +gpu 0 iter : 24 Arret : 0.0249049 s/iter 0.344095 +gpu 0 iter : 25 Arret : 0.0236872 s/iter 0.333915 +gpu 0 iter : 26 Arret : 0.000649816 s/iter 0.333141 +gpu 0 iter : 27 Arret : 0.000117833 s/iter 0.336843 +gpu 0 iter : 28 Arret : 3.89955E-05 s/iter 0.333571 +gpu 0 iter : 29 Arret : 2.68794E-06 s/iter 0.331813 +gpu 0 iter : 30 Arret : 1.05565E-09 s/iter 0.327860 +gpu 0 iter : 31 Arret : 3.2677E-14 s/iter 0.331070 +temps : 17.7034 seconde(s) +Nb iterations : 31 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.35784E-10 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540783 +i* 0.841162| 1|-7.58456E-14 +i* 3.78031E-14| +| 2| -0.992343 +i* -0.123513| 1|-4.36456E-15 +i* 3.59435E-15| +| 3| 0.0563346 +i* 0.998412| 1| 5.70377E-15 +i* 3.3501E-14| +| 4| -0.802793 +i* -0.596258| 1| 2.03657E-15 +i* 1.01915E-14| +| 5| 0.730552 +i* -0.682857| 1|-7.48429E-14 +i* 6.77011E-14| +| 6| -0.442728 +i* 0.896656| 1|-3.77198E-14 +i*-1.89779E-15| +| 7| -0.404888 +i* -0.914366| 1| 3.20195E-14 +i* 9.65894E-15| +| 8| 0.972126 +i* -0.23446| 1| 4.02421E-14 +i*-1.54755E-14| +| 9| -0.826939 +i* 0.562292| 1| -2.4928E-14 +i*-1.59889E-14| +| 10| 0.0979895 +i* -0.995187| 1| 2.90878E-14 +i*-6.75675E-15| +| 11| 0.961513 +i* 0.27476| 1|-9.39769E-14 +i*-2.63912E-13| +| 12| -0.996627 +i* 0.0820589| 1| 2.39773E-14 +i* 1.74825E-14| +| 13| 0.575447 +i* -0.817839| 1|-3.49894E-14 +i*-7.98545E-14| +| 14| 0.701466 +i* 0.712703| 1| 7.52211E-14 +i* 1.53991E-14| +| 15| 0.259346 +i* 0.965785| 1|-2.14863E-14 +i*-2.81355E-14| +| 16| -0.907773 +i* -0.419461| 1|-3.62869E-14 +i*-9.49414E-15| +| 17| 0.903623 +i* -0.428329| 1|-1.24969E-14 +i* 7.51222E-14| +| 18| -0.249979 +i* 0.968251| 1|-1.59074E-14 +i*-1.09721E-14| +| 19| -0.583426 +i* -0.812166| 1| 4.94882E-14 +i*-9.16107E-15| +| 20| 0.997383 +i* 0.072297| 1| 2.53037E-13 +i*-5.92819E-13| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 1 +zone limite de 'log-exp' 1.00237 +CPU thread 0 (of 3) uses CUDA device 0 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 1 (of 3) uses CUDA device 1 +gpu 0 dimgrid 586 dimblock 256 degrePoly 150000 +gpu 0 dimgrid2 196 start 0 size 50005 +gpu 1 dimgrid 586 dimblock 256 degrePoly 150000 +gpu 1 dimgrid2 196 start 50005 size 50005 +gpu 2 dimgrid 586 dimblock 256 degrePoly 150000 +gpu 2 dimgrid2 196 start 100010 size 50005 +gpu 0 iter : 1 Arret : 1.83196E-05 s/iter 1.828662 +gpu 0 iter : 2 Arret : 1.8175E-05 s/iter 1.828375 +gpu 0 iter : 3 Arret : 1.80869E-05 s/iter 1.828381 +gpu 0 iter : 4 Arret : 1.75155E-05 s/iter 1.828566 +gpu 0 iter : 5 Arret : 1.69231E-05 s/iter 1.828230 +gpu 0 iter : 6 Arret : 1.76582E-05 s/iter 1.828408 +gpu 0 iter : 7 Arret : 1.98465E-05 s/iter 1.828242 +gpu 0 iter : 8 Arret : 2.53794E-05 s/iter 1.828046 +gpu 0 iter : 9 Arret : 0.00032835 s/iter 1.833783 +gpu 0 iter : 10 Arret : 0.00175922 s/iter 1.828220 +gpu 0 iter : 11 Arret : 0.0175731 s/iter 1.828275 +gpu 0 iter : 12 Arret : 0.00953654 s/iter 1.828216 +gpu 0 iter : 13 Arret : 1.39903 s/iter 3.476936 +gpu 0 iter : 14 Arret : 0.171392 s/iter 1.827262 +gpu 0 iter : 15 Arret : 0.0745773 s/iter 2.751869 +gpu 0 iter : 16 Arret : 0.035733 s/iter 3.807813 +gpu 0 iter : 17 Arret : 0.00850526 s/iter 1.825655 +gpu 0 iter : 18 Arret : 0.00549164 s/iter 1.822042 +gpu 0 iter : 19 Arret : 0.00323678 s/iter 1.812501 +gpu 0 iter : 20 Arret : 0.00178409 s/iter 1.787063 +gpu 0 iter : 21 Arret : 0.00194964 s/iter 1.769047 +gpu 0 iter : 22 Arret : 0.00146162 s/iter 1.771480 +gpu 0 iter : 23 Arret : 0.000624549 s/iter 1.753749 +gpu 0 iter : 24 Arret : 0.000211682 s/iter 1.776112 +gpu 0 iter : 25 Arret : 8.45179E-05 s/iter 1.740231 +gpu 0 iter : 26 Arret : 0.000326207 s/iter 1.768913 +gpu 0 iter : 27 Arret : 0.000200902 s/iter 1.745549 +gpu 0 iter : 28 Arret : 1.1316E-05 s/iter 1.732325 +gpu 0 iter : 29 Arret : 8.18684E-09 s/iter 1.758605 +gpu 0 iter : 30 Arret : 7.64211E-14 s/iter 1.747829 +temps : 59.7653 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.26507E-09 +Stabilite : 7.64211E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540528 +i* 0.841326| 1| 8.68923E-14 +i* 2.2979E-13| +| 2| -0.905603 +i* -0.424127| 1| 6.50001E-14 +i* -3.0061E-14| +| 3| -0.774122 +i* 0.633037| 1|-3.89619E-14 +i*-6.71876E-14| +| 4| 0.317935 +i* -0.948113| 1| 4.656E-15 +i* 1.15645E-13| +| 5| 0.235938 +i* 0.971768| 1|-1.10779E-14 +i* 1.06056E-13| +| 6| -0.717299 +i* -0.696766| 1| 5.63785E-15 +i*-6.71685E-14| +| 7| 0.992349 +i* -0.123462| 1|-4.81056E-13 +i* 9.00335E-13| +| 8| -0.938482 +i* 0.345329| 1|-6.95555E-14 +i*-3.79159E-14| +| 9| 0.610294 +i* -0.792175| 1| -5.4852E-14 +i*-3.26232E-14| +| 10| -0.0945977 +i* 0.995516| 1| 4.45165E-14 +i* 9.42527E-14| +| 11| -0.450242 +i* -0.892906| 1| 2.41855E-14 +i*-3.23699E-15| +| 12| 0.978218 +i* 0.207583| 1|-2.84429E-13 +i* 4.69725E-13| +| 13| -0.999806 +i* 0.0197069| 1|-4.72365E-14 +i*-2.55716E-14| +| 14| 0.835648 +i* -0.549265| 1|-2.95892E-13 +i* 2.34143E-13| +| 15| -0.414707 +i* 0.909955| 1| 7.26225E-14 +i*-1.70003E-15| +| 16| -0.133754 +i* -0.991015| 1|-2.88485E-14 +i* 2.14499E-14| +| 17| 0.856687 +i* 0.515837| 1| 1.49106E-13 +i* 3.95153E-14| +| 18| -0.951361 +i* -0.308079| 1| 3.78308E-14 +i* 4.65843E-14| +| 19| 0.969257 +i* -0.24605| 1| 5.51163E-13 +i*-4.79498E-13| +| 20| -0.689285 +i* 0.724491| 1| 2.40086E-15 +i*-3.61777E-14| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 1 +zone limite de 'log-exp' 1.00142 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 0 (of 3) uses CUDA device 0 +CPU thread 1 (of 3) uses CUDA device 1 +gpu 1 dimgrid 977 dimblock 256 degrePoly 250000 +gpu 1 dimgrid2 326 start 83370 size 83370 +gpu 0 dimgrid 977 dimblock 256 degrePoly 250000 +gpu 0 dimgrid2 326 start 0 size 83370 +gpu 2 dimgrid 977 dimblock 256 degrePoly 250000 +gpu 2 dimgrid2 326 start 166740 size 83370 +gpu 0 iter : 1 Arret : 1.04122E-05 s/iter 4.597080 +gpu 0 iter : 2 Arret : 9.66981E-06 s/iter 4.598575 +gpu 0 iter : 3 Arret : 9.74545E-06 s/iter 4.597108 +gpu 0 iter : 4 Arret : 9.44307E-06 s/iter 4.597489 +gpu 0 iter : 5 Arret : 9.34819E-06 s/iter 4.598001 +gpu 0 iter : 6 Arret : 1.14416E-05 s/iter 4.598661 +gpu 0 iter : 7 Arret : 1.00875E-05 s/iter 4.598097 +gpu 0 iter : 8 Arret : 1.00498E-05 s/iter 4.597534 +gpu 0 iter : 9 Arret : 1.32154E-05 s/iter 4.597416 +gpu 0 iter : 10 Arret : 0.00051254 s/iter 4.597729 +gpu 0 iter : 11 Arret : 0.000628345 s/iter 4.596129 +gpu 0 iter : 12 Arret : 0.00250283 s/iter 4.597678 +gpu 0 iter : 13 Arret : 0.0026566 s/iter 4.597471 +gpu 0 iter : 14 Arret : 0.00107482 s/iter 4.597721 +gpu 0 iter : 15 Arret : 0.0010467 s/iter 4.579817 +gpu 0 iter : 16 Arret : 0.000858809 s/iter 3.750659 +gpu 0 iter : 17 Arret : 0.00453371 s/iter 2.883509 +gpu 0 iter : 18 Arret : 0.298024 s/iter 5.041367 +gpu 0 iter : 19 Arret : 0.0060016 s/iter 5.070989 +gpu 0 iter : 20 Arret : 0.0020976 s/iter 2.833299 +gpu 0 iter : 21 Arret : 0.000787752 s/iter 2.821846 +gpu 0 iter : 22 Arret : 0.00114118 s/iter 2.808072 +gpu 0 iter : 23 Arret : 0.000242876 s/iter 2.800882 +gpu 0 iter : 24 Arret : 6.73756E-05 s/iter 2.794362 +gpu 0 iter : 25 Arret : 2.16461E-05 s/iter 2.813139 +gpu 0 iter : 26 Arret : 2.86679E-06 s/iter 2.821334 +gpu 0 iter : 27 Arret : 9.41388E-09 s/iter 2.791395 +gpu 0 iter : 28 Arret : 1.06079E-14 s/iter 2.796462 +temps : 112.147 seconde(s) +Nb iterations : 28 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.05316E-09 +Stabilite : 1.06079E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540427 +i* 0.841391| 1| 9.7148E-14 +i*-1.98189E-13| +| 2| -0.997949 +i* 0.0640067| 1| 1.02696E-14 +i* 2.88415E-14| +| 3| 0.450991 +i* -0.892528| 1| 2.39739E-15 +i* 7.66835E-14| +| 4| 0.42851 +i* -0.903537| 1| 1.03733E-13 +i* 1.27433E-14| +| 5| -0.996035 +i* 0.0889649| 1| 5.1386E-14 +i* 4.21729E-14| +| 6| 0.581876 +i* 0.813277| 1| 3.29906E-13 +i* -3.5718E-15| +| 7| 0.405761 +i* -0.913979| 1| 1.69923E-13 +i*-8.86062E-14| +| 8| -0.993496 +i* 0.113867| 1| 6.34562E-14 +i* 6.04291E-14| +| 9| 0.60205 +i* 0.798458| 1| 2.39371E-13 +i* -2.2848E-13| +| 10| 0.382757 +i* -0.923849| 1| 6.36852E-14 +i* 1.1601E-13| +| 11| -0.990335 +i* 0.138698| 1| 8.32286E-14 +i* 4.57395E-14| +| 12| 0.621846 +i* 0.783139| 1| 3.5482E-14 +i*-1.57841E-13| +| 13| 0.359514 +i* -0.93314| 1| 1.00985E-13 +i*-2.52237E-13| +| 14| -0.986553 +i* 0.163442| 1| 3.24636E-14 +i* 4.58574E-14| +| 15| 0.641253 +i* 0.767329| 1| 1.79533E-13 +i* 3.03096E-13| +| 16| 0.336045 +i* -0.941846| 1| 1.38948E-13 +i*-8.14071E-14| +| 17| -0.982153 +i* 0.188084| 1| 6.94549E-14 +i* 3.09405E-14| +| 18| 0.660258 +i* 0.751039| 1| 4.21871E-13 +i* 5.02185E-14| +| 19| 0.312366 +i* -0.949962| 1|-6.37199E-14 +i*-7.39669E-14| +| 20| -0.977138 +i* 0.212608| 1|-3.80633E-14 +i* -8.4285E-14| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 1 +zone limite de 'log-exp' 1.00101 +CPU thread 0 (of 3) uses CUDA device 0 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 1 (of 3) uses CUDA device 1 +gpu 0 dimgrid 1368 dimblock 256 degrePoly 350000 +gpu 0 dimgrid2 456 start 0 size 116736 +gpu 2 dimgrid 1368 dimblock 256 degrePoly 350000 +gpu 2 dimgrid2 456 start 233472 size 116736 +gpu 1 dimgrid 1368 dimblock 256 degrePoly 350000 +gpu 1 dimgrid2 456 start 116736 size 116736 +gpu 0 iter : 1 Arret : 7.55039E-06 s/iter 8.728409 +gpu 0 iter : 2 Arret : 7.39793E-06 s/iter 8.712889 +gpu 0 iter : 3 Arret : 7.14478E-06 s/iter 8.682208 +gpu 0 iter : 4 Arret : 8.2105E-06 s/iter 8.682867 +gpu 0 iter : 5 Arret : 7.11502E-06 s/iter 8.683783 +gpu 0 iter : 6 Arret : 6.76587E-06 s/iter 8.680714 +gpu 0 iter : 7 Arret : 7.0891E-06 s/iter 8.680860 +gpu 0 iter : 8 Arret : 7.80018E-06 s/iter 8.676771 +gpu 0 iter : 9 Arret : 1.16108E-05 s/iter 8.679747 +gpu 0 iter : 10 Arret : 0.000768653 s/iter 8.679484 +gpu 0 iter : 11 Arret : 0.00361976 s/iter 8.676534 +gpu 0 iter : 12 Arret : 0.00104415 s/iter 8.674304 +gpu 0 iter : 13 Arret : 0.820674 s/iter 8.674523 +gpu 0 iter : 14 Arret : 3.33533 s/iter 11.712432 +gpu 0 iter : 15 Arret : 0.122884 s/iter 11.716566 +gpu 0 iter : 16 Arret : 0.0600695 s/iter 11.005801 +gpu 0 iter : 17 Arret : 0.0359638 s/iter 10.051106 +gpu 0 iter : 18 Arret : 0.0231638 s/iter 13.260628 +gpu 0 iter : 19 Arret : 0.0116355 s/iter 13.296853 +gpu 0 iter : 20 Arret : 0.102796 s/iter 11.567596 +gpu 0 iter : 21 Arret : 0.0633274 s/iter 11.618611 +gpu 0 iter : 22 Arret : 0.0252937 s/iter 12.797589 +gpu 0 iter : 23 Arret : 0.0319937 s/iter 11.830702 +gpu 0 iter : 24 Arret : 0.0268738 s/iter 13.413124 +gpu 0 iter : 25 Arret : 0.0121216 s/iter 10.946927 +gpu 0 iter : 26 Arret : 0.00234992 s/iter 8.617752 +gpu 0 iter : 27 Arret : 0.00204079 s/iter 8.617732 +gpu 0 iter : 28 Arret : 0.000634889 s/iter 8.617224 +gpu 0 iter : 29 Arret : 0.000124399 s/iter 8.616406 +gpu 0 iter : 30 Arret : 3.10052E-05 s/iter 8.615337 +gpu 0 iter : 31 Arret : 1.67246E-05 s/iter 8.616948 +gpu 0 iter : 32 Arret : 2.0926E-06 s/iter 8.616524 +gpu 0 iter : 33 Arret : 1.35583E-08 s/iter 8.618103 +gpu 0 iter : 34 Arret : 5.09118E-14 s/iter 8.615345 +temps : 334.994 seconde(s) +Nb iterations : 34 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.46096E-08 +Stabilite : 5.09118E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540399 +i* 0.841409| 1| 5.12961E-13 +i*-3.37404E-15| +| 2| -0.385479 +i* 0.922716| 1| -1.616E-13 +i*-2.73566E-14| +| 3| -0.770131 +i* 0.637886| 1|-1.38431E-15 +i* 1.70921E-13| +| 4| -0.978357 +i* 0.206925| 1|-3.07393E-15 +i* 4.96131E-15| +| 5| -0.962455 +i* -0.27144| 1|-5.85088E-14 +i* 7.9714E-14| +| 6| -0.72607 +i* -0.687621| 1| -2.0612E-14 +i* 2.87948E-13| +| 7| -0.323352 +i* -0.946279| 1| 2.27159E-13 +i* 7.30891E-14| +| 8| 0.153459 +i* -0.988155| 1| 4.60049E-15 +i*-2.43555E-14| +| 9| 0.595097 +i* -0.803654| 1|-3.46265E-13 +i* 1.60098E-14| +| 10| 0.900408 +i* -0.435047| 1| 3.20081E-13 +i*-1.77827E-14| +| 11| 0.999448 +i* 0.0332229| 1|-5.70342E-13 +i* 1.21308E-12| +| 12| 0.869529 +i* 0.493882| 1| 3.01252E-14 +i* 6.11216E-13| +| 13| 0.211292 +i* 0.977423| 1|-6.97532E-14 +i* 1.23212E-13| +| 14| -0.267139 +i* 0.963658| 1|-9.26238E-14 +i*-7.20968E-14| +| 15| -0.684372 +i* 0.729133| 1| 1.64042E-13 +i*-1.89831E-14| +| 16| -0.944825 +i* 0.327574| 1| 3.70572E-14 +i*-6.84904E-14| +| 17| -0.988833 +i* -0.149027| 1|-1.41002E-13 +i* 2.02581E-14| +| 18| -0.806314 +i* -0.591488| 1| 1.24668E-13 +i*-2.62805E-13| +| 19| -0.439079 +i* -0.898448| 1|-1.76949E-13 +i*-1.05707E-13| +| 20| 0.0287415 +i* -0.999587| 1| 1.62724E-13 +i*-6.82891E-14| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 1 +zone limite de 'log-exp' 1.00071 +CPU thread 0 (of 3) uses CUDA device 0 +CPU thread 1 (of 3) uses CUDA device 1 +CPU thread 2 (of 3) uses CUDA device 2 +gpu 1 dimgrid 1954 dimblock 256 degrePoly 500000 +gpu 1 dimgrid2 652 start 166741 size 166741 +gpu 0 dimgrid 1954 dimblock 256 degrePoly 500000 +gpu 0 dimgrid2 652 start 0 size 166741 +gpu 2 dimgrid 1954 dimblock 256 degrePoly 500000 +gpu 2 dimgrid2 652 start 333482 size 166741 +gpu 0 iter : 1 Arret : 5.71659E-06 s/iter 17.161724 +gpu 0 iter : 2 Arret : 4.8241E-06 s/iter 17.102931 +gpu 0 iter : 3 Arret : 4.62087E-06 s/iter 17.128111 +gpu 0 iter : 4 Arret : 5.16204E-06 s/iter 17.101919 +gpu 0 iter : 5 Arret : 4.94408E-06 s/iter 17.092405 +gpu 0 iter : 6 Arret : 4.816E-06 s/iter 17.112302 +gpu 0 iter : 7 Arret : 4.87888E-06 s/iter 17.096377 +gpu 0 iter : 8 Arret : 5.28527E-06 s/iter 17.102422 +gpu 0 iter : 9 Arret : 6.38912E-06 s/iter 17.095757 +gpu 0 iter : 10 Arret : 0.000225655 s/iter 17.102543 +gpu 0 iter : 11 Arret : 0.000912484 s/iter 17.099976 +gpu 0 iter : 12 Arret : 0.001168 s/iter 17.099389 +gpu 0 iter : 13 Arret : 0.00167187 s/iter 21.294197 +gpu 0 iter : 14 Arret : 0.00151006 s/iter 17.896733 +gpu 0 iter : 15 Arret : 0.00184196 s/iter 17.074701 +gpu 0 iter : 16 Arret : 0.00799101 s/iter 18.651210 +gpu 0 iter : 17 Arret : 1.57022 s/iter 15.558990 +gpu 0 iter : 18 Arret : 0.0777881 s/iter 13.332881 +gpu 0 iter : 19 Arret : 0.020549 s/iter 14.677134 +gpu 0 iter : 20 Arret : 0.00806741 s/iter 15.739566 +gpu 0 iter : 21 Arret : 0.00459564 s/iter 12.928791 +gpu 0 iter : 22 Arret : 0.000774045 s/iter 10.091239 +gpu 0 iter : 23 Arret : 0.000687203 s/iter 9.870933 +gpu 0 iter : 24 Arret : 0.000321475 s/iter 8.758152 +gpu 0 iter : 25 Arret : 7.13963E-05 s/iter 8.577885 +gpu 0 iter : 26 Arret : 4.18738E-05 s/iter 8.536888 +gpu 0 iter : 27 Arret : 7.77414E-06 s/iter 8.435734 +gpu 0 iter : 28 Arret : 4.61674E-07 s/iter 8.385966 +gpu 0 iter : 29 Arret : 3.96914E-10 s/iter 8.211682 +gpu 0 iter : 30 Arret : 1.11723E-15 s/iter 8.267906 +temps : 432.911 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.48768E-08 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540372 +i* 0.841426| 1|-3.05235E-13 +i* 1.38721E-13| +| 2| 0.561316 +i* 0.827602| 1|-2.60021E-13 +i* 1.9206E-13| +| 3| 0.57165 +i* 0.820497| 1|-1.83308E-13 +i* 6.15844E-14| +| 4| 0.581895 +i* 0.813264| 1| 3.05839E-13 +i* 6.52482E-14| +| 5| 0.592048 +i* 0.805902| 1|-7.14016E-13 +i*-3.98882E-14| +| 6| 0.602109 +i* 0.798414| 1| 2.66658E-13 +i*-4.75979E-13| +| 7| 0.612074 +i* 0.7908| 1| 3.16743E-13 +i*-3.40844E-13| +| 8| 0.621943 +i* 0.783062| 1| 5.64146E-13 +i*-3.14632E-13| +| 9| 0.631715 +i* 0.775201| 1|-3.83756E-14 +i* 5.41086E-13| +| 10| 0.641387 +i* 0.767218| 1| 4.00499E-13 +i*-3.71465E-13| +| 11| 0.650958 +i* 0.759114| 1| 7.58768E-15 +i*-5.54055E-13| +| 12| 0.660427 +i* 0.750891| 1| 7.47999E-13 +i* 2.73089E-13| +| 13| 0.669792 +i* 0.742549| 1| 9.40577E-13 +i* 3.39433E-14| +| 14| 0.679051 +i* 0.734091| 1| 4.34264E-13 +i*-1.04887E-13| +| 15| 0.688204 +i* 0.725517| 1|-6.26926E-13 +i*-1.86798E-13| +| 16| 0.697248 +i* 0.71683| 1| 2.2389E-13 +i*-9.46795E-14| +| 17| 0.706183 +i* 0.708029| 1| 4.79186E-13 +i* 4.75144E-13| +| 18| 0.715007 +i* 0.699117| 1| 6.39138E-13 +i* 4.95824E-13| +| 19| 0.723718 +i* 0.690096| 1| -1.2694E-13 +i* 4.44528E-13| +| 20| 0.732316 +i* 0.680965| 1|-2.76158E-13 +i* 1.17734E-13| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +zone limite de 'log-exp' 1.00059 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 1 (of 3) uses CUDA device 1 +CPU thread 0 (of 3) uses CUDA device 0 +gpu 2 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 2 dimgrid2 782 start 400042 size 200021 +gpu 1 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 1 dimgrid2 782 start 200021 size 200021 +gpu 0 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 0 dimgrid2 782 start 0 size 200021 +gpu 0 iter : 1 Arret : 4.17374E-06 s/iter 25.502913 +gpu 0 iter : 2 Arret : 4.12988E-06 s/iter 25.466465 +gpu 0 iter : 3 Arret : 3.89098E-06 s/iter 25.456717 +gpu 0 iter : 4 Arret : 3.93498E-06 s/iter 25.471780 +gpu 0 iter : 5 Arret : 4.075E-06 s/iter 25.480147 +gpu 0 iter : 6 Arret : 4.05328E-06 s/iter 25.490152 +gpu 0 iter : 7 Arret : 4.09388E-06 s/iter 25.467915 +gpu 0 iter : 8 Arret : 4.4692E-06 s/iter 25.472589 +gpu 0 iter : 9 Arret : 5.3977E-06 s/iter 25.487936 +gpu 0 iter : 10 Arret : 1.31096E-05 s/iter 25.504106 +gpu 0 iter : 11 Arret : 0.000429141 s/iter 25.483586 +gpu 0 iter : 12 Arret : 0.00225971 s/iter 25.488006 +gpu 0 iter : 13 Arret : 0.918253 s/iter 25.485654 +gpu 0 iter : 14 Arret : 0.738628 s/iter 28.610440 +gpu 0 iter : 15 Arret : 1.06679 s/iter 25.657526 +gpu 0 iter : 16 Arret : 0.00754293 s/iter 28.023636 +gpu 0 iter : 17 Arret : 0.00928206 s/iter 27.385101 +gpu 0 iter : 18 Arret : 0.00238733 s/iter 27.805420 +gpu 0 iter : 19 Arret : 0.0221226 s/iter 23.602314 +gpu 0 iter : 20 Arret : 0.00167275 s/iter 23.298279 +gpu 0 iter : 21 Arret : 0.000828652 s/iter 23.099043 +gpu 0 iter : 22 Arret : 0.00089783 s/iter 22.283044 +gpu 0 iter : 23 Arret : 0.000189743 s/iter 21.934545 +gpu 0 iter : 24 Arret : 5.2959E-05 s/iter 21.894963 +gpu 0 iter : 25 Arret : 1.63869E-05 s/iter 21.689444 +gpu 0 iter : 26 Arret : 5.47754E-06 s/iter 21.811193 +gpu 0 iter : 27 Arret : 1.27747E-07 s/iter 21.641069 +gpu 0 iter : 28 Arret : 4.20926E-13 s/iter 21.740517 +temps : 693.102 seconde(s) +Nb iterations : 28 +Nb de depassements de capacite exponentielle : 0 +Precision : 5.38109E-08 +Stabilite : 4.20926E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540365 +i* 0.841431| 1| 4.39062E-13 +i* 5.83011E-13| +| 2| -0.553493 +i* -0.832854| 1|-5.02858E-13 +i* 3.83374E-15| +| 3| -0.579338 +i* -0.815087| 1| 4.42365E-13 +i* 2.65846E-14| +| 4| 0.592057 +i* 0.805896| 1| 2.06783E-13 +i* 1.94549E-13| +| 5| -0.604613 +i* -0.796519| 1| 2.39135E-13 +i* 2.96967E-13| +| 6| 0.617037 +i* 0.786934| 1|-3.70964E-13 +i* 2.85104E-13| +| 7| -0.629293 +i* -0.777168| 1| 3.4002E-13 +i* 1.14925E-14| +| 8| 0.641411 +i* 0.767198| 1|-6.01835E-13 +i* 5.70316E-13| +| 9| -0.653354 +i* -0.757052| 1| 3.00003E-14 +i* 4.1084E-13| +| 10| 0.665153 +i* 0.746707| 1|-9.55243E-14 +i* 7.739E-13| +| 11| -0.676773 +i* -0.736192| 1|-3.70891E-13 +i* 4.31963E-14| +| 12| 0.688242 +i* 0.725482| 1| 4.17319E-13 +i*-2.25125E-13| +| 13| -0.699526 +i* -0.714607| 1|-1.55074E-13 +i* 3.9467E-13| +| 14| 0.710653 +i* 0.703543| 1|-7.94843E-13 +i* 5.61671E-13| +| 15| -0.721591 +i* -0.69232| 1|-8.20351E-14 +i* 3.39909E-13| +| 16| 0.732366 +i* 0.680912| 1| 5.01595E-13 +i* 2.59279E-13| +| 17| -0.742946 +i* -0.669351| 1|-1.90181E-13 +i* 1.23972E-13| +| 18| 0.753358 +i* 0.657611| 1|-7.14661E-13 +i*-3.96187E-13| +| 19| -0.76357 +i* -0.645725| 1|-3.31242E-13 +i*-8.50865E-14| +| 20| 0.773609 +i* 0.633664| 1|-7.93813E-13 +i* 2.09313E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 1 +zone limite de 'log-exp' 1.00051 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 1 (of 3) uses CUDA device 1 +CPU thread 0 (of 3) uses CUDA device 0 +gpu 2 dimgrid 2735 dimblock 256 degrePoly 700000 +gpu 2 dimgrid2 912 start 466772 size 233386 +gpu 1 dimgrid 2735 dimblock 256 degrePoly 700000 +gpu 1 dimgrid2 912 start 233386 size 233386 +gpu 0 dimgrid 2735 dimblock 256 degrePoly 700000 +gpu 0 dimgrid2 912 start 0 size 233386 +gpu 0 iter : 1 Arret : 4.07574E-06 s/iter 34.223058 +gpu 0 iter : 2 Arret : 3.55154E-06 s/iter 34.224642 +gpu 0 iter : 3 Arret : 3.46878E-06 s/iter 34.212867 +gpu 0 iter : 4 Arret : 3.42717E-06 s/iter 34.222285 +gpu 0 iter : 5 Arret : 3.26935E-06 s/iter 34.215281 +gpu 0 iter : 6 Arret : 3.34195E-06 s/iter 34.197991 +gpu 0 iter : 7 Arret : 3.3903E-06 s/iter 34.208738 +gpu 0 iter : 8 Arret : 3.49838E-06 s/iter 34.196075 +gpu 0 iter : 9 Arret : 3.56276E-06 s/iter 34.209024 +gpu 0 iter : 10 Arret : 5.84108E-06 s/iter 34.213481 +gpu 0 iter : 11 Arret : 0.00066379 s/iter 34.219783 +gpu 0 iter : 12 Arret : 0.00134105 s/iter 34.213025 +gpu 0 iter : 13 Arret : 0.00258505 s/iter 34.466511 +gpu 0 iter : 14 Arret : 0.0103479 s/iter 43.404986 +gpu 0 iter : 15 Arret : 0.00921676 s/iter 37.016770 +gpu 0 iter : 16 Arret : 0.00524991 s/iter 34.402114 +gpu 0 iter : 17 Arret : 0.00461832 s/iter 34.685302 +gpu 0 iter : 18 Arret : 0.0111077 s/iter 37.320698 +gpu 0 iter : 19 Arret : 0.277174 s/iter 35.309915 +gpu 0 iter : 20 Arret : 0.0136382 s/iter 37.689142 +gpu 0 iter : 21 Arret : 0.0160865 s/iter 34.656561 +gpu 0 iter : 22 Arret : 0.0117015 s/iter 34.545629 +gpu 0 iter : 23 Arret : 0.00660409 s/iter 34.694858 +gpu 0 iter : 24 Arret : 0.0024069 s/iter 35.413033 +gpu 0 iter : 25 Arret : 0.00112793 s/iter 34.552170 +gpu 0 iter : 26 Arret : 0.000118329 s/iter 34.545882 +gpu 0 iter : 27 Arret : 7.75369E-06 s/iter 34.554405 +gpu 0 iter : 28 Arret : 1.97801E-06 s/iter 34.600018 +gpu 0 iter : 29 Arret : 1.19455E-08 s/iter 34.514124 +gpu 0 iter : 30 Arret : 5.31286E-15 s/iter 34.636400 +temps : 1053.03 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 7.46263E-08 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540352 +i* 0.841439| 1| 4.39978E-13 +i* 6.25043E-13| +| 2| -0.996034 +i* 0.0889731| 1| 2.2073E-13 +i* 1.55296E-13| +| 3| 0.439836 +i* -0.898078| 1|-3.55927E-13 +i*-1.21738E-13| +| 4| 0.38266 +i* -0.923889| 1|-2.56142E-13 +i*-7.02285E-14| +| 5| -0.988496 +i* 0.15125| 1|-1.52652E-13 +i*-1.11329E-13| +| 6| 0.641421 +i* 0.767189| 1|-1.31044E-13 +i* 5.61736E-13| +| 7| 0.323979 +i* -0.946064| 1|-4.52336E-13 +i* 8.74596E-14| +| 8| -0.977067 +i* 0.212932| 1| 8.58341E-14 +i* 1.73412E-13| +| 9| 0.688262 +i* 0.725462| 1| 4.28754E-14 +i* 1.08849E-12| +| 10| 0.264022 +i* -0.964517| 1|-3.63883E-13 +i*-8.14886E-14| +| 11| -0.961793 +i* 0.273776| 1| -3.0213E-13 +i*-2.13897E-13| +| 12| 0.732395 +i* 0.68088| 1|-3.65194E-14 +i* 7.95483E-13| +| 13| 0.203027 +i* -0.979173| 1|-3.14502E-13 +i* 2.96924E-13| +| 14| -0.942735 +i* 0.333543| 1| 1.82947E-13 +i*-4.73458E-14| +| 15| 0.773646 +i* 0.633619| 1| 2.24352E-13 +i* 2.79674E-13| +| 16| 0.141232 +i* -0.989977| 1| -1.0035E-13 +i* 1.5693E-13| +| 17| -0.919967 +i* 0.391997| 1| 2.89213E-14 +i*-1.86252E-13| +| 18| 0.811852 +i* 0.583864| 1|-1.59939E-12 +i*-4.13669E-13| +| 19| 0.0788818 +i* -0.996884| 1|-2.83003E-13 +i* 1.04711E-13| +| 20| -0.893578 +i* 0.448908| 1| 4.59736E-14 +i* 1.31414E-13| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 1 +zone limite de 'log-exp' 1.00044 +CPU thread 0 (of 3) uses CUDA device 0 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 1 (of 3) uses CUDA device 1 +gpu 0 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 0 dimgrid2 1042 start 0 size 266666 +gpu 2 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 2 dimgrid2 1042 start 533332 size 266666 +gpu 1 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 1 dimgrid2 1042 start 266666 size 266666 +gpu 0 iter : 1 Arret : 3.43128E-06 s/iter 44.316497 +gpu 0 iter : 2 Arret : 3.77153E-06 s/iter 44.131572 +gpu 0 iter : 3 Arret : 3.23873E-06 s/iter 44.315408 +gpu 0 iter : 4 Arret : 3.15113E-06 s/iter 44.328033 +gpu 0 iter : 5 Arret : 3.60598E-06 s/iter 44.311559 +gpu 0 iter : 6 Arret : 3.57581E-06 s/iter 44.316239 +gpu 0 iter : 7 Arret : 3.25175E-06 s/iter 44.224296 +gpu 0 iter : 8 Arret : 3.4699E-06 s/iter 44.325585 +gpu 0 iter : 9 Arret : 4.55022E-06 s/iter 44.283208 +gpu 0 iter : 10 Arret : 3.7857E-05 s/iter 44.288810 +gpu 0 iter : 11 Arret : 0.000824026 s/iter 44.305832 +gpu 0 iter : 12 Arret : 0.00406403 s/iter 49.181390 +gpu 0 iter : 13 Arret : 1.91903 s/iter 44.281962 +gpu 0 iter : 14 Arret : 0.315909 s/iter 52.995186 +gpu 0 iter : 15 Arret : 0.325705 s/iter 48.752573 +gpu 0 iter : 16 Arret : 0.25171 s/iter 48.906019 +gpu 0 iter : 17 Arret : 0.107387 s/iter 44.063529 +gpu 0 iter : 18 Arret : 0.063654 s/iter 40.922131 +gpu 0 iter : 19 Arret : 0.0247294 s/iter 39.343896 +gpu 0 iter : 20 Arret : 0.015705 s/iter 38.504441 +gpu 0 iter : 21 Arret : 0.00670205 s/iter 39.597806 +gpu 0 iter : 22 Arret : 0.00378517 s/iter 35.764039 +gpu 0 iter : 23 Arret : 0.00973025 s/iter 33.436854 +gpu 0 iter : 24 Arret : 0.00954051 s/iter 32.742842 +gpu 0 iter : 25 Arret : 0.000557232 s/iter 31.071844 +gpu 0 iter : 26 Arret : 2.73926E-05 s/iter 30.889921 +gpu 0 iter : 27 Arret : 2.78216E-06 s/iter 30.780761 +gpu 0 iter : 28 Arret : 2.46904E-08 s/iter 30.743643 +gpu 0 iter : 29 Arret : 6.07909E-14 s/iter 30.869112 +temps : 1191.46 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 0.0233219 +Stabilite : 3.24723E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540349 +i* 0.841441| 1|-1.16344E-13 +i* 9.55619E-13| +| 2| 0.592061 +i* 0.805893| 1|-1.57249E-13 +i*-4.43364E-13| +| 3| 0.617051 +i* 0.786923| 1|-6.42805E-13 +i*-3.49094E-13| +| 4| 0.641434 +i* 0.767178| 1| 1.00022E-12 +i*-5.90578E-13| +| 5| 0.665186 +i* 0.746678| 1|-2.53998E-14 +i*-1.14684E-12| +| 6| 0.688283 +i* 0.725442| 1|-8.68732E-13 +i* 8.52696E-13| +| 7| 0.710703 +i* 0.703493| 1| 2.02581E-13 +i* 4.54699E-13| +| 8| 0.732422 +i* 0.680851| 1|-5.22353E-13 +i*-3.99873E-13| +| 9| 0.753421 +i* 0.657538| 1| 1.23356E-13 +i*-1.05986E-12| +| 10| 0.773678 +i* 0.633579| 1|-6.75196E-13 +i* 3.60108E-13| +| 11| 0.793174 +i* 0.608995| 1| 4.43853E-13 +i*-1.42398E-12| +| 12| 0.811888 +i* 0.583813| 1|-4.10491E-13 +i*-4.46651E-13| +| 13| 0.829804 +i* 0.558055| 1| 1.30045E-12 +i* 1.12788E-13| +| 14| 0.846902 +i* 0.531748| 1|-8.09419E-13 +i* 4.98091E-13| +| 15| 0.863167 +i* 0.504918| 1| 2.98522E-13 +i* 3.81547E-13| +| 16| 0.878582 +i* 0.477591| 1|-3.06581E-13 +i*-6.95869E-13| +| 17| 0.893133 +i* 0.449793| 1| 1.24355E-13 +i* -1.3239E-12| +| 18| 0.906804 +i* 0.421553| 1|-1.23117E-12 +i*-5.57117E-13| +| 19| 0.919582 +i* 0.392898| 1|-1.03648E-12 +i* 2.90445E-14| +| 20| 0.931455 +i* 0.363856| 1|-6.42708E-13 +i*-1.50318E-12| ++---+----------------------------+------------+----------------------------+ +799998 racines de module = 1 + 2 racines de module = 0.999973 diff --git a/Simulations/full_openmp/full_openmp_3GPU.sge b/Simulations/full_openmp/full_openmp_3GPU.sge new file mode 100644 index 0000000..c3a277c --- /dev/null +++ b/Simulations/full_openmp/full_openmp_3GPU.sge @@ -0,0 +1,27 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=3 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -pe openmp 3 +#$ -V +#$ -cwd +#$ -N full_openmp_3GPU + +module load gcc/4.9.0 +module load cuda/7.0 + + +./template -r -i 60000 40000 +./template -r -i 150000 50000 +./template -r -i 250000 150000 +./template -r -i 350000 250000 +./template -r -i 500000 300000 +./template -r -i 600000 400000 +./template -r -i 700000 500000 +./template -r -i 800000 600000 +#./template -r -i 900000 700000 +#./template -r -i 1000000 800000 +#./template -r -i 1500000 500000 + + diff --git a/Simulations/full_openmp/full_openmp_4GPU.o140162 b/Simulations/full_openmp/full_openmp_4GPU.o140162 new file mode 100644 index 0000000..5a3649d --- /dev/null +++ b/Simulations/full_openmp/full_openmp_4GPU.o140162 @@ -0,0 +1,590 @@ +REMAINING: 4 +Taking GPU #0 +Taking GPU #1 +Taking GPU #2 +Taking GPU #3 +zone limite de 'log-exp' 1.00593 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 1 (of 4) uses CUDA device 1 +gpu 3 dimgrid 235 dimblock 256 degrePoly 60000 +gpu 3 dimgrid2 59 start 45120 size 15040 +gpu 2 dimgrid 235 dimblock 256 degrePoly 60000 +gpu 2 dimgrid2 59 start 30080 size 15040 +gpu 0 dimgrid 235 dimblock 256 degrePoly 60000 +gpu 0 dimgrid2 59 start 0 size 15040 +gpu 1 dimgrid 235 dimblock 256 degrePoly 60000 +gpu 1 dimgrid2 59 start 15040 size 15040 +gpu 0 iter : 1 Arret : 4.54253E-05 s/iter 0.204175 +gpu 0 iter : 2 Arret : 4.02349E-05 s/iter 0.189665 +gpu 0 iter : 3 Arret : 3.82695E-05 s/iter 0.189681 +gpu 0 iter : 4 Arret : 3.90123E-05 s/iter 0.189717 +gpu 0 iter : 5 Arret : 4.05115E-05 s/iter 0.189657 +gpu 0 iter : 6 Arret : 4.39547E-05 s/iter 0.189790 +gpu 0 iter : 7 Arret : 5.45799E-05 s/iter 0.189703 +gpu 0 iter : 8 Arret : 0.000119388 s/iter 0.189738 +gpu 0 iter : 9 Arret : 0.00119487 s/iter 0.189634 +gpu 0 iter : 10 Arret : 0.00289573 s/iter 0.189661 +gpu 0 iter : 11 Arret : 2.16041 s/iter 0.189628 +gpu 0 iter : 12 Arret : 0.350069 s/iter 0.189703 +gpu 0 iter : 13 Arret : 0.131331 s/iter 1.021619 +gpu 0 iter : 14 Arret : 0.0516998 s/iter 1.018752 +gpu 0 iter : 15 Arret : 0.0205122 s/iter 1.016639 +gpu 0 iter : 16 Arret : 0.012334 s/iter 1.013349 +gpu 0 iter : 17 Arret : 0.00704057 s/iter 1.007092 +gpu 0 iter : 18 Arret : 0.00458473 s/iter 0.868843 +gpu 0 iter : 19 Arret : 0.00325386 s/iter 0.853210 +gpu 0 iter : 20 Arret : 0.00249036 s/iter 0.836780 +gpu 0 iter : 21 Arret : 0.0018094 s/iter 0.184672 +gpu 0 iter : 22 Arret : 0.00401767 s/iter 0.184541 +gpu 0 iter : 23 Arret : 0.048161 s/iter 0.183544 +gpu 0 iter : 24 Arret : 0.00734855 s/iter 0.178753 +gpu 0 iter : 25 Arret : 0.0107124 s/iter 0.178628 +gpu 0 iter : 26 Arret : 0.00180991 s/iter 0.172491 +gpu 0 iter : 27 Arret : 0.000329189 s/iter 0.172292 +gpu 0 iter : 28 Arret : 7.3153E-05 s/iter 0.172287 +gpu 0 iter : 29 Arret : 9.70999E-06 s/iter 0.172276 +gpu 0 iter : 30 Arret : 5.49374E-08 s/iter 0.172248 +gpu 0 iter : 31 Arret : 1.71107E-12 s/iter 0.172323 +gpu 0 iter : 32 Arret : 1.57009E-16 s/iter 0.172301 +temps : 13.5366 seconde(s) +Nb iterations : 32 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.35784E-10 +Stabilite : 1.57009E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540783 +i* 0.841162| 1|-7.58456E-14 +i* 3.78031E-14| +| 2| -0.992343 +i* -0.123513| 1|-4.36456E-15 +i* 3.59435E-15| +| 3| 0.0563346 +i* 0.998412| 1| 5.70377E-15 +i* 3.3501E-14| +| 4| -0.802793 +i* -0.596258| 1| 2.03657E-15 +i* 1.01915E-14| +| 5| 0.730552 +i* -0.682857| 1|-7.48429E-14 +i* 6.77011E-14| +| 6| -0.442728 +i* 0.896656| 1|-3.77198E-14 +i*-1.89779E-15| +| 7| -0.404888 +i* -0.914366| 1| 3.20195E-14 +i* 9.65894E-15| +| 8| 0.972126 +i* -0.23446| 1| 4.02421E-14 +i*-1.54755E-14| +| 9| -0.826939 +i* 0.562292| 1| -2.4928E-14 +i*-1.59889E-14| +| 10| 0.0979895 +i* -0.995187| 1| 2.90878E-14 +i*-6.75675E-15| +| 11| 0.961513 +i* 0.27476| 1|-9.39769E-14 +i*-2.63912E-13| +| 12| -0.996627 +i* 0.0820589| 1| 2.39773E-14 +i* 1.74825E-14| +| 13| 0.575447 +i* -0.817839| 1|-3.49894E-14 +i*-7.98545E-14| +| 14| 0.701466 +i* 0.712703| 1| 7.52211E-14 +i* 1.53991E-14| +| 15| 0.259346 +i* 0.965785| 1|-2.14863E-14 +i*-2.81355E-14| +| 16| -0.907773 +i* -0.419461| 1|-3.62869E-14 +i*-9.49414E-15| +| 17| 0.903623 +i* -0.428329| 1|-1.24969E-14 +i* 7.51222E-14| +| 18| -0.249979 +i* 0.968251| 1|-1.59074E-14 +i*-1.09721E-14| +| 19| -0.583341 +i* -0.812227| 1| 1.92242E-14 +i* 2.27058E-14| +| 20| 0.997383 +i* 0.072297| 1| 2.53037E-13 +i*-5.92819E-13| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 1 +zone limite de 'log-exp' 1.00237 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 1 (of 4) uses CUDA device 1 +CPU thread 2 (of 4) uses CUDA device 2 +gpu 0 dimgrid 586 dimblock 256 degrePoly 150000 +gpu 0 dimgrid2 147 start 0 size 37504 +gpu 3 dimgrid 586 dimblock 256 degrePoly 150000 +gpu 3 dimgrid2 147 start 112512 size 37504 +gpu 1 dimgrid 586 dimblock 256 degrePoly 150000 +gpu 1 dimgrid2 147 start 37504 size 37504 +gpu 2 dimgrid 586 dimblock 256 degrePoly 150000 +gpu 2 dimgrid2 147 start 75008 size 37504 +gpu 0 iter : 1 Arret : 1.6116E-05 s/iter 1.403394 +gpu 0 iter : 2 Arret : 1.52925E-05 s/iter 1.387067 +gpu 0 iter : 3 Arret : 1.51523E-05 s/iter 1.386759 +gpu 0 iter : 4 Arret : 1.86476E-05 s/iter 1.382149 +gpu 0 iter : 5 Arret : 1.57671E-05 s/iter 1.386808 +gpu 0 iter : 6 Arret : 1.6295E-05 s/iter 1.386892 +gpu 0 iter : 7 Arret : 1.80188E-05 s/iter 1.386856 +gpu 0 iter : 8 Arret : 2.08003E-05 s/iter 1.386801 +gpu 0 iter : 9 Arret : 3.59837E-05 s/iter 1.386900 +gpu 0 iter : 10 Arret : 0.00139949 s/iter 1.381972 +gpu 0 iter : 11 Arret : 0.00379917 s/iter 1.387000 +gpu 0 iter : 12 Arret : 0.00480593 s/iter 2.678954 +gpu 0 iter : 13 Arret : 0.0063728 s/iter 2.972359 +gpu 0 iter : 14 Arret : 0.0158488 s/iter 1.381889 +gpu 0 iter : 15 Arret : 0.0137848 s/iter 3.041156 +gpu 0 iter : 16 Arret : 0.0131859 s/iter 1.379081 +gpu 0 iter : 17 Arret : 1.29468 s/iter 3.020840 +gpu 0 iter : 18 Arret : 0.0424345 s/iter 3.418165 +gpu 0 iter : 19 Arret : 0.0201069 s/iter 3.422654 +gpu 0 iter : 20 Arret : 0.00607561 s/iter 2.950185 +gpu 0 iter : 21 Arret : 0.00629018 s/iter 3.290739 +gpu 0 iter : 22 Arret : 0.00557589 s/iter 1.335444 +gpu 0 iter : 23 Arret : 0.000991862 s/iter 1.330521 +gpu 0 iter : 24 Arret : 0.00206487 s/iter 1.322392 +gpu 0 iter : 25 Arret : 0.000365679 s/iter 1.334823 +gpu 0 iter : 26 Arret : 0.000144648 s/iter 1.333867 +gpu 0 iter : 27 Arret : 0.00033044 s/iter 1.332139 +gpu 0 iter : 28 Arret : 1.48376E-05 s/iter 1.334037 +gpu 0 iter : 29 Arret : 4.12386E-10 s/iter 1.324928 +gpu 0 iter : 30 Arret : 4.00547E-15 s/iter 1.333918 +temps : 56.2628 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.26535E-09 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540528 +i* 0.841326| 1| 8.68923E-14 +i* 2.2979E-13| +| 2| -0.905603 +i* -0.424127| 1| 6.50001E-14 +i* -3.0061E-14| +| 3| -0.774122 +i* 0.633037| 1|-3.89619E-14 +i*-6.71876E-14| +| 4| 0.317935 +i* -0.948113| 1| 4.656E-15 +i* 1.15645E-13| +| 5| 0.235978 +i* 0.971758| 1|-2.91295E-14 +i*-3.06716E-14| +| 6| -0.717299 +i* -0.696766| 1| 5.63785E-15 +i*-6.71685E-14| +| 7| 0.992349 +i* -0.123462| 1|-4.81056E-13 +i* 9.00335E-13| +| 8| -0.938482 +i* 0.345329| 1|-6.95555E-14 +i*-3.79159E-14| +| 9| 0.610294 +i* -0.792175| 1| -5.4852E-14 +i*-3.26232E-14| +| 10| -0.0946394 +i* 0.995512| 1|-4.73788E-14 +i*-8.10827E-14| +| 11| -0.450242 +i* -0.892906| 1| 2.41855E-14 +i*-3.23699E-15| +| 12| 0.978218 +i* 0.207583| 1|-2.84429E-13 +i* 4.69725E-13| +| 13| -0.999806 +i* 0.0197069| 1|-4.72365E-14 +i*-2.55716E-14| +| 14| 0.835648 +i* -0.549265| 1|-2.95892E-13 +i* 2.34143E-13| +| 15| -0.414707 +i* 0.909955| 1| 7.26225E-14 +i*-1.70003E-15| +| 16| -0.133754 +i* -0.991015| 1|-2.88485E-14 +i* 2.14499E-14| +| 17| 0.856687 +i* 0.515837| 1| 1.49106E-13 +i* 3.95153E-14| +| 18| -0.951361 +i* -0.308079| 1| 3.78308E-14 +i* 4.65843E-14| +| 19| 0.969257 +i* -0.24605| 1| 5.51163E-13 +i*-4.79498E-13| +| 20| -0.689285 +i* 0.724491| 1| 2.40086E-15 +i*-3.61777E-14| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 1 +zone limite de 'log-exp' 1.00142 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 1 (of 4) uses CUDA device 1 +gpu 2 dimgrid 977 dimblock 256 degrePoly 250000 +gpu 2 dimgrid2 245 start 125056 size 62528 +gpu 0 dimgrid 977 dimblock 256 degrePoly 250000 +gpu 0 dimgrid2 245 start 0 size 62528 +gpu 3 dimgrid 977 dimblock 256 degrePoly 250000 +gpu 3 dimgrid2 245 start 187584 size 62528 +gpu 1 dimgrid 977 dimblock 256 degrePoly 250000 +gpu 1 dimgrid2 245 start 62528 size 62528 +gpu 0 iter : 1 Arret : 1.14841E-05 s/iter 3.820958 +gpu 0 iter : 2 Arret : 9.97904E-06 s/iter 3.814972 +gpu 0 iter : 3 Arret : 1.0158E-05 s/iter 3.809374 +gpu 0 iter : 4 Arret : 9.50123E-06 s/iter 3.808973 +gpu 0 iter : 5 Arret : 9.84188E-06 s/iter 3.808465 +gpu 0 iter : 6 Arret : 9.56156E-06 s/iter 3.815126 +gpu 0 iter : 7 Arret : 9.85167E-06 s/iter 3.816179 +gpu 0 iter : 8 Arret : 1.00437E-05 s/iter 3.818435 +gpu 0 iter : 9 Arret : 3.05444E-05 s/iter 3.817012 +gpu 0 iter : 10 Arret : 0.00147405 s/iter 3.816247 +gpu 0 iter : 11 Arret : 0.00154571 s/iter 3.810174 +gpu 0 iter : 12 Arret : 0.000731342 s/iter 3.808902 +gpu 0 iter : 13 Arret : 0.00122682 s/iter 3.808356 +gpu 0 iter : 14 Arret : 0.00109532 s/iter 3.815259 +gpu 0 iter : 15 Arret : 0.0011892 s/iter 3.779459 +gpu 0 iter : 16 Arret : 0.000794066 s/iter 2.968072 +gpu 0 iter : 17 Arret : 0.00960632 s/iter 2.174069 +gpu 0 iter : 18 Arret : 0.3054 s/iter 4.920214 +gpu 0 iter : 19 Arret : 0.00164869 s/iter 2.134462 +gpu 0 iter : 20 Arret : 0.00100296 s/iter 2.137935 +gpu 0 iter : 21 Arret : 0.000263024 s/iter 2.128112 +gpu 0 iter : 22 Arret : 0.0007086 s/iter 2.111936 +gpu 0 iter : 23 Arret : 0.00101441 s/iter 2.112455 +gpu 0 iter : 24 Arret : 0.000848875 s/iter 2.109033 +gpu 0 iter : 25 Arret : 0.00150539 s/iter 2.111749 +gpu 0 iter : 26 Arret : 5.16459E-05 s/iter 2.096918 +gpu 0 iter : 27 Arret : 1.87546E-07 s/iter 2.098589 +gpu 0 iter : 28 Arret : 2.77608E-13 s/iter 2.110056 +temps : 89.8766 seconde(s) +Nb iterations : 28 +Nb de depassements de capacite exponentielle : 0 +Precision : 5.3128E-09 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540427 +i* 0.841391| 1| 9.7148E-14 +i*-1.98189E-13| +| 2| -0.997949 +i* 0.0640067| 1| 1.02696E-14 +i* 2.88415E-14| +| 3| 0.450991 +i* -0.892528| 1| 2.39739E-15 +i* 7.66835E-14| +| 4| 0.42851 +i* -0.903537| 1| 1.03733E-13 +i* 1.27433E-14| +| 5| -0.996035 +i* 0.0889649| 1| 5.1386E-14 +i* 4.21729E-14| +| 6| 0.581876 +i* 0.813277| 1| 3.29906E-13 +i* -3.5718E-15| +| 7| 0.405761 +i* -0.913979| 1| 1.69923E-13 +i*-8.86062E-14| +| 8| -0.993496 +i* 0.113867| 1| 6.34562E-14 +i* 6.04291E-14| +| 9| 0.60205 +i* 0.798458| 1| 2.39371E-13 +i* -2.2848E-13| +| 10| 0.382757 +i* -0.923849| 1| 6.36852E-14 +i* 1.1601E-13| +| 11| -0.990335 +i* 0.138698| 1| 8.32286E-14 +i* 4.57395E-14| +| 12| 0.621846 +i* 0.783139| 1| 3.5482E-14 +i*-1.57841E-13| +| 13| 0.359514 +i* -0.93314| 1| 1.00985E-13 +i*-2.52237E-13| +| 14| -0.986553 +i* 0.163442| 1| 3.24636E-14 +i* 4.58574E-14| +| 15| 0.641253 +i* 0.767329| 1| 1.79533E-13 +i* 3.03096E-13| +| 16| 0.336045 +i* -0.941846| 1| 1.38948E-13 +i*-8.14071E-14| +| 17| -0.982153 +i* 0.188084| 1| 6.94549E-14 +i* 3.09405E-14| +| 18| 0.660258 +i* 0.751039| 1| 4.21871E-13 +i* 5.02185E-14| +| 19| 0.312366 +i* -0.949962| 1|-6.37199E-14 +i*-7.39669E-14| +| 20| -0.977138 +i* 0.212608| 1|-3.80633E-14 +i* -8.4285E-14| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 1 +zone limite de 'log-exp' 1.00101 +CPU thread 1 (of 4) uses CUDA device 1 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 0 (of 4) uses CUDA device 0 +gpu 3 dimgrid 1368 dimblock 256 degrePoly 350000 +gpu 3 dimgrid2 342 start 262656 size 87552 +gpu 2 dimgrid 1368 dimblock 256 degrePoly 350000 +gpu 2 dimgrid2 342 start 175104 size 87552 +gpu 1 dimgrid 1368 dimblock 256 degrePoly 350000 +gpu 1 dimgrid2 342 start 87552 size 87552 +gpu 0 dimgrid 1368 dimblock 256 degrePoly 350000 +gpu 0 dimgrid2 342 start 0 size 87552 +gpu 0 iter : 1 Arret : 6.88539E-06 s/iter 6.540061 +gpu 0 iter : 2 Arret : 6.8684E-06 s/iter 6.536458 +gpu 0 iter : 3 Arret : 7.55734E-06 s/iter 6.535814 +gpu 0 iter : 4 Arret : 6.96901E-06 s/iter 6.536741 +gpu 0 iter : 5 Arret : 6.72451E-06 s/iter 6.533504 +gpu 0 iter : 6 Arret : 6.76555E-06 s/iter 6.534876 +gpu 0 iter : 7 Arret : 7.08866E-06 s/iter 6.534819 +gpu 0 iter : 8 Arret : 7.79946E-06 s/iter 6.533534 +gpu 0 iter : 9 Arret : 9.74863E-06 s/iter 6.531511 +gpu 0 iter : 10 Arret : 0.000378804 s/iter 6.530246 +gpu 0 iter : 11 Arret : 0.000478777 s/iter 6.545753 +gpu 0 iter : 12 Arret : 0.0010319 s/iter 6.531644 +gpu 0 iter : 13 Arret : 0.810083 s/iter 6.532661 +gpu 0 iter : 14 Arret : 3.38477 s/iter 9.611632 +gpu 0 iter : 15 Arret : 0.137317 s/iter 9.586509 +gpu 0 iter : 16 Arret : 0.0655441 s/iter 11.282824 +gpu 0 iter : 17 Arret : 0.0396702 s/iter 11.222823 +gpu 0 iter : 18 Arret : 0.165636 s/iter 11.248406 +gpu 0 iter : 19 Arret : 0.114767 s/iter 11.345882 +gpu 0 iter : 20 Arret : 0.0535778 s/iter 11.198285 +gpu 0 iter : 21 Arret : 0.0468459 s/iter 10.374819 +gpu 0 iter : 22 Arret : 0.0531479 s/iter 11.376048 +gpu 0 iter : 23 Arret : 0.0587573 s/iter 9.681631 +gpu 0 iter : 24 Arret : 0.380742 s/iter 9.616663 +gpu 0 iter : 25 Arret : 0.158886 s/iter 6.481929 +gpu 0 iter : 26 Arret : 0.19048 s/iter 10.400978 +gpu 0 iter : 27 Arret : 0.115233 s/iter 7.157960 +gpu 0 iter : 28 Arret : 0.0624603 s/iter 7.226846 +gpu 0 iter : 29 Arret : 0.00065803 s/iter 6.480500 +gpu 0 iter : 30 Arret : 2.18809E-05 s/iter 6.480583 +gpu 0 iter : 31 Arret : 3.02291E-05 s/iter 6.478820 +gpu 0 iter : 32 Arret : 6.59107E-06 s/iter 6.479051 +gpu 0 iter : 33 Arret : 1.18098E-07 s/iter 6.480090 +gpu 0 iter : 34 Arret : 1.37334E-12 s/iter 6.481310 +gpu 0 iter : 35 Arret : 1.11023E-16 s/iter 6.479636 +temps : 279.804 seconde(s) +Nb iterations : 35 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.46096E-08 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540399 +i* 0.841409| 1| 5.12961E-13 +i*-3.37404E-15| +| 2| -0.385479 +i* 0.922716| 1| -1.616E-13 +i*-2.73566E-14| +| 3| -0.770131 +i* 0.637886| 1|-1.38431E-15 +i* 1.70921E-13| +| 4| -0.978357 +i* 0.206925| 1|-3.07393E-15 +i* 4.96131E-15| +| 5| -0.962455 +i* -0.27144| 1|-5.85088E-14 +i* 7.9714E-14| +| 6| -0.72607 +i* -0.687621| 1| -2.0612E-14 +i* 2.87948E-13| +| 7| -0.323352 +i* -0.946279| 1| 2.27159E-13 +i* 7.30891E-14| +| 8| 0.153459 +i* -0.988155| 1| 4.60049E-15 +i*-2.43555E-14| +| 9| 0.595097 +i* -0.803654| 1|-3.46265E-13 +i* 1.60098E-14| +| 10| 0.900408 +i* -0.435047| 1| 3.20081E-13 +i*-1.77827E-14| +| 11| 0.999448 +i* 0.0332229| 1|-5.70342E-13 +i* 1.21308E-12| +| 12| 0.869529 +i* 0.493882| 1| 3.01252E-14 +i* 6.11216E-13| +| 13| 0.211292 +i* 0.977423| 1|-6.97532E-14 +i* 1.23212E-13| +| 14| -0.267139 +i* 0.963658| 1|-9.26238E-14 +i*-7.20968E-14| +| 15| -0.684372 +i* 0.729133| 1| 1.64042E-13 +i*-1.89831E-14| +| 16| -0.944825 +i* 0.327574| 1| 3.70572E-14 +i*-6.84904E-14| +| 17| -0.988833 +i* -0.149027| 1|-1.41002E-13 +i* 2.02581E-14| +| 18| -0.806314 +i* -0.591488| 1| 1.24668E-13 +i*-2.62805E-13| +| 19| -0.439079 +i* -0.898448| 1|-1.76949E-13 +i*-1.05707E-13| +| 20| 0.0287415 +i* -0.999587| 1| 1.62724E-13 +i*-6.82891E-14| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 1 +zone limite de 'log-exp' 1.00071 +CPU thread 1 (of 4) uses CUDA device 1 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 2 (of 4) uses CUDA device 2 +gpu 3 dimgrid 1954 dimblock 256 degrePoly 500000 +gpu 3 dimgrid2 489 start 375168 size 125056 +gpu 1 dimgrid 1954 dimblock 256 degrePoly 500000 +gpu 1 dimgrid2 489 start 125056 size 125056 +gpu 0 dimgrid 1954 dimblock 256 degrePoly 500000 +gpu 0 dimgrid2 489 start 0 size 125056 +gpu 2 dimgrid 1954 dimblock 256 degrePoly 500000 +gpu 2 dimgrid2 489 start 250112 size 125056 +gpu 0 iter : 1 Arret : 5.43682E-06 s/iter 13.802902 +gpu 0 iter : 2 Arret : 4.91044E-06 s/iter 13.790958 +gpu 0 iter : 3 Arret : 4.91315E-06 s/iter 13.790511 +gpu 0 iter : 4 Arret : 4.67858E-06 s/iter 13.806112 +gpu 0 iter : 5 Arret : 4.77709E-06 s/iter 13.805612 +gpu 0 iter : 6 Arret : 4.66912E-06 s/iter 13.804348 +gpu 0 iter : 7 Arret : 4.83022E-06 s/iter 13.804019 +gpu 0 iter : 8 Arret : 5.21278E-06 s/iter 13.800214 +gpu 0 iter : 9 Arret : 6.23421E-06 s/iter 13.801225 +gpu 0 iter : 10 Arret : 0.000564578 s/iter 13.800687 +gpu 0 iter : 11 Arret : 0.000810388 s/iter 13.802100 +gpu 0 iter : 12 Arret : 0.00138997 s/iter 13.800427 +gpu 0 iter : 13 Arret : 0.00220275 s/iter 18.005536 +gpu 0 iter : 14 Arret : 0.00421803 s/iter 13.791507 +gpu 0 iter : 15 Arret : 0.00623459 s/iter 13.530051 +gpu 0 iter : 16 Arret : 1.4756 s/iter 11.805523 +gpu 0 iter : 17 Arret : 0.0156198 s/iter 14.532176 +gpu 0 iter : 18 Arret : 0.0107648 s/iter 13.020495 +gpu 0 iter : 19 Arret : 0.0045075 s/iter 12.656318 +gpu 0 iter : 20 Arret : 0.00121976 s/iter 8.450054 +gpu 0 iter : 21 Arret : 0.000890648 s/iter 11.499489 +gpu 0 iter : 22 Arret : 0.00233504 s/iter 7.388259 +gpu 0 iter : 23 Arret : 0.00149094 s/iter 7.283653 +gpu 0 iter : 24 Arret : 0.00113868 s/iter 11.307597 +gpu 0 iter : 25 Arret : 0.000125947 s/iter 7.035207 +gpu 0 iter : 26 Arret : 2.52318E-05 s/iter 6.864347 +gpu 0 iter : 27 Arret : 3.0855E-08 s/iter 6.748053 +gpu 0 iter : 28 Arret : 9.3245E-14 s/iter 5.878949 +temps : 337.034 seconde(s) +Nb iterations : 28 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.48768E-08 +Stabilite : 1.41899E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540372 +i* 0.841426| 1|-3.05235E-13 +i* 1.38721E-13| +| 2| 0.561316 +i* 0.827602| 1|-2.60021E-13 +i* 1.9206E-13| +| 3| 0.57165 +i* 0.820497| 1|-1.83308E-13 +i* 6.15844E-14| +| 4| 0.581895 +i* 0.813264| 1| 3.05839E-13 +i* 6.52482E-14| +| 5| 0.592048 +i* 0.805902| 1|-7.14016E-13 +i*-3.98882E-14| +| 6| 0.602109 +i* 0.798414| 1| 2.66658E-13 +i*-4.75979E-13| +| 7| 0.612074 +i* 0.7908| 1| 3.16743E-13 +i*-3.40844E-13| +| 8| 0.621943 +i* 0.783062| 1| 5.64146E-13 +i*-3.14632E-13| +| 9| 0.631715 +i* 0.775201| 1|-3.83756E-14 +i* 5.41086E-13| +| 10| 0.641387 +i* 0.767218| 1| 4.00499E-13 +i*-3.71465E-13| +| 11| 0.650958 +i* 0.759114| 1| 7.58768E-15 +i*-5.54055E-13| +| 12| 0.660427 +i* 0.750891| 1| 7.47999E-13 +i* 2.73089E-13| +| 13| 0.669792 +i* 0.742549| 1| 9.40577E-13 +i* 3.39433E-14| +| 14| 0.679051 +i* 0.734091| 1| 4.34264E-13 +i*-1.04887E-13| +| 15| 0.688204 +i* 0.725517| 1|-6.26926E-13 +i*-1.86798E-13| +| 16| 0.697248 +i* 0.71683| 1| 2.2389E-13 +i*-9.46795E-14| +| 17| 0.706183 +i* 0.708029| 1| 4.79186E-13 +i* 4.75144E-13| +| 18| 0.715007 +i* 0.699117| 1| 6.39138E-13 +i* 4.95824E-13| +| 19| 0.723718 +i* 0.690096| 1| -1.2694E-13 +i* 4.44528E-13| +| 20| 0.732316 +i* 0.680965| 1|-2.76158E-13 +i* 1.17734E-13| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +zone limite de 'log-exp' 1.00059 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 1 (of 4) uses CUDA device 1 +gpu 0 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 0 dimgrid2 586 start 0 size 150016 +gpu 2 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 2 dimgrid2 586 start 300032 size 150016 +gpu 3 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 3 dimgrid2 586 start 450048 size 150016 +gpu 1 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 1 dimgrid2 586 start 150016 size 150016 +gpu 0 iter : 1 Arret : 4.20321E-06 s/iter 18.776658 +gpu 0 iter : 2 Arret : 4.13056E-06 s/iter 18.721323 +gpu 0 iter : 3 Arret : 4.11084E-06 s/iter 18.739702 +gpu 0 iter : 4 Arret : 4.14768E-06 s/iter 18.725990 +gpu 0 iter : 5 Arret : 3.97777E-06 s/iter 18.735245 +gpu 0 iter : 6 Arret : 4.16195E-06 s/iter 18.723334 +gpu 0 iter : 7 Arret : 4.19454E-06 s/iter 18.733188 +gpu 0 iter : 8 Arret : 4.62315E-06 s/iter 18.730439 +gpu 0 iter : 9 Arret : 6.05437E-06 s/iter 18.723590 +gpu 0 iter : 10 Arret : 1.53978E-05 s/iter 18.723454 +gpu 0 iter : 11 Arret : 0.000456524 s/iter 18.740808 +gpu 0 iter : 12 Arret : 0.00137167 s/iter 18.729445 +gpu 0 iter : 13 Arret : 0.00165831 s/iter 18.748008 +gpu 0 iter : 14 Arret : 1.38016 s/iter 18.749001 +gpu 0 iter : 15 Arret : 0.619057 s/iter 19.564421 +gpu 0 iter : 16 Arret : 0.0544873 s/iter 20.890543 +gpu 0 iter : 17 Arret : 0.0338392 s/iter 23.493737 +gpu 0 iter : 18 Arret : 0.0124964 s/iter 20.037893 +gpu 0 iter : 19 Arret : 0.00639686 s/iter 21.581791 +gpu 0 iter : 20 Arret : 0.00399724 s/iter 18.002558 +gpu 0 iter : 21 Arret : 0.00256288 s/iter 17.692790 +gpu 0 iter : 22 Arret : 0.000413689 s/iter 17.539980 +gpu 0 iter : 23 Arret : 0.0010819 s/iter 17.582527 +gpu 0 iter : 24 Arret : 0.000517706 s/iter 17.387151 +gpu 0 iter : 25 Arret : 1.40294E-05 s/iter 17.415382 +gpu 0 iter : 26 Arret : 1.44098E-06 s/iter 17.345061 +gpu 0 iter : 27 Arret : 2.93009E-09 s/iter 16.538716 +gpu 0 iter : 28 Arret : 8.5314E-15 s/iter 16.484147 +temps : 525.532 seconde(s) +Nb iterations : 28 +Nb de depassements de capacite exponentielle : 0 +Precision : 5.38109E-08 +Stabilite : 8.5314E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540365 +i* 0.841431| 1| 4.39062E-13 +i* 5.83011E-13| +| 2| -0.553493 +i* -0.832854| 1|-5.02858E-13 +i* 3.83374E-15| +| 3| -0.579338 +i* -0.815087| 1| 4.42365E-13 +i* 2.65846E-14| +| 4| 0.592057 +i* 0.805896| 1| 2.06783E-13 +i* 1.94549E-13| +| 5| -0.604613 +i* -0.796519| 1| 2.39135E-13 +i* 2.96967E-13| +| 6| 0.617037 +i* 0.786934| 1|-3.70964E-13 +i* 2.85104E-13| +| 7| -0.629293 +i* -0.777168| 1| 3.4002E-13 +i* 1.14925E-14| +| 8| 0.641411 +i* 0.767198| 1|-6.01835E-13 +i* 5.70316E-13| +| 9| -0.653354 +i* -0.757052| 1| 3.00003E-14 +i* 4.1084E-13| +| 10| 0.665153 +i* 0.746707| 1|-9.55243E-14 +i* 7.739E-13| +| 11| -0.676773 +i* -0.736192| 1|-3.70891E-13 +i* 4.31963E-14| +| 12| 0.688242 +i* 0.725482| 1| 4.17319E-13 +i*-2.25125E-13| +| 13| -0.699526 +i* -0.714607| 1|-1.55074E-13 +i* 3.9467E-13| +| 14| 0.710653 +i* 0.703543| 1|-7.94843E-13 +i* 5.61671E-13| +| 15| -0.721591 +i* -0.69232| 1|-8.20351E-14 +i* 3.39909E-13| +| 16| 0.732366 +i* 0.680912| 1| 5.01595E-13 +i* 2.59279E-13| +| 17| -0.742946 +i* -0.669351| 1|-1.90181E-13 +i* 1.23972E-13| +| 18| 0.753358 +i* 0.657611| 1|-7.14661E-13 +i*-3.96187E-13| +| 19| -0.76357 +i* -0.645725| 1|-3.31242E-13 +i*-8.50865E-14| +| 20| 0.773609 +i* 0.633664| 1|-7.93813E-13 +i* 2.09313E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 1 +zone limite de 'log-exp' 1.00051 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 1 (of 4) uses CUDA device 1 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 3 (of 4) uses CUDA device 3 +gpu 2 dimgrid 2735 dimblock 256 degrePoly 700000 +gpu 2 dimgrid2 684 start 350080 size 175040 +gpu 0 dimgrid 2735 dimblock 256 degrePoly 700000 +gpu 1 dimgrid 2735 dimblock 256 degrePoly 700000 +gpu 1 dimgrid2 684 start 175040 size 175040 +gpu 0 dimgrid2 684 start 0 size 175040 +gpu 3 dimgrid 2735 dimblock 256 degrePoly 700000 +gpu 3 dimgrid2 684 start 525120 size 175040 +gpu 0 iter : 1 Arret : 4.05179E-06 s/iter 26.057760 +gpu 0 iter : 2 Arret : 3.69041E-06 s/iter 26.006401 +gpu 0 iter : 3 Arret : 3.54349E-06 s/iter 26.017285 +gpu 0 iter : 4 Arret : 3.54342E-06 s/iter 26.011286 +gpu 0 iter : 5 Arret : 3.59693E-06 s/iter 26.022969 +gpu 0 iter : 6 Arret : 3.48529E-06 s/iter 26.021812 +gpu 0 iter : 7 Arret : 3.57662E-06 s/iter 26.011888 +gpu 0 iter : 8 Arret : 3.69147E-06 s/iter 26.008709 +gpu 0 iter : 9 Arret : 3.94782E-06 s/iter 26.004937 +gpu 0 iter : 10 Arret : 6.25107E-05 s/iter 26.012739 +gpu 0 iter : 11 Arret : 0.00192614 s/iter 26.023084 +gpu 0 iter : 12 Arret : 0.00191367 s/iter 26.017884 +gpu 0 iter : 13 Arret : 0.0032574 s/iter 26.009004 +gpu 0 iter : 14 Arret : 0.00729301 s/iter 35.180983 +gpu 0 iter : 15 Arret : 0.00245317 s/iter 26.015276 +gpu 0 iter : 16 Arret : 0.00433319 s/iter 25.893105 +gpu 0 iter : 17 Arret : 0.00843918 s/iter 31.680916 +gpu 0 iter : 18 Arret : 0.00512235 s/iter 31.753281 +gpu 0 iter : 19 Arret : 0.161408 s/iter 28.844658 +gpu 0 iter : 20 Arret : 0.0369396 s/iter 28.748462 +gpu 0 iter : 21 Arret : 0.0443209 s/iter 28.918638 +gpu 0 iter : 22 Arret : 0.00926227 s/iter 28.518098 +gpu 0 iter : 23 Arret : 0.10139 s/iter 28.915161 +gpu 0 iter : 24 Arret : 0.087367 s/iter 28.998391 +gpu 0 iter : 25 Arret : 0.00915331 s/iter 28.869297 +gpu 0 iter : 26 Arret : 0.000166928 s/iter 25.732016 +gpu 0 iter : 27 Arret : 8.36929E-05 s/iter 25.736037 +gpu 0 iter : 28 Arret : 1.72536E-05 s/iter 25.733697 +gpu 0 iter : 29 Arret : 7.0611E-08 s/iter 25.745297 +gpu 0 iter : 30 Arret : 2.0544E-12 s/iter 25.733511 +gpu 0 iter : 31 Arret : 1.57009E-16 s/iter 25.739637 +temps : 846.791 seconde(s) +Nb iterations : 31 +Nb de depassements de capacite exponentielle : 0 +Precision : 7.46262E-08 +Stabilite : 1.57009E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540352 +i* 0.841439| 1| 4.39978E-13 +i* 6.25043E-13| +| 2| -0.996034 +i* 0.0889731| 1| 2.2073E-13 +i* 1.55296E-13| +| 3| 0.439836 +i* -0.898078| 1|-3.55927E-13 +i*-1.21738E-13| +| 4| 0.38266 +i* -0.923889| 1|-2.56142E-13 +i*-7.02285E-14| +| 5| -0.988496 +i* 0.15125| 1|-1.52652E-13 +i*-1.11329E-13| +| 6| 0.641421 +i* 0.767189| 1|-1.31044E-13 +i* 5.61736E-13| +| 7| 0.323979 +i* -0.946064| 1|-4.52336E-13 +i* 8.74596E-14| +| 8| -0.977067 +i* 0.212932| 1| 8.58341E-14 +i* 1.73412E-13| +| 9| 0.688262 +i* 0.725462| 1| 4.28754E-14 +i* 1.08849E-12| +| 10| 0.264022 +i* -0.964517| 1|-3.63883E-13 +i*-8.14886E-14| +| 11| -0.961793 +i* 0.273776| 1| -3.0213E-13 +i*-2.13897E-13| +| 12| 0.732395 +i* 0.68088| 1|-3.65194E-14 +i* 7.95483E-13| +| 13| 0.203027 +i* -0.979173| 1|-3.14502E-13 +i* 2.96924E-13| +| 14| -0.942735 +i* 0.333543| 1| 1.82947E-13 +i*-4.73458E-14| +| 15| 0.773646 +i* 0.633619| 1| 2.24352E-13 +i* 2.79674E-13| +| 16| 0.141232 +i* -0.989977| 1| -1.0035E-13 +i* 1.5693E-13| +| 17| -0.919967 +i* 0.391997| 1| 2.89213E-14 +i*-1.86252E-13| +| 18| 0.811852 +i* 0.583864| 1|-1.59939E-12 +i*-4.13669E-13| +| 19| 0.0788818 +i* -0.996884| 1|-2.83003E-13 +i* 1.04711E-13| +| 20| -0.893578 +i* 0.448908| 1| 4.59736E-14 +i* 1.31414E-13| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 1 +zone limite de 'log-exp' 1.00044 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 1 (of 4) uses CUDA device 1 +gpu 3 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 3 dimgrid2 782 start 600000 size 200000 +gpu 2 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 2 dimgrid2 782 start 400000 size 200000 +gpu 0 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 0 dimgrid2 782 start 0 size 200000 +gpu 1 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 1 dimgrid2 782 start 200000 size 200000 +gpu 0 iter : 1 Arret : 3.03518E-06 s/iter 34.140422 +gpu 0 iter : 2 Arret : 3.08048E-06 s/iter 34.112195 +gpu 0 iter : 3 Arret : 3.01956E-06 s/iter 34.096993 +gpu 0 iter : 4 Arret : 3.09293E-06 s/iter 34.110543 +gpu 0 iter : 5 Arret : 3.08006E-06 s/iter 34.076662 +gpu 0 iter : 6 Arret : 3.01434E-06 s/iter 34.084058 +gpu 0 iter : 7 Arret : 3.18584E-06 s/iter 34.136831 +gpu 0 iter : 8 Arret : 3.3042E-06 s/iter 34.131267 +gpu 0 iter : 9 Arret : 4.06872E-06 s/iter 34.106772 +gpu 0 iter : 10 Arret : 8.81449E-06 s/iter 34.108408 +gpu 0 iter : 11 Arret : 0.000633965 s/iter 34.129789 +gpu 0 iter : 12 Arret : 0.00092939 s/iter 34.108349 +gpu 0 iter : 13 Arret : 2.168 s/iter 34.099124 +gpu 0 iter : 14 Arret : 0.959162 s/iter 39.514454 +gpu 0 iter : 15 Arret : 1.25264 s/iter 39.163345 +gpu 0 iter : 16 Arret : 0.0492202 s/iter 41.068013 +gpu 0 iter : 17 Arret : 0.0215834 s/iter 32.733350 +gpu 0 iter : 18 Arret : 0.0247446 s/iter 37.879052 +gpu 0 iter : 19 Arret : 0.0179454 s/iter 29.650763 +gpu 0 iter : 20 Arret : 0.0206764 s/iter 29.407317 +gpu 0 iter : 21 Arret : 0.0222049 s/iter 35.012713 +gpu 0 iter : 22 Arret : 0.00255914 s/iter 27.067142 +gpu 0 iter : 23 Arret : 0.000919373 s/iter 25.980531 +gpu 0 iter : 24 Arret : 0.0031468 s/iter 24.573430 +gpu 0 iter : 25 Arret : 0.00100214 s/iter 23.918440 +gpu 0 iter : 26 Arret : 4.12095E-06 s/iter 23.670339 +gpu 0 iter : 27 Arret : 1.25002E-07 s/iter 23.794441 +gpu 0 iter : 28 Arret : 1.03352E-11 s/iter 23.663739 +gpu 0 iter : 29 Arret : 1.57009E-16 s/iter 23.563580 +temps : 925.912 seconde(s) +Nb iterations : 29 +Nb de depassements de capacite exponentielle : 0 +Precision : 6.26383E-08 +Stabilite : 1.11022E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540349 +i* 0.841441| 1|-1.16344E-13 +i* 9.55619E-13| +| 2| 0.592061 +i* 0.805893| 1|-1.57249E-13 +i*-4.43364E-13| +| 3| 0.617051 +i* 0.786923| 1|-6.42805E-13 +i*-3.49094E-13| +| 4| 0.641434 +i* 0.767178| 1| 1.00022E-12 +i*-5.90578E-13| +| 5| 0.665186 +i* 0.746678| 1|-2.53998E-14 +i*-1.14684E-12| +| 6| 0.688283 +i* 0.725442| 1|-8.68732E-13 +i* 8.52696E-13| +| 7| 0.710703 +i* 0.703493| 1| 2.02581E-13 +i* 4.54699E-13| +| 8| 0.732422 +i* 0.680851| 1|-5.22353E-13 +i*-3.99873E-13| +| 9| 0.753421 +i* 0.657538| 1| 1.23356E-13 +i*-1.05986E-12| +| 10| 0.773678 +i* 0.633579| 1|-6.75196E-13 +i* 3.60108E-13| +| 11| 0.793174 +i* 0.608995| 1| 4.43853E-13 +i*-1.42398E-12| +| 12| 0.811888 +i* 0.583813| 1|-4.10491E-13 +i*-4.46651E-13| +| 13| 0.829804 +i* 0.558055| 1| 1.30045E-12 +i* 1.12788E-13| +| 14| 0.846902 +i* 0.531748| 1|-8.09419E-13 +i* 4.98091E-13| +| 15| 0.863167 +i* 0.504918| 1| 2.98522E-13 +i* 3.81547E-13| +| 16| 0.878582 +i* 0.477591| 1|-3.06581E-13 +i*-6.95869E-13| +| 17| 0.893133 +i* 0.449793| 1| 1.24355E-13 +i* -1.3239E-12| +| 18| 0.906804 +i* 0.421553| 1|-1.23117E-12 +i*-5.57117E-13| +| 19| 0.919582 +i* 0.392898| 1|-1.03648E-12 +i* 2.90445E-14| +| 20| 0.931455 +i* 0.363856| 1|-6.42708E-13 +i*-1.50318E-12| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 1 diff --git a/Simulations/full_openmp/full_openmp_4GPU.sge b/Simulations/full_openmp/full_openmp_4GPU.sge new file mode 100644 index 0000000..4aab3cf --- /dev/null +++ b/Simulations/full_openmp/full_openmp_4GPU.sge @@ -0,0 +1,27 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=4 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -pe openmp 4 +#$ -V +#$ -cwd +#$ -N full_openmp_4GPU + +module load gcc/4.9.0 +module load cuda/7.0 + + +./template -r -i 60000 40000 +./template -r -i 150000 50000 +./template -r -i 250000 150000 +./template -r -i 350000 250000 +./template -r -i 500000 300000 +./template -r -i 600000 400000 +./template -r -i 700000 500000 +./template -r -i 800000 600000 +#./template -r -i 900000 700000 +#./template -r -i 1000000 800000 +#./template -r -i 1500000 500000 + + diff --git a/Simulations/mpi.txt b/Simulations/mpi.txt new file mode 100644 index 0000000..e7156d7 --- /dev/null +++ b/Simulations/mpi.txt @@ -0,0 +1,9 @@ +#degree S1GPU S2GPU S3GPU S4GPU F1GPU F2GPU F3GPU F4GPU +100000 16.1017 8.65634 7.13273 4.60588 24.1491 15.9313 16.3645 13.0123 +200000 63.5651 40.9684 39.5342 21.5922 146.49 78.4263 63.3058 51.6331 +400000 452.145 122.138 81.0542 63.5457 300.171 169.022 122.621 98.5095 +600000 646.009 297.134 193.628 153.471 757.352 457.417 350.829 289.016 +800000 1656.28 746.426 545.367 282.444 1148.46 637.538 410.952 358.278 +1000000 3173.19 812.655 542.745 440.06 2059.61 1055.82 688.615 539.966 +1200000 3906.03 1647.22 1617.65 1762.58 2827.9 1484.54 985.364 871.12 +1400000 3229.79 1991.85 1707.73 1478.01 3326.77 1766.95 1218.9 917.174 \ No newline at end of file diff --git a/Simulations/mpivsomp.txt b/Simulations/mpivsomp.txt new file mode 100644 index 0000000..4de459d --- /dev/null +++ b/Simulations/mpivsomp.txt @@ -0,0 +1,5 @@ +#nbGPU SMPI.14 SOMP.14 FMPI.14 FOMP.14 SMPI.8 SOMP.8 FMPI.8 FOMP.8 SMPI.2 SOMP.2 FMPI.2 FOMP.2 +1 3229.79 3523.14 3326.77 3442.42 1656.28 1180.82 1148.46 1194.76 63.5651 70.1186 146.49 151.38 +2 1991.85 2371.12 1766.95 1778.69 746.426 576.437 637.538 628.842 40.9684 35.62 78.4263 82.6744 +3 1707.73 1786.83 1218.9 1191.46 545.367 351.42 410.952 432.911 39.5342 37.8394 63.3058 59.7653 +4 1478.01 1704.89 917.174 925.912 282.444 258.82 358.278 337.034 21.5922 22.9576 51.6331 56.2628 \ No newline at end of file diff --git a/Simulations/openmp.txt b/Simulations/openmp.txt new file mode 100644 index 0000000..14d6a4d --- /dev/null +++ b/Simulations/openmp.txt @@ -0,0 +1,9 @@ +#degree S1GPU S2GPU S3GPU S4GPU F1GPU F2GPU F3GPU F4GPU +100000 16.1926 9.12342 8.00955 5.86914 24.3248 16.8078 17.7034 13.5366 +200000 70.1186 35.62 37.8394 22.9576 151.38 82.6744 59.7653 56.2628 +400000 248.893 122.327 86.1208 68.0633 296.321 161.369 112.147 89.8766 +600000 589.718 297.898 202.419 154.313 833.807 458.792 334.994 279.804 +800000 1180.82 576.437 351.42 258.82 1194.76 628.842 432.911 337.034 +1000000 1621.79 850.208 598.968 422.324 1931.46 1049.55 693.102 525.532 +1200000 4148.3 1631.66 2056.31 1556.58 3017.33 1589.66 1053.03 846.791 +1400000 3523.14 2371.12 1786.83 1704.89 3442.42 1778.69 1191.46 925.912 \ No newline at end of file diff --git a/Simulations/sparse_mpi/sparse_mpi_1GPU.o140032 b/Simulations/sparse_mpi/sparse_mpi_1GPU.o140032 new file mode 100644 index 0000000..42d7416 --- /dev/null +++ b/Simulations/sparse_mpi/sparse_mpi_1GPU.o140032 @@ -0,0 +1,642 @@ +REMAINING: 1 +Taking GPU #3 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^40000 + (-10 +i*0)*x^60000 + (1 +i*0)*x^100000 + +(-4000 +i*0)*x^39999 + (-600000 +i*0)*x^59999 + (100000 +i*0)*x^99999 + +zone limite de 'log-exp' 1.00356 +dimgrid 391 dimblock 256 degrePoly 100000 +proc 0, start 0 size 100096 +proc 0 start 0 size 100096 +iter : 1 Arret : 0.00679606 s/iter 0.774483 +iter : 2 Arret : 0.0240773 s/iter 0.852783 +iter : 3 Arret : 0.0190607 s/iter 0.841876 +iter : 4 Arret : 0.00753578 s/iter 0.774557 +iter : 5 Arret : 0.0903866 s/iter 0.774496 +iter : 6 Arret : 0.0766923 s/iter 0.843947 +iter : 7 Arret : 0.0135773 s/iter 0.851241 +iter : 8 Arret : 0.00988122 s/iter 0.846496 +iter : 9 Arret : 0.00740796 s/iter 0.842720 +iter : 10 Arret : 0.00490463 s/iter 0.774748 +iter : 11 Arret : 0.00478656 s/iter 0.774554 +iter : 12 Arret : 0.00116597 s/iter 0.774390 +iter : 13 Arret : 0.000965078 s/iter 0.774238 +iter : 14 Arret : 0.000208722 s/iter 0.774212 +iter : 15 Arret : 0.00022059 s/iter 0.774088 +iter : 16 Arret : 2.47061E-05 s/iter 0.774123 +iter : 17 Arret : 2.20962E-07 s/iter 0.774117 +iter : 18 Arret : 7.04174E-10 s/iter 0.774131 +iter : 19 Arret : 2.22676E-12 s/iter 0.773993 +iter : 20 Arret : 7.50806E-15 s/iter 0.774073 +temps : 16.1017 seconde(s) +Nb iterations : 20 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.61117E-09 +Stabilite : 7.50806E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540308 +i* 0.841422| 0.999962|-1.95866E-12 +i*-4.55465E-13| +| 2| -0.113164 +i* 0.993538| 0.999962|-4.34919E-12 +i* 9.60242E-13| +| 3| -0.226711 +i* -0.973923| 0.999962|-4.27658E-13 +i* 6.01027E-13| +| 4| -0.715763 +i* 0.698289| 0.999962| 9.11271E-13 +i* 2.47219E-12| +| 5| 0.439922 +i* -0.897993| 0.999962|-3.49498E-13 +i* 1.66432E-12| +| 6| -0.996021 +i* 0.0886823| 0.999962| 2.0266E-12 +i*-2.01894E-13| +| 7| 0.908546 +i* -0.417692| 0.999962| 4.78506E-13 +i* 1.54377E-13| +| 8| -0.827813 +i* -0.560935| 0.999962| 9.76996E-13 +i*-2.04309E-12| +| 9| 0.968049 +i* 0.250607| 0.999962|-1.07025E-13 +i*-1.15224E-12| +| 10| -0.286815 +i* -0.957946| 0.999962|-6.55254E-13 +i* 1.20869E-12| +| 11| 0.591653 +i* 0.806145| 0.999962|-9.87654E-13 +i*-3.03635E-12| +| 12| -0.0511836 +i* 0.998651| 0.999962|-2.22622E-12 +i*-3.69013E-14| +| 13| -0.67097 +i* 0.741432| 0.999962|-8.03801E-14 +i*-1.68204E-12| +| 14| 0.383249 +i* -0.923603| 0.999962|-1.29119E-12 +i*-1.37426E-12| +| 15| -0.988582 +i* 0.150427| 0.999962|-1.54698E-12 +i*-6.48537E-13| +| 16| 0.880824 +i* -0.473363| 0.999962| 1.58029E-12 +i*-2.34379E-12| +| 17| -0.861082 +i* -0.508391| 0.999962| 9.8066E-13 +i* 3.40478E-12| +| 18| 0.981756 +i* 0.189945| 0.999962|-9.84324E-13 +i*-1.03573E-12| +| 19| -0.345809 +i* -0.938264| 0.999962| 1.03906E-12 +i* 1.95398E-12| +| 20| 0.640621 +i* 0.767807| 0.999962|-6.98774E-13 +i* 1.13798E-12| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 0.999962 +40000 racines de module = 1.00006 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^50000 + (-10 +i*0)*x^150000 + (1 +i*0)*x^200000 + +(-5000 +i*0)*x^49999 + (-1.5E+06 +i*0)*x^149999 + (200000 +i*0)*x^199999 + +zone limite de 'log-exp' 1.00178 +dimgrid 782 dimblock 256 degrePoly 200000 +proc 0, start 0 size 200192 +proc 0 start 0 size 200192 +iter : 1 Arret : 0.000149243 s/iter 3.009897 +iter : 2 Arret : 0.000107669 s/iter 3.006186 +iter : 3 Arret : 0.000104952 s/iter 3.008833 +iter : 4 Arret : 0.000608712 s/iter 3.007077 +iter : 5 Arret : 0.00102516 s/iter 3.006467 +iter : 6 Arret : 0.00265088 s/iter 3.006726 +iter : 7 Arret : 0.0373682 s/iter 3.008694 +iter : 8 Arret : 0.0563565 s/iter 3.008459 +iter : 9 Arret : 0.130843 s/iter 3.042271 +iter : 10 Arret : 0.213629 s/iter 3.036578 +iter : 11 Arret : 0.153708 s/iter 3.075704 +iter : 12 Arret : 0.0916516 s/iter 3.036504 +iter : 13 Arret : 0.0619829 s/iter 3.025077 +iter : 14 Arret : 0.0382728 s/iter 3.001649 +iter : 15 Arret : 0.0125846 s/iter 3.026965 +iter : 16 Arret : 0.00175812 s/iter 3.007895 +iter : 17 Arret : 0.000317125 s/iter 3.006004 +iter : 18 Arret : 1.05887E-05 s/iter 3.006536 +iter : 19 Arret : 5.5903E-08 s/iter 3.012414 +iter : 20 Arret : 5.55768E-12 s/iter 3.013007 +iter : 21 Arret : 5.57854E-16 s/iter 3.013024 +temps : 63.5651 seconde(s) +Nb iterations : 21 +Nb de depassements de capacite exponentielle : 0 +Precision : 9.52377E-08 +Stabilite : 5.57854E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540195 +i* 0.841595| 1.00005|-2.98043E-09 +i*-3.27611E-08| +| 2| -0.837195 +i* 0.546877| 0.999985| 7.09943E-12 +i* 5.1133E-12| +| 3| -0.553418 +i* -0.832885| 0.999985| -1.9722E-12 +i*-7.40397E-12| +| 4| 0.828525 +i* -0.559925| 0.999985|-4.34675E-12 +i* 1.07137E-12| +| 5| -0.819774 +i* 0.572768| 1.00005| 2.53887E-08 +i* 2.42315E-09| +| 6| -0.57917 +i* -0.815188| 0.999985|-5.13034E-12 +i*-1.52645E-12| +| 7| 0.810626 +i* -0.585537| 0.999985|-6.36846E-12 +i*-5.86797E-12| +| 8| 0.591869 +i* 0.806015| 0.999985| 1.73195E-13 +i* 8.72591E-12| +| 9| -0.801379 +i* 0.598131| 0.999985| -1.2701E-12 +i* 3.96189E-12| +| 10| -0.60436 +i* -0.796769| 1.00005|-3.33815E-08 +i* 3.89061E-08| +| 11| 0.791937 +i* -0.610578| 0.999985| 6.0707E-13 +i* 1.52922E-12| +| 12| 0.616763 +i* 0.78713| 0.999985|-4.48042E-12 +i* -2.6295E-12| +| 13| -0.782301 +i* 0.622877| 0.999985|-2.15827E-12 +i*-6.27114E-12| +| 14| -0.628985 +i* -0.777398| 0.999985|-4.05476E-12 +i*-5.17236E-12| +| 15| 0.772548 +i* -0.635029| 1.00005| 1.1634E-09 +i* 1.87351E-08| +| 16| 0.641054 +i* 0.767476| 0.999985|-3.47633E-12 +i* 1.20617E-11| +| 17| -0.762458 +i* 0.647014| 0.999985|-7.74447E-12 +i* 7.566E-12| +| 18| -0.652967 +i* -0.757366| 0.999985| 5.10392E-12 +i*-6.61069E-12| +| 19| 0.752229 +i* -0.658879| 0.999985| 1.34497E-11 +i*-6.49125E-12| +| 20| 0.664729 +i* 0.747146| 1.00005|-1.71597E-08 +i* 8.68463E-09| ++---+----------------------------+------------+----------------------------+ +50000 racines de module = 1.00005 +150000 racines de module = 0.999985 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^150000 + (-10 +i*0)*x^250000 + (1 +i*0)*x^400000 + +(-15000 +i*0)*x^149999 + (-2.5E+06 +i*0)*x^249999 + (400000 +i*0)*x^399999 + +zone limite de 'log-exp' 1.00089 +dimgrid 1563 dimblock 256 degrePoly 400000 +proc 0, start 0 size 400128 +proc 0 start 0 size 400128 +iter : 1 Arret : 0.00730522 s/iter 11.729578 +iter : 2 Arret : 8.77601 s/iter 11.759538 +iter : 3 Arret : 1.00039 s/iter 11.791553 +iter : 4 Arret : 1.66037 s/iter 11.980569 +iter : 5 Arret : 1.60415 s/iter 11.887203 +iter : 6 Arret : 1.09308 s/iter 11.903519 +iter : 7 Arret : 1.03725 s/iter 11.950159 +iter : 8 Arret : 0.785865 s/iter 12.039659 +iter : 9 Arret : 0.676674 s/iter 12.064157 +iter : 10 Arret : 0.653102 s/iter 12.043182 +iter : 11 Arret : 0.61815 s/iter 12.032295 +iter : 12 Arret : 0.572922 s/iter 11.944839 +iter : 13 Arret : 0.514395 s/iter 11.923777 +iter : 14 Arret : 0.460854 s/iter 11.923746 +iter : 15 Arret : 0.546102 s/iter 11.925322 +iter : 16 Arret : 0.44308 s/iter 11.925810 +iter : 17 Arret : 0.411387 s/iter 11.926822 +iter : 18 Arret : 0.391387 s/iter 11.925774 +iter : 19 Arret : 0.377716 s/iter 11.927355 +iter : 20 Arret : 0.368007 s/iter 11.928976 +iter : 21 Arret : 0.476382 s/iter 11.927179 +iter : 22 Arret : 0.434562 s/iter 11.925163 +iter : 23 Arret : 0.42152 s/iter 11.926021 +iter : 24 Arret : 0.423381 s/iter 11.925847 +iter : 25 Arret : 0.433232 s/iter 11.929953 +iter : 26 Arret : 0.401895 s/iter 11.931379 +iter : 27 Arret : 0.411949 s/iter 11.917976 +iter : 28 Arret : 0.186193 s/iter 11.913066 +iter : 29 Arret : 0.106074 s/iter 11.943724 +iter : 30 Arret : 0.0412794 s/iter 11.831994 +iter : 31 Arret : 0.0419846 s/iter 11.810695 +iter : 32 Arret : 0.0167499 s/iter 11.814252 +iter : 33 Arret : 0.00536444 s/iter 11.787890 +iter : 34 Arret : 0.000655097 s/iter 11.754599 +iter : 35 Arret : 3.44296E-07 s/iter 11.747199 +iter : 36 Arret : 7.50023E-10 s/iter 11.751889 +iter : 37 Arret : 1.61565E-12 s/iter 11.752682 +iter : 38 Arret : 3.38203E-15 s/iter 11.747277 +temps : 452.145 seconde(s) +Nb iterations : 38 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.49185E-08 +Stabilite : 3.38203E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540313 +i* 0.841453| 0.999991| 9.34197E-12 +i*-1.23633E-11| +| 2| -0.998329 +i* 0.057622| 0.999991| 4.43912E-12 +i* 1.27665E-12| +| 3| 0.439867 +i* -0.898052| 0.999991|-8.50653E-12 +i*-8.85586E-12| +| 4| -0.996033 +i* 0.0888768| 0.999991|-3.15592E-12 +i* 1.17456E-12| +| 5| 0.411533 +i* -0.911385| 0.999991|-2.45048E-12 +i* 4.6238E-12| +| 6| 0.59196 +i* 0.805956| 0.999991| 5.24358E-13 +i*-8.53073E-12| +| 7| -0.992759 +i* 0.120044| 0.999991| 2.58804E-12 +i* 2.47274E-12| +| 8| 0.382796 +i* -0.923823| 0.999991|-1.63092E-11 +i* 4.26312E-12| +| 9| 0.616925 +i* 0.78701| 0.999991| 4.27514E-12 +i*-1.13966E-11| +| 10| -0.98851 +i* 0.151094| 0.999991| 1.67755E-11 +i* 4.06477E-12| +| 11| 0.35366 +i* -0.935364| 0.999991|-1.92664E-11 +i* 1.19958E-11| +| 12| 0.641283 +i* 0.767292| 0.999991| 1.73468E-11 +i*-3.74729E-12| +| 13| -0.983286 +i* 0.18202| 0.999991| 3.21676E-12 +i*-9.48297E-13| +| 14| 0.324176 +i* -0.945987| 0.999991|-5.20695E-12 +i*-7.06984E-12| +| 15| 0.66503 +i* 0.746804| 0.999991| 5.74873E-13 +i* 8.53884E-12| +| 16| -0.977104 +i* 0.212717| 0.999991|-7.47291E-12 +i*-5.77033E-12| +| 17| 0.294374 +i* -0.955681| 0.999991| 1.82907E-11 +i*-2.45448E-12| +| 18| 0.688087 +i* 0.725616| 0.999991|-1.67164E-11 +i*-1.12573E-11| +| 19| -0.969965 +i* 0.243206| 0.999991| 6.88072E-12 +i* 3.20268E-13| +| 20| 0.264283 +i* -0.964436| 0.999991|-6.93356E-12 +i*-6.23118E-12| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 0.999991 +150000 racines de module = 1.00002 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^250000 + (-10 +i*0)*x^350000 + (1 +i*0)*x^600000 + +(-25000 +i*0)*x^249999 + (-3.5E+06 +i*0)*x^349999 + (600000 +i*0)*x^599999 + +zone limite de 'log-exp' 1.00059 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 0, start 0 size 600064 +proc 0 start 0 size 600064 +iter : 1 Arret : 0.00438586 s/iter 26.290359 +iter : 2 Arret : 0.424079 s/iter 26.667931 +iter : 3 Arret : 0.949363 s/iter 26.761853 +iter : 4 Arret : 11.5671 s/iter 26.845045 +iter : 5 Arret : 0.975219 s/iter 27.289618 +iter : 6 Arret : 9.61533 s/iter 27.433768 +iter : 7 Arret : 1.85508 s/iter 27.722970 +iter : 8 Arret : 0.857551 s/iter 27.711823 +iter : 9 Arret : 1.17971 s/iter 27.827595 +iter : 10 Arret : 0.452875 s/iter 27.966012 +iter : 11 Arret : 0.892919 s/iter 27.734509 +iter : 12 Arret : 0.512768 s/iter 27.492632 +iter : 13 Arret : 0.378076 s/iter 27.324440 +iter : 14 Arret : 0.0806363 s/iter 26.960487 +iter : 15 Arret : 0.0453167 s/iter 26.499557 +iter : 16 Arret : 0.0240592 s/iter 26.395465 +iter : 17 Arret : 0.0199765 s/iter 26.315790 +iter : 18 Arret : 0.00860028 s/iter 26.347303 +iter : 19 Arret : 0.00210663 s/iter 26.347784 +iter : 20 Arret : 5.04056E-05 s/iter 26.356018 +iter : 21 Arret : 4.72721E-06 s/iter 26.365127 +iter : 22 Arret : 3.9901E-08 s/iter 26.360411 +iter : 23 Arret : 1.57869E-10 s/iter 26.353428 +iter : 24 Arret : 6.28564E-13 s/iter 26.351250 +temps : 646.009 seconde(s) +Nb iterations : 24 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.58777E-07 +Stabilite : 6.28564E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540302 +i* 0.841463| 0.999993| 8.34199E-12 +i* -1.9051E-11| +| 2| -0.553438 +i* -0.832883| 0.999993|-4.48197E-12 +i* 2.11486E-11| +| 3| -0.579282 +i* -0.815119| 0.999993|-1.44751E-12 +i* 7.66798E-12| +| 4| 0.592043 +i* 0.805898| 0.999993|-1.75726E-12 +i*-2.31848E-11| +| 5| -0.604557 +i* -0.796554| 0.999993|-2.82974E-12 +i* 9.99473E-12| +| 6| 0.61698 +i* 0.78697| 0.999993| 9.01823E-12 +i*-5.69156E-12| +| 7| -0.629237 +i* -0.777205| 0.999993|-2.92122E-12 +i*-4.85867E-12| +| 8| 0.641354 +i* 0.767237| 0.999993| 1.4493E-11 +i* 1.3687E-11| +| 9| -0.653299 +i* -0.757092| 0.999993|-8.22453E-13 +i* 2.82818E-12| +| 10| 0.665096 +i* 0.746749| 0.999993| -1.2145E-11 +i* 1.89129E-11| +| 11| -0.676717 +i* -0.736234| 0.999993|-1.26079E-11 +i*-1.25073E-11| +| 12| 0.688185 +i* 0.725526| 0.999993| 2.69875E-11 +i* 1.65411E-11| +| 13| -0.699509 +i* -0.714614| 0.999993| 1.85989E-11 +i*-4.93269E-12| +| 14| 0.710597 +i* 0.70359| 0.999993| 1.28564E-11 +i* 1.56626E-11| +| 15| -0.721517 +i* -0.69241| 1.00001| 1.76709E-09 +i*-4.04041E-09| +| 16| 0.73231 +i* 0.680962| 0.999993| 1.34706E-11 +i*-4.43489E-12| +| 17| -0.742916 +i* -0.669375| 0.999993| 1.59349E-11 +i* 1.71025E-11| +| 18| 0.753326 +i* 0.657637| 0.999993| 2.26833E-11 +i* 1.58007E-11| +| 19| -0.76354 +i* -0.64575| 0.999993| 2.24043E-11 +i*-1.30496E-12| +| 20| 0.773555 +i* 0.633743| 1.00001| 3.19794E-09 +i*-4.58601E-10| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 0.999993 +250000 racines de module = 1.00001 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^300000 + (-10 +i*0)*x^500000 + (1 +i*0)*x^800000 + +(-30000 +i*0)*x^299999 + (-5E+06 +i*0)*x^499999 + (800000 +i*0)*x^799999 + +zone limite de 'log-exp' 1.00044 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 0, start 0 size 800000 +proc 0 start 0 size 800000 +iter : 1 Arret : 0.00154846 s/iter 46.736609 +iter : 2 Arret : 0.00623603 s/iter 46.773178 +iter : 3 Arret : 0.0858187 s/iter 46.841571 +iter : 4 Arret : 1.67232 s/iter 47.156772 +iter : 5 Arret : 1.01806 s/iter 47.406800 +iter : 6 Arret : 1.57506 s/iter 47.457844 +iter : 7 Arret : 1.13953 s/iter 47.697558 +iter : 8 Arret : 0.73881 s/iter 48.174119 +iter : 9 Arret : 0.626435 s/iter 48.572632 +iter : 10 Arret : 0.622256 s/iter 48.458622 +iter : 11 Arret : 0.692053 s/iter 48.464982 +iter : 12 Arret : 1.00181 s/iter 48.341828 +iter : 13 Arret : 0.551097 s/iter 48.068502 +iter : 14 Arret : 1.04389 s/iter 47.905646 +iter : 15 Arret : 1.21414 s/iter 47.815372 +iter : 16 Arret : 2.39612 s/iter 47.598487 +iter : 17 Arret : 0.78181 s/iter 47.580209 +iter : 18 Arret : 1.57712 s/iter 47.513484 +iter : 19 Arret : 0.980627 s/iter 47.491805 +iter : 20 Arret : 2.61529 s/iter 47.318510 +iter : 21 Arret : 0.836959 s/iter 47.192301 +iter : 22 Arret : 0.6961 s/iter 47.065027 +iter : 23 Arret : 1.08455 s/iter 47.015412 +iter : 24 Arret : 0.186278 s/iter 46.892588 +iter : 25 Arret : 0.155923 s/iter 46.834330 +iter : 26 Arret : 0.090441 s/iter 46.771351 +iter : 27 Arret : 0.093651 s/iter 46.749380 +iter : 28 Arret : 0.0452468 s/iter 46.755619 +iter : 29 Arret : 0.00859257 s/iter 46.764196 +iter : 30 Arret : 0.00968923 s/iter 46.773667 +iter : 31 Arret : 0.00619702 s/iter 46.763704 +iter : 32 Arret : 0.000332677 s/iter 46.713764 +iter : 33 Arret : 1.75349E-07 s/iter 46.747193 +iter : 34 Arret : 4.01254E-10 s/iter 46.753422 +iter : 35 Arret : 8.64369E-13 s/iter 46.729435 +temps : 1656.28 seconde(s) +Nb iterations : 35 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.64697E-07 +Stabilite : 8.64369E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540305 +i* 0.841464| 0.999995|-5.33817E-12 +i*-1.81878E-11| +| 2| 0.592014 +i* 0.805922| 0.999995|-1.82734E-11 +i* 2.10218E-11| +| 3| 0.617007 +i* 0.786952| 0.999995| 4.23442E-11 +i* -6.2147E-12| +| 4| 0.641392 +i* 0.767207| 0.999995|-4.99742E-11 +i* 1.43873E-11| +| 5| 0.665146 +i* 0.746707| 0.999995| 2.02977E-11 +i* 7.48579E-12| +| 6| 0.688245 +i* 0.725472| 0.999995|-1.73153E-11 +i* -1.2656E-11| +| 7| 0.710667 +i* 0.703522| 0.999995| 3.69782E-12 +i* 2.3081E-12| +| 8| 0.732388 +i* 0.68088| 0.999995| 9.45355E-12 +i* 2.09024E-11| +| 9| 0.753381 +i* 0.657577| 0.999995| 3.40094E-11 +i* 1.45989E-12| +| 10| 0.77364 +i* 0.633618| 0.999995|-1.72307E-11 +i* 1.22723E-11| +| 11| 0.793138 +i* 0.609034| 0.999995| 3.89222E-12 +i* 2.21356E-11| +| 12| 0.811855 +i* 0.583851| 0.999995|-1.28337E-11 +i*-5.47207E-12| +| 13| 0.829772 +i* 0.558094| 0.999995|-1.63114E-11 +i*-1.64246E-12| +| 14| 0.846873 +i* 0.531786| 0.999995|-3.30451E-11 +i*-8.10676E-12| +| 15| 0.86314 +i* 0.504956| 0.999995|-4.00413E-12 +i* 3.04823E-11| +| 16| 0.878557 +i* 0.477628| 0.999995|-2.16493E-12 +i* 1.10533E-11| +| 17| 0.893104 +i* 0.449841| 0.999995|-1.48552E-11 +i* 1.06063E-11| +| 18| 0.906777 +i* 0.4216| 0.999995|-1.38745E-11 +i* 5.33384E-12| +| 19| 0.919557 +i* 0.392944| 0.999995| 4.13796E-11 +i*-2.48189E-11| +| 20| 0.931433 +i* 0.363901| 0.999995| 4.93219E-11 +i*-2.82651E-11| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 0.999995 +300000 racines de module = 1.00001 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^400000 + (-10 +i*0)*x^600000 + (1 +i*0)*x^1000000 + +(-40000 +i*0)*x^399999 + (-6E+06 +i*0)*x^599999 + (1E+06 +i*0)*x^999999 + +zone limite de 'log-exp' 1.00035 +dimgrid 3907 dimblock 256 degrePoly 1000000 +proc 0, start 0 size 1000192 +proc 0 start 0 size 1000192 +iter : 1 Arret : 0.00156919 s/iter 72.939595 +iter : 2 Arret : 1.90389 s/iter 73.046565 +iter : 3 Arret : 0.502696 s/iter 73.071131 +iter : 4 Arret : 1.00039 s/iter 73.810096 +iter : 5 Arret : 1.69451 s/iter 73.906653 +iter : 6 Arret : 1.26606 s/iter 73.980438 +iter : 7 Arret : 0.651915 s/iter 74.703433 +iter : 8 Arret : 0.531762 s/iter 74.806612 +iter : 9 Arret : 0.502687 s/iter 74.773948 +iter : 10 Arret : 0.48618 s/iter 74.532337 +iter : 11 Arret : 0.444215 s/iter 74.279878 +iter : 12 Arret : 0.427439 s/iter 74.140663 +iter : 13 Arret : 0.41232 s/iter 74.008804 +iter : 14 Arret : 0.406535 s/iter 74.075135 +iter : 15 Arret : 0.401671 s/iter 74.022094 +iter : 16 Arret : 0.398196 s/iter 74.055174 +iter : 17 Arret : 0.395555 s/iter 73.932752 +iter : 18 Arret : 0.394204 s/iter 74.040270 +iter : 19 Arret : 0.39412 s/iter 73.999365 +iter : 20 Arret : 0.395512 s/iter 74.042163 +iter : 21 Arret : 0.398528 s/iter 73.913334 +iter : 22 Arret : 0.404063 s/iter 74.043199 +iter : 23 Arret : 0.413614 s/iter 74.018474 +iter : 24 Arret : 0.430817 s/iter 73.977216 +iter : 25 Arret : 0.464104 s/iter 73.990264 +iter : 26 Arret : 0.534702 s/iter 73.999109 +iter : 27 Arret : 0.777706 s/iter 73.922712 +iter : 28 Arret : 0.780386 s/iter 73.805326 +iter : 29 Arret : 0.391957 s/iter 73.593419 +iter : 30 Arret : 0.489974 s/iter 73.269694 +iter : 31 Arret : 0.327545 s/iter 73.343344 +iter : 32 Arret : 0.110619 s/iter 73.177304 +iter : 33 Arret : 0.19712 s/iter 73.089524 +iter : 34 Arret : 0.288284 s/iter 73.082763 +iter : 35 Arret : 0.0226925 s/iter 73.058524 +iter : 36 Arret : 0.00572618 s/iter 73.055652 +iter : 37 Arret : 0.00398682 s/iter 72.948081 +iter : 38 Arret : 0.000421174 s/iter 72.910444 +iter : 39 Arret : 5.0226E-07 s/iter 72.907146 +iter : 40 Arret : 7.2296E-09 s/iter 72.950438 +iter : 41 Arret : 1.02029E-10 s/iter 72.929637 +iter : 42 Arret : 1.43894E-12 s/iter 72.923863 +iter : 43 Arret : 2.03366E-14 s/iter 72.908337 +temps : 3173.19 seconde(s) +Nb iterations : 43 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.65132E-08 +Stabilite : 2.03366E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841468| 0.999996| 5.07216E-12 +i* 6.41236E-12| +| 2| 0.52971 +i* 0.848174| 0.999996|-2.56639E-12 +i*-3.27674E-11| +| 3| 0.524361 +i* 0.851491| 0.999996|-2.47296E-11 +i* 1.78327E-11| +| 4| 0.51901 +i* 0.854764| 0.999996| 9.45599E-12 +i* 2.07434E-11| +| 5| 0.513629 +i* 0.858008| 0.999996| 2.32483E-11 +i* 6.70747E-12| +| 6| 0.508237 +i* 0.861213| 0.999996|-1.34339E-11 +i* 9.87854E-12| +| 7| 0.502834 +i* 0.864379| 0.999996|-2.85585E-11 +i* 6.91519E-12| +| 8| 0.497384 +i* 0.867526| 0.999996| 2.97429E-11 +i*-6.06626E-13| +| 9| 0.491932 +i* 0.870629| 0.999996|-1.74121E-11 +i*-2.86359E-11| +| 10| 0.486452 +i* 0.873703| 0.999996| 3.0312E-11 +i* 1.02214E-11| +| 11| 0.480962 +i* 0.876737| 0.999996| 1.81546E-11 +i* 8.04012E-12| +| 12| 0.475463 +i* 0.879732| 0.999996|-5.09415E-12 +i*-3.20905E-11| +| 13| 0.469917 +i* 0.882706| 0.999996|-1.29106E-11 +i*-2.31489E-11| +| 14| 0.46437 +i* 0.885637| 0.999996| 1.38481E-11 +i* -1.517E-11| +| 15| 0.458797 +i* 0.888537| 0.999996| 2.78862E-11 +i* 1.10441E-11| +| 16| 0.453214 +i* 0.891397| 0.999996| 2.45506E-11 +i* 3.1726E-11| +| 17| 0.447623 +i* 0.894218| 0.999996| -2.5447E-11 +i*-4.61239E-11| +| 18| 0.441986 +i* 0.897017| 0.999996| 2.72476E-11 +i* 3.22485E-11| +| 19| 0.436351 +i* 0.899772| 0.999996|-3.70284E-11 +i*-5.06729E-12| +| 20| 0.430689 +i* 0.902496| 0.999996|-1.25435E-11 +i* 3.86925E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 0.999996 +400000 racines de module = 1.00001 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^500000 + (-10 +i*0)*x^700000 + (1 +i*0)*x^1200000 + +(-50000 +i*0)*x^499999 + (-7E+06 +i*0)*x^699999 + (1.2E+06 +i*0)*x^1199999 + +zone limite de 'log-exp' 1.0003 +dimgrid 4688 dimblock 256 degrePoly 1200000 +proc 0, start 0 size 1200128 +proc 0 start 0 size 1200128 +iter : 1 Arret : 0.00677598 s/iter 104.842623 +iter : 2 Arret : 1.43332 s/iter 108.451498 +iter : 3 Arret : 0.428119 s/iter 109.604920 +iter : 4 Arret : 0.429249 s/iter 111.528327 +iter : 5 Arret : 1.08646 s/iter 112.126605 +iter : 6 Arret : 4.298 s/iter 112.878995 +iter : 7 Arret : 1.29187 s/iter 114.015483 +iter : 8 Arret : 4.5768 s/iter 114.431935 +iter : 9 Arret : 0.867548 s/iter 114.405770 +iter : 10 Arret : 1.11265 s/iter 113.890021 +iter : 11 Arret : 0.535846 s/iter 113.718788 +iter : 12 Arret : 0.531876 s/iter 112.691524 +iter : 13 Arret : 2.32463 s/iter 111.476924 +iter : 14 Arret : 0.834993 s/iter 110.712739 +iter : 15 Arret : 1.67285 s/iter 110.494250 +iter : 16 Arret : 1.01044 s/iter 109.494899 +iter : 17 Arret : 0.807065 s/iter 109.193175 +iter : 18 Arret : 0.909238 s/iter 108.712803 +iter : 19 Arret : 1.14066 s/iter 108.492397 +iter : 20 Arret : 0.335581 s/iter 107.960425 +iter : 21 Arret : 0.196963 s/iter 107.373274 +iter : 22 Arret : 0.128663 s/iter 106.913981 +iter : 23 Arret : 0.275217 s/iter 106.284145 +iter : 24 Arret : 0.179897 s/iter 106.054702 +iter : 25 Arret : 0.420437 s/iter 105.799691 +iter : 26 Arret : 0.358355 s/iter 105.198589 +iter : 27 Arret : 0.11514 s/iter 105.120453 +iter : 28 Arret : 0.217484 s/iter 104.911034 +iter : 29 Arret : 0.207195 s/iter 104.903818 +iter : 30 Arret : 0.037319 s/iter 104.938544 +iter : 31 Arret : 0.0122038 s/iter 104.836750 +iter : 32 Arret : 0.000983648 s/iter 104.776137 +iter : 33 Arret : 4.35825E-07 s/iter 104.872755 +iter : 34 Arret : 1.94444E-09 s/iter 104.822262 +iter : 35 Arret : 1.37935E-11 s/iter 104.776349 +iter : 36 Arret : 1.88726E-13 s/iter 104.825146 +temps : 3906.03 seconde(s) +Nb iterations : 36 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.78618E-08 +Stabilite : 1.88726E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540312 +i* 0.841461| 0.999997|-2.16913E-11 +i* 1.91294E-11| +| 2| 0.513645 +i* 0.857999| 0.999997|-6.29718E-12 +i*-2.39364E-12| +| 3| 0.486457 +i* 0.873701| 0.999997| 1.53235E-11 +i* 6.36435E-13| +| 4| 0.458805 +i* 0.888533| 0.999997| 1.78773E-11 +i* 1.55684E-11| +| 5| 0.430685 +i* 0.902499| 0.999997| 2.12053E-13 +i*-1.16324E-11| +| 6| 0.402126 +i* 0.915589| 1| 2.50282E-09 +i*-6.10471E-09| +| 7| 0.3732 +i* 0.927747| 0.999997| -2.5707E-11 +i* 3.11093E-13| +| 8| 0.3439 +i* 0.939003| 0.999997|-1.12714E-11 +i* 1.5453E-11| +| 9| 0.314261 +i* 0.949333| 0.999997| 1.93628E-11 +i* 2.50909E-11| +| 10| 0.284313 +i* 0.958728| 0.999997| 2.69426E-11 +i* 2.77974E-11| +| 11| 0.254084 +i* 0.967179| 0.999997| 1.5277E-11 +i* 4.73027E-12| +| 12| 0.223614 +i* 0.974674| 0.999997| 7.05391E-12 +i* 1.2797E-11| +| 13| 0.192915 +i* 0.981212| 0.999997| 1.07495E-11 +i* 5.766E-12| +| 14| 0.162052 +i* 0.986779| 0.999997|-2.06171E-11 +i* 5.16515E-12| +| 15| 0.130977 +i* 0.991382| 0.999997| 5.89659E-11 +i* 7.29122E-12| +| 16| 0.0998077 +i* 0.995003| 0.999997|-3.45761E-11 +i*-1.61701E-11| +| 17| 0.0685225 +i* 0.997646| 0.999997| 2.33641E-11 +i* 2.51787E-12| +| 18| 0.0371504 +i* 0.999314| 1|-3.18728E-10 +i*-2.97119E-09| +| 19| 0.00578048 +i* 0.99998| 0.999997| 3.46787E-11 +i* 1.94857E-13| +| 20| -0.0256056 +i* 0.999669| 0.999997| 2.04742E-11 +i* 1.15624E-12| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 0.999997 +500000 racines de module = 1 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^600000 + (-10 +i*0)*x^800000 + (1 +i*0)*x^1400000 + +(-60000 +i*0)*x^599999 + (-8E+06 +i*0)*x^799999 + (1.4E+06 +i*0)*x^1399999 + +zone limite de 'log-exp' 1.00025 +dimgrid 5469 dimblock 256 degrePoly 1400000 +proc 0, start 0 size 1400064 +proc 0 start 0 size 1400064 +iter : 1 Arret : 0.00938725 s/iter 142.328326 +iter : 2 Arret : 0.761578 s/iter 147.052418 +iter : 3 Arret : 1.35081 s/iter 149.289333 +iter : 4 Arret : 0.488828 s/iter 151.454940 +iter : 5 Arret : 0.352825 s/iter 152.322211 +iter : 6 Arret : 0.142284 s/iter 153.010051 +iter : 7 Arret : 0.0560259 s/iter 152.431968 +iter : 8 Arret : 0.196308 s/iter 152.003440 +iter : 9 Arret : 0.124897 s/iter 151.872606 +iter : 10 Arret : 0.0975323 s/iter 151.560877 +iter : 11 Arret : 0.147128 s/iter 149.300671 +iter : 12 Arret : 0.109558 s/iter 147.230298 +iter : 13 Arret : 0.0563761 s/iter 144.834459 +iter : 14 Arret : 0.0352169 s/iter 143.795377 +iter : 15 Arret : 0.0177334 s/iter 143.112879 +iter : 16 Arret : 0.0155926 s/iter 142.695503 +iter : 17 Arret : 0.00246736 s/iter 142.533975 +iter : 18 Arret : 9.78659E-05 s/iter 142.374961 +iter : 19 Arret : 5.69989E-07 s/iter 142.290712 +iter : 20 Arret : 3.43839E-09 s/iter 142.588568 +iter : 21 Arret : 1.59577E-11 s/iter 142.684647 +iter : 22 Arret : 7.40742E-14 s/iter 142.549602 +temps : 3229.79 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.95958E-08 +Stabilite : 7.40742E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841469| 0.999997|-5.74141E-12 +i*-6.39521E-11| +| 2| 0.513623 +i* 0.858013| 0.999997|-2.15776E-11 +i*-2.98557E-11| +| 3| -0.52703 +i* -0.849843| 0.999997|-6.50922E-11 +i* 8.44216E-12| +| 4| 0.486439 +i* 0.873711| 0.999997| 5.60277E-11 +i* 4.36779E-11| +| 5| -0.500096 +i* -0.865967| 0.999997| 3.56147E-11 +i*-3.12713E-11| +| 6| 0.458776 +i* 0.888549| 0.999997|-1.89702E-11 +i* 4.08274E-12| +| 7| -0.472669 +i* -0.881237| 0.999997|-1.66496E-11 +i*-3.61498E-11| +| 8| 0.430661 +i* 0.902511| 0.999997|-1.60558E-11 +i*-1.29949E-11| +| 9| -0.444791 +i* -0.895631| 0.999997|-8.89955E-13 +i* 2.61938E-12| +| 10| 0.402136 +i* 0.915577| 0.999997| 6.5834E-12 +i* -1.3935E-11| +| 11| -0.416439 +i* -0.90916| 0.999997|-1.66807E-11 +i* 2.56219E-11| +| 12| 0.373179 +i* 0.927756| 0.999997|-7.07252E-11 +i*-5.29587E-11| +| 13| -0.387698 +i* -0.921783| 0.999997|-1.86324E-11 +i* -4.6545E-11| +| 14| 0.343875 +i* 0.939012| 0.999997| 3.84962E-11 +i* 2.59646E-11| +| 15| -0.358575 +i* -0.933498| 0.999997|-3.74776E-11 +i*-3.89954E-11| +| 16| 0.314233 +i* 0.949343| 0.999997| 3.86503E-11 +i* 2.08775E-11| +| 17| -0.329098 +i* -0.944293| 0.999997|-1.57903E-11 +i* 2.05052E-11| +| 18| 0.284281 +i* 0.958738| 0.999997| 2.51592E-11 +i* 2.09243E-11| +| 19| -0.299297 +i* -0.954157| 0.999997| 5.03608E-12 +i* 1.70503E-11| +| 20| 0.254048 +i* 0.967189| 0.999997|-2.81228E-11 +i*-1.66302E-11| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 0.999997 +600000 racines de module = 1 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^700000 + (-10 +i*0)*x^900000 + (1 +i*0)*x^1600000 + +(-70000 +i*0)*x^699999 + (-9E+06 +i*0)*x^899999 + (1.6E+06 +i*0)*x^1599999 + + +template:823 terminated with signal 11 at PC=404ae1 SP=7fff080bdf50. Backtrace: +./template[0x404ae1] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +-------------------------------------------------------------------------- +mpirun has exited due to process rank 0 with PID 823 on +node node1-50 exiting improperly. There are two reasons this could occur: + +1. this process did not call "init" before exiting, but others in +the job did. This can cause a job to hang indefinitely while it waits +for all processes to call "init". By rule, if one process calls "init", +then ALL processes must call "init" prior to termination. + +2. this process called "init", but exited without calling "finalize". +By rule, all processes that call "init" MUST call "finalize" prior to +exiting or it will be considered an "abnormal termination" + +This may have caused other processes in the application to be +terminated by signals sent by mpirun (as reported here). +-------------------------------------------------------------------------- +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^800000 + (-10 +i*0)*x^1000000 + (1 +i*0)*x^1800000 + +(-80000 +i*0)*x^799999 + (-1E+07 +i*0)*x^999999 + (1.8E+06 +i*0)*x^1799999 + + +template:827 terminated with signal 11 at PC=404ae1 SP=7fffb55d2a00. Backtrace: +./template[0x404ae1] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +-------------------------------------------------------------------------- +mpirun has exited due to process rank 0 with PID 827 on +node node1-50 exiting improperly. There are two reasons this could occur: + +1. this process did not call "init" before exiting, but others in +the job did. This can cause a job to hang indefinitely while it waits +for all processes to call "init". By rule, if one process calls "init", +then ALL processes must call "init" prior to termination. + +2. this process called "init", but exited without calling "finalize". +By rule, all processes that call "init" MUST call "finalize" prior to +exiting or it will be considered an "abnormal termination" + +This may have caused other processes in the application to be +terminated by signals sent by mpirun (as reported here). +-------------------------------------------------------------------------- +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^500000 + (-10 +i*0)*x^1500000 + (1 +i*0)*x^2000000 + +(-50000 +i*0)*x^499999 + (-1.5E+07 +i*0)*x^1499999 + (2E+06 +i*0)*x^1999999 + + +template:831 terminated with signal 11 at PC=404ae1 SP=7fff64363320. Backtrace: +./template[0x404ae1] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +-------------------------------------------------------------------------- +mpirun has exited due to process rank 0 with PID 831 on +node node1-50 exiting improperly. There are two reasons this could occur: + +1. this process did not call "init" before exiting, but others in +the job did. This can cause a job to hang indefinitely while it waits +for all processes to call "init". By rule, if one process calls "init", +then ALL processes must call "init" prior to termination. + +2. this process called "init", but exited without calling "finalize". +By rule, all processes that call "init" MUST call "finalize" prior to +exiting or it will be considered an "abnormal termination" + +This may have caused other processes in the application to be +terminated by signals sent by mpirun (as reported here). +-------------------------------------------------------------------------- diff --git a/Simulations/sparse_mpi/sparse_mpi_1GPU.sge b/Simulations/sparse_mpi/sparse_mpi_1GPU.sge new file mode 100644 index 0000000..8661da2 --- /dev/null +++ b/Simulations/sparse_mpi/sparse_mpi_1GPU.sge @@ -0,0 +1,25 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=1 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -V +#$ -cwd +#$ -N sparse_mpi_1GPU +#$ -pe mpi 1 + + +module load cuda/7.0 +module load ompi/gcc + +mpirun -np $NSLOTS ./template -r -i 60000 40000 +mpirun -np $NSLOTS ./template -r -i 150000 50000 +mpirun -np $NSLOTS ./template -r -i 250000 150000 +mpirun -np $NSLOTS ./template -r -i 350000 250000 +mpirun -np $NSLOTS ./template -r -i 500000 300000 +mpirun -np $NSLOTS ./template -r -i 600000 400000 +mpirun -np $NSLOTS ./template -r -i 700000 500000 +mpirun -np $NSLOTS ./template -r -i 800000 600000 +mpirun -np $NSLOTS ./template -r -i 900000 700000 +mpirun -np $NSLOTS ./template -r -i 1000000 800000 +mpirun -np $NSLOTS ./template -r -i 1500000 500000 diff --git a/Simulations/sparse_mpi/sparse_mpi_2GPU.o140031 b/Simulations/sparse_mpi/sparse_mpi_2GPU.o140031 new file mode 100644 index 0000000..15b43d7 --- /dev/null +++ b/Simulations/sparse_mpi/sparse_mpi_2GPU.o140031 @@ -0,0 +1,662 @@ +REMAINING: 2 +Taking GPU #0 +Taking GPU #1 +proc 0 +proc 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^40000 + (-10 +i*0)*x^60000 + (1 +i*0)*x^100000 + +(-4000 +i*0)*x^39999 + (-600000 +i*0)*x^59999 + (100000 +i*0)*x^99999 + +zone limite de 'log-exp' 1.00356 +zone limite de 'log-exp' 1.00356 +dimgrid 391 dimblock 256 degrePoly 100000 +proc 1, start 50048 size 50048 +proc 1 start 50048 size 50048 +dimgrid 391 dimblock 256 degrePoly 100000 +proc 0, start 0 size 50048 +proc 0 start 0 size 50048 +iter : 1 Arret : 0.00512448 s/iter 0.442006 +iter : 2 Arret : 0.00518524 s/iter 0.441749 +iter : 3 Arret : 0.0136123 s/iter 0.441743 +iter : 4 Arret : 0.0172088 s/iter 0.520551 +iter : 5 Arret : 0.0127637 s/iter 0.441752 +iter : 6 Arret : 0.00575024 s/iter 0.441718 +iter : 7 Arret : 0.00480045 s/iter 0.441722 +iter : 8 Arret : 0.0058672 s/iter 0.441765 +iter : 9 Arret : 0.00681665 s/iter 0.439578 +iter : 10 Arret : 0.00633876 s/iter 0.441755 +iter : 11 Arret : 0.0024546 s/iter 0.441765 +iter : 12 Arret : 0.00167883 s/iter 0.441695 +iter : 13 Arret : 0.000524245 s/iter 0.441627 +iter : 14 Arret : 0.000135332 s/iter 0.441622 +iter : 15 Arret : 4.9518E-06 s/iter 0.441652 +iter : 16 Arret : 7.49618E-08 s/iter 0.441569 +iter : 17 Arret : 1.11657E-09 s/iter 0.441553 +iter : 18 Arret : 1.66345E-11 s/iter 0.441549 +iter : 19 Arret : 2.47882E-13 s/iter 0.441578 +temps : 8.65634 seconde(s) +Nb iterations : 19 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.43376E-08 +Stabilite : 3.20054E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.54036 +i* 0.841503| 1.00006|-5.00602E-11 +i* 9.0853E-12| +| 2| -0.113164 +i* 0.993538| 0.999962|-4.34919E-12 +i* 9.60242E-13| +| 3| -0.226732 +i* -0.974016| 1.00006|-1.34468E-09 +i*-3.70749E-10| +| 4| -0.715763 +i* 0.698289| 0.999962| 9.11271E-13 +i* 2.47219E-12| +| 5| 0.439922 +i* -0.897993| 0.999962|-3.49498E-13 +i* 1.66432E-12| +| 6| -0.996122 +i* 0.0886386| 1.00006| 4.72785E-10 +i* 4.13616E-11| +| 7| 0.908546 +i* -0.417692| 0.999962| 2.07334E-12 +i* 2.33003E-12| +| 8| -0.827813 +i* -0.560935| 0.999962| 9.76996E-13 +i*-2.04309E-12| +| 9| 0.968129 +i* 0.250682| 1.00006| 1.35693E-10 +i*-3.47657E-10| +| 10| -0.286842 +i* -0.958038| 1.00006|-5.93554E-10 +i*-2.45345E-10| +| 11| 0.591653 +i* 0.806145| 0.999962|-9.87654E-13 +i*-3.03635E-12| +| 12| -0.0511836 +i* 0.998651| 0.999962|-2.22622E-12 +i*-3.69013E-14| +| 13| -0.67097 +i* 0.741432| 0.999962|-8.03801E-14 +i*-1.68204E-12| +| 14| 0.383249 +i* -0.923603| 0.999962|-1.29119E-12 +i*-1.37426E-12| +| 15| -0.988685 +i* 0.15039| 1.00006|-1.61051E-10 +i* 7.18515E-11| +| 16| 0.880824 +i* -0.473363| 0.999962| 1.58029E-12 +i*-2.34379E-12| +| 17| -0.861082 +i* -0.508391| 0.999962| 9.8066E-13 +i* 3.40478E-12| +| 18| 0.98184 +i* 0.190015| 1.00006| 8.88373E-10 +i*-2.66385E-10| +| 19| -0.345842 +i* -0.938354| 1.00006| 1.38421E-10 +i*-2.31696E-10| +| 20| 0.640621 +i* 0.767807| 0.999962|-6.98774E-13 +i* 1.13798E-12| ++---+----------------------------+------------+----------------------------+ +40000 racines de module = 1.00006 +60000 racines de module = 0.999962 +proc 1 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^50000 + (-10 +i*0)*x^150000 + (1 +i*0)*x^200000 + +(-5000 +i*0)*x^49999 + (-1.5E+06 +i*0)*x^149999 + (200000 +i*0)*x^199999 + +zone limite de 'log-exp' 1.00178 +zone limite de 'log-exp' 1.00178 +dimgrid 782 dimblock 256 degrePoly 200000 +proc 1, start 100096 size 100096 +proc 1 start 100096 size 100096 +dimgrid 782 dimblock 256 degrePoly 200000 +proc 0, start 0 size 100096 +proc 0 start 0 size 100096 +iter : 1 Arret : 0.000100591 s/iter 1.548764 +iter : 2 Arret : 9.98047E-05 s/iter 1.548592 +iter : 3 Arret : 0.000401454 s/iter 1.548606 +iter : 4 Arret : 0.000612146 s/iter 1.548661 +iter : 5 Arret : 0.00261257 s/iter 1.548859 +iter : 6 Arret : 0.00389809 s/iter 1.707848 +iter : 7 Arret : 0.108958 s/iter 1.548567 +iter : 8 Arret : 0.0989986 s/iter 1.548572 +iter : 9 Arret : 0.159452 s/iter 1.549964 +iter : 10 Arret : 0.284956 s/iter 1.552722 +iter : 11 Arret : 0.805953 s/iter 1.552547 +iter : 12 Arret : 0.51544 s/iter 1.711577 +iter : 13 Arret : 0.544938 s/iter 1.707829 +iter : 14 Arret : 0.643974 s/iter 1.548388 +iter : 15 Arret : 1.69207 s/iter 1.548432 +iter : 16 Arret : 0.924273 s/iter 1.548552 +iter : 17 Arret : 0.444862 s/iter 1.548574 +iter : 18 Arret : 4.9242 s/iter 1.549903 +iter : 19 Arret : 0.716282 s/iter 1.548377 +iter : 20 Arret : 0.40305 s/iter 1.548788 +iter : 21 Arret : 0.294354 s/iter 1.548624 +iter : 22 Arret : 0.0209093 s/iter 1.548518 +iter : 23 Arret : 0.00144046 s/iter 1.548527 +iter : 24 Arret : 0.000306925 s/iter 1.548770 +iter : 25 Arret : 3.17447E-10 s/iter 1.548617 +iter : 26 Arret : 3.17541E-14 s/iter 1.548825 +temps : 40.9684 seconde(s) +Nb iterations : 26 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.58606E-05 +Stabilite : 6.47336E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540303 +i* 0.841453| 0.999985| 1.08703E-11 +i*-2.49217E-12| +| 2| -0.837195 +i* 0.546877| 0.999985| -5.4492E-12 +i* 1.09163E-12| +| 3| -0.553418 +i* -0.832885| 0.999985| -1.9722E-12 +i*-7.40397E-12| +| 4| 0.828599 +i* -0.559925| 1.00005|-7.54521E-09 +i* 1.47059E-08| +| 5| -0.8197 +i* 0.572767| 0.999985|-4.21663E-13 +i* -2.8616E-12| +| 6| -0.57917 +i* -0.815188| 0.999985|-5.13034E-12 +i*-1.52645E-12| +| 7| 0.810626 +i* -0.585537| 0.999985|-6.36846E-12 +i*-5.86797E-12| +| 8| 0.591872 +i* 0.806089| 1.00005|-1.69803E-09 +i* 9.43795E-09| +| 9| -0.801454 +i* 0.598134| 1.00005|-3.72767E-08 +i*-1.30274E-08| +| 10| -0.604356 +i* -0.796695| 0.999985|-1.64091E-13 +i* 1.59084E-12| +| 11| 0.791937 +i* -0.610578| 0.999985| 6.0707E-13 +i* 1.52922E-12| +| 12| 0.616763 +i* 0.78713| 0.999985|-4.48042E-12 +i* -2.6295E-12| +| 13| -0.782301 +i* 0.622877| 0.999985|-2.15827E-12 +i*-6.27114E-12| +| 14| -0.628991 +i* -0.777472| 1.00005| 6.93065E-09 +i*-8.65443E-09| +| 15| 0.772474 +i* -0.635023| 0.999985| 1.54783E-11 +i*-1.81338E-12| +| 16| 0.641054 +i* 0.767476| 0.999985| 9.05009E-12 +i*-2.91295E-12| +| 17| -0.762458 +i* 0.647014| 0.999985| 5.81724E-12 +i*-9.99384E-12| +| 18| -0.652967 +i* -0.757366| 0.999985|-6.31406E-12 +i* 8.49495E-12| +| 19| 0.752302 +i* -0.658888| 1.00005| 3.99107E-09 +i* 1.02117E-08| +| 20| 0.66472 +i* 0.747072| 0.999985|-1.93379E-12 +i*-1.29726E-11| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 0.999985 +50000 racines de module = 1.00005 +proc 0 +proc 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^150000 + (-10 +i*0)*x^250000 + (1 +i*0)*x^400000 + +(-15000 +i*0)*x^149999 + (-2.5E+06 +i*0)*x^249999 + (400000 +i*0)*x^399999 + +zone limite de 'log-exp' 1.00089 +zone limite de 'log-exp' 1.00089 +dimgrid 1563 dimblock 256 degrePoly 400000 +proc 0, start 0 size 200064 +proc 0 start 0 size 200064 +dimgrid 1563 dimblock 256 degrePoly 400000 +proc 1, start 200064 size 200064 +proc 1 start 200064 size 200064 +iter : 1 Arret : 0.000550449 s/iter 6.082917 +iter : 2 Arret : 0.00291862 s/iter 6.079734 +iter : 3 Arret : 0.00675438 s/iter 6.082746 +iter : 4 Arret : 0.00891928 s/iter 6.157166 +iter : 5 Arret : 0.0118747 s/iter 6.150345 +iter : 6 Arret : 0.0109883 s/iter 6.091520 +iter : 7 Arret : 0.00656673 s/iter 6.112417 +iter : 8 Arret : 0.00575864 s/iter 6.085608 +iter : 9 Arret : 0.00288805 s/iter 6.150350 +iter : 10 Arret : 0.00168944 s/iter 6.083333 +iter : 11 Arret : 0.00101594 s/iter 6.079295 +iter : 12 Arret : 0.000961205 s/iter 6.079555 +iter : 13 Arret : 0.000805832 s/iter 6.078713 +iter : 14 Arret : 0.00034457 s/iter 6.079666 +iter : 15 Arret : 0.000125967 s/iter 6.080354 +iter : 16 Arret : 2.22934E-05 s/iter 6.079409 +iter : 17 Arret : 5.34301E-06 s/iter 6.079653 +iter : 18 Arret : 3.49738E-08 s/iter 6.081697 +iter : 19 Arret : 7.48893E-11 s/iter 6.080662 +iter : 20 Arret : 1.61404E-13 s/iter 6.081309 +temps : 122.138 seconde(s) +Nb iterations : 20 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.09706E-08 +Stabilite : 1.61404E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540334 +i* 0.84144| 0.999991| 6.97609E-12 +i* 5.61207E-12| +| 2| -0.998329 +i* 0.057622| 0.999991| 4.43912E-12 +i* 1.27665E-12| +| 3| 0.43989 +i* -0.898041| 0.999991|-2.08855E-12 +i*-1.75276E-12| +| 4| -0.996033 +i* 0.0888768| 0.999991|-3.15592E-12 +i* 1.17456E-12| +| 5| 0.411533 +i* -0.911385| 0.999991|-2.45048E-12 +i* 4.6238E-12| +| 6| 0.59196 +i* 0.805956| 0.999991| 5.24358E-13 +i*-8.53073E-12| +| 7| -0.992759 +i* 0.120044| 0.999991| 2.58804E-12 +i* 2.47274E-12| +| 8| 0.382796 +i* -0.923823| 0.999991|-1.63092E-11 +i* 4.26312E-12| +| 9| 0.616925 +i* 0.78701| 0.999991| 4.27514E-12 +i*-1.13966E-11| +| 10| -0.98851 +i* 0.151094| 0.999991|-1.29017E-11 +i*-4.43427E-12| +| 11| 0.35366 +i* -0.935364| 0.999991|-1.92664E-11 +i* 1.19958E-11| +| 12| 0.641283 +i* 0.767292| 0.999991|-4.70735E-12 +i* -1.4127E-11| +| 13| -0.98329 +i* 0.181995| 0.999991|-6.62759E-12 +i*-5.46796E-12| +| 14| 0.324176 +i* -0.945987| 0.999991|-5.20695E-12 +i*-7.06984E-12| +| 15| 0.665012 +i* 0.746821| 0.999991| 5.27178E-12 +i*-4.27913E-12| +| 16| -0.977104 +i* 0.212717| 0.999991|-1.01148E-11 +i* 2.41479E-12| +| 17| 0.294374 +i* -0.955681| 0.999991|-2.37395E-11 +i*-2.53098E-12| +| 18| 0.688087 +i* 0.725616| 0.999991| 6.67011E-12 +i* 1.57173E-11| +| 19| -0.969965 +i* 0.243206| 0.999991| 6.88072E-12 +i* 3.20268E-13| +| 20| 0.264283 +i* -0.964436| 0.999991|-6.93356E-12 +i*-6.23118E-12| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 0.999991 +150000 racines de module = 1.00002 +proc 1 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^250000 + (-10 +i*0)*x^350000 + (1 +i*0)*x^600000 + +(-25000 +i*0)*x^249999 + (-3.5E+06 +i*0)*x^349999 + (600000 +i*0)*x^599999 + +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 1, start 300032 size 300032 +proc 1 start 300032 size 300032 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 0, start 0 size 300032 +proc 0 start 0 size 300032 +iter : 1 Arret : 0.00169532 s/iter 13.268293 +iter : 2 Arret : 0.00577451 s/iter 13.754899 +iter : 3 Arret : 0.00560656 s/iter 13.317734 +iter : 4 Arret : 0.026637 s/iter 13.287596 +iter : 5 Arret : 0.0224878 s/iter 13.756785 +iter : 6 Arret : 0.0273249 s/iter 14.009301 +iter : 7 Arret : 0.0242205 s/iter 13.722890 +iter : 8 Arret : 0.0206627 s/iter 14.046207 +iter : 9 Arret : 0.0154355 s/iter 14.068750 +iter : 10 Arret : 0.0112335 s/iter 13.832264 +iter : 11 Arret : 0.00926749 s/iter 13.793343 +iter : 12 Arret : 0.0165133 s/iter 13.276606 +iter : 13 Arret : 0.00281445 s/iter 13.275977 +iter : 14 Arret : 0.0019915 s/iter 13.269355 +iter : 15 Arret : 0.00135028 s/iter 13.267568 +iter : 16 Arret : 0.00186824 s/iter 13.268070 +iter : 17 Arret : 0.000810658 s/iter 13.268154 +iter : 18 Arret : 0.000232438 s/iter 13.268534 +iter : 19 Arret : 3.11501E-07 s/iter 13.267454 +iter : 20 Arret : 1.18566E-09 s/iter 13.267871 +iter : 21 Arret : 9.65413E-12 s/iter 13.268070 +iter : 22 Arret : 1.37719E-13 s/iter 13.267729 +temps : 297.134 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.32595E-08 +Stabilite : 1.37719E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540302 +i* 0.841463| 0.999993| 8.34199E-12 +i* -1.9051E-11| +| 2| -0.553438 +i* -0.832883| 0.999993|-2.10654E-12 +i*-2.55273E-11| +| 3| -0.579282 +i* -0.815119| 0.999993| 1.33613E-11 +i*-1.98701E-11| +| 4| 0.591992 +i* 0.805956| 1.00001|-3.89872E-09 +i* 2.08385E-09| +| 5| -0.604557 +i* -0.796554| 0.999993|-2.82974E-12 +i* 9.99473E-12| +| 6| 0.61698 +i* 0.78697| 0.999993|-4.77973E-12 +i* 2.40621E-11| +| 7| -0.629237 +i* -0.777205| 0.999993|-2.92122E-12 +i*-4.85867E-12| +| 8| 0.641354 +i* 0.767237| 0.999993|-1.64209E-11 +i* 1.12904E-12| +| 9| -0.653299 +i* -0.757092| 0.999993|-8.22453E-13 +i* 2.82818E-12| +| 10| 0.665096 +i* 0.746749| 0.999993| -1.2145E-11 +i* 1.89129E-11| +| 11| -0.676717 +i* -0.736234| 0.999993|-1.26079E-11 +i*-1.25073E-11| +| 12| 0.688185 +i* 0.725526| 0.999993| 2.69875E-11 +i* 1.65411E-11| +| 13| -0.699466 +i* -0.714679| 1.00001| 3.92343E-10 +i*-3.02623E-09| +| 14| 0.710597 +i* 0.70359| 0.999993| -2.6851E-11 +i*-1.44801E-11| +| 15| -0.721524 +i* -0.69238| 0.999993| 2.63193E-11 +i*-6.76318E-13| +| 16| 0.73231 +i* 0.680962| 0.999993| 1.34706E-11 +i*-4.43489E-12| +| 17| -0.74294 +i* -0.669349| 0.999993| 1.02707E-12 +i* 2.14607E-11| +| 18| 0.753317 +i* 0.657672| 1.00001| 2.8295E-09 +i*-3.45603E-09| +| 19| -0.76354 +i* -0.64575| 0.999993| 2.24043E-11 +i*-1.30496E-12| +| 20| 0.773543 +i* 0.633733| 0.999993|-3.47811E-12 +i*-5.94756E-12| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 0.999993 +250000 racines de module = 1.00001 +proc 0 +proc 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^300000 + (-10 +i*0)*x^500000 + (1 +i*0)*x^800000 + +(-30000 +i*0)*x^299999 + (-5E+06 +i*0)*x^499999 + (800000 +i*0)*x^799999 + +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 0, start 0 size 400000 +proc 0 start 0 size 400000 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 1, start 400000 size 400000 +proc 1 start 400000 size 400000 +iter : 1 Arret : 0.00108387 s/iter 23.672446 +iter : 2 Arret : 0.00660333 s/iter 23.805408 +iter : 3 Arret : 1.16255 s/iter 23.798567 +iter : 4 Arret : 1.00538 s/iter 23.799772 +iter : 5 Arret : 4.35503 s/iter 23.835095 +iter : 6 Arret : 2.85741 s/iter 24.191376 +iter : 7 Arret : 1.06724 s/iter 24.343970 +iter : 8 Arret : 0.752896 s/iter 24.414141 +iter : 9 Arret : 0.681451 s/iter 24.504496 +iter : 10 Arret : 0.666362 s/iter 24.940388 +iter : 11 Arret : 0.660981 s/iter 25.494551 +iter : 12 Arret : 0.6721 s/iter 24.530242 +iter : 13 Arret : 0.722307 s/iter 24.518027 +iter : 14 Arret : 0.735973 s/iter 24.579973 +iter : 15 Arret : 1.60274 s/iter 24.425419 +iter : 16 Arret : 1.08224 s/iter 24.263282 +iter : 17 Arret : 1.66761 s/iter 24.117742 +iter : 18 Arret : 0.562533 s/iter 23.946009 +iter : 19 Arret : 0.334526 s/iter 23.926164 +iter : 20 Arret : 0.247191 s/iter 23.871930 +iter : 21 Arret : 0.0856694 s/iter 23.809304 +iter : 22 Arret : 0.100266 s/iter 23.817817 +iter : 23 Arret : 0.0450244 s/iter 23.791545 +iter : 24 Arret : 0.0252731 s/iter 23.803368 +iter : 25 Arret : 0.0214701 s/iter 23.778507 +iter : 26 Arret : 0.00697008 s/iter 23.796671 +iter : 27 Arret : 0.00107605 s/iter 23.651300 +iter : 28 Arret : 1.6145E-06 s/iter 23.654996 +iter : 29 Arret : 4.22205E-09 s/iter 23.650903 +iter : 30 Arret : 9.10881E-12 s/iter 23.650544 +iter : 31 Arret : 1.96015E-14 s/iter 23.654309 +temps : 746.426 seconde(s) +Nb iterations : 31 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.73089E-06 +Stabilite : 2.22043E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540305 +i* 0.841464| 0.999995| -2.03E-11 +i* 2.74701E-11| +| 2| 0.592014 +i* 0.805922| 0.999995| 2.33948E-11 +i*-2.13005E-11| +| 3| 0.617007 +i* 0.786952| 0.999995| 4.23442E-11 +i* -6.2147E-12| +| 4| 0.641392 +i* 0.767207| 0.999995|-4.99742E-11 +i* 1.43873E-11| +| 5| 0.665146 +i* 0.746707| 0.999995| 2.02977E-11 +i* 7.48579E-12| +| 6| 0.688245 +i* 0.725472| 0.999995|-1.73153E-11 +i* -1.2656E-11| +| 7| 0.710667 +i* 0.703522| 0.999995| 3.69782E-12 +i* 2.3081E-12| +| 8| 0.732388 +i* 0.68088| 0.999995| 9.45355E-12 +i* 2.09024E-11| +| 9| 0.753381 +i* 0.657577| 0.999995| 1.7531E-11 +i*-4.02243E-11| +| 10| 0.77364 +i* 0.633618| 0.999995|-1.72307E-11 +i* 1.22723E-11| +| 11| 0.793138 +i* 0.609034| 0.999995| 3.89222E-12 +i* 2.21356E-11| +| 12| 0.811855 +i* 0.583851| 0.999995|-1.28337E-11 +i*-5.47207E-12| +| 13| 0.829772 +i* 0.558094| 0.999995|-1.63114E-11 +i*-1.64246E-12| +| 14| 0.846873 +i* 0.531786| 0.999995|-3.30451E-11 +i*-8.10676E-12| +| 15| 0.86314 +i* 0.504956| 0.999995|-4.00413E-12 +i* 3.04823E-11| +| 16| 0.878557 +i* 0.477628| 0.999995|-2.16493E-12 +i* 1.10533E-11| +| 17| 0.893104 +i* 0.449841| 0.999995|-1.48552E-11 +i* 1.06063E-11| +| 18| 0.906777 +i* 0.4216| 0.999995|-1.38745E-11 +i* 5.33384E-12| +| 19| 0.919557 +i* 0.392944| 0.999995|-3.33245E-11 +i* 5.94386E-12| +| 20| 0.931433 +i* 0.363901| 0.999995| 4.93219E-11 +i*-2.82651E-11| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 0.999995 +300000 racines de module = 1.00001 +proc 1 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^400000 + (-10 +i*0)*x^600000 + (1 +i*0)*x^1000000 + +(-40000 +i*0)*x^399999 + (-6E+06 +i*0)*x^599999 + (1E+06 +i*0)*x^999999 + +zone limite de 'log-exp' 1.00035 +zone limite de 'log-exp' 1.00035 +dimgrid 3907 dimblock 256 degrePoly 1000000 +proc 1, start 500096 size 500096 +proc 1 start 500096 size 500096 +dimgrid 3907 dimblock 256 degrePoly 1000000 +proc 0, start 0 size 500096 +proc 0 start 0 size 500096 +iter : 1 Arret : 0.00111034 s/iter 36.535863 +iter : 2 Arret : 0.00130138 s/iter 36.531318 +iter : 3 Arret : 0.095171 s/iter 36.617316 +iter : 4 Arret : 0.110384 s/iter 36.603388 +iter : 5 Arret : 0.0159644 s/iter 37.200734 +iter : 6 Arret : 0.0148525 s/iter 37.186773 +iter : 7 Arret : 0.0189588 s/iter 37.285760 +iter : 8 Arret : 0.0122669 s/iter 37.242480 +iter : 9 Arret : 0.025395 s/iter 37.493437 +iter : 10 Arret : 0.0249756 s/iter 36.552191 +iter : 11 Arret : 0.0032083 s/iter 36.587117 +iter : 12 Arret : 0.00514671 s/iter 36.496415 +iter : 13 Arret : 0.0026206 s/iter 36.537986 +iter : 14 Arret : 0.0021181 s/iter 36.525452 +iter : 15 Arret : 0.000448616 s/iter 36.534784 +iter : 16 Arret : 0.000260446 s/iter 36.531377 +iter : 17 Arret : 9.00305E-05 s/iter 36.520451 +iter : 18 Arret : 0.000137571 s/iter 36.497467 +iter : 19 Arret : 3.90888E-05 s/iter 36.496056 +iter : 20 Arret : 8.22264E-08 s/iter 36.494517 +iter : 21 Arret : 2.59921E-10 s/iter 36.529540 +iter : 22 Arret : 8.21945E-13 s/iter 36.531093 +temps : 812.655 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.28809E-07 +Stabilite : 8.21945E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540305 +i* 0.841476| 1.00001| 4.82795E-10 +i* 3.31212E-09| +| 2| 0.529701 +i* 0.84818| 0.999996|-4.61853E-13 +i*-4.17888E-12| +| 3| 0.524361 +i* 0.851491| 0.999996|-2.47296E-11 +i* 1.78327E-11| +| 4| 0.51901 +i* 0.854764| 0.999996| 9.45599E-12 +i* 2.07434E-11| +| 5| 0.513638 +i* 0.858002| 0.999996|-2.64786E-11 +i* 1.3235E-12| +| 6| 0.508237 +i* 0.861213| 0.999996|-1.34339E-11 +i* 9.87854E-12| +| 7| 0.502825 +i* 0.864384| 0.999996|-3.18459E-11 +i* 7.64744E-12| +| 8| 0.497384 +i* 0.867526| 0.999996| 1.87346E-11 +i* 4.7471E-11| +| 9| 0.491932 +i* 0.870629| 0.999996|-2.65525E-11 +i* 1.22525E-11| +| 10| 0.486462 +i* 0.873698| 0.999996|-2.18452E-11 +i*-1.14808E-11| +| 11| 0.480962 +i* 0.876737| 0.999996| 1.81546E-11 +i* 8.04012E-12| +| 12| 0.475453 +i* 0.879736| 0.999996| 3.09861E-11 +i* 4.093E-12| +| 13| 0.469917 +i* 0.882706| 0.999996|-1.29106E-11 +i*-2.31489E-11| +| 14| 0.46437 +i* 0.885637| 0.999996|-5.47384E-12 +i* 1.02452E-11| +| 15| 0.458801 +i* 0.888545| 1.00001| 8.56622E-10 +i* 9.50588E-10| +| 16| 0.453214 +i* 0.891397| 0.999996| 2.45506E-11 +i* 3.1726E-11| +| 17| 0.447614 +i* 0.894223| 0.999996|-1.08491E-12 +i*-2.12277E-11| +| 18| 0.441986 +i* 0.897017| 0.999996| 2.72476E-11 +i* 3.22485E-11| +| 19| 0.436351 +i* 0.899772| 0.999996|-1.24334E-11 +i*-2.66317E-11| +| 20| 0.430689 +i* 0.902496| 0.999996|-1.25435E-11 +i* 3.86925E-13| ++---+----------------------------+------------+----------------------------+ +400000 racines de module = 1.00001 +600000 racines de module = 0.999996 +proc 0 +proc 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^500000 + (-10 +i*0)*x^700000 + (1 +i*0)*x^1200000 + +(-50000 +i*0)*x^499999 + (-7E+06 +i*0)*x^699999 + (1.2E+06 +i*0)*x^1199999 + +zone limite de 'log-exp' 1.0003 +zone limite de 'log-exp' 1.0003 +dimgrid 4688 dimblock 256 degrePoly 1200000 +proc 0, start 0 size 600064 +proc 0 start 0 size 600064 +dimgrid 4688 dimblock 256 degrePoly 1200000 +proc 1, start 600064 size 600064 +proc 1 start 600064 size 600064 +iter : 1 Arret : 0.0323131 s/iter 52.941074 +iter : 2 Arret : 2.76888 s/iter 55.568853 +iter : 3 Arret : 2.88621 s/iter 56.575624 +iter : 4 Arret : 1.26993 s/iter 55.935739 +iter : 5 Arret : 3.86036 s/iter 56.102261 +iter : 6 Arret : 5.37784 s/iter 57.046755 +iter : 7 Arret : 1.03129 s/iter 56.920764 +iter : 8 Arret : 3.95796 s/iter 57.471965 +iter : 9 Arret : 1.30769 s/iter 57.104425 +iter : 10 Arret : 1.0707 s/iter 57.036191 +iter : 11 Arret : 1.02855 s/iter 56.856622 +iter : 12 Arret : 0.563478 s/iter 56.398393 +iter : 13 Arret : 1.5244 s/iter 56.034393 +iter : 14 Arret : 1.47905 s/iter 55.457328 +iter : 15 Arret : 0.774422 s/iter 55.020273 +iter : 16 Arret : 10.8889 s/iter 54.981257 +iter : 17 Arret : 0.715912 s/iter 54.702463 +iter : 18 Arret : 0.577843 s/iter 54.436841 +iter : 19 Arret : 0.747995 s/iter 54.297662 +iter : 20 Arret : 0.163426 s/iter 53.892957 +iter : 21 Arret : 0.181209 s/iter 53.840332 +iter : 22 Arret : 0.0761215 s/iter 53.719165 +iter : 23 Arret : 0.0217437 s/iter 53.677726 +iter : 24 Arret : 0.00705727 s/iter 53.242080 +iter : 25 Arret : 0.00154816 s/iter 52.922070 +iter : 26 Arret : 1.96753E-05 s/iter 52.904231 +iter : 27 Arret : 2.53613E-08 s/iter 52.924736 +iter : 28 Arret : 3.62869E-10 s/iter 52.921481 +iter : 29 Arret : 5.17537E-12 s/iter 52.895150 +iter : 30 Arret : 7.38669E-14 s/iter 52.910075 +temps : 1647.22 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.62324E-08 +Stabilite : 7.38669E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540304 +i* 0.841466| 0.999997| 3.08649E-11 +i* 2.05843E-11| +| 2| 0.513629 +i* 0.858008| 0.999997| 3.02357E-11 +i* 3.41858E-11| +| 3| 0.486451 +i* 0.873713| 1|-5.85295E-09 +i*-2.49566E-10| +| 4| 0.458812 +i* 0.888539| 1|-7.79592E-09 +i*-3.64417E-09| +| 5| 0.430677 +i* 0.902502| 0.999997|-2.03271E-11 +i*-3.18325E-11| +| 6| 0.402126 +i* 0.915589| 1| 2.50282E-09 +i*-6.10471E-09| +| 7| 0.3732 +i* 0.927747| 0.999997|-1.54374E-11 +i*-2.76083E-11| +| 8| 0.3439 +i* 0.939003| 0.999997|-1.12714E-11 +i* 1.5453E-11| +| 9| 0.314261 +i* 0.949333| 0.999997| 1.93628E-11 +i* 2.50909E-11| +| 10| 0.284313 +i* 0.958728| 0.999997| 2.69426E-11 +i* 2.77974E-11| +| 11| 0.254084 +i* 0.967179| 0.999997| 1.5277E-11 +i* 4.73027E-12| +| 12| 0.223605 +i* 0.974676| 0.999997| -8.1017E-11 +i*-3.77299E-11| +| 13| 0.192897 +i* 0.981224| 1| 2.91999E-10 +i* 9.18678E-11| +| 14| 0.162017 +i* 0.986785| 0.999997| 4.59321E-12 +i*-4.42106E-13| +| 15| 0.130967 +i* 0.991391| 1| 1.71549E-09 +i* 3.54225E-10| +| 16| 0.099812 +i* 0.995011| 1|-4.01255E-09 +i*-1.01435E-08| +| 17| 0.0685136 +i* 0.997647| 0.999997|-2.98188E-11 +i* 2.79243E-12| +| 18| 0.0371504 +i* 0.999314| 1|-1.38879E-09 +i*-2.32658E-09| +| 19| 0.00578048 +i* 0.99998| 0.999997| 3.46787E-11 +i* 1.94857E-13| +| 20| -0.0256056 +i* 0.999669| 0.999997| 2.01068E-11 +i*-1.22213E-12| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 0.999997 +500000 racines de module = 1 +proc 0 +proc 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^600000 + (-10 +i*0)*x^800000 + (1 +i*0)*x^1400000 + +(-60000 +i*0)*x^599999 + (-8E+06 +i*0)*x^799999 + (1.4E+06 +i*0)*x^1399999 + +zone limite de 'log-exp' 1.00025 +zone limite de 'log-exp' 1.00025 +dimgrid 5469 dimblock 256 degrePoly 1400000 +proc 0, start 0 size 700032 +proc 0 start 0 size 700032 +dimgrid 5469 dimblock 256 degrePoly 1400000 +proc 1, start 700032 size 700032 +proc 1 start 700032 size 700032 +iter : 1 Arret : 0.00634591 s/iter 71.315735 +iter : 2 Arret : 0.356583 s/iter 73.499155 +iter : 3 Arret : 0.616585 s/iter 74.055679 +iter : 4 Arret : 0.383366 s/iter 75.001269 +iter : 5 Arret : 0.113316 s/iter 76.417550 +iter : 6 Arret : 0.198101 s/iter 77.541428 +iter : 7 Arret : 0.157259 s/iter 77.127574 +iter : 8 Arret : 0.381996 s/iter 77.411132 +iter : 9 Arret : 0.254414 s/iter 77.254944 +iter : 10 Arret : 0.178383 s/iter 77.505940 +iter : 11 Arret : 0.147268 s/iter 76.909819 +iter : 12 Arret : 0.0894984 s/iter 77.135647 +iter : 13 Arret : 0.117288 s/iter 74.937817 +iter : 14 Arret : 0.0966418 s/iter 73.691614 +iter : 15 Arret : 0.0293232 s/iter 72.705894 +iter : 16 Arret : 0.0436007 s/iter 72.446877 +iter : 17 Arret : 0.0302845 s/iter 72.160465 +iter : 18 Arret : 0.00422446 s/iter 71.431150 +iter : 19 Arret : 0.00359251 s/iter 71.490724 +iter : 20 Arret : 0.00270137 s/iter 71.471506 +iter : 21 Arret : 0.00209394 s/iter 71.343579 +iter : 22 Arret : 0.000416465 s/iter 71.476428 +iter : 23 Arret : 4.15934E-05 s/iter 71.308920 +iter : 24 Arret : 5.37967E-08 s/iter 71.432393 +iter : 25 Arret : 2.48195E-10 s/iter 71.421751 +iter : 26 Arret : 1.15205E-12 s/iter 71.414405 +iter : 27 Arret : 5.31631E-15 s/iter 71.409806 +temps : 1991.85 seconde(s) +Nb iterations : 27 +Nb de depassements de capacite exponentielle : 0 +Precision : 6.8707E-07 +Stabilite : 3.51082E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841469| 0.999997| 5.65794E-11 +i*-4.66756E-12| +| 2| 0.513623 +i* 0.858013| 0.999997|-2.15776E-11 +i*-2.98557E-11| +| 3| -0.52703 +i* -0.849843| 0.999997|-8.72191E-12 +i* 2.97079E-11| +| 4| 0.486439 +i* 0.873711| 0.999997|-3.15932E-11 +i*-1.15957E-12| +| 5| -0.500096 +i* -0.865967| 0.999997| 3.56147E-11 +i*-3.12713E-11| +| 6| 0.458776 +i* 0.888549| 0.999997|-1.89702E-11 +i* 4.08274E-12| +| 7| -0.472673 +i* -0.881242| 1|-5.56631E-09 +i*-2.23833E-09| +| 8| 0.430664 +i* 0.902517| 1|-8.83373E-11 +i*-2.09199E-09| +| 9| -0.444791 +i* -0.895631| 0.999997| 3.68259E-11 +i* 1.36002E-12| +| 10| 0.402136 +i* 0.915577| 0.999997| 6.5834E-12 +i* -1.3935E-11| +| 11| -0.416432 +i* -0.909164| 0.999997| 1.97816E-11 +i* 3.10848E-11| +| 12| 0.373171 +i* 0.927759| 0.999997|-2.17995E-11 +i*-2.96867E-12| +| 13| -0.387698 +i* -0.921783| 0.999997|-1.86324E-11 +i* -4.6545E-11| +| 14| 0.343875 +i* 0.939012| 0.999997| 3.06317E-11 +i* 7.08794E-11| +| 15| -0.358575 +i* -0.933498| 0.999997|-3.74776E-11 +i*-3.89954E-11| +| 16| 0.314233 +i* 0.949343| 0.999997| 1.02587E-11 +i*-4.25648E-11| +| 17| -0.329098 +i* -0.944293| 0.999997|-1.57903E-11 +i* 2.05052E-11| +| 18| 0.284281 +i* 0.958738| 0.999997| 2.51592E-11 +i* 2.09243E-11| +| 19| -0.299297 +i* -0.954157| 0.999997| 5.03608E-12 +i* 1.70503E-11| +| 20| 0.254048 +i* 0.967189| 0.999997|-2.81228E-11 +i*-1.66302E-11| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 0.999997 +600000 racines de module = 1 +proc 1 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^700000 + (-10 +i*0)*x^900000 + (1 +i*0)*x^1600000 + +(-70000 +i*0)*x^699999 + (-9E+06 +i*0)*x^899999 + (1.6E+06 +i*0)*x^1599999 + + +template:32580 terminated with signal 11 at PC=404ae1 SP=7fffd45f56a0. Backtrace: + +template:32579 terminated with signal 11 at PC=404ae1 SP=7fff316ce300. Backtrace: +./template[0x404ae1] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +./template[0x404ae1] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +-------------------------------------------------------------------------- +mpirun has exited due to process rank 1 with PID 32580 on +node node1-50 exiting improperly. There are two reasons this could occur: + +1. this process did not call "init" before exiting, but others in +the job did. This can cause a job to hang indefinitely while it waits +for all processes to call "init". By rule, if one process calls "init", +then ALL processes must call "init" prior to termination. + +2. this process called "init", but exited without calling "finalize". +By rule, all processes that call "init" MUST call "finalize" prior to +exiting or it will be considered an "abnormal termination" + +This may have caused other processes in the application to be +terminated by signals sent by mpirun (as reported here). +-------------------------------------------------------------------------- +proc 1 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^800000 + (-10 +i*0)*x^1000000 + (1 +i*0)*x^1800000 + +(-80000 +i*0)*x^799999 + (-1E+07 +i*0)*x^999999 + (1.8E+06 +i*0)*x^1799999 + + +template:32586 terminated with signal 11 at PC=404ae1 SP=7fffbfe9f8d0. Backtrace: +./template[0x404ae1] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:32587 terminated with signal 11 at PC=404ae1 SP=7fff632aee60. Backtrace: +./template[0x404ae1] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +-------------------------------------------------------------------------- +mpirun has exited due to process rank 1 with PID 32587 on +node node1-50 exiting improperly. There are two reasons this could occur: + +1. this process did not call "init" before exiting, but others in +the job did. This can cause a job to hang indefinitely while it waits +for all processes to call "init". By rule, if one process calls "init", +then ALL processes must call "init" prior to termination. + +2. this process called "init", but exited without calling "finalize". +By rule, all processes that call "init" MUST call "finalize" prior to +exiting or it will be considered an "abnormal termination" + +This may have caused other processes in the application to be +terminated by signals sent by mpirun (as reported here). +-------------------------------------------------------------------------- +proc 0 +proc 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^500000 + (-10 +i*0)*x^1500000 + (1 +i*0)*x^2000000 + +(-50000 +i*0)*x^499999 + (-1.5E+07 +i*0)*x^1499999 + (2E+06 +i*0)*x^1999999 + + +template:32594 terminated with signal 11 at PC=404ae1 SP=7fff28fd9250. Backtrace: +./template[0x404ae1] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:32593 terminated with signal 11 at PC=404ae1 SP=7fffe3e03f90. Backtrace: +./template[0x404ae1] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +-------------------------------------------------------------------------- +mpirun has exited due to process rank 1 with PID 32594 on +node node1-50 exiting improperly. There are two reasons this could occur: + +1. this process did not call "init" before exiting, but others in +the job did. This can cause a job to hang indefinitely while it waits +for all processes to call "init". By rule, if one process calls "init", +then ALL processes must call "init" prior to termination. + +2. this process called "init", but exited without calling "finalize". +By rule, all processes that call "init" MUST call "finalize" prior to +exiting or it will be considered an "abnormal termination" + +This may have caused other processes in the application to be +terminated by signals sent by mpirun (as reported here). +-------------------------------------------------------------------------- diff --git a/Simulations/sparse_mpi/sparse_mpi_2GPU.sge b/Simulations/sparse_mpi/sparse_mpi_2GPU.sge new file mode 100644 index 0000000..2817b6b --- /dev/null +++ b/Simulations/sparse_mpi/sparse_mpi_2GPU.sge @@ -0,0 +1,25 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=2 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -V +#$ -cwd +#$ -N sparse_mpi_2GPU +#$ -pe mpi 2 + + +module load cuda/7.0 +module load ompi/gcc + +mpirun -np $NSLOTS ./template -r -i 60000 40000 +mpirun -np $NSLOTS ./template -r -i 150000 50000 +mpirun -np $NSLOTS ./template -r -i 250000 150000 +mpirun -np $NSLOTS ./template -r -i 350000 250000 +mpirun -np $NSLOTS ./template -r -i 500000 300000 +mpirun -np $NSLOTS ./template -r -i 600000 400000 +mpirun -np $NSLOTS ./template -r -i 700000 500000 +mpirun -np $NSLOTS ./template -r -i 800000 600000 +mpirun -np $NSLOTS ./template -r -i 900000 700000 +mpirun -np $NSLOTS ./template -r -i 1000000 800000 +mpirun -np $NSLOTS ./template -r -i 1500000 500000 diff --git a/Simulations/sparse_mpi/sparse_mpi_3GPU.o140030 b/Simulations/sparse_mpi/sparse_mpi_3GPU.o140030 new file mode 100644 index 0000000..b62c8d1 --- /dev/null +++ b/Simulations/sparse_mpi/sparse_mpi_3GPU.o140030 @@ -0,0 +1,758 @@ +REMAINING: 3 +Taking GPU #0 +Taking GPU #1 +Taking GPU #2 +proc 0 +proc 1 +proc 2 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^40000 + (-10 +i*0)*x^60000 + (1 +i*0)*x^100000 + +(-4000 +i*0)*x^39999 + (-600000 +i*0)*x^59999 + (100000 +i*0)*x^99999 + +zone limite de 'log-exp' 1.00356 +zone limite de 'log-exp' 1.00356 +zone limite de 'log-exp' 1.00356 +dimgrid 391 dimblock 256 degrePoly 100000 +proc 0, start 0 size 33365 +proc 0 start 0 size 33365 +dimgrid 391 dimblock 256 degrePoly 100000 +proc 1, start 33365 size 33365 +proc 1 start 33365 size 33365 +dimgrid 391 dimblock 256 degrePoly 100000 +proc 2, start 66730 size 33365 +proc 2 start 66730 size 33365 +iter : 1 Arret : 0.00638362 s/iter 0.326715 +iter : 2 Arret : 0.00780885 s/iter 0.399767 +iter : 3 Arret : 0.00278939 s/iter 0.327124 +iter : 4 Arret : 0.00312024 s/iter 0.327290 +iter : 5 Arret : 0.00261461 s/iter 0.327081 +iter : 6 Arret : 0.00443129 s/iter 0.326569 +iter : 7 Arret : 0.00529933 s/iter 0.326526 +iter : 8 Arret : 0.00962751 s/iter 0.327146 +iter : 9 Arret : 0.0107359 s/iter 0.326473 +iter : 10 Arret : 0.00603516 s/iter 0.326463 +iter : 11 Arret : 0.00278461 s/iter 0.327154 +iter : 12 Arret : 0.000336786 s/iter 0.326455 +iter : 13 Arret : 0.000245415 s/iter 0.326273 +iter : 14 Arret : 0.000266948 s/iter 0.326718 +iter : 15 Arret : 0.000254585 s/iter 0.326250 +iter : 16 Arret : 0.000456802 s/iter 0.326186 +iter : 17 Arret : 0.000147565 s/iter 0.326750 +iter : 18 Arret : 2.07387E-07 s/iter 0.326144 +iter : 19 Arret : 3.08546E-09 s/iter 0.326199 +iter : 20 Arret : 4.59676E-11 s/iter 0.326798 +iter : 21 Arret : 6.84814E-13 s/iter 0.326219 +temps : 7.13273 seconde(s) +Nb iterations : 21 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.61117E-09 +Stabilite : 6.84814E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.54036 +i* 0.841503| 1.00006|-5.00602E-11 +i* 9.0853E-12| +| 2| -0.113164 +i* 0.993538| 0.999962|-4.34919E-12 +i* 9.60242E-13| +| 3| -0.226885 +i* -0.973981| 1.00006|-5.81993E-10 +i*-4.18547E-10| +| 4| -0.715763 +i* 0.698289| 0.999962| 9.11271E-13 +i* 2.47219E-12| +| 5| 0.439922 +i* -0.897993| 0.999962|-3.49498E-13 +i* 1.66432E-12| +| 6| -0.996122 +i* 0.0886386| 1.00006| 4.72785E-10 +i* 4.13616E-11| +| 7| 0.908546 +i* -0.417692| 0.999962| 4.78506E-13 +i* 1.54377E-13| +| 8| -0.827813 +i* -0.560935| 0.999962| 9.76996E-13 +i*-2.04309E-12| +| 9| 0.968129 +i* 0.250682| 1.00006|-2.31715E-10 +i* 1.34848E-10| +| 10| -0.286842 +i* -0.958038| 1.00006|-5.93554E-10 +i*-2.45345E-10| +| 11| 0.591653 +i* 0.806145| 0.999962|-9.87654E-13 +i*-3.03635E-12| +| 12| -0.0511836 +i* 0.998651| 0.999962|-2.22622E-12 +i*-3.69013E-14| +| 13| -0.67097 +i* 0.741432| 0.999962|-8.03801E-14 +i*-1.68204E-12| +| 14| 0.383249 +i* -0.923603| 0.999962|-1.29119E-12 +i*-1.37426E-12| +| 15| -0.988685 +i* 0.15039| 1.00006|-1.61051E-10 +i* 7.18515E-11| +| 16| 0.880824 +i* -0.473363| 0.999962| 1.58029E-12 +i*-2.34379E-12| +| 17| -0.861082 +i* -0.508391| 0.999962| 1.02962E-12 +i*-4.51911E-12| +| 18| 0.98184 +i* 0.190015| 1.00006| 8.88373E-10 +i*-2.66385E-10| +| 19| -0.345842 +i* -0.938354| 1.00006| 1.38421E-10 +i*-2.31696E-10| +| 20| 0.640621 +i* 0.767807| 0.999962|-6.98774E-13 +i* 1.13798E-12| ++---+----------------------------+------------+----------------------------+ +40000 racines de module = 1.00006 +60000 racines de module = 0.999962 +proc 0 +proc 1 +proc 2 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^50000 + (-10 +i*0)*x^150000 + (1 +i*0)*x^200000 + +(-5000 +i*0)*x^49999 + (-1.5E+06 +i*0)*x^149999 + (200000 +i*0)*x^199999 + +zone limite de 'log-exp' 1.00178 +zone limite de 'log-exp' 1.00178 +zone limite de 'log-exp' 1.00178 +dimgrid 782 dimblock 256 degrePoly 200000 +proc 2, start 133460 size 66730 +dimgrid 782 dimblock 256 degrePoly 200000 +proc 1, start 66730 size 66730 +proc 1 start 66730 size 66730 +dimgrid 782 dimblock 256 degrePoly 200000 +proc 0, start 0 size 66730 +proc 0 start 0 size 66730 +proc 2 start 133460 size 66730 +iter : 1 Arret : 0.000533936 s/iter 1.097687 +iter : 2 Arret : 0.00054918 s/iter 1.097788 +iter : 3 Arret : 0.000302619 s/iter 1.097094 +iter : 4 Arret : 0.000610723 s/iter 1.097469 +iter : 5 Arret : 0.0013942 s/iter 1.097408 +iter : 6 Arret : 0.0123305 s/iter 1.097332 +iter : 7 Arret : 0.0276413 s/iter 1.097585 +iter : 8 Arret : 0.0390327 s/iter 1.097910 +iter : 9 Arret : 0.0768762 s/iter 1.098286 +iter : 10 Arret : 0.261559 s/iter 1.199021 +iter : 11 Arret : 0.996838 s/iter 1.231967 +iter : 12 Arret : 2.41454 s/iter 1.226149 +iter : 13 Arret : 2.18621 s/iter 1.224592 +iter : 14 Arret : 1.07886 s/iter 1.189416 +iter : 15 Arret : 2.0468 s/iter 1.225182 +iter : 16 Arret : 2.06331 s/iter 1.228381 +iter : 17 Arret : 0.85728 s/iter 1.201017 +iter : 18 Arret : 0.652722 s/iter 1.225600 +iter : 19 Arret : 0.985485 s/iter 1.227406 +iter : 20 Arret : 4.10993 s/iter 1.228101 +iter : 21 Arret : 0.600123 s/iter 1.227670 +iter : 22 Arret : 0.86582 s/iter 1.231663 +iter : 23 Arret : 0.31213 s/iter 1.227752 +iter : 24 Arret : 0.424877 s/iter 1.223962 +iter : 25 Arret : 0.275449 s/iter 1.097197 +iter : 26 Arret : 0.212806 s/iter 1.221990 +iter : 27 Arret : 0.124734 s/iter 1.097336 +iter : 28 Arret : 0.088182 s/iter 1.096934 +iter : 29 Arret : 0.0330763 s/iter 1.097169 +iter : 30 Arret : 0.0100338 s/iter 1.097086 +iter : 31 Arret : 0.000168049 s/iter 1.097161 +iter : 32 Arret : 7.37376E-08 s/iter 1.096969 +iter : 33 Arret : 7.38629E-12 s/iter 1.097234 +iter : 34 Arret : 7.3696E-16 s/iter 1.097489 +temps : 39.5342 seconde(s) +Nb iterations : 34 +Nb de depassements de capacite exponentielle : 0 +Precision : 9.52377E-08 +Stabilite : 7.3696E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540303 +i* 0.841453| 0.999985| 1.08703E-11 +i*-2.49217E-12| +| 2| -0.837195 +i* 0.546877| 0.999985| -5.4492E-12 +i* 1.09163E-12| +| 3| -0.553418 +i* -0.832885| 0.999985| -1.9722E-12 +i*-7.40397E-12| +| 4| 0.828599 +i* -0.559925| 1.00005|-7.54521E-09 +i* 1.47059E-08| +| 5| -0.8197 +i* 0.572767| 0.999985|-4.21663E-13 +i* -2.8616E-12| +| 6| -0.57917 +i* -0.815188| 0.999985|-5.13034E-12 +i*-1.52645E-12| +| 7| 0.810626 +i* -0.585537| 0.999985|-6.36846E-12 +i*-5.86797E-12| +| 8| 0.592783 +i* 0.805419| 1.00005| 1.3403E-08 +i* 2.35166E-09| +| 9| -0.800777 +i* 0.59904| 1.00005|-1.05967E-08 +i* 2.82759E-08| +| 10| -0.604356 +i* -0.796695| 0.999985|-1.64091E-13 +i* 1.59084E-12| +| 11| 0.791937 +i* -0.610578| 0.999985| 6.0707E-13 +i* 1.52922E-12| +| 12| 0.616763 +i* 0.78713| 0.999985|-4.48042E-12 +i* -2.6295E-12| +| 13| -0.782301 +i* 0.622877| 0.999985|-2.15827E-12 +i*-6.27114E-12| +| 14| -0.628991 +i* -0.777472| 1.00005| 6.93065E-09 +i*-8.65443E-09| +| 15| 0.772474 +i* -0.635023| 0.999985| 1.54783E-11 +i*-1.81338E-12| +| 16| 0.641054 +i* 0.767476| 0.999985| 9.05009E-12 +i*-2.91295E-12| +| 17| -0.762458 +i* 0.647014| 0.999985| 5.81724E-12 +i*-9.99384E-12| +| 18| -0.652967 +i* -0.757366| 0.999985|-6.31406E-12 +i* 8.49495E-12| +| 19| 0.752302 +i* -0.658888| 1.00005| 3.99107E-09 +i* 1.02117E-08| +| 20| 0.66472 +i* 0.747072| 0.999985|-7.79776E-12 +i*-2.52076E-13| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 0.999985 +50000 racines de module = 1.00005 +proc 1 +proc 2 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^150000 + (-10 +i*0)*x^250000 + (1 +i*0)*x^400000 + +(-15000 +i*0)*x^149999 + (-2.5E+06 +i*0)*x^249999 + (400000 +i*0)*x^399999 + +zone limite de 'log-exp' 1.00089 +zone limite de 'log-exp' 1.00089 +zone limite de 'log-exp' 1.00089 +dimgrid 1563 dimblock 256 degrePoly 400000 +proc 1, start 133376 size 133376 +dimgrid 1563 dimblock 256 degrePoly 400000 +proc 2, start 266752 size 133376 +dimgrid 1563 dimblock 256 degrePoly 400000 +proc 0, start 0 size 133376 +proc 2 start 266752 size 133376 +proc 1 start 133376 size 133376 +proc 0 start 0 size 133376 +iter : 1 Arret : 0.000533421 s/iter 3.991725 +iter : 2 Arret : 0.00367072 s/iter 3.993299 +iter : 3 Arret : 0.00493773 s/iter 4.310647 +iter : 4 Arret : 0.00496697 s/iter 3.992603 +iter : 5 Arret : 0.0140779 s/iter 3.991503 +iter : 6 Arret : 0.0122345 s/iter 3.993227 +iter : 7 Arret : 0.0118851 s/iter 4.320085 +iter : 8 Arret : 0.00413608 s/iter 3.992019 +iter : 9 Arret : 0.0042286 s/iter 4.269756 +iter : 10 Arret : 0.00316824 s/iter 3.992259 +iter : 11 Arret : 0.00072238 s/iter 3.992655 +iter : 12 Arret : 0.000430893 s/iter 3.992601 +iter : 13 Arret : 0.000433942 s/iter 3.991813 +iter : 14 Arret : 0.000150382 s/iter 3.993178 +iter : 15 Arret : 0.000238887 s/iter 3.991814 +iter : 16 Arret : 0.000121494 s/iter 3.993291 +iter : 17 Arret : 9.71544E-07 s/iter 3.992093 +iter : 18 Arret : 2.43359E-09 s/iter 3.992688 +iter : 19 Arret : 5.24302E-12 s/iter 3.992746 +iter : 20 Arret : 5.96461E-14 s/iter 3.992444 +temps : 81.0542 seconde(s) +Nb iterations : 20 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.49185E-08 +Stabilite : 1.1328E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540334 +i* 0.84144| 0.999991| 6.97609E-12 +i* 5.61207E-12| +| 2| -0.998329 +i* 0.057622| 0.999991| 4.43912E-12 +i* 1.27665E-12| +| 3| 0.439867 +i* -0.898052| 0.999991|-8.50653E-12 +i*-8.85586E-12| +| 4| -0.996033 +i* 0.0888768| 0.999991|-3.15592E-12 +i* 1.17456E-12| +| 5| 0.411559 +i* -0.9114| 1.00002| 1.04334E-09 +i*-9.84037E-10| +| 6| 0.59196 +i* 0.805956| 0.999991| 5.24358E-13 +i*-8.53073E-12| +| 7| -0.992759 +i* 0.120044| 0.999991| 2.58804E-12 +i* 2.47274E-12| +| 8| 0.382796 +i* -0.923823| 0.999991|-1.63092E-11 +i* 4.26312E-12| +| 9| 0.616925 +i* 0.78701| 0.999991| 4.27514E-12 +i*-1.13966E-11| +| 10| -0.988534 +i* 0.151098| 1.00002|-8.27014E-10 +i* 9.44171E-10| +| 11| 0.35366 +i* -0.935364| 0.999991|-1.92664E-11 +i* 1.19958E-11| +| 12| 0.641299 +i* 0.767311| 1.00002|-2.44657E-09 +i* -6.7886E-11| +| 13| -0.983286 +i* 0.18202| 0.999991| 3.21676E-12 +i*-9.48297E-13| +| 14| 0.324176 +i* -0.945987| 0.999991| 1.53594E-11 +i*-1.57324E-12| +| 15| 0.66503 +i* 0.746804| 0.999991| 5.74873E-13 +i* 8.53884E-12| +| 16| -0.977132 +i* 0.212706| 1.00002|-2.02093E-10 +i* 3.44548E-10| +| 17| 0.294374 +i* -0.955681| 0.999991| -1.2063E-11 +i* 1.32238E-11| +| 18| 0.688092 +i* 0.725645| 1.00002|-4.51021E-09 +i* 1.95437E-09| +| 19| -0.969965 +i* 0.243206| 0.999991| 6.88072E-12 +i* 3.20268E-13| +| 20| 0.264283 +i* -0.964436| 0.999991| 2.5573E-11 +i*-6.45539E-12| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 0.999991 +150000 racines de module = 1.00002 +proc 2 +proc 0 +proc 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^250000 + (-10 +i*0)*x^350000 + (1 +i*0)*x^600000 + +(-25000 +i*0)*x^249999 + (-3.5E+06 +i*0)*x^349999 + (600000 +i*0)*x^599999 + +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 1, start 200021 size 200021 +proc 1 start 200021 size 200021 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 0, start 0 size 200021 +proc 0 start 0 size 200021 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 2, start 400042 size 200021 +proc 2 start 400042 size 200021 +iter : 1 Arret : 0.00226498 s/iter 9.046598 +iter : 2 Arret : 0.286514 s/iter 9.041345 +iter : 3 Arret : 0.37126 s/iter 9.194828 +iter : 4 Arret : 0.357158 s/iter 9.425406 +iter : 5 Arret : 0.489627 s/iter 9.503770 +iter : 6 Arret : 0.0394603 s/iter 9.532369 +iter : 7 Arret : 0.0346491 s/iter 9.595128 +iter : 8 Arret : 0.058482 s/iter 9.502225 +iter : 9 Arret : 0.0456855 s/iter 9.517820 +iter : 10 Arret : 0.00888245 s/iter 9.163517 +iter : 11 Arret : 0.00755074 s/iter 9.164057 +iter : 12 Arret : 0.00999277 s/iter 9.132635 +iter : 13 Arret : 0.00331316 s/iter 9.163813 +iter : 14 Arret : 0.00348352 s/iter 9.037872 +iter : 15 Arret : 0.00131143 s/iter 9.062842 +iter : 16 Arret : 0.000194649 s/iter 9.032916 +iter : 17 Arret : 0.000108537 s/iter 9.040569 +iter : 18 Arret : 4.32539E-06 s/iter 9.040533 +iter : 19 Arret : 1.30764E-08 s/iter 9.032518 +iter : 20 Arret : 5.19734E-11 s/iter 9.039277 +iter : 21 Arret : 2.06945E-13 s/iter 9.037120 +temps : 193.628 seconde(s) +Nb iterations : 21 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.29984E-05 +Stabilite : 6.87034E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540302 +i* 0.841463| 0.999993| 8.34199E-12 +i* -1.9051E-11| +| 2| -0.553438 +i* -0.832883| 0.999993|-4.48197E-12 +i* 2.11486E-11| +| 3| -0.579282 +i* -0.815119| 0.999993| 1.33613E-11 +i*-1.98701E-11| +| 4| 0.592014 +i* 0.805919| 0.999993|-3.98037E-12 +i* 9.55808E-12| +| 5| -0.604557 +i* -0.796554| 0.999993|-2.82974E-12 +i* 9.99473E-12| +| 6| 0.61698 +i* 0.78697| 0.999993|-4.77973E-12 +i* 2.40621E-11| +| 7| -0.629237 +i* -0.777205| 0.999993|-2.92122E-12 +i*-4.85867E-12| +| 8| 0.641354 +i* 0.767237| 0.999993|-1.64209E-11 +i* 1.12904E-12| +| 9| -0.653299 +i* -0.757092| 0.999993|-8.22453E-13 +i* 2.82818E-12| +| 10| 0.665096 +i* 0.746749| 0.999993| -1.2145E-11 +i* 1.89129E-11| +| 11| -0.676717 +i* -0.736234| 0.999993|-1.26079E-11 +i*-1.25073E-11| +| 12| 0.688185 +i* 0.725526| 0.999993|-4.43978E-12 +i*-2.31382E-11| +| 13| -0.699466 +i* -0.714679| 1.00001| 3.92343E-10 +i*-3.02623E-09| +| 14| 0.710597 +i* 0.70359| 0.999993| 1.28564E-11 +i* 1.56626E-11| +| 15| -0.721517 +i* -0.69241| 1.00001| 1.76709E-09 +i*-4.04041E-09| +| 16| 0.73231 +i* 0.680962| 0.999993| 1.34706E-11 +i*-4.43489E-12| +| 17| -0.742904 +i* -0.669389| 0.999993|-7.78222E-12 +i* 1.50098E-11| +| 18| 0.7533 +i* 0.657691| 1.00001| 1.64587E-09 +i*-3.03669E-09| +| 19| -0.763538 +i* -0.645777| 1.00001|-8.22278E-10 +i*-5.86372E-10| +| 20| 0.773539 +i* 0.633763| 1.00001| -4.2314E-09 +i* 1.86243E-09| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 0.999993 +250000 racines de module = 1.00001 +proc 1 +proc 2 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^300000 + (-10 +i*0)*x^500000 + (1 +i*0)*x^800000 + +(-30000 +i*0)*x^299999 + (-5E+06 +i*0)*x^499999 + (800000 +i*0)*x^799999 + +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 1, start 266666 size 266666 +proc 1 start 266666 size 266666 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 2, start 533332 size 266666 +proc 2 start 533332 size 266666 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 0, start 0 size 266666 +proc 0 start 0 size 266666 +iter : 1 Arret : 0.013303 s/iter 15.845449 +iter : 2 Arret : 1.22368 s/iter 15.831599 +iter : 3 Arret : 0.34478 s/iter 15.835186 +iter : 4 Arret : 0.804966 s/iter 15.861997 +iter : 5 Arret : 0.957981 s/iter 15.872722 +iter : 6 Arret : 0.716801 s/iter 16.172143 +iter : 7 Arret : 0.496135 s/iter 16.224317 +iter : 8 Arret : 0.326979 s/iter 16.181063 +iter : 9 Arret : 0.252467 s/iter 16.538160 +iter : 10 Arret : 0.244395 s/iter 16.297675 +iter : 11 Arret : 0.173672 s/iter 16.136429 +iter : 12 Arret : 0.197369 s/iter 16.323607 +iter : 13 Arret : 0.168305 s/iter 16.324722 +iter : 14 Arret : 0.168579 s/iter 16.212899 +iter : 15 Arret : 0.208926 s/iter 16.207350 +iter : 16 Arret : 0.165995 s/iter 16.153929 +iter : 17 Arret : 0.223284 s/iter 16.250807 +iter : 18 Arret : 0.324113 s/iter 16.164325 +iter : 19 Arret : 0.771739 s/iter 16.136061 +iter : 20 Arret : 1.00477 s/iter 16.138977 +iter : 21 Arret : 1.00247 s/iter 16.140663 +iter : 22 Arret : 0.543015 s/iter 16.140175 +iter : 23 Arret : 0.476319 s/iter 15.852664 +iter : 24 Arret : 0.401176 s/iter 15.844834 +iter : 25 Arret : 0.142005 s/iter 15.837565 +iter : 26 Arret : 0.0393995 s/iter 15.832097 +iter : 27 Arret : 0.0199662 s/iter 15.824967 +iter : 28 Arret : 0.00992138 s/iter 15.835004 +iter : 29 Arret : 0.00549329 s/iter 15.825203 +iter : 30 Arret : 0.000480868 s/iter 15.805032 +iter : 31 Arret : 3.00435E-06 s/iter 15.832975 +iter : 32 Arret : 3.08148E-09 s/iter 15.816239 +iter : 33 Arret : 6.64256E-12 s/iter 15.831931 +iter : 34 Arret : 1.43767E-14 s/iter 15.816196 +temps : 545.367 seconde(s) +Nb iterations : 34 +Nb de depassements de capacite exponentielle : 0 +Precision : 12.9528 +Stabilite : 2.22043E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540305 +i* 0.841464| 0.999995| -2.03E-11 +i* 2.74701E-11| +| 2| 0.592014 +i* 0.805922| 0.999995|-1.82734E-11 +i* 2.10218E-11| +| 3| 0.617007 +i* 0.786952| 0.999995| 4.23442E-11 +i* -6.2147E-12| +| 4| 0.641392 +i* 0.767207| 0.999995| 6.90537E-12 +i*-5.12417E-11| +| 5| 0.665146 +i* 0.746707| 0.999995| 2.02977E-11 +i* 7.48579E-12| +| 6| 0.688245 +i* 0.725472| 0.999995|-1.73153E-11 +i* -1.2656E-11| +| 7| 0.710675 +i* 0.703514| 0.999995|-8.58691E-12 +i* 2.79902E-11| +| 8| 0.732388 +i* 0.68088| 0.999995| 9.45355E-12 +i* 2.09024E-11| +| 9| 0.753381 +i* 0.657577| 0.999995|-1.40248E-11 +i* 5.11502E-11| +| 10| 0.77364 +i* 0.633618| 0.999995|-1.72307E-11 +i* 1.22723E-11| +| 11| 0.793138 +i* 0.609034| 0.999995| 3.89222E-12 +i* 2.21356E-11| +| 12| 0.811855 +i* 0.583851| 0.999995|-1.28337E-11 +i*-5.47207E-12| +| 13| 0.829772 +i* 0.558094| 0.999995|-1.63114E-11 +i*-1.64246E-12| +| 14| 0.846873 +i* 0.531786| 0.999995|-1.80345E-12 +i* 5.96675E-11| +| 15| 0.863146 +i* 0.504945| 0.999995|-1.01228E-11 +i* 1.20409E-11| +| 16| 0.878557 +i* 0.477628| 0.999995|-2.16493E-12 +i* 1.10533E-11| +| 17| 0.893104 +i* 0.449841| 0.999995|-1.48552E-11 +i* 1.06063E-11| +| 18| 0.906777 +i* 0.4216| 0.999995|-1.38745E-11 +i* 5.33384E-12| +| 19| 0.919557 +i* 0.392944| 0.999995|-3.33245E-11 +i* 5.94386E-12| +| 20| 0.931433 +i* 0.363901| 0.999995| 4.93219E-11 +i*-2.82651E-11| ++---+----------------------------+------------+----------------------------+ +499999 racines de module = 0.999995 +299999 racines de module = 1.00001 + 2 racines de module = 1 +proc 0 +proc 1 +proc 2 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^400000 + (-10 +i*0)*x^600000 + (1 +i*0)*x^1000000 + +(-40000 +i*0)*x^399999 + (-6E+06 +i*0)*x^599999 + (1E+06 +i*0)*x^999999 + +zone limite de 'log-exp' 1.00035 +zone limite de 'log-exp' 1.00035 +zone limite de 'log-exp' 1.00035 +dimgrid 3907 dimblock 256 degrePoly 1000000 +proc 1, start 333397 size 333397 +dimgrid 3907 dimblock 256 degrePoly 1000000 +proc 2, start 666794 size 333397 +dimgrid 3907 dimblock 256 degrePoly 1000000 +proc 0, start 0 size 333397 +proc 0 start 0 size 333397 +proc 1 start 333397 size 333397 +proc 2 start 666794 size 333397 +iter : 1 Arret : 0.000575468 s/iter 24.305180 +iter : 2 Arret : 0.00170361 s/iter 24.785627 +iter : 3 Arret : 0.00222192 s/iter 24.748506 +iter : 4 Arret : 0.017164 s/iter 24.358793 +iter : 5 Arret : 0.0140181 s/iter 24.395447 +iter : 6 Arret : 0.00863706 s/iter 24.606501 +iter : 7 Arret : 0.00646893 s/iter 24.858810 +iter : 8 Arret : 0.00503905 s/iter 24.788762 +iter : 9 Arret : 0.0052262 s/iter 24.427751 +iter : 10 Arret : 0.00485981 s/iter 24.358969 +iter : 11 Arret : 0.00893375 s/iter 24.357900 +iter : 12 Arret : 0.00681765 s/iter 24.368587 +iter : 13 Arret : 0.0016963 s/iter 24.362646 +iter : 14 Arret : 0.00106588 s/iter 24.361655 +iter : 15 Arret : 0.000173681 s/iter 24.354770 +iter : 16 Arret : 1.82719E-05 s/iter 24.350867 +iter : 17 Arret : 2.03911E-05 s/iter 24.358719 +iter : 18 Arret : 3.78438E-06 s/iter 24.284202 +iter : 19 Arret : 1.28475E-07 s/iter 24.295585 +iter : 20 Arret : 1.88663E-09 s/iter 24.290679 +iter : 21 Arret : 2.81124E-11 s/iter 24.288024 +iter : 22 Arret : 4.1882E-13 s/iter 24.288788 +temps : 542.745 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.4225E-07 +Stabilite : 4.77796E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841468| 0.999996| 5.07216E-12 +i* 6.41236E-12| +| 2| 0.529701 +i* 0.84818| 0.999996|-4.61853E-13 +i*-4.17888E-12| +| 3| 0.524361 +i* 0.851491| 0.999996|-2.47296E-11 +i* 1.78327E-11| +| 4| 0.51901 +i* 0.854764| 0.999996| 9.45599E-12 +i* 2.07434E-11| +| 5| 0.513629 +i* 0.858008| 0.999996| 2.32483E-11 +i* 6.70747E-12| +| 6| 0.508237 +i* 0.861213| 0.999996|-1.34339E-11 +i* 9.87854E-12| +| 7| 0.502825 +i* 0.864384| 0.999996|-3.18459E-11 +i* 7.64744E-12| +| 8| 0.497384 +i* 0.867526| 0.999996| 2.97429E-11 +i*-6.06626E-13| +| 9| 0.491932 +i* 0.870629| 0.999996|-1.74121E-11 +i*-2.86359E-11| +| 10| 0.486452 +i* 0.873703| 0.999996| 3.0312E-11 +i* 1.02214E-11| +| 11| 0.480962 +i* 0.876737| 0.999996| 1.81546E-11 +i* 8.04012E-12| +| 12| 0.475453 +i* 0.879736| 0.999996| 3.09861E-11 +i* 4.093E-12| +| 13| 0.469917 +i* 0.882706| 0.999996|-1.29106E-11 +i*-2.31489E-11| +| 14| 0.46437 +i* 0.885637| 0.999996| 1.38481E-11 +i* -1.517E-11| +| 15| 0.458797 +i* 0.888537| 0.999996| 2.78862E-11 +i* 1.10441E-11| +| 16| 0.453214 +i* 0.891397| 0.999996| 2.45506E-11 +i* 3.1726E-11| +| 17| 0.447614 +i* 0.894223| 0.999996|-1.08491E-12 +i*-2.12277E-11| +| 18| 0.441986 +i* 0.897017| 0.999996| 2.72476E-11 +i* 3.22485E-11| +| 19| 0.436351 +i* 0.899772| 0.999996| 2.92226E-11 +i* 2.71536E-11| +| 20| 0.430689 +i* 0.902496| 0.999996|-1.25435E-11 +i* 3.86925E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 0.999996 +400000 racines de module = 1.00001 +proc 1 +proc 2 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^500000 + (-10 +i*0)*x^700000 + (1 +i*0)*x^1200000 + +(-50000 +i*0)*x^499999 + (-7E+06 +i*0)*x^699999 + (1.2E+06 +i*0)*x^1199999 + +zone limite de 'log-exp' 1.0003 +zone limite de 'log-exp' 1.0003 +zone limite de 'log-exp' 1.0003 +dimgrid 4688 dimblock 256 degrePoly 1200000 +proc 1, start 400042 size 400042 +dimgrid 4688 dimblock 256 degrePoly 1200000 +proc 0, start 0 size 400042 +proc 1 start 400042 size 400042 +dimgrid 4688 dimblock 256 degrePoly 1200000 +proc 2, start 800084 size 400042 +proc 2 start 800084 size 400042 +proc 0 start 0 size 400042 +iter : 1 Arret : 0.00577737 s/iter 35.191437 +iter : 2 Arret : 1.60124 s/iter 35.687308 +iter : 3 Arret : 2.50845 s/iter 38.522110 +iter : 4 Arret : 0.88974 s/iter 37.972511 +iter : 5 Arret : 1.13571 s/iter 38.354084 +iter : 6 Arret : 0.802875 s/iter 38.309790 +iter : 7 Arret : 1.23189 s/iter 38.251469 +iter : 8 Arret : 2.00112 s/iter 38.369432 +iter : 9 Arret : 0.783463 s/iter 39.250540 +iter : 10 Arret : 1.64822 s/iter 38.419390 +iter : 11 Arret : 1.13791 s/iter 38.520696 +iter : 12 Arret : 4.19099 s/iter 38.244319 +iter : 13 Arret : 1.7036 s/iter 37.449747 +iter : 14 Arret : 0.953437 s/iter 37.710513 +iter : 15 Arret : 0.86512 s/iter 37.422749 +iter : 16 Arret : 3.83001 s/iter 37.601442 +iter : 17 Arret : 1.37636 s/iter 37.548538 +iter : 18 Arret : 1.57226 s/iter 37.331887 +iter : 19 Arret : 0.995472 s/iter 37.376323 +iter : 20 Arret : 0.780537 s/iter 37.065303 +iter : 21 Arret : 3.73222 s/iter 36.965816 +iter : 22 Arret : 1.52875 s/iter 36.851015 +iter : 23 Arret : 0.925666 s/iter 36.788322 +iter : 24 Arret : 0.416457 s/iter 36.673216 +iter : 25 Arret : 1.21819 s/iter 36.551043 +iter : 26 Arret : 0.782138 s/iter 36.720148 +iter : 27 Arret : 0.611118 s/iter 36.382233 +iter : 28 Arret : 1.40936 s/iter 36.605900 +iter : 29 Arret : 0.136834 s/iter 36.551610 +iter : 30 Arret : 0.982775 s/iter 36.549899 +iter : 31 Arret : 0.482303 s/iter 36.446318 +iter : 32 Arret : 0.314354 s/iter 35.262030 +iter : 33 Arret : 0.221468 s/iter 35.437839 +iter : 34 Arret : 0.148832 s/iter 35.903162 +iter : 35 Arret : 0.0771528 s/iter 35.243527 +iter : 36 Arret : 0.00786376 s/iter 35.408694 +iter : 37 Arret : 0.00153832 s/iter 35.423139 +iter : 38 Arret : 0.00226222 s/iter 35.250849 +iter : 39 Arret : 0.000875734 s/iter 35.254600 +iter : 40 Arret : 2.10425E-05 s/iter 35.253398 +iter : 41 Arret : 2.59204E-06 s/iter 35.253869 +iter : 42 Arret : 2.06088E-08 s/iter 35.143640 +iter : 43 Arret : 8.18267E-11 s/iter 35.260245 +iter : 44 Arret : 3.25714E-13 s/iter 35.264980 +temps : 1617.65 seconde(s) +Nb iterations : 44 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.09088E-05 +Stabilite : 2.22047E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.54031 +i* 0.841472| 1| 1.4588E-09 +i* 4.51768E-09| +| 2| 0.513629 +i* 0.858008| 0.999997| 3.02357E-11 +i* 3.41858E-11| +| 3| 0.486451 +i* 0.873713| 1|-5.85295E-09 +i*-2.49566E-10| +| 4| 0.458789 +i* 0.888542| 0.999997| 2.48135E-13 +i*-2.88822E-11| +| 5| 0.430677 +i* 0.902502| 0.999997|-2.03271E-11 +i*-3.18325E-11| +| 6| 0.402092 +i* 0.915605| 1| 5.55538E-09 +i*-1.34284E-09| +| 7| 0.3732 +i* 0.927747| 0.999997| -2.5707E-11 +i* 3.11093E-13| +| 8| 0.3439 +i* 0.939003| 0.999997|-1.12714E-11 +i* 1.5453E-11| +| 9| 0.314261 +i* 0.949333| 0.999997| 5.41895E-11 +i*-2.05278E-11| +| 10| 0.284313 +i* 0.958728| 0.999997| 2.69426E-11 +i* 2.77974E-11| +| 11| 0.254084 +i* 0.967179| 0.999997| 1.5277E-11 +i* 4.73027E-12| +| 12| 0.223605 +i* 0.974676| 0.999997| -8.1017E-11 +i*-3.77299E-11| +| 13| 0.192915 +i* 0.981212| 0.999997| 1.07495E-11 +i* 5.766E-12| +| 14| 0.162017 +i* 0.986785| 0.999997| 4.59321E-12 +i*-4.42106E-13| +| 15| 0.130977 +i* 0.991382| 0.999997| 5.89659E-11 +i* 7.29122E-12| +| 16| 0.0997898 +i* 0.995005| 0.999997|-3.84177E-11 +i*-1.21923E-11| +| 17| 0.0685136 +i* 0.997647| 0.999997|-2.98188E-11 +i* 2.79243E-12| +| 18| 0.0371504 +i* 0.999314| 1|-3.18728E-10 +i*-2.97119E-09| +| 19| 0.00578048 +i* 0.99998| 0.999997| 3.46787E-11 +i* 1.94857E-13| +| 20| -0.0256056 +i* 0.999669| 0.999997| 2.01068E-11 +i*-1.22213E-12| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +700000 racines de module = 0.999997 +proc 0 +proc 1 +proc 2 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^600000 + (-10 +i*0)*x^800000 + (1 +i*0)*x^1400000 + +(-60000 +i*0)*x^599999 + (-8E+06 +i*0)*x^799999 + (1.4E+06 +i*0)*x^1399999 + +zone limite de 'log-exp' 1.00025 +zone limite de 'log-exp' 1.00025 +zone limite de 'log-exp' 1.00025 +dimgrid 5469 dimblock 256 degrePoly 1400000 +proc 1, start 466688 size 466688 +proc 1 start 466688 size 466688 +dimgrid 5469 dimblock 256 degrePoly 1400000 +proc 2, start 933376 size 466688 +proc 2 start 933376 size 466688 +dimgrid 5469 dimblock 256 degrePoly 1400000 +proc 0, start 0 size 466688 +proc 0 start 0 size 466688 +iter : 1 Arret : 0.0476652 s/iter 48.053051 +iter : 2 Arret : 1.02145 s/iter 49.162936 +iter : 3 Arret : 3.11851 s/iter 50.138080 +iter : 4 Arret : 1.87547 s/iter 50.661272 +iter : 5 Arret : 1.24028 s/iter 52.617942 +iter : 6 Arret : 1.33274 s/iter 52.723740 +iter : 7 Arret : 1.1089 s/iter 52.451625 +iter : 8 Arret : 1.32856 s/iter 53.817849 +iter : 9 Arret : 0.584436 s/iter 54.233382 +iter : 10 Arret : 0.682561 s/iter 53.018367 +iter : 11 Arret : 1.10899 s/iter 52.903852 +iter : 12 Arret : 1.24673 s/iter 52.699001 +iter : 13 Arret : 2.03756 s/iter 51.822577 +iter : 14 Arret : 0.74595 s/iter 51.940124 +iter : 15 Arret : 0.336711 s/iter 51.566761 +iter : 16 Arret : 0.386748 s/iter 51.449106 +iter : 17 Arret : 0.175345 s/iter 51.008579 +iter : 18 Arret : 0.0799077 s/iter 50.523143 +iter : 19 Arret : 0.106562 s/iter 50.311514 +iter : 20 Arret : 0.102063 s/iter 50.013859 +iter : 21 Arret : 0.0811226 s/iter 48.967237 +iter : 22 Arret : 0.0777804 s/iter 48.802184 +iter : 23 Arret : 0.06176 s/iter 48.968763 +iter : 24 Arret : 0.0274141 s/iter 48.869900 +iter : 25 Arret : 0.0246722 s/iter 48.033190 +iter : 26 Arret : 0.0140326 s/iter 48.024256 +iter : 27 Arret : 0.00823776 s/iter 48.046597 +iter : 28 Arret : 0.00458441 s/iter 48.050189 +iter : 29 Arret : 0.000250093 s/iter 48.028503 +iter : 30 Arret : 6.92011E-06 s/iter 48.046144 +iter : 31 Arret : 1.1801E-07 s/iter 48.051103 +iter : 32 Arret : 1.60292E-09 s/iter 48.032612 +iter : 33 Arret : 2.20691E-11 s/iter 48.032677 +iter : 34 Arret : 3.03651E-13 s/iter 48.049192 +temps : 1707.73 seconde(s) +Nb iterations : 34 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.35409E-07 +Stabilite : 2.22046E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841469| 0.999997|-8.47142E-11 +i* 1.92466E-11| +| 2| 0.513623 +i* 0.858013| 0.999997|-2.15776E-11 +i*-2.98557E-11| +| 3| -0.52703 +i* -0.849843| 0.999997|-6.50922E-11 +i* 8.44216E-12| +| 4| 0.486439 +i* 0.873711| 0.999997|-3.15932E-11 +i*-1.15957E-12| +| 5| -0.500096 +i* -0.865967| 0.999997| 3.56147E-11 +i*-3.12713E-11| +| 6| 0.458776 +i* 0.888549| 0.999997|-1.89702E-11 +i* 4.08274E-12| +| 7| -0.472669 +i* -0.881237| 0.999997|-1.66496E-11 +i*-3.61498E-11| +| 8| 0.430661 +i* 0.902511| 0.999997|-1.60558E-11 +i*-1.29949E-11| +| 9| -0.444791 +i* -0.895631| 0.999997|-8.89955E-13 +i* 2.61938E-12| +| 10| 0.402136 +i* 0.915577| 0.999997| 6.5834E-12 +i* -1.3935E-11| +| 11| -0.416432 +i* -0.909164| 0.999997| 1.97816E-11 +i* 3.10848E-11| +| 12| 0.373171 +i* 0.927759| 0.999997|-2.17995E-11 +i*-2.96867E-12| +| 13| -0.387698 +i* -0.921783| 0.999997|-1.86324E-11 +i* -4.6545E-11| +| 14| 0.343875 +i* 0.939012| 0.999997| 3.84962E-11 +i* 2.59646E-11| +| 15| -0.358575 +i* -0.933498| 0.999997|-3.74776E-11 +i*-3.89954E-11| +| 16| 0.314233 +i* 0.949343| 0.999997| 1.02587E-11 +i*-4.25648E-11| +| 17| -0.329098 +i* -0.944293| 0.999997|-1.57903E-11 +i* 2.05052E-11| +| 18| 0.284281 +i* 0.958738| 0.999997| 2.51592E-11 +i* 2.09243E-11| +| 19| -0.299297 +i* -0.954157| 0.999997| 5.03608E-12 +i* 1.70503E-11| +| 20| 0.254048 +i* 0.967189| 0.999997|-2.81228E-11 +i*-1.66302E-11| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 0.999997 +600000 racines de module = 1 +proc 0 +proc 1 +proc 2 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^700000 + (-10 +i*0)*x^900000 + (1 +i*0)*x^1600000 + +(-70000 +i*0)*x^699999 + (-9E+06 +i*0)*x^899999 + (1.6E+06 +i*0)*x^1599999 + + +template:31135 terminated with signal 11 at PC=404b41 SP=7fffb89650f0. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:31134 terminated with signal 11 at PC=404b41 SP=7fff9a829580. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:31136 terminated with signal 11 at PC=404b41 SP=7fffe0fa8a40. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +-------------------------------------------------------------------------- +mpirun has exited due to process rank 1 with PID 31135 on +node node1-50 exiting improperly. There are two reasons this could occur: + +1. this process did not call "init" before exiting, but others in +the job did. This can cause a job to hang indefinitely while it waits +for all processes to call "init". By rule, if one process calls "init", +then ALL processes must call "init" prior to termination. + +2. this process called "init", but exited without calling "finalize". +By rule, all processes that call "init" MUST call "finalize" prior to +exiting or it will be considered an "abnormal termination" + +This may have caused other processes in the application to be +terminated by signals sent by mpirun (as reported here). +-------------------------------------------------------------------------- +proc 1 +proc 2 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^800000 + (-10 +i*0)*x^1000000 + (1 +i*0)*x^1800000 + +(-80000 +i*0)*x^799999 + (-1E+07 +i*0)*x^999999 + (1.8E+06 +i*0)*x^1799999 + + +template:31146 terminated with signal 11 at PC=404b41 SP=7fff82ca5fc0. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:31144 terminated with signal 11 at PC=404b41 SP=7fff0a32a700. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:31145 terminated with signal 11 at PC=404b41 SP=7fff9885ac60. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +-------------------------------------------------------------------------- +mpirun has exited due to process rank 1 with PID 31145 on +node node1-50 exiting improperly. There are two reasons this could occur: + +1. this process did not call "init" before exiting, but others in +the job did. This can cause a job to hang indefinitely while it waits +for all processes to call "init". By rule, if one process calls "init", +then ALL processes must call "init" prior to termination. + +2. this process called "init", but exited without calling "finalize". +By rule, all processes that call "init" MUST call "finalize" prior to +exiting or it will be considered an "abnormal termination" + +This may have caused other processes in the application to be +terminated by signals sent by mpirun (as reported here). +-------------------------------------------------------------------------- +proc 1 +proc 2 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^500000 + (-10 +i*0)*x^1500000 + (1 +i*0)*x^2000000 + +(-50000 +i*0)*x^499999 + (-1.5E+07 +i*0)*x^1499999 + (2E+06 +i*0)*x^1999999 + + +template:31155 terminated with signal 11 at PC=404b41 SP=7fff5c26c610. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:31154 terminated with signal 11 at PC=404b41 SP=7fffd7c701a0. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:31156 terminated with signal 11 at PC=404b41 SP=7fff9a2a1b00. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +-------------------------------------------------------------------------- +mpirun has exited due to process rank 1 with PID 31155 on +node node1-50 exiting improperly. There are two reasons this could occur: + +1. this process did not call "init" before exiting, but others in +the job did. This can cause a job to hang indefinitely while it waits +for all processes to call "init". By rule, if one process calls "init", +then ALL processes must call "init" prior to termination. + +2. this process called "init", but exited without calling "finalize". +By rule, all processes that call "init" MUST call "finalize" prior to +exiting or it will be considered an "abnormal termination" + +This may have caused other processes in the application to be +terminated by signals sent by mpirun (as reported here). +-------------------------------------------------------------------------- diff --git a/Simulations/sparse_mpi/sparse_mpi_3GPU.sge b/Simulations/sparse_mpi/sparse_mpi_3GPU.sge new file mode 100644 index 0000000..e779c55 --- /dev/null +++ b/Simulations/sparse_mpi/sparse_mpi_3GPU.sge @@ -0,0 +1,25 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=3 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -V +#$ -cwd +#$ -N sparse_mpi_3GPU +#$ -pe mpi 3 + + +module load cuda/7.0 +module load ompi/gcc + +mpirun -np $NSLOTS ./template -r -i 60000 40000 +mpirun -np $NSLOTS ./template -r -i 150000 50000 +mpirun -np $NSLOTS ./template -r -i 250000 150000 +mpirun -np $NSLOTS ./template -r -i 350000 250000 +mpirun -np $NSLOTS ./template -r -i 500000 300000 +mpirun -np $NSLOTS ./template -r -i 600000 400000 +mpirun -np $NSLOTS ./template -r -i 700000 500000 +mpirun -np $NSLOTS ./template -r -i 800000 600000 +mpirun -np $NSLOTS ./template -r -i 900000 700000 +mpirun -np $NSLOTS ./template -r -i 1000000 800000 +mpirun -np $NSLOTS ./template -r -i 1500000 500000 diff --git a/Simulations/sparse_mpi/sparse_mpi_4GPU.o140023 b/Simulations/sparse_mpi/sparse_mpi_4GPU.o140023 new file mode 100644 index 0000000..872679a --- /dev/null +++ b/Simulations/sparse_mpi/sparse_mpi_4GPU.o140023 @@ -0,0 +1,841 @@ +REMAINING: 4 +Taking GPU #0 +Taking GPU #1 +Taking GPU #2 +Taking GPU #3 +proc 2 +proc 3 +proc 0 +proc 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^40000 + (-10 +i*0)*x^60000 + (1 +i*0)*x^100000 + +(-4000 +i*0)*x^39999 + (-600000 +i*0)*x^59999 + (100000 +i*0)*x^99999 + +zone limite de 'log-exp' 1.00356 +zone limite de 'log-exp' 1.00356 +zone limite de 'log-exp' 1.00356 +zone limite de 'log-exp' 1.00356 +dimgrid 391 dimblock 256 degrePoly 100000 +proc 2, start 50048 size 25024 +dimgrid 391 dimblock 256 degrePoly 100000 +proc 0, start 0 size 25024 +dimgrid 391 dimblock 256 degrePoly 100000 +proc 1, start 25024 size 25024 +proc 2 start 50048 size 25024 +dimgrid 391 dimblock 256 degrePoly 100000 +proc 3, start 75072 size 25024 +proc 3 start 75072 size 25024 +proc 0 start 0 size 25024 +proc 1 start 25024 size 25024 +iter : 1 Arret : 0.00317264 s/iter 0.222955 +iter : 2 Arret : 0.00227167 s/iter 0.222762 +iter : 3 Arret : 0.00211003 s/iter 0.222838 +iter : 4 Arret : 0.00200743 s/iter 0.222746 +iter : 5 Arret : 0.00207223 s/iter 0.222703 +iter : 6 Arret : 0.00517083 s/iter 0.222804 +iter : 7 Arret : 0.0188667 s/iter 0.297002 +iter : 8 Arret : 0.0181557 s/iter 0.222717 +iter : 9 Arret : 0.0045178 s/iter 0.295501 +iter : 10 Arret : 0.000994006 s/iter 0.222726 +iter : 11 Arret : 0.00103689 s/iter 0.222762 +iter : 12 Arret : 0.000385068 s/iter 0.222694 +iter : 13 Arret : 0.000378374 s/iter 0.222655 +iter : 14 Arret : 0.000135377 s/iter 0.222528 +iter : 15 Arret : 2.77949E-05 s/iter 0.222508 +iter : 16 Arret : 6.74524E-07 s/iter 0.222580 +iter : 17 Arret : 2.18155E-09 s/iter 0.222640 +iter : 18 Arret : 2.22292E-11 s/iter 0.222554 +iter : 19 Arret : 3.31178E-13 s/iter 0.222495 +temps : 4.60588 seconde(s) +Nb iterations : 19 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.75156E-07 +Stabilite : 1.57015E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540308 +i* 0.841422| 0.999962|-1.95866E-12 +i*-4.55465E-13| +| 2| -0.113164 +i* 0.993538| 0.999962|-4.34919E-12 +i* 9.60242E-13| +| 3| -0.226732 +i* -0.974016| 1.00006|-1.34468E-09 +i*-3.70749E-10| +| 4| -0.715763 +i* 0.698289| 0.999962| 9.11271E-13 +i* 2.47219E-12| +| 5| 0.439922 +i* -0.897993| 0.999962|-3.49498E-13 +i* 1.66432E-12| +| 6| -0.996122 +i* 0.0886386| 1.00006| 4.72785E-10 +i* 4.13616E-11| +| 7| 0.908546 +i* -0.417692| 0.999962| 4.78506E-13 +i* 1.54377E-13| +| 8| -0.827813 +i* -0.560935| 0.999962| 9.76996E-13 +i*-2.04309E-12| +| 9| 0.968129 +i* 0.250682| 1.00006|-2.31715E-10 +i* 1.34848E-10| +| 10| -0.286842 +i* -0.958038| 1.00006|-5.93554E-10 +i*-2.45345E-10| +| 11| 0.591653 +i* 0.806145| 0.999962|-9.87654E-13 +i*-3.03635E-12| +| 12| -0.0511836 +i* 0.998651| 0.999962|-2.22622E-12 +i*-3.69013E-14| +| 13| -0.67097 +i* 0.741432| 0.999962|-8.03801E-14 +i*-1.68204E-12| +| 14| 0.383249 +i* -0.923603| 0.999962|-1.29119E-12 +i*-1.37426E-12| +| 15| -0.988685 +i* 0.15039| 1.00006|-1.61051E-10 +i* 7.18515E-11| +| 16| 0.880824 +i* -0.473363| 0.999962|-4.03455E-13 +i* 2.85139E-12| +| 17| -0.861082 +i* -0.508391| 0.999962| 9.8066E-13 +i* 3.40478E-12| +| 18| 0.98184 +i* 0.190015| 1.00006| 8.88373E-10 +i*-2.66385E-10| +| 19| -0.345842 +i* -0.938354| 1.00006| 1.38421E-10 +i*-2.31696E-10| +| 20| 0.640621 +i* 0.767807| 0.999962|-6.98774E-13 +i* 1.13798E-12| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 0.999962 +40000 racines de module = 1.00006 +proc 0 +proc 1 +proc 2 +proc 3 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^50000 + (-10 +i*0)*x^150000 + (1 +i*0)*x^200000 + +(-5000 +i*0)*x^49999 + (-1.5E+06 +i*0)*x^149999 + (200000 +i*0)*x^199999 + +zone limite de 'log-exp' 1.00178 +zone limite de 'log-exp' 1.00178 +zone limite de 'log-exp' 1.00178 +zone limite de 'log-exp' 1.00178 +dimgrid 782 dimblock 256 degrePoly 200000 +proc 3, start 150144 size 50048 +dimgrid 782 dimblock 256 degrePoly 200000 +proc 2, start 100096 size 50048 +dimgrid 782 dimblock 256 degrePoly 200000 +proc 1, start 50048 size 50048 +proc 2 start 100096 size 50048 +proc 3 start 150144 size 50048 +dimgrid 782 dimblock 256 degrePoly 200000 +proc 0, start 0 size 50048 +proc 0 start 0 size 50048 +proc 1 start 50048 size 50048 +iter : 1 Arret : 0.000151301 s/iter 0.883876 +iter : 2 Arret : 0.000148172 s/iter 0.883954 +iter : 3 Arret : 0.000150921 s/iter 0.883918 +iter : 4 Arret : 0.00104559 s/iter 0.884013 +iter : 5 Arret : 0.00193123 s/iter 0.883951 +iter : 6 Arret : 0.0272836 s/iter 1.046760 +iter : 7 Arret : 0.102911 s/iter 1.039676 +iter : 8 Arret : 0.511951 s/iter 1.007660 +iter : 9 Arret : 0.34938 s/iter 1.017711 +iter : 10 Arret : 0.169476 s/iter 1.028045 +iter : 11 Arret : 0.0996115 s/iter 1.022146 +iter : 12 Arret : 0.0682782 s/iter 1.027682 +iter : 13 Arret : 0.0829552 s/iter 0.882503 +iter : 14 Arret : 0.0066689 s/iter 0.883836 +iter : 15 Arret : 0.0948233 s/iter 0.883899 +iter : 16 Arret : 0.00657146 s/iter 0.883885 +iter : 17 Arret : 0.00573604 s/iter 0.883894 +iter : 18 Arret : 0.00176675 s/iter 0.883914 +iter : 19 Arret : 0.000248502 s/iter 0.883875 +iter : 20 Arret : 6.04596E-05 s/iter 0.883987 +iter : 21 Arret : 4.48743E-06 s/iter 0.883955 +iter : 22 Arret : 4.98896E-09 s/iter 0.883421 +iter : 23 Arret : 4.99197E-13 s/iter 0.883862 +temps : 21.5922 seconde(s) +Nb iterations : 23 +Nb de depassements de capacite exponentielle : 0 +Precision : 0.000249603 +Stabilite : 2.22061E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540303 +i* 0.841453| 0.999985| 1.08703E-11 +i*-2.49217E-12| +| 2| -0.837195 +i* 0.546877| 0.999985| -5.4492E-12 +i* 1.09163E-12| +| 3| -0.553418 +i* -0.832885| 0.999985| -1.9722E-12 +i*-7.40397E-12| +| 4| 0.828599 +i* -0.559925| 1.00005|-7.54521E-09 +i* 1.47059E-08| +| 5| -0.8197 +i* 0.572767| 0.999985|-4.21663E-13 +i* -2.8616E-12| +| 6| -0.57917 +i* -0.815188| 0.999985|-5.13034E-12 +i*-1.52645E-12| +| 7| 0.810626 +i* -0.585537| 0.999985| 8.64808E-12 +i* 7.46794E-12| +| 8| 0.591872 +i* 0.806089| 1.00005|-1.69803E-09 +i* 9.43795E-09| +| 9| -0.801454 +i* 0.598134| 1.00005| 2.77439E-08 +i*-6.74504E-09| +| 10| -0.604356 +i* -0.796695| 0.999985|-1.64091E-13 +i* 1.59084E-12| +| 11| 0.791937 +i* -0.610578| 0.999985| 6.0707E-13 +i* 1.52922E-12| +| 12| 0.616763 +i* 0.78713| 0.999985|-4.48042E-12 +i* -2.6295E-12| +| 13| -0.782301 +i* 0.622877| 0.999985|-2.15827E-12 +i*-6.27114E-12| +| 14| -0.628991 +i* -0.777472| 1.00005| 6.93065E-09 +i*-8.65443E-09| +| 15| 0.772474 +i* -0.635023| 0.999985| 1.54783E-11 +i*-1.81338E-12| +| 16| 0.641054 +i* 0.767476| 0.999985|-3.47633E-12 +i* 1.20617E-11| +| 17| -0.762458 +i* 0.647014| 0.999985|-7.74447E-12 +i* 7.566E-12| +| 18| -0.652967 +i* -0.757366| 0.999985| 5.10392E-12 +i*-6.61069E-12| +| 19| 0.752302 +i* -0.658888| 1.00005| 3.99107E-09 +i* 1.02117E-08| +| 20| 0.66472 +i* 0.747072| 0.999985|-7.79776E-12 +i*-2.52076E-13| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 0.999985 +50000 racines de module = 1.00005 +proc 0 +proc 1 +proc 2 +proc 3 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^150000 + (-10 +i*0)*x^250000 + (1 +i*0)*x^400000 + +(-15000 +i*0)*x^149999 + (-2.5E+06 +i*0)*x^249999 + (400000 +i*0)*x^399999 + +zone limite de 'log-exp' 1.00089 +zone limite de 'log-exp' 1.00089 +zone limite de 'log-exp' 1.00089 +zone limite de 'log-exp' 1.00089 +dimgrid 1563 dimblock 256 degrePoly 400000 +proc 1, start 100032 size 100032 +dimgrid 1563 dimblock 256 degrePoly 400000 +proc 0, start 0 size 100032 +dimgrid 1563 dimblock 256 degrePoly 400000 +proc 2, start 200064 size 100032 +proc 0 start 0 size 100032 +dimgrid 1563 dimblock 256 degrePoly 400000 +proc 3, start 300096 size 100032 +proc 3 start 300096 size 100032 +proc 1 start 100032 size 100032 +proc 2 start 200064 size 100032 +iter : 1 Arret : 0.00163991 s/iter 3.109950 +iter : 2 Arret : 0.00132877 s/iter 3.110375 +iter : 3 Arret : 0.00184513 s/iter 3.110742 +iter : 4 Arret : 0.00262495 s/iter 3.111236 +iter : 5 Arret : 0.0150209 s/iter 3.111022 +iter : 6 Arret : 0.0137099 s/iter 3.414358 +iter : 7 Arret : 0.00835719 s/iter 3.385934 +iter : 8 Arret : 0.00440643 s/iter 3.394557 +iter : 9 Arret : 0.0060742 s/iter 3.385816 +iter : 10 Arret : 0.0050336 s/iter 3.099272 +iter : 11 Arret : 0.00112426 s/iter 3.099497 +iter : 12 Arret : 0.000775148 s/iter 3.099486 +iter : 13 Arret : 0.000376719 s/iter 3.099346 +iter : 14 Arret : 0.00024255 s/iter 3.099473 +iter : 15 Arret : 0.00012922 s/iter 3.099323 +iter : 16 Arret : 7.83137E-06 s/iter 3.099139 +iter : 17 Arret : 1.24719E-07 s/iter 3.099356 +iter : 18 Arret : 1.90294E-09 s/iter 3.099211 +iter : 19 Arret : 2.90173E-11 s/iter 3.099200 +iter : 20 Arret : 4.42472E-13 s/iter 3.099323 +temps : 63.5457 seconde(s) +Nb iterations : 20 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.49185E-08 +Stabilite : 4.42472E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540313 +i* 0.841453| 0.999991| 9.34197E-12 +i*-1.23633E-11| +| 2| -0.998329 +i* 0.057622| 0.999991| 4.43912E-12 +i* 1.27665E-12| +| 3| 0.439833 +i* -0.898097| 1.00002| 5.42841E-10 +i*-5.60653E-10| +| 4| -0.996033 +i* 0.0888768| 0.999991|-3.15592E-12 +i* 1.17456E-12| +| 5| 0.411559 +i* -0.9114| 1.00002| 1.04334E-09 +i*-9.84037E-10| +| 6| 0.59196 +i* 0.805956| 0.999991| 5.24358E-13 +i*-8.53073E-12| +| 7| -0.992759 +i* 0.120044| 0.999991| 2.58804E-12 +i* 2.47274E-12| +| 8| 0.382796 +i* -0.923823| 0.999991|-1.63092E-11 +i* 4.26312E-12| +| 9| 0.616925 +i* 0.78701| 0.999991| 4.27514E-12 +i*-1.13966E-11| +| 10| -0.988534 +i* 0.151098| 1.00002|-8.27014E-10 +i* 9.44171E-10| +| 11| 0.35366 +i* -0.935364| 0.999991|-1.92664E-11 +i* 1.19958E-11| +| 12| 0.641299 +i* 0.767311| 1.00002|-2.44657E-09 +i* -6.7886E-11| +| 13| -0.983301 +i* 0.182074| 1.00002| 4.64689E-09 +i* 2.00425E-09| +| 14| 0.324176 +i* -0.945987| 0.999991|-5.20695E-12 +i*-7.06984E-12| +| 15| 0.665084 +i* 0.746789| 1.00002| 1.80952E-09 +i* 3.83855E-09| +| 16| -0.977132 +i* 0.212706| 1.00002|-2.02093E-10 +i* 3.44548E-10| +| 17| 0.294374 +i* -0.955681| 0.999991|-2.37395E-11 +i*-2.53098E-12| +| 18| 0.688092 +i* 0.725645| 1.00002|-4.51021E-09 +i* 1.95437E-09| +| 19| -0.969965 +i* 0.243206| 0.999991| 6.88072E-12 +i* 3.20268E-13| +| 20| 0.264283 +i* -0.964436| 0.999991|-6.93356E-12 +i*-6.23118E-12| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 0.999991 +150000 racines de module = 1.00002 +proc 1 +proc 2 +proc 3 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^250000 + (-10 +i*0)*x^350000 + (1 +i*0)*x^600000 + +(-25000 +i*0)*x^249999 + (-3.5E+06 +i*0)*x^349999 + (600000 +i*0)*x^599999 + +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +zone limite de 'log-exp' 1.00059 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 0, start 0 size 150016 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 1, start 150016 size 150016 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 2, start 300032 size 150016 +proc 2 start 300032 size 150016 +dimgrid 2344 dimblock 256 degrePoly 600000 +proc 3, start 450048 size 150016 +proc 3 start 450048 size 150016 +proc 0 start 0 size 150016 +proc 1 start 150016 size 150016 +iter : 1 Arret : 0.00232098 s/iter 6.732718 +iter : 2 Arret : 0.0100189 s/iter 7.051391 +iter : 3 Arret : 0.283193 s/iter 6.895968 +iter : 4 Arret : 0.546502 s/iter 7.050469 +iter : 5 Arret : 1.13206 s/iter 7.216506 +iter : 6 Arret : 0.441232 s/iter 7.188011 +iter : 7 Arret : 0.210349 s/iter 7.506718 +iter : 8 Arret : 0.182959 s/iter 7.511723 +iter : 9 Arret : 0.15465 s/iter 7.074342 +iter : 10 Arret : 0.0273709 s/iter 7.116926 +iter : 11 Arret : 0.0179972 s/iter 7.067210 +iter : 12 Arret : 0.00914143 s/iter 7.085819 +iter : 13 Arret : 0.0269815 s/iter 7.021625 +iter : 14 Arret : 0.0268503 s/iter 6.729633 +iter : 15 Arret : 0.00822944 s/iter 6.729247 +iter : 16 Arret : 0.000264736 s/iter 6.731353 +iter : 17 Arret : 8.47333E-05 s/iter 6.730750 +iter : 18 Arret : 5.17416E-06 s/iter 6.730768 +iter : 19 Arret : 1.12397E-07 s/iter 6.731123 +iter : 20 Arret : 1.61278E-09 s/iter 6.731670 +iter : 21 Arret : 2.30014E-11 s/iter 6.731613 +iter : 22 Arret : 3.28041E-13 s/iter 6.730969 +temps : 153.471 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.81388E-08 +Stabilite : 3.28041E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540302 +i* 0.841463| 0.999993| 8.34199E-12 +i* -1.9051E-11| +| 2| -0.553438 +i* -0.832883| 0.999993|-2.10654E-12 +i*-2.55273E-11| +| 3| -0.579282 +i* -0.815119| 0.999993|-1.44751E-12 +i* 7.66798E-12| +| 4| 0.592012 +i* 0.805941| 1.00001| 4.1526E-09 +i* 1.02046E-09| +| 5| -0.604557 +i* -0.796554| 0.999993|-2.82974E-12 +i* 9.99473E-12| +| 6| 0.61698 +i* 0.78697| 0.999993| 9.01823E-12 +i*-5.69156E-12| +| 7| -0.629237 +i* -0.777205| 0.999993|-2.92122E-12 +i*-4.85867E-12| +| 8| 0.641354 +i* 0.767237| 0.999993|-1.64209E-11 +i* 1.12904E-12| +| 9| -0.653299 +i* -0.757092| 0.999993|-8.22453E-13 +i* 2.82818E-12| +| 10| 0.665096 +i* 0.746749| 0.999993| -1.2145E-11 +i* 1.89129E-11| +| 11| -0.676717 +i* -0.736234| 0.999993|-1.26079E-11 +i*-1.25073E-11| +| 12| 0.688185 +i* 0.725526| 0.999993|-4.43978E-12 +i*-2.31382E-11| +| 13| -0.699466 +i* -0.714679| 1.00001| 3.92343E-10 +i*-3.02623E-09| +| 14| 0.710597 +i* 0.70359| 0.999993| 1.28564E-11 +i* 1.56626E-11| +| 15| -0.721517 +i* -0.69241| 1.00001| 1.76709E-09 +i*-4.04041E-09| +| 16| 0.73231 +i* 0.680962| 0.999993| 1.34706E-11 +i*-4.43489E-12| +| 17| -0.742916 +i* -0.669375| 0.999993| 1.59349E-11 +i* 1.71025E-11| +| 18| 0.7533 +i* 0.657691| 1.00001|-2.76219E-09 +i* 4.10298E-09| +| 19| -0.76354 +i* -0.64575| 0.999993| 2.24043E-11 +i*-1.30496E-12| +| 20| 0.773539 +i* 0.633763| 1.00001|-3.80449E-10 +i* 3.97541E-09| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 0.999993 +250000 racines de module = 1.00001 +proc 1 +proc 2 +proc 3 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^300000 + (-10 +i*0)*x^500000 + (1 +i*0)*x^800000 + +(-30000 +i*0)*x^299999 + (-5E+06 +i*0)*x^499999 + (800000 +i*0)*x^799999 + +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +zone limite de 'log-exp' 1.00044 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 3, start 600000 size 200000 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 1, start 200000 size 200000 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 0, start 0 size 200000 +dimgrid 3125 dimblock 256 degrePoly 800000 +proc 3 start 600000 size 200000 +proc 0 start 0 size 200000 +proc 1 start 200000 size 200000 +proc 2, start 400000 size 200000 +proc 2 start 400000 size 200000 +iter : 1 Arret : 0.00108417 s/iter 12.159097 +iter : 2 Arret : 0.00154617 s/iter 12.285160 +iter : 3 Arret : 0.0140448 s/iter 12.174373 +iter : 4 Arret : 0.150783 s/iter 12.211473 +iter : 5 Arret : 0.984534 s/iter 12.253215 +iter : 6 Arret : 0.846873 s/iter 12.667593 +iter : 7 Arret : 0.850687 s/iter 12.449265 +iter : 8 Arret : 0.239017 s/iter 12.498637 +iter : 9 Arret : 0.0932856 s/iter 12.372293 +iter : 10 Arret : 0.0273595 s/iter 12.770787 +iter : 11 Arret : 0.0236411 s/iter 12.268012 +iter : 12 Arret : 0.0229952 s/iter 12.192238 +iter : 13 Arret : 0.00327267 s/iter 12.153660 +iter : 14 Arret : 0.00103051 s/iter 12.183109 +iter : 15 Arret : 0.000584357 s/iter 12.153559 +iter : 16 Arret : 0.000158231 s/iter 12.151369 +iter : 17 Arret : 9.49875E-05 s/iter 12.153222 +iter : 18 Arret : 4.14038E-05 s/iter 12.152653 +iter : 19 Arret : 3.27846E-05 s/iter 12.153803 +iter : 20 Arret : 7.57551E-06 s/iter 12.157708 +iter : 21 Arret : 4.73473E-08 s/iter 12.155670 +iter : 22 Arret : 1.01116E-10 s/iter 12.154833 +iter : 23 Arret : 2.17895E-13 s/iter 12.155276 +temps : 282.444 seconde(s) +Nb iterations : 23 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.01989E-05 +Stabilite : 2.17895E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540305 +i* 0.841464| 0.999995|-5.33817E-12 +i*-1.81878E-11| +| 2| 0.592014 +i* 0.805922| 0.999995| 2.33948E-11 +i*-2.13005E-11| +| 3| 0.617007 +i* 0.786952| 0.999995| 4.23442E-11 +i* -6.2147E-12| +| 4| 0.641392 +i* 0.767207| 0.999995|-4.99742E-11 +i* 1.43873E-11| +| 5| 0.665146 +i* 0.746707| 0.999995| 2.02977E-11 +i* 7.48579E-12| +| 6| 0.688245 +i* 0.725472| 0.999995|-1.73153E-11 +i* -1.2656E-11| +| 7| 0.710667 +i* 0.703522| 0.999995| 3.69782E-12 +i* 2.3081E-12| +| 8| 0.732388 +i* 0.68088| 0.999995| 9.45355E-12 +i* 2.09024E-11| +| 9| 0.753381 +i* 0.657577| 0.999995| 1.7531E-11 +i*-4.02243E-11| +| 10| 0.77364 +i* 0.633618| 0.999995|-1.72307E-11 +i* 1.22723E-11| +| 11| 0.793138 +i* 0.609034| 0.999995| 3.89222E-12 +i* 2.21356E-11| +| 12| 0.811855 +i* 0.583851| 0.999995|-1.28337E-11 +i*-5.47207E-12| +| 13| 0.829772 +i* 0.558094| 0.999995|-1.63114E-11 +i*-1.64246E-12| +| 14| 0.846873 +i* 0.531786| 0.999995|-1.80345E-12 +i* 5.96675E-11| +| 15| 0.86314 +i* 0.504956| 0.999995|-4.00413E-12 +i* 3.04823E-11| +| 16| 0.878557 +i* 0.477628| 0.999995|-2.16493E-12 +i* 1.10533E-11| +| 17| 0.893104 +i* 0.449841| 0.999995|-1.48552E-11 +i* 1.06063E-11| +| 18| 0.906777 +i* 0.4216| 0.999995|-1.38745E-11 +i* 5.33384E-12| +| 19| 0.919557 +i* 0.392944| 0.999995| 4.13796E-11 +i*-2.48189E-11| +| 20| 0.931433 +i* 0.363901| 0.999995| 4.93219E-11 +i*-2.82651E-11| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 0.999995 +300000 racines de module = 1.00001 +proc 0 +proc 1 +proc 2 +proc 3 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^400000 + (-10 +i*0)*x^600000 + (1 +i*0)*x^1000000 + +(-40000 +i*0)*x^399999 + (-6E+06 +i*0)*x^599999 + (1E+06 +i*0)*x^999999 + +zone limite de 'log-exp' 1.00035 +zone limite de 'log-exp' 1.00035 +zone limite de 'log-exp' 1.00035 +zone limite de 'log-exp' 1.00035 +dimgrid 3907 dimblock 256 degrePoly 1000000 +proc 1, start 250048 size 250048 +dimgrid 3907 dimblock 256 degrePoly 1000000 +proc 2, start 500096 size 250048 +dimgrid 3907 dimblock 256 degrePoly 1000000 +proc 3, start 750144 size 250048 +dimgrid 3907 dimblock 256 degrePoly 1000000 +proc 0, start 0 size 250048 +proc 0 start 0 size 250048 +proc 1 start 250048 size 250048 +proc 2 start 500096 size 250048 +proc 3 start 750144 size 250048 +iter : 1 Arret : 0.00113008 s/iter 18.764692 +iter : 2 Arret : 0.00490148 s/iter 18.766269 +iter : 3 Arret : 0.00255472 s/iter 18.765964 +iter : 4 Arret : 0.00771565 s/iter 19.551743 +iter : 5 Arret : 0.0148595 s/iter 19.510100 +iter : 6 Arret : 0.079485 s/iter 18.780627 +iter : 7 Arret : 1.0761 s/iter 19.466310 +iter : 8 Arret : 0.523791 s/iter 19.319585 +iter : 9 Arret : 0.256077 s/iter 18.918614 +iter : 10 Arret : 0.128041 s/iter 18.796063 +iter : 11 Arret : 0.0619619 s/iter 18.783666 +iter : 12 Arret : 0.0408163 s/iter 18.797339 +iter : 13 Arret : 0.028885 s/iter 18.787154 +iter : 14 Arret : 0.0101069 s/iter 18.869406 +iter : 15 Arret : 0.00233147 s/iter 18.789676 +iter : 16 Arret : 0.000443751 s/iter 18.784933 +iter : 17 Arret : 2.02171E-05 s/iter 18.760903 +iter : 18 Arret : 3.97233E-05 s/iter 18.758606 +iter : 19 Arret : 4.71594E-06 s/iter 18.782682 +iter : 20 Arret : 1.93517E-07 s/iter 18.760467 +iter : 21 Arret : 1.50186E-09 s/iter 18.801736 +iter : 22 Arret : 2.23717E-11 s/iter 18.757476 +iter : 23 Arret : 3.33298E-13 s/iter 18.760972 +temps : 440.06 seconde(s) +Nb iterations : 23 +Nb de depassements de capacite exponentielle : 0 +Precision : 7.68365E-07 +Stabilite : 2.22044E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540414 +i* 0.841394| 0.999996| 2.27135E-11 +i*-8.06094E-12| +| 2| 0.529701 +i* 0.84818| 0.999996|-4.61853E-13 +i*-4.17888E-12| +| 3| 0.524361 +i* 0.851491| 0.999996|-2.47296E-11 +i* 1.78327E-11| +| 4| 0.51901 +i* 0.854764| 0.999996| 9.45599E-12 +i* 2.07434E-11| +| 5| 0.513629 +i* 0.858008| 0.999996| 2.32483E-11 +i* 6.70747E-12| +| 6| 0.508237 +i* 0.861213| 0.999996|-1.34339E-11 +i* 9.87854E-12| +| 7| 0.502825 +i* 0.864384| 0.999996|-3.18459E-11 +i* 7.64744E-12| +| 8| 0.497384 +i* 0.867526| 0.999996| 1.87346E-11 +i* 4.7471E-11| +| 9| 0.491932 +i* 0.870629| 0.999996|-2.65525E-11 +i* 1.22525E-11| +| 10| 0.486452 +i* 0.873703| 0.999996| 3.0312E-11 +i* 1.02214E-11| +| 11| 0.480962 +i* 0.876737| 0.999996|-3.09397E-11 +i*-1.68578E-11| +| 12| 0.475453 +i* 0.879736| 0.999996| 3.09861E-11 +i* 4.093E-12| +| 13| 0.469917 +i* 0.882706| 0.999996|-1.29106E-11 +i*-2.31489E-11| +| 14| 0.46437 +i* 0.885637| 0.999996|-5.47384E-12 +i* 1.02452E-11| +| 15| 0.458797 +i* 0.888537| 0.999996| 2.78862E-11 +i* 1.10441E-11| +| 16| 0.453214 +i* 0.891397| 0.999996| 2.45506E-11 +i* 3.1726E-11| +| 17| 0.447614 +i* 0.894223| 0.999996|-1.08491E-12 +i*-2.12277E-11| +| 18| 0.441986 +i* 0.897017| 0.999996| 2.72476E-11 +i* 3.22485E-11| +| 19| 0.436351 +i* 0.899772| 0.999996|-1.24334E-11 +i*-2.66317E-11| +| 20| 0.430689 +i* 0.902496| 0.999996|-1.25435E-11 +i* 3.86925E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 0.999996 +400000 racines de module = 1.00001 +proc 1 +proc 2 +proc 3 +proc 0 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^500000 + (-10 +i*0)*x^700000 + (1 +i*0)*x^1200000 + +(-50000 +i*0)*x^499999 + (-7E+06 +i*0)*x^699999 + (1.2E+06 +i*0)*x^1199999 + +zone limite de 'log-exp' 1.0003 +zone limite de 'log-exp' 1.0003 +zone limite de 'log-exp' 1.0003 +zone limite de 'log-exp' 1.0003 +dimgrid 4688 dimblock 256 degrePoly 1200000 +proc 1, start 300032 size 300032 +dimgrid 4688 dimblock 256 degrePoly 1200000 +proc 0, start 0 size 300032 +proc 0 start 0 size 300032 +dimgrid 4688 dimblock 256 degrePoly 1200000 +proc 2, start 600064 size 300032 +proc 2 start 600064 size 300032 +dimgrid 4688 dimblock 256 degrePoly 1200000 +proc 3, start 900096 size 300032 +proc 3 start 900096 size 300032 +proc 1 start 300032 size 300032 +iter : 1 Arret : 0.00819256 s/iter 26.577664 +iter : 2 Arret : 2.02982 s/iter 28.548195 +iter : 3 Arret : 1.20559 s/iter 28.444826 +iter : 4 Arret : 2.45066 s/iter 28.500080 +iter : 5 Arret : 2.54532 s/iter 28.613591 +iter : 6 Arret : 2.62994 s/iter 29.464998 +iter : 7 Arret : 0.906074 s/iter 29.815525 +iter : 8 Arret : 0.993745 s/iter 29.873610 +iter : 9 Arret : 0.405461 s/iter 30.471669 +iter : 10 Arret : 0.367721 s/iter 30.642427 +iter : 11 Arret : 0.351446 s/iter 30.327877 +iter : 12 Arret : 0.35197 s/iter 30.656805 +iter : 13 Arret : 0.356371 s/iter 29.659115 +iter : 14 Arret : 0.361711 s/iter 29.463647 +iter : 15 Arret : 0.337763 s/iter 29.495300 +iter : 16 Arret : 0.31327 s/iter 29.423447 +iter : 17 Arret : 0.311198 s/iter 29.291099 +iter : 18 Arret : 0.318456 s/iter 29.460846 +iter : 19 Arret : 0.32907 s/iter 29.325250 +iter : 20 Arret : 0.301059 s/iter 29.261791 +iter : 21 Arret : 0.265061 s/iter 29.531117 +iter : 22 Arret : 0.259472 s/iter 29.429866 +iter : 23 Arret : 0.281898 s/iter 29.291621 +iter : 24 Arret : 0.346388 s/iter 29.302478 +iter : 25 Arret : 1.26802 s/iter 29.286807 +iter : 26 Arret : 0.283944 s/iter 29.171558 +iter : 27 Arret : 1.48554 s/iter 29.009241 +iter : 28 Arret : 1.52006 s/iter 28.992115 +iter : 29 Arret : 0.739441 s/iter 28.878319 +iter : 30 Arret : 0.752787 s/iter 28.680746 +iter : 31 Arret : 0.846761 s/iter 28.681431 +iter : 32 Arret : 1.66027 s/iter 28.631316 +iter : 33 Arret : 1.18999 s/iter 28.536383 +iter : 34 Arret : 1.7472 s/iter 28.533855 +iter : 35 Arret : 0.99662 s/iter 28.619741 +iter : 36 Arret : 0.685041 s/iter 28.524906 +iter : 37 Arret : 3.10061 s/iter 28.469691 +iter : 38 Arret : 2.19552 s/iter 28.360443 +iter : 39 Arret : 0.82349 s/iter 28.436085 +iter : 40 Arret : 3.50591 s/iter 28.172287 +iter : 41 Arret : 1.02641 s/iter 27.664102 +iter : 42 Arret : 1.74412 s/iter 27.599336 +iter : 43 Arret : 0.666046 s/iter 27.622028 +iter : 44 Arret : 0.436645 s/iter 27.665222 +iter : 45 Arret : 0.362378 s/iter 27.576919 +iter : 46 Arret : 0.355561 s/iter 27.619140 +iter : 47 Arret : 0.261884 s/iter 27.609494 +iter : 48 Arret : 0.135369 s/iter 27.625744 +iter : 49 Arret : 0.0915402 s/iter 27.430183 +iter : 50 Arret : 0.161087 s/iter 27.574724 +iter : 51 Arret : 0.133264 s/iter 27.503435 +iter : 52 Arret : 0.19955 s/iter 27.556902 +iter : 53 Arret : 0.16774 s/iter 27.535538 +iter : 54 Arret : 0.0367464 s/iter 26.597157 +iter : 55 Arret : 0.0226237 s/iter 26.593894 +iter : 56 Arret : 0.0108181 s/iter 26.570226 +iter : 57 Arret : 0.00267111 s/iter 26.648842 +iter : 58 Arret : 0.000387499 s/iter 26.572189 +iter : 59 Arret : 3.11267E-06 s/iter 26.574203 +iter : 60 Arret : 2.51854E-08 s/iter 26.572782 +iter : 61 Arret : 1.01362E-10 s/iter 26.570380 +iter : 62 Arret : 4.03524E-13 s/iter 26.570734 +temps : 1762.58 seconde(s) +Nb iterations : 62 +Nb de depassements de capacite exponentielle : 0 +Precision : 5.06807E-05 +Stabilite : 1.0906E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.54031 +i* 0.841472| 1| 1.4588E-09 +i* 4.51768E-09| +| 2| 0.513629 +i* 0.858008| 0.999997| 3.02357E-11 +i* 3.41858E-11| +| 3| 0.486451 +i* 0.873713| 1| 1.95054E-09 +i* 6.77633E-10| +| 4| 0.458789 +i* 0.888542| 0.999997| 2.48135E-13 +i*-2.88822E-11| +| 5| 0.430685 +i* 0.902499| 0.999997| 2.12053E-13 +i*-1.16324E-11| +| 6| 0.402126 +i* 0.915589| 1| 2.50282E-09 +i*-6.10471E-09| +| 7| 0.3732 +i* 0.927747| 0.999997|-1.54374E-11 +i*-2.76083E-11| +| 8| 0.3439 +i* 0.939003| 0.999997|-1.12714E-11 +i* 1.5453E-11| +| 9| 0.314261 +i* 0.949333| 0.999997| 1.93628E-11 +i* 2.50909E-11| +| 10| 0.284313 +i* 0.958728| 0.999997| 2.69426E-11 +i* 2.77974E-11| +| 11| 0.254084 +i* 0.967179| 0.999997| 1.5277E-11 +i* 4.73027E-12| +| 12| 0.223605 +i* 0.974676| 0.999997| -8.1017E-11 +i*-3.77299E-11| +| 13| 0.192897 +i* 0.981224| 1| 2.91999E-10 +i* 9.18678E-11| +| 14| 0.162017 +i* 0.986785| 0.999997| 4.59321E-12 +i*-4.42106E-13| +| 15| 0.130967 +i* 0.991391| 1| 1.71549E-09 +i* 3.54225E-10| +| 16| 0.0997898 +i* 0.995005| 0.999997| -3.8231E-11 +i* 3.92186E-14| +| 17| 0.0685225 +i* 0.997646| 0.999997| 2.33641E-11 +i* 2.51787E-12| +| 18| 0.0371504 +i* 0.999314| 1|-1.38879E-09 +i*-2.32658E-09| +| 19| 0.00578048 +i* 0.99998| 0.999997| 3.46787E-11 +i* 1.94857E-13| +| 20| -0.0256056 +i* 0.999669| 0.999997| 2.01068E-11 +i*-1.22213E-12| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +700000 racines de module = 0.999997 +proc 2 +proc 3 +proc 0 +proc 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^600000 + (-10 +i*0)*x^800000 + (1 +i*0)*x^1400000 + +(-60000 +i*0)*x^599999 + (-8E+06 +i*0)*x^799999 + (1.4E+06 +i*0)*x^1399999 + +zone limite de 'log-exp' 1.00025 +zone limite de 'log-exp' 1.00025 +zone limite de 'log-exp' 1.00025 +zone limite de 'log-exp' 1.00025 +dimgrid 5469 dimblock 256 degrePoly 1400000 +proc 3, start 1050048 size 350016 +dimgrid 5469 dimblock 256 degrePoly 1400000 +proc 1, start 350016 size 350016 +dimgrid 5469 dimblock 256 degrePoly 1400000 +proc 2, start 700032 size 350016 +proc 2 start 700032 size 350016 +dimgrid 5469 dimblock 256 degrePoly 1400000 +proc 0, start 0 size 350016 +proc 0 start 0 size 350016 +proc 3 start 1050048 size 350016 +proc 1 start 350016 size 350016 +iter : 1 Arret : 0.00218957 s/iter 36.159933 +iter : 2 Arret : 0.133227 s/iter 36.695373 +iter : 3 Arret : 6.01621 s/iter 37.299386 +iter : 4 Arret : 3.16113 s/iter 37.976941 +iter : 5 Arret : 2.89902 s/iter 37.835787 +iter : 6 Arret : 1.55692 s/iter 38.098839 +iter : 7 Arret : 1.64303 s/iter 39.033767 +iter : 8 Arret : 9.63322 s/iter 39.962469 +iter : 9 Arret : 3.25551 s/iter 40.250439 +iter : 10 Arret : 1.80839 s/iter 41.322631 +iter : 11 Arret : 2.10312 s/iter 39.721944 +iter : 12 Arret : 1.27787 s/iter 40.175542 +iter : 13 Arret : 1.28405 s/iter 39.345510 +iter : 14 Arret : 1.10597 s/iter 39.326031 +iter : 15 Arret : 1.54753 s/iter 39.371562 +iter : 16 Arret : 3.97338 s/iter 39.040715 +iter : 17 Arret : 1.16165 s/iter 39.074694 +iter : 18 Arret : 1.33248 s/iter 38.851097 +iter : 19 Arret : 0.864994 s/iter 38.922556 +iter : 20 Arret : 0.781144 s/iter 38.428134 +iter : 21 Arret : 0.717927 s/iter 38.952301 +iter : 22 Arret : 0.651466 s/iter 38.352980 +iter : 23 Arret : 0.458583 s/iter 38.047111 +iter : 24 Arret : 0.283507 s/iter 38.133746 +iter : 25 Arret : 0.279826 s/iter 37.853592 +iter : 26 Arret : 0.243863 s/iter 36.926821 +iter : 27 Arret : 0.220856 s/iter 37.645303 +iter : 28 Arret : 0.139293 s/iter 36.485655 +iter : 29 Arret : 0.66161 s/iter 36.276980 +iter : 30 Arret : 0.269576 s/iter 36.156120 +iter : 31 Arret : 0.139673 s/iter 36.247656 +iter : 32 Arret : 0.055674 s/iter 36.155399 +iter : 33 Arret : 0.0217982 s/iter 36.204812 +iter : 34 Arret : 0.00427148 s/iter 36.153944 +iter : 35 Arret : 0.000628248 s/iter 36.153697 +iter : 36 Arret : 1.01228E-07 s/iter 36.154597 +iter : 37 Arret : 4.84665E-10 s/iter 36.152819 +iter : 38 Arret : 2.2498E-12 s/iter 36.150757 +iter : 39 Arret : 1.80732E-14 s/iter 36.149673 +temps : 1478.01 seconde(s) +Nb iterations : 39 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.34519E-06 +Stabilite : 2.22046E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841469| 0.999997| 5.65794E-11 +i*-4.66756E-12| +| 2| 0.513623 +i* 0.858013| 0.999997|-2.15776E-11 +i*-2.98557E-11| +| 3| -0.52703 +i* -0.849843| 0.999997|-6.50922E-11 +i* 8.44216E-12| +| 4| 0.486439 +i* 0.873711| 0.999997| 5.60277E-11 +i* 4.36779E-11| +| 5| -0.500096 +i* -0.865967| 0.999997| 3.56147E-11 +i*-3.12713E-11| +| 6| 0.458776 +i* 0.888549| 0.999997|-1.89702E-11 +i* 4.08274E-12| +| 7| -0.472673 +i* -0.881242| 1|-5.56631E-09 +i*-2.23833E-09| +| 8| 0.430664 +i* 0.902517| 1|-8.83373E-11 +i*-2.09199E-09| +| 9| -0.444791 +i* -0.895631| 0.999997| 3.68259E-11 +i* 1.36002E-12| +| 10| 0.402136 +i* 0.915577| 0.999997| 6.5834E-12 +i* -1.3935E-11| +| 11| -0.416432 +i* -0.909164| 0.999997| 1.97816E-11 +i* 3.10848E-11| +| 12| 0.373171 +i* 0.927759| 0.999997|-2.17995E-11 +i*-2.96867E-12| +| 13| -0.387698 +i* -0.921783| 0.999997|-1.86324E-11 +i* -4.6545E-11| +| 14| 0.343875 +i* 0.939012| 0.999997| 3.84962E-11 +i* 2.59646E-11| +| 15| -0.358575 +i* -0.933498| 0.999997|-4.93405E-11 +i*-7.15173E-13| +| 16| 0.314233 +i* 0.949343| 0.999997| 3.86503E-11 +i* 2.08775E-11| +| 17| -0.329098 +i* -0.944293| 0.999997|-1.57903E-11 +i* 2.05052E-11| +| 18| 0.284281 +i* 0.958738| 0.999997| 2.51592E-11 +i* 2.09243E-11| +| 19| -0.299297 +i* -0.954157| 0.999997| 5.03608E-12 +i* 1.70503E-11| +| 20| 0.254048 +i* 0.967189| 0.999997|-2.81228E-11 +i*-1.66302E-11| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 0.999997 +600000 racines de module = 1 +proc 0 +proc 1 +proc 2 +proc 3 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^700000 + (-10 +i*0)*x^900000 + (1 +i*0)*x^1600000 + +(-70000 +i*0)*x^699999 + (-9E+06 +i*0)*x^899999 + (1.6E+06 +i*0)*x^1599999 + + +template:29834 terminated with signal 11 at PC=404b41 SP=7fff0b4740b0. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:29835 terminated with signal 11 at PC=404b41 SP=7fff081a2530. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:29833 terminated with signal 11 at PC=404b41 SP=7fffe6ecdf90. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:29836 terminated with signal 11 at PC=404b41 SP=7fff35c7eff0. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +-------------------------------------------------------------------------- +mpirun has exited due to process rank 1 with PID 29834 on +node node1-50 exiting improperly. There are two reasons this could occur: + +1. this process did not call "init" before exiting, but others in +the job did. This can cause a job to hang indefinitely while it waits +for all processes to call "init". By rule, if one process calls "init", +then ALL processes must call "init" prior to termination. + +2. this process called "init", but exited without calling "finalize". +By rule, all processes that call "init" MUST call "finalize" prior to +exiting or it will be considered an "abnormal termination" + +This may have caused other processes in the application to be +terminated by signals sent by mpirun (as reported here). +-------------------------------------------------------------------------- +proc 0 +proc 1 +proc 2 +proc 3 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^800000 + (-10 +i*0)*x^1000000 + (1 +i*0)*x^1800000 + +(-80000 +i*0)*x^799999 + (-1E+07 +i*0)*x^999999 + (1.8E+06 +i*0)*x^1799999 + + +template:29849 terminated with signal 11 at PC=404b41 SP=7fff6792aa30. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:29846 terminated with signal 11 at PC=404b41 SP=7ffffaf225e0. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:29848 terminated with signal 11 at PC=404b41 SP=7fff7de06640. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] + +template:29847 terminated with signal 11 at PC=404b41 SP=7fff5bacc3f0. Backtrace: +./template[0x404b41] +./template[0x406726] +/lib64/libc.so.6(__libc_start_main+0xfd)[0x36e341ecdd] +./template[0x4031f9] +-------------------------------------------------------------------------- +mpirun has exited due to process rank 0 with PID 29846 on +node node1-50 exiting improperly. There are two reasons this could occur: + +1. this process did not call "init" before exiting, but others in +the job did. This can cause a job to hang indefinitely while it waits +for all processes to call "init". By rule, if one process calls "init", +then ALL processes must call "init" prior to termination. + +2. this process called "init", but exited without calling "finalize". +By rule, all processes that call "init" MUST call "finalize" prior to +exiting or it will be considered an "abnormal termination" + +This may have caused other processes in the application to be +terminated by signals sent by mpirun (as reported here). +-------------------------------------------------------------------------- +proc 2 +proc 3 +proc 0 +proc 1 +zone limite de 'log-exp' 1.03613 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^2000 + (-10 +i*0)*x^8000 + (1 +i*0)*x^10000 + +(-200 +i*0)*x^1999 + (-80000 +i*0)*x^7999 + (10000 +i*0)*x^9999 + +zone limite de 'log-exp' 1.03613 +zone limite de 'log-exp' 1.03613 +zone limite de 'log-exp' 1.03613 +dimgrid 40 dimblock 256 degrePoly 10000 +proc 1, start 2560 size 2560 +dimgrid 40 dimblock 256 degrePoly 10000 +proc 0, start 0 size 2560 +dimgrid 40 dimblock 256 degrePoly 10000 +proc 3, start 7680 size 2560 +proc 0 start 0 size 2560 +proc 3 start 7680 size 2560 +proc 1 start 2560 size 2560 +dimgrid 40 dimblock 256 degrePoly 10000 +proc 2, start 5120 size 2560 +proc 2 start 5120 size 2560 +iter : 1 Arret : 0.000540066 s/iter 0.008420 +iter : 2 Arret : 0.0239499 s/iter 0.008298 +iter : 3 Arret : 0.0108994 s/iter 0.008290 +iter : 4 Arret : 0.00347071 s/iter 0.008305 +iter : 5 Arret : 0.00757939 s/iter 0.008311 +iter : 6 Arret : 0.00186666 s/iter 0.008310 +iter : 7 Arret : 0.00179112 s/iter 0.008306 +iter : 8 Arret : 0.00147265 s/iter 0.008305 +iter : 9 Arret : 0.00165602 s/iter 0.008296 +iter : 10 Arret : 0.00248191 s/iter 0.008307 +iter : 11 Arret : 0.000812537 s/iter 0.008297 +iter : 12 Arret : 5.39531E-05 s/iter 0.008412 +iter : 13 Arret : 1.08824E-08 s/iter 0.008404 +iter : 14 Arret : 1.089E-13 s/iter 0.008419 +temps : 0.323036 seconde(s) +Nb iterations : 14 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.17761E-05 +Stabilite : 8.2797E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.547024 +i* 0.838493| 1.00115|-6.21719E-10 +i*-5.53774E-09| +| 2| -0.540305 +i* 0.841127| 0.999712|-1.60982E-13 +i*-4.97213E-14| +| 3| -0.909192 +i* 0.415685| 0.999712| 4.35207E-14 +i* 5.29003E-13| +| 4| -0.989628 +i* -0.141638| 0.999712|-2.84439E-13 +i*-1.69935E-14| +| 5| -0.759236 +i* -0.652585| 1.00115|-6.07508E-09 +i* 4.66733E-09| +| 6| -0.281925 +i* -0.959136| 0.999712|-1.54099E-13 +i* 3.80991E-14| +| 7| 0.281172 +i* -0.959357| 0.999712|-1.43663E-13 +i*-1.53777E-13| +| 8| 0.755064 +i* -0.655212| 0.999712| 4.61076E-13 +i* 3.15322E-13| +| 9| 0.989404 +i* -0.143192| 0.999712|-1.63203E-13 +i*-1.45101E-14| +| 10| 0.912453 +i* 0.411988| 1.00115|-1.77634E-10 +i* 4.15663E-09| +| 11| 0.540966 +i* 0.840703| 0.999712| -2.5091E-14 +i*-1.99096E-13| +| 12| 0.540305 +i* 0.841127| 0.999712| 3.22853E-13 +i* 1.07785E-13| +| 13| 0.00314521 +i* 1.00115| 1.00115| 4.5119E-09 +i*-6.21719E-11| +| 14| -0.540966 +i* 0.840703| 0.999712| -2.5091E-14 +i* 1.99096E-13| +| 15| -0.909518 +i* 0.414971| 0.999712|-1.80966E-13 +i*-6.20692E-14| +| 16| -0.989516 +i* -0.142415| 0.999712| 2.81108E-13 +i* 5.11239E-14| +| 17| -0.755579 +i* -0.654618| 0.999712| 5.59774E-13 +i* 8.84721E-14| +| 18| -0.285348 +i* -0.959626| 1.00115|-9.98303E-09 +i*-1.88292E-09| +| 19| 0.281925 +i* -0.959136| 0.999712| 1.08247E-13 +i*-4.02221E-13| +| 20| 0.755579 +i* -0.654618| 0.999712| 5.59774E-13 +i*-8.84721E-14| ++---+----------------------------+------------+----------------------------+ +2000 racines de module = 1.00115 +8000 racines de module = 0.999712 diff --git a/Simulations/sparse_mpi/sparse_mpi_4GPU.sge b/Simulations/sparse_mpi/sparse_mpi_4GPU.sge new file mode 100644 index 0000000..d9ab42c --- /dev/null +++ b/Simulations/sparse_mpi/sparse_mpi_4GPU.sge @@ -0,0 +1,25 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=4 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -V +#$ -cwd +#$ -N sparse_mpi_4GPU +#$ -pe mpi 4 + + +module load cuda/7.0 +module load ompi/gcc + +mpirun -np $NSLOTS ./template -r -i 60000 40000 +mpirun -np $NSLOTS ./template -r -i 150000 50000 +mpirun -np $NSLOTS ./template -r -i 250000 150000 +mpirun -np $NSLOTS ./template -r -i 350000 250000 +mpirun -np $NSLOTS ./template -r -i 500000 300000 +mpirun -np $NSLOTS ./template -r -i 600000 400000 +mpirun -np $NSLOTS ./template -r -i 700000 500000 +mpirun -np $NSLOTS ./template -r -i 800000 600000 +mpirun -np $NSLOTS ./template -r -i 900000 700000 +mpirun -np $NSLOTS ./template -r -i 1000000 800000 +mpirun -np $NSLOTS ./template -r -i 1500000 500000 diff --git a/Simulations/sparse_openmp/sparse_openmp_1GPU.o140100 b/Simulations/sparse_openmp/sparse_openmp_1GPU.o140100 new file mode 100644 index 0000000..7332981 --- /dev/null +++ b/Simulations/sparse_openmp/sparse_openmp_1GPU.o140100 @@ -0,0 +1,512 @@ +REMAINING: 1 +Taking GPU #3 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^40000 + (-10 +i*0)*x^60000 + (1 +i*0)*x^100000 + +(-4000 +i*0)*x^39999 + (-600000 +i*0)*x^59999 + (100000 +i*0)*x^99999 + +zone limite de 'log-exp' 1.00356 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 391 dimblock 256 degrePoly 100000 +gpu 0 dimgrid2 391 start 0 size 100096 +gpu 0 iter : 1 Arret : 0.0052669 s/iter 0.775408 +gpu 0 iter : 2 Arret : 0.00752645 s/iter 0.775369 +gpu 0 iter : 3 Arret : 0.0240999 s/iter 0.775305 +gpu 0 iter : 4 Arret : 0.0224589 s/iter 0.850697 +gpu 0 iter : 5 Arret : 0.00804703 s/iter 0.844340 +gpu 0 iter : 6 Arret : 0.00438171 s/iter 0.775251 +gpu 0 iter : 7 Arret : 0.00744568 s/iter 0.775238 +gpu 0 iter : 8 Arret : 0.00764888 s/iter 0.775261 +gpu 0 iter : 9 Arret : 0.00410621 s/iter 0.775320 +gpu 0 iter : 10 Arret : 0.00247273 s/iter 0.775247 +gpu 0 iter : 11 Arret : 0.00227795 s/iter 0.775273 +gpu 0 iter : 12 Arret : 0.00210901 s/iter 0.775117 +gpu 0 iter : 13 Arret : 0.000438336 s/iter 0.774935 +gpu 0 iter : 14 Arret : 0.000273199 s/iter 0.774865 +gpu 0 iter : 15 Arret : 0.000137109 s/iter 0.774789 +gpu 0 iter : 16 Arret : 1.40101E-05 s/iter 0.774828 +gpu 0 iter : 17 Arret : 1.89958E-07 s/iter 0.774719 +gpu 0 iter : 18 Arret : 2.82623E-09 s/iter 0.774706 +gpu 0 iter : 19 Arret : 4.21054E-11 s/iter 0.774674 +gpu 0 iter : 20 Arret : 6.27215E-13 s/iter 0.774731 +temps : 16.1926 seconde(s) +Nb iterations : 20 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.61117E-09 +Stabilite : 6.27215E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540308 +i* 0.841422| 0.999962|-1.95866E-12 +i*-4.55465E-13| +| 2| -0.113164 +i* 0.993538| 0.999962|-4.34919E-12 +i* 9.60242E-13| +| 3| -0.226711 +i* -0.973923| 0.999962|-4.27658E-13 +i* 6.01027E-13| +| 4| -0.715763 +i* 0.698289| 0.999962| 9.11271E-13 +i* 2.47219E-12| +| 5| 0.439922 +i* -0.897993| 0.999962|-3.49498E-13 +i* 1.66432E-12| +| 6| -0.996021 +i* 0.0886823| 0.999962| 1.17772E-12 +i* 6.16285E-13| +| 7| 0.908546 +i* -0.417692| 0.999962| 4.78506E-13 +i* 1.54377E-13| +| 8| -0.827813 +i* -0.560935| 0.999962| 9.76996E-13 +i*-2.04309E-12| +| 9| 0.968049 +i* 0.250607| 0.999962|-1.07025E-13 +i*-1.15224E-12| +| 10| -0.286815 +i* -0.957946| 0.999962|-6.55254E-13 +i* 1.20869E-12| +| 11| 0.591653 +i* 0.806145| 0.999962|-9.87654E-13 +i*-3.03635E-12| +| 12| -0.0511836 +i* 0.998651| 0.999962|-2.22622E-12 +i*-3.69013E-14| +| 13| -0.67097 +i* 0.741432| 0.999962|-8.03801E-14 +i*-1.68204E-12| +| 14| 0.383249 +i* -0.923603| 0.999962|-1.29119E-12 +i*-1.37426E-12| +| 15| -0.988582 +i* 0.150427| 0.999962|-1.54698E-12 +i*-6.48537E-13| +| 16| 0.880824 +i* -0.473363| 0.999962| 1.58029E-12 +i*-2.34379E-12| +| 17| -0.861082 +i* -0.508391| 0.999962| 9.8066E-13 +i* 3.40478E-12| +| 18| 0.981756 +i* 0.189945| 0.999962|-1.13665E-12 +i* 1.13043E-12| +| 19| -0.345809 +i* -0.938264| 0.999962| 1.03906E-12 +i* 1.95398E-12| +| 20| 0.640621 +i* 0.767807| 0.999962|-6.98774E-13 +i* 1.13798E-12| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 0.999962 +40000 racines de module = 1.00006 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^50000 + (-10 +i*0)*x^150000 + (1 +i*0)*x^200000 + +(-5000 +i*0)*x^49999 + (-1.5E+06 +i*0)*x^149999 + (200000 +i*0)*x^199999 + +zone limite de 'log-exp' 1.00178 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 782 dimblock 256 degrePoly 200000 +gpu 0 dimgrid2 782 start 0 size 200192 +gpu 0 iter : 1 Arret : 0.000149329 s/iter 3.019382 +gpu 0 iter : 2 Arret : 0.000107708 s/iter 3.016857 +gpu 0 iter : 3 Arret : 0.000113605 s/iter 3.016990 +gpu 0 iter : 4 Arret : 0.000830779 s/iter 3.018300 +gpu 0 iter : 5 Arret : 0.00353705 s/iter 3.017239 +gpu 0 iter : 6 Arret : 0.0150507 s/iter 3.033347 +gpu 0 iter : 7 Arret : 0.0172496 s/iter 3.028650 +gpu 0 iter : 8 Arret : 0.032361 s/iter 3.025908 +gpu 0 iter : 9 Arret : 0.0281394 s/iter 3.030298 +gpu 0 iter : 10 Arret : 0.116314 s/iter 3.043482 +gpu 0 iter : 11 Arret : 0.129494 s/iter 3.073542 +gpu 0 iter : 12 Arret : 0.0352338 s/iter 3.047419 +gpu 0 iter : 13 Arret : 0.0316693 s/iter 3.041094 +gpu 0 iter : 14 Arret : 0.0153664 s/iter 3.020001 +gpu 0 iter : 15 Arret : 0.0125995 s/iter 3.011952 +gpu 0 iter : 16 Arret : 0.00505109 s/iter 3.013206 +gpu 0 iter : 17 Arret : 0.0072726 s/iter 3.013400 +gpu 0 iter : 18 Arret : 0.00841241 s/iter 3.012671 +gpu 0 iter : 19 Arret : 0.00316401 s/iter 3.011866 +gpu 0 iter : 20 Arret : 1.36142E-05 s/iter 3.011905 +gpu 0 iter : 21 Arret : 1.07816E-09 s/iter 3.012487 +gpu 0 iter : 22 Arret : 2.83648E-12 s/iter 3.012609 +gpu 0 iter : 23 Arret : 4.24948E-14 s/iter 3.012386 +temps : 70.1186 seconde(s) +Nb iterations : 23 +Nb de depassements de capacite exponentielle : 0 +Precision : 9.52377E-08 +Stabilite : 4.24948E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540195 +i* 0.841595| 1.00005|-2.98043E-09 +i*-3.27611E-08| +| 2| -0.837195 +i* 0.546877| 0.999985| 7.09943E-12 +i* 5.1133E-12| +| 3| -0.553418 +i* -0.832885| 0.999985| -1.9722E-12 +i*-7.40397E-12| +| 4| 0.828525 +i* -0.559925| 0.999985|-4.34675E-12 +i* 1.07137E-12| +| 5| -0.819774 +i* 0.572768| 1.00005| 2.53887E-08 +i* 2.42315E-09| +| 6| -0.57917 +i* -0.815188| 0.999985|-5.13034E-12 +i*-1.52645E-12| +| 7| 0.810626 +i* -0.585537| 0.999985| 8.64808E-12 +i* 7.46794E-12| +| 8| 0.591869 +i* 0.806015| 0.999985| 1.73195E-13 +i* 8.72591E-12| +| 9| -0.801379 +i* 0.598131| 0.999985| -1.2701E-12 +i* 3.96189E-12| +| 10| -0.60436 +i* -0.796769| 1.00005|-3.33815E-08 +i* 3.89061E-08| +| 11| 0.791937 +i* -0.610578| 0.999985| 6.0707E-13 +i* 1.52922E-12| +| 12| 0.616763 +i* 0.78713| 0.999985|-4.48042E-12 +i* -2.6295E-12| +| 13| -0.782301 +i* 0.622877| 0.999985|-2.15827E-12 +i*-6.27114E-12| +| 14| -0.628985 +i* -0.777398| 0.999985|-4.05476E-12 +i*-5.17236E-12| +| 15| 0.772548 +i* -0.635029| 1.00005| 1.1634E-09 +i* 1.87351E-08| +| 16| 0.641054 +i* 0.767476| 0.999985|-3.47633E-12 +i* 1.20617E-11| +| 17| -0.762458 +i* 0.647014| 0.999985|-7.74447E-12 +i* 7.566E-12| +| 18| -0.652967 +i* -0.757366| 0.999985| 5.10392E-12 +i*-6.61069E-12| +| 19| 0.752229 +i* -0.658879| 0.999985|-5.97611E-12 +i* 1.03431E-11| +| 20| 0.664729 +i* 0.747146| 1.00005|-1.71597E-08 +i* 8.68463E-09| ++---+----------------------------+------------+----------------------------+ +50000 racines de module = 1.00005 +150000 racines de module = 0.999985 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^150000 + (-10 +i*0)*x^250000 + (1 +i*0)*x^400000 + +(-15000 +i*0)*x^149999 + (-2.5E+06 +i*0)*x^249999 + (400000 +i*0)*x^399999 + +zone limite de 'log-exp' 1.00089 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 1563 dimblock 256 degrePoly 400000 +gpu 0 dimgrid2 1563 start 0 size 400128 +gpu 0 iter : 1 Arret : 0.00172099 s/iter 11.753718 +gpu 0 iter : 2 Arret : 0.0208557 s/iter 11.747391 +gpu 0 iter : 3 Arret : 0.221528 s/iter 11.807046 +gpu 0 iter : 4 Arret : 0.572248 s/iter 11.998301 +gpu 0 iter : 5 Arret : 0.542189 s/iter 11.842988 +gpu 0 iter : 6 Arret : 0.306206 s/iter 11.822805 +gpu 0 iter : 7 Arret : 0.0317191 s/iter 12.059261 +gpu 0 iter : 8 Arret : 0.0184143 s/iter 12.061589 +gpu 0 iter : 9 Arret : 0.030511 s/iter 11.936705 +gpu 0 iter : 10 Arret : 0.023696 s/iter 11.899096 +gpu 0 iter : 11 Arret : 0.0135298 s/iter 11.850230 +gpu 0 iter : 12 Arret : 0.0119889 s/iter 11.808974 +gpu 0 iter : 13 Arret : 0.00485045 s/iter 11.776383 +gpu 0 iter : 14 Arret : 0.00522437 s/iter 11.809750 +gpu 0 iter : 15 Arret : 0.00252909 s/iter 11.735442 +gpu 0 iter : 16 Arret : 0.000417464 s/iter 11.739448 +gpu 0 iter : 17 Arret : 0.000235756 s/iter 11.733345 +gpu 0 iter : 18 Arret : 6.4985E-07 s/iter 11.743853 +gpu 0 iter : 19 Arret : 1.48939E-09 s/iter 11.732225 +gpu 0 iter : 20 Arret : 3.20792E-12 s/iter 11.734648 +gpu 0 iter : 21 Arret : 1.34164E-14 s/iter 11.732088 +temps : 248.893 seconde(s) +Nb iterations : 21 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.49185E-08 +Stabilite : 1.34164E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540334 +i* 0.84144| 0.999991| 6.97609E-12 +i* 5.61207E-12| +| 2| -0.998329 +i* 0.057622| 0.999991| 4.43912E-12 +i* 1.27665E-12| +| 3| 0.439867 +i* -0.898052| 0.999991|-8.50653E-12 +i*-8.85586E-12| +| 4| -0.996033 +i* 0.0888768| 0.999991|-3.15592E-12 +i* 1.17456E-12| +| 5| 0.411533 +i* -0.911385| 0.999991|-2.45048E-12 +i* 4.6238E-12| +| 6| 0.59196 +i* 0.805956| 0.999991| 5.24358E-13 +i*-8.53073E-12| +| 7| -0.992759 +i* 0.120044| 0.999991| 2.58804E-12 +i* 2.47274E-12| +| 8| 0.382796 +i* -0.923823| 0.999991| 1.11042E-11 +i*-9.27687E-12| +| 9| 0.616925 +i* 0.78701| 0.999991| 4.27514E-12 +i*-1.13966E-11| +| 10| -0.98851 +i* 0.151094| 0.999991| 1.67755E-11 +i* 4.06477E-12| +| 11| 0.35366 +i* -0.935364| 0.999991|-1.92664E-11 +i* 1.19958E-11| +| 12| 0.641283 +i* 0.767292| 0.999991| 1.73468E-11 +i*-3.74729E-12| +| 13| -0.98329 +i* 0.181995| 0.999991|-6.62759E-12 +i*-5.46796E-12| +| 14| 0.324176 +i* -0.945987| 0.999991| 1.53594E-11 +i*-1.57324E-12| +| 15| 0.665012 +i* 0.746821| 0.999991| 5.27178E-12 +i*-4.27913E-12| +| 16| -0.977104 +i* 0.212717| 0.999991|-1.01148E-11 +i* 2.41479E-12| +| 17| 0.294374 +i* -0.955681| 0.999991| -1.2063E-11 +i* 1.32238E-11| +| 18| 0.688087 +i* 0.725616| 0.999991|-1.67164E-11 +i*-1.12573E-11| +| 19| -0.969965 +i* 0.243206| 0.999991| 6.88072E-12 +i* 3.20268E-13| +| 20| 0.264283 +i* -0.964436| 0.999991|-6.93356E-12 +i*-6.23118E-12| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 0.999991 +150000 racines de module = 1.00002 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^250000 + (-10 +i*0)*x^350000 + (1 +i*0)*x^600000 + +(-25000 +i*0)*x^249999 + (-3.5E+06 +i*0)*x^349999 + (600000 +i*0)*x^599999 + +zone limite de 'log-exp' 1.00059 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 0 dimgrid2 2344 start 0 size 600064 +gpu 0 iter : 1 Arret : 0.00525558 s/iter 26.336656 +gpu 0 iter : 2 Arret : 0.441677 s/iter 26.703831 +gpu 0 iter : 3 Arret : 0.906705 s/iter 26.966169 +gpu 0 iter : 4 Arret : 3.755 s/iter 26.950936 +gpu 0 iter : 5 Arret : 1.26305 s/iter 27.316144 +gpu 0 iter : 6 Arret : 3.03186 s/iter 27.389925 +gpu 0 iter : 7 Arret : 0.213406 s/iter 27.490831 +gpu 0 iter : 8 Arret : 1.0101 s/iter 27.559501 +gpu 0 iter : 9 Arret : 0.207377 s/iter 27.194849 +gpu 0 iter : 10 Arret : 0.0920517 s/iter 27.466967 +gpu 0 iter : 11 Arret : 0.0893085 s/iter 27.380003 +gpu 0 iter : 12 Arret : 0.0218947 s/iter 26.617878 +gpu 0 iter : 13 Arret : 0.00718218 s/iter 26.491846 +gpu 0 iter : 14 Arret : 0.014641 s/iter 26.379537 +gpu 0 iter : 15 Arret : 0.00209026 s/iter 26.349906 +gpu 0 iter : 16 Arret : 0.00174853 s/iter 26.344560 +gpu 0 iter : 17 Arret : 0.00249398 s/iter 26.348383 +gpu 0 iter : 18 Arret : 0.00020801 s/iter 26.354612 +gpu 0 iter : 19 Arret : 1.26142E-07 s/iter 26.370520 +gpu 0 iter : 20 Arret : 5.14341E-10 s/iter 26.370752 +gpu 0 iter : 21 Arret : 2.04751E-12 s/iter 26.372247 +gpu 0 iter : 22 Arret : 8.06082E-15 s/iter 26.364052 +temps : 589.718 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.32595E-08 +Stabilite : 8.06082E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540302 +i* 0.841463| 0.999993| 8.34199E-12 +i* -1.9051E-11| +| 2| -0.553438 +i* -0.832883| 0.999993| 2.30783E-11 +i*-6.91999E-12| +| 3| -0.579282 +i* -0.815119| 0.999993|-1.44751E-12 +i* 7.66798E-12| +| 4| 0.592029 +i* 0.805909| 0.999993| 8.2111E-12 +i* 2.02799E-11| +| 5| -0.604557 +i* -0.796554| 0.999993|-2.82974E-12 +i* 9.99473E-12| +| 6| 0.61698 +i* 0.78697| 0.999993| 9.01823E-12 +i*-5.69156E-12| +| 7| -0.629237 +i* -0.777205| 0.999993|-2.92122E-12 +i*-4.85867E-12| +| 8| 0.641354 +i* 0.767237| 0.999993|-1.64209E-11 +i* 1.12904E-12| +| 9| -0.653299 +i* -0.757092| 0.999993|-8.22453E-13 +i* 2.82818E-12| +| 10| 0.665096 +i* 0.746749| 0.999993| -1.2145E-11 +i* 1.89129E-11| +| 11| -0.676717 +i* -0.736234| 0.999993|-1.26079E-11 +i*-1.25073E-11| +| 12| 0.688185 +i* 0.725526| 0.999993| 2.69875E-11 +i* 1.65411E-11| +| 13| -0.699466 +i* -0.714679| 1.00001| 3.92343E-10 +i*-3.02623E-09| +| 14| 0.710597 +i* 0.70359| 0.999993| -2.6851E-11 +i*-1.44801E-11| +| 15| -0.721517 +i* -0.69241| 1.00001| 2.88447E-09 +i* 3.69506E-09| +| 16| 0.73231 +i* 0.680962| 0.999993|-5.73186E-12 +i* 1.14335E-11| +| 17| -0.742916 +i* -0.669375| 0.999993| 1.59349E-11 +i* 1.71025E-11| +| 18| 0.7533 +i* 0.657691| 1.00001| 1.64587E-09 +i*-3.03669E-09| +| 19| -0.76354 +i* -0.64575| 0.999993| 2.24043E-11 +i*-1.30496E-12| +| 20| 0.773539 +i* 0.633763| 1.00001| -4.2314E-09 +i* 1.86243E-09| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 0.999993 +250000 racines de module = 1.00001 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^300000 + (-10 +i*0)*x^500000 + (1 +i*0)*x^800000 + +(-30000 +i*0)*x^299999 + (-5E+06 +i*0)*x^499999 + (800000 +i*0)*x^799999 + +zone limite de 'log-exp' 1.00044 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 0 dimgrid2 3125 start 0 size 800000 +gpu 0 iter : 1 Arret : 0.00051726 s/iter 46.868704 +gpu 0 iter : 2 Arret : 0.00517255 s/iter 46.735194 +gpu 0 iter : 3 Arret : 0.0728679 s/iter 46.891988 +gpu 0 iter : 4 Arret : 0.771691 s/iter 46.979491 +gpu 0 iter : 5 Arret : 0.75662 s/iter 47.336136 +gpu 0 iter : 6 Arret : 0.635995 s/iter 47.811859 +gpu 0 iter : 7 Arret : 0.505749 s/iter 48.056193 +gpu 0 iter : 8 Arret : 0.931022 s/iter 48.270194 +gpu 0 iter : 9 Arret : 0.398721 s/iter 48.514679 +gpu 0 iter : 10 Arret : 0.247741 s/iter 48.434629 +gpu 0 iter : 11 Arret : 0.0707263 s/iter 48.136785 +gpu 0 iter : 12 Arret : 0.0344289 s/iter 47.624785 +gpu 0 iter : 13 Arret : 0.0278743 s/iter 46.948359 +gpu 0 iter : 14 Arret : 0.0109553 s/iter 46.857728 +gpu 0 iter : 15 Arret : 0.0093023 s/iter 46.844682 +gpu 0 iter : 16 Arret : 0.00935315 s/iter 46.835990 +gpu 0 iter : 17 Arret : 0.0162429 s/iter 46.715238 +gpu 0 iter : 18 Arret : 0.00648616 s/iter 46.741249 +gpu 0 iter : 19 Arret : 0.000839627 s/iter 46.741507 +gpu 0 iter : 20 Arret : 0.00184254 s/iter 46.754071 +gpu 0 iter : 21 Arret : 4.91346E-06 s/iter 46.769016 +gpu 0 iter : 22 Arret : 4.60158E-08 s/iter 46.820581 +gpu 0 iter : 23 Arret : 6.70363E-10 s/iter 46.824110 +gpu 0 iter : 24 Arret : 9.78247E-12 s/iter 46.828052 +gpu 0 iter : 25 Arret : 1.42634E-13 s/iter 46.828472 +temps : 1180.82 seconde(s) +Nb iterations : 25 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.1101E-08 +Stabilite : 1.42634E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540305 +i* 0.841464| 0.999995|-5.33817E-12 +i*-1.81878E-11| +| 2| 0.592014 +i* 0.805922| 0.999995| 2.33948E-11 +i*-2.13005E-11| +| 3| 0.617007 +i* 0.786952| 0.999995| 4.23442E-11 +i* -6.2147E-12| +| 4| 0.641392 +i* 0.767207| 0.999995|-4.99742E-11 +i* 1.43873E-11| +| 5| 0.665146 +i* 0.746707| 0.999995| 2.02977E-11 +i* 7.48579E-12| +| 6| 0.688245 +i* 0.725472| 0.999995|-1.73153E-11 +i* -1.2656E-11| +| 7| 0.710667 +i* 0.703522| 0.999995| 3.69782E-12 +i* 2.3081E-12| +| 8| 0.732388 +i* 0.68088| 0.999995| 9.45355E-12 +i* 2.09024E-11| +| 9| 0.753381 +i* 0.657577| 0.999995| 3.40094E-11 +i* 1.45989E-12| +| 10| 0.77364 +i* 0.633618| 0.999995|-1.72307E-11 +i* 1.22723E-11| +| 11| 0.793138 +i* 0.609034| 0.999995| 3.89222E-12 +i* 2.21356E-11| +| 12| 0.811855 +i* 0.583851| 0.999995|-1.28337E-11 +i*-5.47207E-12| +| 13| 0.829772 +i* 0.558094| 0.999995|-1.63114E-11 +i*-1.64246E-12| +| 14| 0.846873 +i* 0.531786| 0.999995| 3.88137E-11 +i*-3.00611E-11| +| 15| 0.86314 +i* 0.504956| 0.999995|-4.00413E-12 +i* 3.04823E-11| +| 16| 0.878557 +i* 0.477628| 0.999995|-2.16493E-12 +i* 1.10533E-11| +| 17| 0.893104 +i* 0.449841| 0.999995|-1.48552E-11 +i* 1.06063E-11| +| 18| 0.906777 +i* 0.4216| 0.999995|-1.38745E-11 +i* 5.33384E-12| +| 19| 0.919557 +i* 0.392944| 0.999995|-3.33245E-11 +i* 5.94386E-12| +| 20| 0.931433 +i* 0.363901| 0.999995| 4.93219E-11 +i*-2.82651E-11| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 0.999995 +300000 racines de module = 1.00001 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^400000 + (-10 +i*0)*x^600000 + (1 +i*0)*x^1000000 + +(-40000 +i*0)*x^399999 + (-6E+06 +i*0)*x^599999 + (1E+06 +i*0)*x^999999 + +zone limite de 'log-exp' 1.00035 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 3907 dimblock 256 degrePoly 1000000 +gpu 0 dimgrid2 3907 start 0 size 1000192 +gpu 0 iter : 1 Arret : 0.00369829 s/iter 72.960026 +gpu 0 iter : 2 Arret : 0.656453 s/iter 73.009854 +gpu 0 iter : 3 Arret : 1.85379 s/iter 73.909530 +gpu 0 iter : 4 Arret : 0.184697 s/iter 73.870387 +gpu 0 iter : 5 Arret : 0.149335 s/iter 73.917721 +gpu 0 iter : 6 Arret : 0.0961951 s/iter 74.759550 +gpu 0 iter : 7 Arret : 0.0847578 s/iter 74.840915 +gpu 0 iter : 8 Arret : 0.0292103 s/iter 74.694556 +gpu 0 iter : 9 Arret : 0.0283648 s/iter 74.484213 +gpu 0 iter : 10 Arret : 0.0181273 s/iter 73.989131 +gpu 0 iter : 11 Arret : 0.0158134 s/iter 73.602331 +gpu 0 iter : 12 Arret : 0.0047499 s/iter 73.110712 +gpu 0 iter : 13 Arret : 0.00558216 s/iter 73.004439 +gpu 0 iter : 14 Arret : 0.00502349 s/iter 72.957971 +gpu 0 iter : 15 Arret : 0.00203782 s/iter 72.966516 +gpu 0 iter : 16 Arret : 0.000101539 s/iter 72.953065 +gpu 0 iter : 17 Arret : 0.000105985 s/iter 72.981166 +gpu 0 iter : 18 Arret : 7.62032E-06 s/iter 72.955710 +gpu 0 iter : 19 Arret : 2.53593E-08 s/iter 72.953928 +gpu 0 iter : 20 Arret : 2.22162E-10 s/iter 72.808169 +gpu 0 iter : 21 Arret : 3.30983E-12 s/iter 72.824788 +gpu 0 iter : 22 Arret : 4.92853E-14 s/iter 72.871341 +temps : 1621.79 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.65132E-08 +Stabilite : 4.92853E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540305 +i* 0.841476| 1.00001| 4.82795E-10 +i* 3.31212E-09| +| 2| 0.52971 +i* 0.848174| 0.999996|-2.56639E-12 +i*-3.27674E-11| +| 3| 0.524361 +i* 0.851491| 0.999996|-2.47296E-11 +i* 1.78327E-11| +| 4| 0.519019 +i* 0.854758| 0.999996|-1.39375E-11 +i* 5.79731E-12| +| 5| 0.513629 +i* 0.858008| 0.999996| 2.32483E-11 +i* 6.70747E-12| +| 6| 0.508237 +i* 0.861213| 0.999996|-1.34339E-11 +i* 9.87854E-12| +| 7| 0.502834 +i* 0.864379| 0.999996|-2.85585E-11 +i* 6.91519E-12| +| 8| 0.497384 +i* 0.867526| 0.999996| 2.97429E-11 +i*-6.06626E-13| +| 9| 0.491942 +i* 0.870624| 0.999996| -1.9825E-11 +i*-1.52329E-11| +| 10| 0.486452 +i* 0.873703| 0.999996| 3.0312E-11 +i* 1.02214E-11| +| 11| 0.480962 +i* 0.876737| 0.999996| 1.81546E-11 +i* 8.04012E-12| +| 12| 0.475453 +i* 0.879736| 0.999996| 3.09861E-11 +i* 4.093E-12| +| 13| 0.469917 +i* 0.882706| 0.999996|-1.29106E-11 +i*-2.31489E-11| +| 14| 0.46438 +i* 0.885632| 0.999996| 1.33844E-11 +i*-1.06731E-12| +| 15| 0.458797 +i* 0.888537| 0.999996| 2.78862E-11 +i* 1.10441E-11| +| 16| 0.453214 +i* 0.891397| 0.999996| 2.45506E-11 +i* 3.1726E-11| +| 17| 0.447623 +i* 0.894218| 0.999996| 3.85803E-11 +i* 3.3129E-11| +| 18| 0.441986 +i* 0.897017| 0.999996| 2.72476E-11 +i* 3.22485E-11| +| 19| 0.43636 +i* 0.899768| 0.999996| 3.23241E-12 +i* 9.4037E-12| +| 20| 0.430689 +i* 0.902496| 0.999996|-1.25435E-11 +i* 3.86925E-13| ++---+----------------------------+------------+----------------------------+ +400000 racines de module = 1.00001 +600000 racines de module = 0.999996 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^500000 + (-10 +i*0)*x^700000 + (1 +i*0)*x^1200000 + +(-50000 +i*0)*x^499999 + (-7E+06 +i*0)*x^699999 + (1.2E+06 +i*0)*x^1199999 + +zone limite de 'log-exp' 1.0003 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 4688 dimblock 256 degrePoly 1200000 +gpu 0 dimgrid2 4688 start 0 size 1200128 +gpu 0 iter : 1 Arret : 0.0182376 s/iter 104.837597 +gpu 0 iter : 2 Arret : 1.12373 s/iter 108.563668 +gpu 0 iter : 3 Arret : 0.426381 s/iter 110.022983 +gpu 0 iter : 4 Arret : 0.721244 s/iter 111.488820 +gpu 0 iter : 5 Arret : 1.17091 s/iter 111.916174 +gpu 0 iter : 6 Arret : 0.351155 s/iter 112.354360 +gpu 0 iter : 7 Arret : 0.375654 s/iter 113.067528 +gpu 0 iter : 8 Arret : 1.04032 s/iter 113.381487 +gpu 0 iter : 9 Arret : 1.12875 s/iter 114.128347 +gpu 0 iter : 10 Arret : 12.358 s/iter 114.591594 +gpu 0 iter : 11 Arret : 1.18398 s/iter 114.167437 +gpu 0 iter : 12 Arret : 4.45048 s/iter 113.754284 +gpu 0 iter : 13 Arret : 5.09703 s/iter 112.914247 +gpu 0 iter : 14 Arret : 1.04453 s/iter 112.076259 +gpu 0 iter : 15 Arret : 3.05711 s/iter 111.467739 +gpu 0 iter : 16 Arret : 0.859735 s/iter 110.945464 +gpu 0 iter : 17 Arret : 4.25309 s/iter 110.793391 +gpu 0 iter : 18 Arret : 0.893951 s/iter 110.388272 +gpu 0 iter : 19 Arret : 0.603038 s/iter 110.132291 +gpu 0 iter : 20 Arret : 3.09335 s/iter 109.413247 +gpu 0 iter : 21 Arret : 1.28616 s/iter 109.106140 +gpu 0 iter : 22 Arret : 2.25952 s/iter 109.082492 +gpu 0 iter : 23 Arret : 1.67614 s/iter 108.802369 +gpu 0 iter : 24 Arret : 0.645561 s/iter 108.387380 +gpu 0 iter : 25 Arret : 0.661038 s/iter 108.106268 +gpu 0 iter : 26 Arret : 0.728448 s/iter 107.627940 +gpu 0 iter : 27 Arret : 0.456849 s/iter 107.304474 +gpu 0 iter : 28 Arret : 0.254278 s/iter 106.811137 +gpu 0 iter : 29 Arret : 0.111958 s/iter 106.339104 +gpu 0 iter : 30 Arret : 0.0531874 s/iter 105.891059 +gpu 0 iter : 31 Arret : 0.0531871 s/iter 105.523621 +gpu 0 iter : 32 Arret : 0.013254 s/iter 105.034027 +gpu 0 iter : 33 Arret : 0.00334602 s/iter 104.894966 +gpu 0 iter : 34 Arret : 0.00027649 s/iter 104.840988 +gpu 0 iter : 35 Arret : 1.17344E-07 s/iter 104.858305 +gpu 0 iter : 36 Arret : 4.79311E-10 s/iter 104.840632 +gpu 0 iter : 37 Arret : 1.90774E-12 s/iter 104.820758 +gpu 0 iter : 38 Arret : 8.88875E-15 s/iter 104.804403 +temps : 4148.3 seconde(s) +Nb iterations : 38 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.76717E-08 +Stabilite : 8.88875E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540312 +i* 0.841461| 0.999997|-2.16913E-11 +i* 1.91294E-11| +| 2| 0.513645 +i* 0.857999| 0.999997|-6.29718E-12 +i*-2.39364E-12| +| 3| 0.486457 +i* 0.873701| 0.999997| 1.53235E-11 +i* 6.36435E-13| +| 4| 0.458797 +i* 0.888537| 0.999997| 1.72345E-11 +i* 1.48229E-11| +| 5| 0.430698 +i* 0.902501| 1| 9.83414E-09 +i*-4.46881E-09| +| 6| 0.402138 +i* 0.915584| 1|-5.37264E-09 +i* 9.04446E-09| +| 7| 0.3732 +i* 0.927747| 0.999997|-1.54374E-11 +i*-2.76083E-11| +| 8| 0.3439 +i* 0.939003| 0.999997|-1.12714E-11 +i* 1.5453E-11| +| 9| 0.314261 +i* 0.949333| 0.999997| 1.93628E-11 +i* 2.50909E-11| +| 10| 0.284313 +i* 0.958728| 0.999997| 2.69426E-11 +i* 2.77974E-11| +| 11| 0.254084 +i* 0.967179| 0.999997| 1.5277E-11 +i* 4.73027E-12| +| 12| 0.223605 +i* 0.974676| 0.999997| -8.1017E-11 +i*-3.77299E-11| +| 13| 0.192915 +i* 0.981212| 0.999997| 1.07495E-11 +i* 5.766E-12| +| 14| 0.162034 +i* 0.986782| 0.999997| 3.99512E-11 +i* 6.63664E-12| +| 15| 0.130977 +i* 0.991382| 0.999997| 5.89659E-11 +i* 7.29122E-12| +| 16| 0.0997987 +i* 0.995004| 0.999997|-2.34084E-11 +i*-4.34534E-12| +| 17| 0.0685225 +i* 0.997646| 0.999997| 2.33641E-11 +i* 2.51787E-12| +| 18| 0.0371629 +i* 0.999314| 1| 1.55887E-09 +i*-4.23222E-09| +| 19| 0.00578048 +i* 0.99998| 0.999997| 3.46787E-11 +i* 1.94857E-13| +| 20| -0.0256056 +i* 0.999669| 0.999997| 2.01068E-11 +i*-1.22213E-12| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 0.999997 +500000 racines de module = 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^600000 + (-10 +i*0)*x^800000 + (1 +i*0)*x^1400000 + +(-60000 +i*0)*x^599999 + (-8E+06 +i*0)*x^799999 + (1.4E+06 +i*0)*x^1399999 + +zone limite de 'log-exp' 1.00025 +CPU thread 0 (of 1) uses CUDA device 0 +gpu 0 dimgrid 5469 dimblock 256 degrePoly 1400000 +gpu 0 dimgrid2 5469 start 0 size 1400064 +gpu 0 iter : 1 Arret : 0.00928965 s/iter 142.375846 +gpu 0 iter : 2 Arret : 0.576413 s/iter 147.373084 +gpu 0 iter : 3 Arret : 0.762551 s/iter 150.232559 +gpu 0 iter : 4 Arret : 1.07413 s/iter 151.768093 +gpu 0 iter : 5 Arret : 0.0991065 s/iter 153.056251 +gpu 0 iter : 6 Arret : 0.123507 s/iter 152.742000 +gpu 0 iter : 7 Arret : 0.136183 s/iter 152.857808 +gpu 0 iter : 8 Arret : 0.113786 s/iter 152.881427 +gpu 0 iter : 9 Arret : 0.0800623 s/iter 152.835777 +gpu 0 iter : 10 Arret : 0.0571798 s/iter 151.922898 +gpu 0 iter : 11 Arret : 0.0727241 s/iter 150.276395 +gpu 0 iter : 12 Arret : 0.0702862 s/iter 147.770220 +gpu 0 iter : 13 Arret : 0.0246309 s/iter 145.850735 +gpu 0 iter : 14 Arret : 0.0213611 s/iter 144.099565 +gpu 0 iter : 15 Arret : 0.0247135 s/iter 143.346943 +gpu 0 iter : 16 Arret : 0.0164575 s/iter 142.914262 +gpu 0 iter : 17 Arret : 0.00452215 s/iter 142.729324 +gpu 0 iter : 18 Arret : 0.00260492 s/iter 142.530031 +gpu 0 iter : 19 Arret : 0.000151029 s/iter 142.510219 +gpu 0 iter : 20 Arret : 1.40988E-06 s/iter 142.510180 +gpu 0 iter : 21 Arret : 1.38776E-08 s/iter 142.480080 +gpu 0 iter : 22 Arret : 1.91581E-10 s/iter 142.453226 +gpu 0 iter : 23 Arret : 2.63708E-12 s/iter 142.412633 +gpu 0 iter : 24 Arret : 3.63243E-14 s/iter 142.487841 +temps : 3523.14 seconde(s) +Nb iterations : 24 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.65661E-08 +Stabilite : 3.63243E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841469| 0.999997|-8.47142E-11 +i* 1.92466E-11| +| 2| 0.513623 +i* 0.858013| 0.999997|-2.15776E-11 +i*-2.98557E-11| +| 3| -0.52703 +i* -0.849843| 0.999997|-6.50922E-11 +i* 8.44216E-12| +| 4| 0.486439 +i* 0.873711| 0.999997| 5.60277E-11 +i* 4.36779E-11| +| 5| -0.500096 +i* -0.865967| 0.999997| 3.56147E-11 +i*-3.12713E-11| +| 6| 0.458776 +i* 0.888549| 0.999997|-1.89702E-11 +i* 4.08274E-12| +| 7| -0.472669 +i* -0.881237| 0.999997|-1.66496E-11 +i*-3.61498E-11| +| 8| 0.430661 +i* 0.902511| 0.999997|-1.60558E-11 +i*-1.29949E-11| +| 9| -0.444791 +i* -0.895631| 0.999997| 3.68259E-11 +i* 1.36002E-12| +| 10| 0.402136 +i* 0.915577| 0.999997| 6.5834E-12 +i* -1.3935E-11| +| 11| -0.416439 +i* -0.90916| 0.999997|-1.66807E-11 +i* 2.56219E-11| +| 12| 0.373179 +i* 0.927756| 0.999997| 2.89372E-11 +i*-2.61371E-11| +| 13| -0.387698 +i* -0.921783| 0.999997|-1.86324E-11 +i* -4.6545E-11| +| 14| 0.343875 +i* 0.939012| 0.999997| 3.06317E-11 +i* 7.08794E-11| +| 15| -0.358575 +i* -0.933498| 0.999997|-4.93405E-11 +i*-7.15173E-13| +| 16| 0.314233 +i* 0.949343| 0.999997| 3.86503E-11 +i* 2.08775E-11| +| 17| -0.329098 +i* -0.944293| 0.999997|-1.57903E-11 +i* 2.05052E-11| +| 18| 0.284281 +i* 0.958738| 0.999997| 2.51592E-11 +i* 2.09243E-11| +| 19| -0.299297 +i* -0.954157| 0.999997| 5.03608E-12 +i* 1.70503E-11| +| 20| 0.254048 +i* 0.967189| 0.999997|-2.81228E-11 +i*-1.66302E-11| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 0.999997 +600000 racines de module = 1 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140100: line 23: 13069 Segmentation fault (core dumped) ./template -r -i 900000 700000 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140100: line 24: 13073 Segmentation fault (core dumped) ./template -r -i 1000000 800000 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140100: line 25: 13075 Segmentation fault (core dumped) ./template -r -i 1500000 500000 diff --git a/Simulations/sparse_openmp/sparse_openmp_1GPU.sge b/Simulations/sparse_openmp/sparse_openmp_1GPU.sge new file mode 100644 index 0000000..ceb97b1 --- /dev/null +++ b/Simulations/sparse_openmp/sparse_openmp_1GPU.sge @@ -0,0 +1,27 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=1 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -pe openmp 1 +#$ -V +#$ -cwd +#$ -N sparse_openmp_1GPU + +module load gcc/4.9.0 +module load cuda/7.0 +export OMP_NUM_THREADS=1 + +./template -r -i 60000 40000 +./template -r -i 150000 50000 +./template -r -i 250000 150000 +./template -r -i 350000 250000 +./template -r -i 500000 300000 +./template -r -i 600000 400000 +./template -r -i 700000 500000 +./template -r -i 800000 600000 +./template -r -i 900000 700000 +./template -r -i 1000000 800000 +./template -r -i 1500000 500000 + + diff --git a/Simulations/sparse_openmp/sparse_openmp_2GPU.o140099 b/Simulations/sparse_openmp/sparse_openmp_2GPU.o140099 new file mode 100644 index 0000000..b18a418 --- /dev/null +++ b/Simulations/sparse_openmp/sparse_openmp_2GPU.o140099 @@ -0,0 +1,534 @@ +REMAINING: 2 +Taking GPU #0 +Taking GPU #1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^40000 + (-10 +i*0)*x^60000 + (1 +i*0)*x^100000 + +(-4000 +i*0)*x^39999 + (-600000 +i*0)*x^59999 + (100000 +i*0)*x^99999 + +zone limite de 'log-exp' 1.00356 +CPU thread 1 (of 2) uses CUDA device 1 +CPU thread 0 (of 2) uses CUDA device 0 +gpu 0 dimgrid 391 dimblock 256 degrePoly 100000 +gpu 0 dimgrid2 196 start 0 size 50048 +gpu 1 dimgrid 391 dimblock 256 degrePoly 100000 +gpu 1 dimgrid2 196 start 50048 size 50048 +gpu 0 iter : 1 Arret : 0.00380313 s/iter 0.441566 +gpu 0 iter : 2 Arret : 0.00367222 s/iter 0.441506 +gpu 0 iter : 3 Arret : 0.00329063 s/iter 0.441545 +gpu 0 iter : 4 Arret : 0.00599232 s/iter 0.441517 +gpu 0 iter : 5 Arret : 0.00559475 s/iter 0.441533 +gpu 0 iter : 6 Arret : 0.0062995 s/iter 0.441538 +gpu 0 iter : 7 Arret : 0.00458799 s/iter 0.441558 +gpu 0 iter : 8 Arret : 0.00622521 s/iter 0.441510 +gpu 0 iter : 9 Arret : 0.0073983 s/iter 0.439550 +gpu 0 iter : 10 Arret : 0.00804763 s/iter 0.441536 +gpu 0 iter : 11 Arret : 0.00548469 s/iter 0.441528 +gpu 0 iter : 12 Arret : 0.00120813 s/iter 0.441416 +gpu 0 iter : 13 Arret : 0.000406962 s/iter 0.441414 +gpu 0 iter : 14 Arret : 0.00112455 s/iter 0.441391 +gpu 0 iter : 15 Arret : 0.000729656 s/iter 0.441398 +gpu 0 iter : 16 Arret : 6.06095E-06 s/iter 0.441340 +gpu 0 iter : 17 Arret : 1.51135E-08 s/iter 0.441471 +gpu 0 iter : 18 Arret : 4.78213E-11 s/iter 0.441372 +gpu 0 iter : 19 Arret : 1.51316E-13 s/iter 0.441309 +temps : 9.12342 seconde(s) +Nb iterations : 19 +Nb de depassements de capacite exponentielle : 0 +Precision : 6.21439E-09 +Stabilite : 1.51316E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.54036 +i* 0.841503| 1.00006|-5.00602E-11 +i* 9.0853E-12| +| 2| -0.113164 +i* 0.993538| 0.999962|-4.34919E-12 +i* 9.60242E-13| +| 3| -0.226732 +i* -0.974016| 1.00006|-1.34468E-09 +i*-3.70749E-10| +| 4| -0.715763 +i* 0.698289| 0.999962| 9.11271E-13 +i* 2.47219E-12| +| 5| 0.439922 +i* -0.897993| 0.999962|-3.49498E-13 +i* 1.66432E-12| +| 6| -0.996122 +i* 0.0886386| 1.00006| 4.72785E-10 +i* 4.13616E-11| +| 7| 0.908546 +i* -0.417692| 0.999962| 4.78506E-13 +i* 1.54377E-13| +| 8| -0.827813 +i* -0.560935| 0.999962| 9.76996E-13 +i*-2.04309E-12| +| 9| 0.968129 +i* 0.250682| 1.00006| 1.35693E-10 +i*-3.47657E-10| +| 10| -0.286842 +i* -0.958038| 1.00006|-5.93554E-10 +i*-2.45345E-10| +| 11| 0.591653 +i* 0.806145| 0.999962|-9.87654E-13 +i*-3.03635E-12| +| 12| -0.0511836 +i* 0.998651| 0.999962|-2.22622E-12 +i*-3.69013E-14| +| 13| -0.67097 +i* 0.741432| 0.999962|-8.03801E-14 +i*-1.68204E-12| +| 14| 0.383249 +i* -0.923603| 0.999962|-1.29119E-12 +i*-1.37426E-12| +| 15| -0.988685 +i* 0.15039| 1.00006|-1.61051E-10 +i* 7.18515E-11| +| 16| 0.880824 +i* -0.473363| 0.999962| 1.58029E-12 +i*-2.34379E-12| +| 17| -0.861082 +i* -0.508391| 0.999962| 1.02962E-12 +i*-4.51911E-12| +| 18| 0.981895 +i* 0.189225| 0.999962|-4.05187E-12 +i* 1.36536E-13| +| 19| -0.345842 +i* -0.938354| 1.00006| 1.38421E-10 +i*-2.31696E-10| +| 20| 0.640621 +i* 0.767807| 0.999962|-6.98774E-13 +i* 1.13798E-12| ++---+----------------------------+------------+----------------------------+ +40000 racines de module = 1.00006 +60000 racines de module = 0.999962 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^50000 + (-10 +i*0)*x^150000 + (1 +i*0)*x^200000 + +(-5000 +i*0)*x^49999 + (-1.5E+06 +i*0)*x^149999 + (200000 +i*0)*x^199999 + +zone limite de 'log-exp' 1.00178 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 1 dimgrid 782 dimblock 256 degrePoly 200000 +gpu 1 dimgrid2 391 start 100096 size 100096 +gpu 0 dimgrid 782 dimblock 256 degrePoly 200000 +gpu 0 dimgrid2 391 start 0 size 100096 +gpu 0 iter : 1 Arret : 0.000107626 s/iter 1.547978 +gpu 0 iter : 2 Arret : 9.81369E-05 s/iter 1.548082 +gpu 0 iter : 3 Arret : 0.000765995 s/iter 1.548065 +gpu 0 iter : 4 Arret : 0.000973277 s/iter 1.548057 +gpu 0 iter : 5 Arret : 0.00848586 s/iter 1.548089 +gpu 0 iter : 6 Arret : 0.0120973 s/iter 1.707264 +gpu 0 iter : 7 Arret : 0.029256 s/iter 1.698285 +gpu 0 iter : 8 Arret : 0.134426 s/iter 1.548025 +gpu 0 iter : 9 Arret : 0.152262 s/iter 1.549290 +gpu 0 iter : 10 Arret : 0.121741 s/iter 1.710977 +gpu 0 iter : 11 Arret : 0.196968 s/iter 1.549235 +gpu 0 iter : 12 Arret : 0.832961 s/iter 1.703810 +gpu 0 iter : 13 Arret : 0.389199 s/iter 1.552020 +gpu 0 iter : 14 Arret : 0.303622 s/iter 1.712838 +gpu 0 iter : 15 Arret : 0.0708981 s/iter 1.549269 +gpu 0 iter : 16 Arret : 0.0516286 s/iter 1.547858 +gpu 0 iter : 17 Arret : 0.0237403 s/iter 1.547965 +gpu 0 iter : 18 Arret : 0.00575736 s/iter 1.548048 +gpu 0 iter : 19 Arret : 0.00016543 s/iter 1.547970 +gpu 0 iter : 20 Arret : 8.19796E-06 s/iter 1.547960 +gpu 0 iter : 21 Arret : 1.89926E-09 s/iter 1.548018 +gpu 0 iter : 22 Arret : 1.89968E-13 s/iter 1.548057 +temps : 35.62 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 9.49941E-05 +Stabilite : 5.04191E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540303 +i* 0.841453| 0.999985| 1.08703E-11 +i*-2.49217E-12| +| 2| -0.837195 +i* 0.546877| 0.999985| -5.4492E-12 +i* 1.09163E-12| +| 3| -0.553418 +i* -0.832885| 0.999985| -1.9722E-12 +i*-7.40397E-12| +| 4| 0.828599 +i* -0.559925| 1.00005|-7.54521E-09 +i* 1.47059E-08| +| 5| -0.8197 +i* 0.572767| 0.999985|-4.21663E-13 +i* -2.8616E-12| +| 6| -0.57917 +i* -0.815188| 0.999985|-5.13034E-12 +i*-1.52645E-12| +| 7| 0.810626 +i* -0.585537| 0.999985|-6.36846E-12 +i*-5.86797E-12| +| 8| 0.591872 +i* 0.806089| 1.00005|-1.69803E-09 +i* 9.43795E-09| +| 9| -0.801454 +i* 0.598134| 1.00005|-3.72767E-08 +i*-1.30274E-08| +| 10| -0.604356 +i* -0.796695| 0.999985|-1.64091E-13 +i* 1.59084E-12| +| 11| 0.791937 +i* -0.610578| 0.999985| 6.0707E-13 +i* 1.52922E-12| +| 12| 0.616763 +i* 0.78713| 0.999985|-4.48042E-12 +i* -2.6295E-12| +| 13| -0.782301 +i* 0.622877| 0.999985|-2.15827E-12 +i*-6.27114E-12| +| 14| -0.628991 +i* -0.777472| 1.00005| 6.93065E-09 +i*-8.65443E-09| +| 15| 0.772474 +i* -0.635023| 0.999985| 1.54783E-11 +i*-1.81338E-12| +| 16| 0.641054 +i* 0.767476| 0.999985| 9.05009E-12 +i*-2.91295E-12| +| 17| -0.762458 +i* 0.647014| 0.999985| 5.81724E-12 +i*-9.99384E-12| +| 18| -0.652967 +i* -0.757366| 0.999985|-6.31406E-12 +i* 8.49495E-12| +| 19| 0.752302 +i* -0.658888| 1.00005| 3.99107E-09 +i* 1.02117E-08| +| 20| 0.66472 +i* 0.747072| 0.999985|-7.79776E-12 +i*-2.52076E-13| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 0.999985 +50000 racines de module = 1.00005 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^150000 + (-10 +i*0)*x^250000 + (1 +i*0)*x^400000 + +(-15000 +i*0)*x^149999 + (-2.5E+06 +i*0)*x^249999 + (400000 +i*0)*x^399999 + +zone limite de 'log-exp' 1.00089 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 0 dimgrid 1563 dimblock 256 degrePoly 400000 +gpu 0 dimgrid2 782 start 0 size 200064 +gpu 1 dimgrid 1563 dimblock 256 degrePoly 400000 +gpu 1 dimgrid2 782 start 200064 size 200064 +gpu 0 iter : 1 Arret : 0.000533421 s/iter 6.081044 +gpu 0 iter : 2 Arret : 0.00294166 s/iter 6.077042 +gpu 0 iter : 3 Arret : 0.00816274 s/iter 6.076551 +gpu 0 iter : 4 Arret : 0.0970896 s/iter 6.051363 +gpu 0 iter : 5 Arret : 0.1861 s/iter 6.117092 +gpu 0 iter : 6 Arret : 0.205221 s/iter 6.087839 +gpu 0 iter : 7 Arret : 0.0897097 s/iter 6.084694 +gpu 0 iter : 8 Arret : 0.0591358 s/iter 6.078173 +gpu 0 iter : 9 Arret : 0.023858 s/iter 6.079091 +gpu 0 iter : 10 Arret : 0.00304425 s/iter 6.076912 +gpu 0 iter : 11 Arret : 0.00136708 s/iter 6.063903 +gpu 0 iter : 12 Arret : 0.000789721 s/iter 6.076452 +gpu 0 iter : 13 Arret : 0.00195862 s/iter 6.078631 +gpu 0 iter : 14 Arret : 0.00243823 s/iter 6.075599 +gpu 0 iter : 15 Arret : 0.000282668 s/iter 6.076158 +gpu 0 iter : 16 Arret : 4.27745E-05 s/iter 6.075788 +gpu 0 iter : 17 Arret : 4.20725E-06 s/iter 6.077506 +gpu 0 iter : 18 Arret : 1.6828E-08 s/iter 6.078853 +gpu 0 iter : 19 Arret : 3.63614E-11 s/iter 6.079236 +gpu 0 iter : 20 Arret : 1.38589E-13 s/iter 6.077430 +temps : 122.327 seconde(s) +Nb iterations : 20 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.45366E-07 +Stabilite : 1.02274E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540319 +i* 0.841478| 1.00002|-2.32809E-09 +i* 1.97672E-09| +| 2| -0.998329 +i* 0.057622| 0.999991| 4.43912E-12 +i* 1.27665E-12| +| 3| 0.43989 +i* -0.898041| 0.999991|-2.08855E-12 +i*-1.75276E-12| +| 4| -0.996033 +i* 0.0888768| 0.999991|-3.15592E-12 +i* 1.17456E-12| +| 5| 0.411533 +i* -0.911385| 0.999991|-2.45048E-12 +i* 4.6238E-12| +| 6| 0.59196 +i* 0.805956| 0.999991| 5.24358E-13 +i*-8.53073E-12| +| 7| -0.992759 +i* 0.120044| 0.999991| 2.58804E-12 +i* 2.47274E-12| +| 8| 0.382796 +i* -0.923823| 0.999991| 1.11042E-11 +i*-9.27687E-12| +| 9| 0.616925 +i* 0.78701| 0.999991| 4.27514E-12 +i*-1.13966E-11| +| 10| -0.98851 +i* 0.151094| 0.999991|-1.29017E-11 +i*-4.43427E-12| +| 11| 0.35366 +i* -0.935364| 0.999991|-1.92664E-11 +i* 1.19958E-11| +| 12| 0.641283 +i* 0.767292| 0.999991|-4.70735E-12 +i* -1.4127E-11| +| 13| -0.98329 +i* 0.181995| 0.999991|-6.62759E-12 +i*-5.46796E-12| +| 14| 0.324176 +i* -0.945987| 0.999991|-5.20695E-12 +i*-7.06984E-12| +| 15| 0.665012 +i* 0.746821| 0.999991| 5.27178E-12 +i*-4.27913E-12| +| 16| -0.977104 +i* 0.212717| 0.999991|-1.01148E-11 +i* 2.41479E-12| +| 17| 0.294374 +i* -0.955681| 0.999991|-2.37395E-11 +i*-2.53098E-12| +| 18| 0.688087 +i* 0.725616| 0.999991| 6.67011E-12 +i* 1.57173E-11| +| 19| -0.969965 +i* 0.243206| 0.999991| 6.88072E-12 +i* 3.20268E-13| +| 20| 0.264283 +i* -0.964436| 0.999991|-6.93356E-12 +i*-6.23118E-12| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 1.00002 +250000 racines de module = 0.999991 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^250000 + (-10 +i*0)*x^350000 + (1 +i*0)*x^600000 + +(-25000 +i*0)*x^249999 + (-3.5E+06 +i*0)*x^349999 + (600000 +i*0)*x^599999 + +zone limite de 'log-exp' 1.00059 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 0 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 0 dimgrid2 1172 start 0 size 300032 +gpu 1 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 1 dimgrid2 1172 start 300032 size 300032 +gpu 0 iter : 1 Arret : 0.00183894 s/iter 13.264868 +gpu 0 iter : 2 Arret : 0.00332589 s/iter 13.263027 +gpu 0 iter : 3 Arret : 0.0778545 s/iter 13.329862 +gpu 0 iter : 4 Arret : 0.134953 s/iter 13.784249 +gpu 0 iter : 5 Arret : 0.100777 s/iter 14.153947 +gpu 0 iter : 6 Arret : 0.107368 s/iter 13.911608 +gpu 0 iter : 7 Arret : 0.112184 s/iter 13.982400 +gpu 0 iter : 8 Arret : 0.0819523 s/iter 13.863669 +gpu 0 iter : 9 Arret : 0.0470621 s/iter 13.750970 +gpu 0 iter : 10 Arret : 0.0265395 s/iter 13.686381 +gpu 0 iter : 11 Arret : 0.0114418 s/iter 13.768352 +gpu 0 iter : 12 Arret : 0.0132102 s/iter 13.687711 +gpu 0 iter : 13 Arret : 0.0107799 s/iter 13.263263 +gpu 0 iter : 14 Arret : 0.00702915 s/iter 13.271004 +gpu 0 iter : 15 Arret : 0.00272883 s/iter 13.265259 +gpu 0 iter : 16 Arret : 0.000385595 s/iter 13.264764 +gpu 0 iter : 17 Arret : 0.000332015 s/iter 13.264693 +gpu 0 iter : 18 Arret : 0.000909613 s/iter 13.264925 +gpu 0 iter : 19 Arret : 9.10926E-07 s/iter 13.264547 +gpu 0 iter : 20 Arret : 4.37366E-09 s/iter 13.265195 +gpu 0 iter : 21 Arret : 1.73951E-11 s/iter 13.264664 +gpu 0 iter : 22 Arret : 6.9226E-14 s/iter 13.264587 +temps : 297.898 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.80963E-08 +Stabilite : 6.9226E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540302 +i* 0.841463| 0.999993| 8.34199E-12 +i* -1.9051E-11| +| 2| -0.553438 +i* -0.832883| 0.999993|-2.10654E-12 +i*-2.55273E-11| +| 3| -0.579282 +i* -0.815119| 0.999993|-1.44751E-12 +i* 7.66798E-12| +| 4| 0.592012 +i* 0.805941| 1.00001| 4.1526E-09 +i* 1.02046E-09| +| 5| -0.604557 +i* -0.796554| 0.999993|-2.82974E-12 +i* 9.99473E-12| +| 6| 0.61698 +i* 0.78697| 0.999993|-4.77973E-12 +i* 2.40621E-11| +| 7| -0.629237 +i* -0.777205| 0.999993|-2.92122E-12 +i*-4.85867E-12| +| 8| 0.641354 +i* 0.767237| 0.999993|-1.64209E-11 +i* 1.12904E-12| +| 9| -0.653299 +i* -0.757092| 0.999993|-8.22453E-13 +i* 2.82818E-12| +| 10| 0.665096 +i* 0.746749| 0.999993| -1.2145E-11 +i* 1.89129E-11| +| 11| -0.676717 +i* -0.736234| 0.999993|-1.26079E-11 +i*-1.25073E-11| +| 12| 0.688185 +i* 0.725526| 0.999993|-4.43978E-12 +i*-2.31382E-11| +| 13| -0.699466 +i* -0.714679| 1.00001| 3.92343E-10 +i*-3.02623E-09| +| 14| 0.710597 +i* 0.70359| 0.999993| -2.6851E-11 +i*-1.44801E-11| +| 15| -0.721524 +i* -0.69238| 0.999993| 2.63193E-11 +i*-6.76318E-13| +| 16| 0.73231 +i* 0.680962| 0.999993| 1.34706E-11 +i*-4.43489E-12| +| 17| -0.742928 +i* -0.669362| 0.999993| 3.04134E-12 +i*-9.84154E-12| +| 18| 0.7533 +i* 0.657691| 1.00001|-2.76219E-09 +i* 4.10298E-09| +| 19| -0.76354 +i* -0.64575| 0.999993| 2.24043E-11 +i*-1.30496E-12| +| 20| 0.773543 +i* 0.633733| 0.999993| 6.56308E-12 +i* 2.27492E-11| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 0.999993 +250000 racines de module = 1.00001 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^300000 + (-10 +i*0)*x^500000 + (1 +i*0)*x^800000 + +(-30000 +i*0)*x^299999 + (-5E+06 +i*0)*x^499999 + (800000 +i*0)*x^799999 + +zone limite de 'log-exp' 1.00044 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 1 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 1 dimgrid2 1563 start 400000 size 400000 +gpu 0 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 0 dimgrid2 1563 start 0 size 400000 +gpu 0 iter : 1 Arret : 0.000985945 s/iter 23.676133 +gpu 0 iter : 2 Arret : 0.00575711 s/iter 23.813100 +gpu 0 iter : 3 Arret : 0.80372 s/iter 23.766696 +gpu 0 iter : 4 Arret : 1.12755 s/iter 23.828097 +gpu 0 iter : 5 Arret : 0.927252 s/iter 23.871271 +gpu 0 iter : 6 Arret : 1.8727 s/iter 23.858341 +gpu 0 iter : 7 Arret : 1.02108 s/iter 24.362443 +gpu 0 iter : 8 Arret : 0.40485 s/iter 24.813205 +gpu 0 iter : 9 Arret : 0.204025 s/iter 24.848475 +gpu 0 iter : 10 Arret : 0.322307 s/iter 24.766030 +gpu 0 iter : 11 Arret : 0.966794 s/iter 24.450352 +gpu 0 iter : 12 Arret : 0.519786 s/iter 24.347418 +gpu 0 iter : 13 Arret : 0.209179 s/iter 24.204030 +gpu 0 iter : 14 Arret : 0.0738373 s/iter 23.789427 +gpu 0 iter : 15 Arret : 0.0394797 s/iter 23.786761 +gpu 0 iter : 16 Arret : 0.0224964 s/iter 23.792150 +gpu 0 iter : 17 Arret : 0.0104646 s/iter 23.802294 +gpu 0 iter : 18 Arret : 0.00882482 s/iter 23.804999 +gpu 0 iter : 19 Arret : 0.000586803 s/iter 23.663425 +gpu 0 iter : 20 Arret : 1.2904E-06 s/iter 23.667331 +gpu 0 iter : 21 Arret : 2.17443E-08 s/iter 23.669417 +gpu 0 iter : 22 Arret : 3.31651E-10 s/iter 23.663042 +gpu 0 iter : 23 Arret : 5.05742E-12 s/iter 23.667395 +gpu 0 iter : 24 Arret : 7.71156E-14 s/iter 23.671701 +temps : 576.437 seconde(s) +Nb iterations : 24 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.80859E-08 +Stabilite : 7.7914E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540305 +i* 0.841464| 0.999995|-5.33817E-12 +i*-1.81878E-11| +| 2| 0.592014 +i* 0.805922| 0.999995|-1.82734E-11 +i* 2.10218E-11| +| 3| 0.617007 +i* 0.786952| 0.999995| 4.23442E-11 +i* -6.2147E-12| +| 4| 0.641392 +i* 0.767207| 0.999995|-4.99742E-11 +i* 1.43873E-11| +| 5| 0.665146 +i* 0.746707| 0.999995| 2.02977E-11 +i* 7.48579E-12| +| 6| 0.688245 +i* 0.725472| 0.999995|-1.73153E-11 +i* -1.2656E-11| +| 7| 0.710667 +i* 0.703522| 0.999995| 3.69782E-12 +i* 2.3081E-12| +| 8| 0.732388 +i* 0.68088| 0.999995| 9.45355E-12 +i* 2.09024E-11| +| 9| 0.753381 +i* 0.657577| 0.999995|-1.40248E-11 +i* 5.11502E-11| +| 10| 0.77364 +i* 0.633618| 0.999995|-1.72307E-11 +i* 1.22723E-11| +| 11| 0.793138 +i* 0.609034| 0.999995| 3.89222E-12 +i* 2.21356E-11| +| 12| 0.811855 +i* 0.583851| 0.999995|-1.28337E-11 +i*-5.47207E-12| +| 13| 0.829772 +i* 0.558094| 0.999995|-1.63114E-11 +i*-1.64246E-12| +| 14| 0.846873 +i* 0.531786| 0.999995|-1.80345E-12 +i* 5.96675E-11| +| 15| 0.86314 +i* 0.504956| 0.999995|-4.00413E-12 +i* 3.04823E-11| +| 16| 0.878557 +i* 0.477628| 0.999995|-2.16493E-12 +i* 1.10533E-11| +| 17| 0.893104 +i* 0.449841| 0.999995|-1.48552E-11 +i* 1.06063E-11| +| 18| 0.906777 +i* 0.4216| 0.999995|-1.38745E-11 +i* 5.33384E-12| +| 19| 0.919557 +i* 0.392944| 0.999995| 4.13796E-11 +i*-2.48189E-11| +| 20| 0.931433 +i* 0.363901| 0.999995| 4.93219E-11 +i*-2.82651E-11| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 0.999995 +300000 racines de module = 1.00001 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^400000 + (-10 +i*0)*x^600000 + (1 +i*0)*x^1000000 + +(-40000 +i*0)*x^399999 + (-6E+06 +i*0)*x^599999 + (1E+06 +i*0)*x^999999 + +zone limite de 'log-exp' 1.00035 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 0 dimgrid 3907 dimblock 256 degrePoly 1000000 +gpu 0 dimgrid2 1954 start 0 size 500096 +gpu 1 dimgrid 3907 dimblock 256 degrePoly 1000000 +gpu 1 dimgrid2 1954 start 500096 size 500096 +gpu 0 iter : 1 Arret : 0.000661333 s/iter 36.538739 +gpu 0 iter : 2 Arret : 0.00112864 s/iter 36.545395 +gpu 0 iter : 3 Arret : 0.00370767 s/iter 36.541300 +gpu 0 iter : 4 Arret : 0.00748235 s/iter 37.223998 +gpu 0 iter : 5 Arret : 0.0147148 s/iter 37.021293 +gpu 0 iter : 6 Arret : 0.0212816 s/iter 37.146418 +gpu 0 iter : 7 Arret : 0.00895178 s/iter 37.219267 +gpu 0 iter : 8 Arret : 0.00887668 s/iter 37.316626 +gpu 0 iter : 9 Arret : 0.00504713 s/iter 36.647500 +gpu 0 iter : 10 Arret : 0.00709815 s/iter 37.285606 +gpu 0 iter : 11 Arret : 0.00694487 s/iter 36.891551 +gpu 0 iter : 12 Arret : 0.00243476 s/iter 36.546690 +gpu 0 iter : 13 Arret : 0.00268555 s/iter 36.502800 +gpu 0 iter : 14 Arret : 0.000904871 s/iter 36.508349 +gpu 0 iter : 15 Arret : 0.0005848 s/iter 36.503946 +gpu 0 iter : 16 Arret : 8.64186E-05 s/iter 36.503619 +gpu 0 iter : 17 Arret : 8.33778E-05 s/iter 36.511641 +gpu 0 iter : 18 Arret : 1.10486E-05 s/iter 36.503510 +gpu 0 iter : 19 Arret : 1.76382E-05 s/iter 36.534320 +gpu 0 iter : 20 Arret : 1.2926E-06 s/iter 36.537729 +gpu 0 iter : 21 Arret : 5.95413E-09 s/iter 36.503894 +gpu 0 iter : 22 Arret : 1.88485E-11 s/iter 36.540363 +gpu 0 iter : 23 Arret : 5.96427E-14 s/iter 36.541307 +temps : 850.208 seconde(s) +Nb iterations : 23 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.65132E-08 +Stabilite : 5.96427E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841468| 0.999996| 5.07216E-12 +i* 6.41236E-12| +| 2| 0.529701 +i* 0.84818| 0.999996|-4.61853E-13 +i*-4.17888E-12| +| 3| 0.524361 +i* 0.851491| 0.999996|-2.47296E-11 +i* 1.78327E-11| +| 4| 0.51901 +i* 0.854764| 0.999996| 9.45599E-12 +i* 2.07434E-11| +| 5| 0.513629 +i* 0.858008| 0.999996| 2.32483E-11 +i* 6.70747E-12| +| 6| 0.508237 +i* 0.861213| 0.999996|-1.34339E-11 +i* 9.87854E-12| +| 7| 0.502825 +i* 0.864384| 0.999996|-3.18459E-11 +i* 7.64744E-12| +| 8| 0.497384 +i* 0.867526| 0.999996| 1.87346E-11 +i* 4.7471E-11| +| 9| 0.491932 +i* 0.870629| 0.999996|-1.74121E-11 +i*-2.86359E-11| +| 10| 0.486452 +i* 0.873703| 0.999996| 3.0312E-11 +i* 1.02214E-11| +| 11| 0.480962 +i* 0.876737| 0.999996| 1.81546E-11 +i* 8.04012E-12| +| 12| 0.475453 +i* 0.879736| 0.999996| 3.09861E-11 +i* 4.093E-12| +| 13| 0.469917 +i* 0.882706| 0.999996|-1.29106E-11 +i*-2.31489E-11| +| 14| 0.46437 +i* 0.885637| 0.999996| 1.38481E-11 +i* -1.517E-11| +| 15| 0.458797 +i* 0.888537| 0.999996| 2.60997E-11 +i*-9.69844E-12| +| 16| 0.453214 +i* 0.891397| 0.999996| 2.45506E-11 +i* 3.1726E-11| +| 17| 0.447614 +i* 0.894223| 0.999996|-1.08491E-12 +i*-2.12277E-11| +| 18| 0.441986 +i* 0.897017| 0.999996| 2.72476E-11 +i* 3.22485E-11| +| 19| 0.436351 +i* 0.899772| 0.999996|-1.24334E-11 +i*-2.66317E-11| +| 20| 0.430689 +i* 0.902496| 0.999996| 2.73914E-12 +i* 2.25153E-11| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 0.999996 +400000 racines de module = 1.00001 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^500000 + (-10 +i*0)*x^700000 + (1 +i*0)*x^1200000 + +(-50000 +i*0)*x^499999 + (-7E+06 +i*0)*x^699999 + (1.2E+06 +i*0)*x^1199999 + +zone limite de 'log-exp' 1.0003 +CPU thread 0 (of 2) uses CUDA device 0 +CPU thread 1 (of 2) uses CUDA device 1 +gpu 0 dimgrid 4688 dimblock 256 degrePoly 1200000 +gpu 0 dimgrid2 2344 start 0 size 600064 +gpu 1 dimgrid 4688 dimblock 256 degrePoly 1200000 +gpu 1 dimgrid2 2344 start 600064 size 600064 +gpu 0 iter : 1 Arret : 0.00780904 s/iter 52.957678 +gpu 0 iter : 2 Arret : 0.698753 s/iter 54.370408 +gpu 0 iter : 3 Arret : 0.512229 s/iter 55.903856 +gpu 0 iter : 4 Arret : 0.256495 s/iter 56.546686 +gpu 0 iter : 5 Arret : 0.481397 s/iter 56.384400 +gpu 0 iter : 6 Arret : 0.892443 s/iter 56.641431 +gpu 0 iter : 7 Arret : 1.58519 s/iter 56.603728 +gpu 0 iter : 8 Arret : 1.00461 s/iter 56.787414 +gpu 0 iter : 9 Arret : 0.667954 s/iter 56.936636 +gpu 0 iter : 10 Arret : 1.69048 s/iter 56.433809 +gpu 0 iter : 11 Arret : 0.673973 s/iter 56.247309 +gpu 0 iter : 12 Arret : 0.286904 s/iter 55.583712 +gpu 0 iter : 13 Arret : 0.809155 s/iter 54.972406 +gpu 0 iter : 14 Arret : 1.04967 s/iter 54.200475 +gpu 0 iter : 15 Arret : 0.767419 s/iter 54.073912 +gpu 0 iter : 16 Arret : 1.25055 s/iter 53.969523 +gpu 0 iter : 17 Arret : 0.313555 s/iter 53.619940 +gpu 0 iter : 18 Arret : 0.0612844 s/iter 53.103551 +gpu 0 iter : 19 Arret : 0.0812813 s/iter 53.087654 +gpu 0 iter : 20 Arret : 0.0798413 s/iter 52.895378 +gpu 0 iter : 21 Arret : 0.0193508 s/iter 52.929617 +gpu 0 iter : 22 Arret : 0.0112127 s/iter 52.923694 +gpu 0 iter : 23 Arret : 0.00926876 s/iter 52.906420 +gpu 0 iter : 24 Arret : 0.00234025 s/iter 52.924598 +gpu 0 iter : 25 Arret : 0.000902467 s/iter 52.922805 +gpu 0 iter : 26 Arret : 2.88058E-05 s/iter 52.927734 +gpu 0 iter : 27 Arret : 3.35406E-07 s/iter 52.973958 +gpu 0 iter : 28 Arret : 1.39702E-09 s/iter 52.974028 +gpu 0 iter : 29 Arret : 8.02785E-12 s/iter 52.966681 +gpu 0 iter : 30 Arret : 1.1441E-13 s/iter 52.951515 +temps : 1631.66 seconde(s) +Nb iterations : 30 +Nb de depassements de capacite exponentielle : 0 +Precision : 7.74574E-08 +Stabilite : 2.21335E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540304 +i* 0.841466| 0.999997| 3.08649E-11 +i* 2.05843E-11| +| 2| 0.513629 +i* 0.858008| 0.999997| 3.02357E-11 +i* 3.41858E-11| +| 3| 0.486451 +i* 0.873713| 1| 1.95054E-09 +i* 6.77633E-10| +| 4| 0.458805 +i* 0.888533| 0.999997| 1.78773E-11 +i* 1.55684E-11| +| 5| 0.43071 +i* 0.902487| 0.999997|-9.50928E-12 +i*-1.85143E-11| +| 6| 0.402126 +i* 0.915589| 1| 2.50282E-09 +i*-6.10471E-09| +| 7| 0.3732 +i* 0.927747| 0.999997| -2.5707E-11 +i* 3.11093E-13| +| 8| 0.3439 +i* 0.939003| 0.999997|-1.12714E-11 +i* 1.5453E-11| +| 9| 0.314261 +i* 0.949333| 0.999997| 1.93628E-11 +i* 2.50909E-11| +| 10| 0.284313 +i* 0.958728| 0.999997| 2.69426E-11 +i* 2.77974E-11| +| 11| 0.254084 +i* 0.967179| 0.999997| 1.5277E-11 +i* 4.73027E-12| +| 12| 0.223605 +i* 0.974676| 0.999997| -8.1017E-11 +i*-3.77299E-11| +| 13| 0.192909 +i* 0.981221| 1|-1.95729E-09 +i* 4.84549E-09| +| 14| 0.162017 +i* 0.986785| 0.999997| 4.59321E-12 +i*-4.42106E-13| +| 15| 0.130967 +i* 0.991391| 1|-1.93729E-10 +i*-4.06442E-10| +| 16| 0.0998077 +i* 0.995003| 0.999997| -4.5103E-11 +i*-6.66658E-12| +| 17| 0.0685225 +i* 0.997646| 0.999997| 2.33641E-11 +i* 2.51787E-12| +| 18| 0.0371504 +i* 0.999314| 1|-3.18728E-10 +i*-2.97119E-09| +| 19| 0.00578048 +i* 0.99998| 0.999997| 3.46787E-11 +i* 1.94857E-13| +| 20| -0.0256056 +i* 0.999669| 0.999997| 2.01068E-11 +i*-1.22213E-12| ++---+----------------------------+------------+----------------------------+ +700000 racines de module = 0.999997 +500000 racines de module = 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^600000 + (-10 +i*0)*x^800000 + (1 +i*0)*x^1400000 + +(-60000 +i*0)*x^599999 + (-8E+06 +i*0)*x^799999 + (1.4E+06 +i*0)*x^1399999 + +zone limite de 'log-exp' 1.00025 +CPU thread 1 (of 2) uses CUDA device 1 +CPU thread 0 (of 2) uses CUDA device 0 +gpu 1 dimgrid 5469 dimblock 256 degrePoly 1400000 +gpu 1 dimgrid2 2735 start 700032 size 700032 +gpu 0 dimgrid 5469 dimblock 256 degrePoly 1400000 +gpu 0 dimgrid2 2735 start 0 size 700032 +gpu 0 iter : 1 Arret : 0.00527111 s/iter 71.308499 +gpu 0 iter : 2 Arret : 0.172644 s/iter 72.713414 +gpu 0 iter : 3 Arret : 0.69639 s/iter 72.958242 +gpu 0 iter : 4 Arret : 1.18582 s/iter 75.255529 +gpu 0 iter : 5 Arret : 0.29345 s/iter 76.866618 +gpu 0 iter : 6 Arret : 0.163076 s/iter 77.369587 +gpu 0 iter : 7 Arret : 1.88246 s/iter 78.558083 +gpu 0 iter : 8 Arret : 1.71023 s/iter 77.826546 +gpu 0 iter : 9 Arret : 1.23231 s/iter 77.642649 +gpu 0 iter : 10 Arret : 0.367931 s/iter 79.759527 +gpu 0 iter : 11 Arret : 1.0997 s/iter 78.755024 +gpu 0 iter : 12 Arret : 2.11197 s/iter 77.725889 +gpu 0 iter : 13 Arret : 0.848296 s/iter 76.267112 +gpu 0 iter : 14 Arret : 0.433295 s/iter 75.435820 +gpu 0 iter : 15 Arret : 0.817759 s/iter 74.683488 +gpu 0 iter : 16 Arret : 0.767209 s/iter 74.057568 +gpu 0 iter : 17 Arret : 0.573024 s/iter 73.720984 +gpu 0 iter : 18 Arret : 0.597274 s/iter 73.499266 +gpu 0 iter : 19 Arret : 0.303085 s/iter 72.741656 +gpu 0 iter : 20 Arret : 0.180774 s/iter 72.806213 +gpu 0 iter : 21 Arret : 0.0722903 s/iter 72.559828 +gpu 0 iter : 22 Arret : 0.146427 s/iter 72.512488 +gpu 0 iter : 23 Arret : 0.129512 s/iter 72.128992 +gpu 0 iter : 24 Arret : 0.0402274 s/iter 71.576335 +gpu 0 iter : 25 Arret : 0.0124264 s/iter 71.526353 +gpu 0 iter : 26 Arret : 0.00203683 s/iter 71.463273 +gpu 0 iter : 27 Arret : 0.000373803 s/iter 71.462289 +gpu 0 iter : 28 Arret : 7.43881E-07 s/iter 71.336304 +gpu 0 iter : 29 Arret : 9.02153E-09 s/iter 71.333249 +gpu 0 iter : 30 Arret : 1.20401E-10 s/iter 71.481701 +gpu 0 iter : 31 Arret : 1.60504E-12 s/iter 71.339739 +gpu 0 iter : 32 Arret : 2.14019E-14 s/iter 71.437524 +temps : 2371.12 seconde(s) +Nb iterations : 32 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.65661E-08 +Stabilite : 5.97875E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841469| 0.999997| 5.65794E-11 +i*-4.66756E-12| +| 2| 0.513623 +i* 0.858013| 0.999997|-2.15776E-11 +i*-2.98557E-11| +| 3| -0.52703 +i* -0.849843| 0.999997|-8.72191E-12 +i* 2.97079E-11| +| 4| 0.486439 +i* 0.873711| 0.999997| 5.60277E-11 +i* 4.36779E-11| +| 5| -0.500096 +i* -0.865967| 0.999997| 3.56147E-11 +i*-3.12713E-11| +| 6| 0.458776 +i* 0.888549| 0.999997|-1.89702E-11 +i* 4.08274E-12| +| 7| -0.472669 +i* -0.881237| 0.999997|-1.66496E-11 +i*-3.61498E-11| +| 8| 0.430661 +i* 0.902511| 0.999997|-1.60558E-11 +i*-1.29949E-11| +| 9| -0.444791 +i* -0.895631| 0.999997| 3.68259E-11 +i* 1.36002E-12| +| 10| 0.402136 +i* 0.915577| 0.999997| 6.5834E-12 +i* -1.3935E-11| +| 11| -0.416432 +i* -0.909164| 0.999997| 1.97816E-11 +i* 3.10848E-11| +| 12| 0.373171 +i* 0.927759| 0.999997|-2.17995E-11 +i*-2.96867E-12| +| 13| -0.387698 +i* -0.921783| 0.999997|-1.86324E-11 +i* -4.6545E-11| +| 14| 0.343875 +i* 0.939012| 0.999997| 3.84962E-11 +i* 2.59646E-11| +| 15| -0.358575 +i* -0.933498| 0.999997| 8.13599E-11 +i*-1.42233E-11| +| 16| 0.314233 +i* 0.949343| 0.999997| 3.86503E-11 +i* 2.08775E-11| +| 17| -0.329098 +i* -0.944293| 0.999997|-1.57903E-11 +i* 2.05052E-11| +| 18| 0.284281 +i* 0.958738| 0.999997| 2.51592E-11 +i* 2.09243E-11| +| 19| -0.299297 +i* -0.954157| 0.999997| 5.03608E-12 +i* 1.70503E-11| +| 20| 0.254048 +i* 0.967189| 0.999997|-2.81228E-11 +i*-1.66302E-11| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 0.999997 +600000 racines de module = 1 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140099: line 23: 12958 Segmentation fault (core dumped) ./template -r -i 900000 700000 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140099: line 24: 12962 Segmentation fault (core dumped) ./template -r -i 1000000 800000 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140099: line 25: 12964 Segmentation fault (core dumped) ./template -r -i 1500000 500000 diff --git a/Simulations/sparse_openmp/sparse_openmp_2GPU.sge b/Simulations/sparse_openmp/sparse_openmp_2GPU.sge new file mode 100644 index 0000000..769c2b7 --- /dev/null +++ b/Simulations/sparse_openmp/sparse_openmp_2GPU.sge @@ -0,0 +1,27 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=2 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -pe openmp 2 +#$ -V +#$ -cwd +#$ -N sparse_openmp_2GPU + +module load gcc/4.9.0 +module load cuda/7.0 +export OMP_NUM_THREADS=2 + +./template -r -i 60000 40000 +./template -r -i 150000 50000 +./template -r -i 250000 150000 +./template -r -i 350000 250000 +./template -r -i 500000 300000 +./template -r -i 600000 400000 +./template -r -i 700000 500000 +./template -r -i 800000 600000 +./template -r -i 900000 700000 +./template -r -i 1000000 800000 +./template -r -i 1500000 500000 + + diff --git a/Simulations/sparse_openmp/sparse_openmp_3GPU.o140098 b/Simulations/sparse_openmp/sparse_openmp_3GPU.o140098 new file mode 100644 index 0000000..2aea52b --- /dev/null +++ b/Simulations/sparse_openmp/sparse_openmp_3GPU.o140098 @@ -0,0 +1,602 @@ +REMAINING: 3 +Taking GPU #0 +Taking GPU #1 +Taking GPU #2 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^40000 + (-10 +i*0)*x^60000 + (1 +i*0)*x^100000 + +(-4000 +i*0)*x^39999 + (-600000 +i*0)*x^59999 + (100000 +i*0)*x^99999 + +zone limite de 'log-exp' 1.00356 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 0 (of 3) uses CUDA device 0 +CPU thread 1 (of 3) uses CUDA device 1 +gpu 0 dimgrid 391 dimblock 256 degrePoly 100000 +gpu 0 dimgrid2 131 start 0 size 33365 +gpu 1 dimgrid 391 dimblock 256 degrePoly 100000 +gpu 1 dimgrid2 131 start 33365 size 33365 +gpu 2 dimgrid 391 dimblock 256 degrePoly 100000 +gpu 2 dimgrid2 131 start 66730 size 33365 +gpu 0 iter : 1 Arret : 0.00638376 s/iter 0.326852 +gpu 0 iter : 2 Arret : 0.00780969 s/iter 0.399828 +gpu 0 iter : 3 Arret : 0.00239395 s/iter 0.326756 +gpu 0 iter : 4 Arret : 0.00316529 s/iter 0.326768 +gpu 0 iter : 5 Arret : 0.0038084 s/iter 0.326767 +gpu 0 iter : 6 Arret : 0.00482452 s/iter 0.326696 +gpu 0 iter : 7 Arret : 0.00928999 s/iter 0.326751 +gpu 0 iter : 8 Arret : 0.0101647 s/iter 0.326710 +gpu 0 iter : 9 Arret : 0.0111077 s/iter 0.326857 +gpu 0 iter : 10 Arret : 0.00655022 s/iter 0.326801 +gpu 0 iter : 11 Arret : 0.00316276 s/iter 0.326810 +gpu 0 iter : 12 Arret : 0.000516233 s/iter 0.326609 +gpu 0 iter : 13 Arret : 0.00040416 s/iter 0.326572 +gpu 0 iter : 14 Arret : 0.000177079 s/iter 0.326480 +gpu 0 iter : 15 Arret : 8.53367E-05 s/iter 0.326486 +gpu 0 iter : 16 Arret : 4.34291E-05 s/iter 0.326528 +gpu 0 iter : 17 Arret : 2.94612E-06 s/iter 0.326471 +gpu 0 iter : 18 Arret : 4.24038E-08 s/iter 0.326469 +gpu 0 iter : 19 Arret : 6.31898E-10 s/iter 0.326431 +gpu 0 iter : 20 Arret : 9.41384E-12 s/iter 0.326448 +gpu 0 iter : 21 Arret : 1.40182E-13 s/iter 0.326484 +temps : 8.00955 seconde(s) +Nb iterations : 21 +Nb de depassements de capacite exponentielle : 0 +Precision : 8.10777E-09 +Stabilite : 1.57015E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.54036 +i* 0.841503| 1.00006|-5.00602E-11 +i* 9.0853E-12| +| 2| -0.113164 +i* 0.993538| 0.999962|-4.34919E-12 +i* 9.60242E-13| +| 3| -0.226885 +i* -0.973981| 1.00006|-5.81993E-10 +i*-4.18547E-10| +| 4| -0.715763 +i* 0.698289| 0.999962| 9.11271E-13 +i* 2.47219E-12| +| 5| 0.439922 +i* -0.897993| 0.999962|-3.49498E-13 +i* 1.66432E-12| +| 6| -0.996122 +i* 0.0886386| 1.00006| 4.72785E-10 +i* 4.13616E-11| +| 7| 0.908546 +i* -0.417692| 0.999962| 4.78506E-13 +i* 1.54377E-13| +| 8| -0.827813 +i* -0.560935| 0.999962| 9.76996E-13 +i*-2.04309E-12| +| 9| 0.968129 +i* 0.250682| 1.00006|-2.31715E-10 +i* 1.34848E-10| +| 10| -0.286842 +i* -0.958038| 1.00006|-5.93554E-10 +i*-2.45345E-10| +| 11| 0.591653 +i* 0.806145| 0.999962|-9.87654E-13 +i*-3.03635E-12| +| 12| -0.0511836 +i* 0.998651| 0.999962|-2.22622E-12 +i*-3.69013E-14| +| 13| -0.67097 +i* 0.741432| 0.999962|-8.03801E-14 +i*-1.68204E-12| +| 14| 0.383249 +i* -0.923603| 0.999962|-1.29119E-12 +i*-1.37426E-12| +| 15| -0.988685 +i* 0.15039| 1.00006|-1.61051E-10 +i* 7.18515E-11| +| 16| 0.880824 +i* -0.473363| 0.999962|-4.03455E-13 +i* 2.85139E-12| +| 17| -0.861082 +i* -0.508391| 0.999962| 1.02962E-12 +i*-4.51911E-12| +| 18| 0.98184 +i* 0.190015| 1.00006| -8.9615E-10 +i* 1.84549E-11| +| 19| -0.345842 +i* -0.938354| 1.00006| 1.38421E-10 +i*-2.31696E-10| +| 20| 0.640621 +i* 0.767807| 0.999962|-6.98774E-13 +i* 1.13798E-12| ++---+----------------------------+------------+----------------------------+ +40000 racines de module = 1.00006 +60000 racines de module = 0.999962 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^50000 + (-10 +i*0)*x^150000 + (1 +i*0)*x^200000 + +(-5000 +i*0)*x^49999 + (-1.5E+06 +i*0)*x^149999 + (200000 +i*0)*x^199999 + +zone limite de 'log-exp' 1.00178 +CPU thread 1 (of 3) uses CUDA device 1 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 0 (of 3) uses CUDA device 0 +gpu 1 dimgrid 782 dimblock 256 degrePoly 200000 +gpu 1 dimgrid2 261 start 66730 size 66730 +gpu 0 dimgrid 782 dimblock 256 degrePoly 200000 +gpu 0 dimgrid2 261 start 0 size 66730 +gpu 2 dimgrid 782 dimblock 256 degrePoly 200000 +gpu 2 dimgrid2 261 start 133460 size 66730 +gpu 0 iter : 1 Arret : 0.000229669 s/iter 1.096870 +gpu 0 iter : 2 Arret : 0.00021193 s/iter 1.097026 +gpu 0 iter : 3 Arret : 0.000280313 s/iter 1.096954 +gpu 0 iter : 4 Arret : 0.000636926 s/iter 1.096899 +gpu 0 iter : 5 Arret : 0.00105388 s/iter 1.096829 +gpu 0 iter : 6 Arret : 0.0149052 s/iter 1.096638 +gpu 0 iter : 7 Arret : 0.0123684 s/iter 1.096797 +gpu 0 iter : 8 Arret : 0.0421817 s/iter 1.098043 +gpu 0 iter : 9 Arret : 0.0899445 s/iter 1.098654 +gpu 0 iter : 10 Arret : 0.204522 s/iter 1.186313 +gpu 0 iter : 11 Arret : 2.97201 s/iter 1.218384 +gpu 0 iter : 12 Arret : 0.648253 s/iter 1.218710 +gpu 0 iter : 13 Arret : 1.88772 s/iter 1.241862 +gpu 0 iter : 14 Arret : 1.33785 s/iter 1.208066 +gpu 0 iter : 15 Arret : 1.70034 s/iter 1.098449 +gpu 0 iter : 16 Arret : 1.16245 s/iter 1.197714 +gpu 0 iter : 17 Arret : 2.06315 s/iter 1.228122 +gpu 0 iter : 18 Arret : 1.22433 s/iter 1.198366 +gpu 0 iter : 19 Arret : 0.795342 s/iter 1.228114 +gpu 0 iter : 20 Arret : 0.622909 s/iter 1.095861 +gpu 0 iter : 21 Arret : 1.12395 s/iter 1.224956 +gpu 0 iter : 22 Arret : 1.99041 s/iter 1.227156 +gpu 0 iter : 23 Arret : 1.15739 s/iter 1.209773 +gpu 0 iter : 24 Arret : 0.455675 s/iter 1.226888 +gpu 0 iter : 25 Arret : 0.680625 s/iter 1.097847 +gpu 0 iter : 26 Arret : 0.577238 s/iter 1.095693 +gpu 0 iter : 27 Arret : 0.0687706 s/iter 1.095867 +gpu 0 iter : 28 Arret : 0.0224681 s/iter 1.096036 +gpu 0 iter : 29 Arret : 0.002804 s/iter 1.095993 +gpu 0 iter : 30 Arret : 6.05493E-06 s/iter 1.095754 +gpu 0 iter : 31 Arret : 3.11042E-10 s/iter 1.095829 +gpu 0 iter : 32 Arret : 3.1096E-14 s/iter 1.096050 +temps : 37.8394 seconde(s) +Nb iterations : 32 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.30431E-05 +Stabilite : 3.1096E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540303 +i* 0.841453| 0.999985| 1.08703E-11 +i*-2.49217E-12| +| 2| -0.837195 +i* 0.546877| 0.999985| -5.4492E-12 +i* 1.09163E-12| +| 3| -0.553418 +i* -0.832885| 0.999985| -1.9722E-12 +i*-7.40397E-12| +| 4| 0.828599 +i* -0.559925| 1.00005|-7.54521E-09 +i* 1.47059E-08| +| 5| -0.8197 +i* 0.572767| 0.999985|-4.21663E-13 +i* -2.8616E-12| +| 6| -0.57917 +i* -0.815188| 0.999985|-5.13034E-12 +i*-1.52645E-12| +| 7| 0.810626 +i* -0.585537| 0.999985| 8.64808E-12 +i* 7.46794E-12| +| 8| 0.59177 +i* 0.806164| 1.00005|-6.74238E-09 +i* 4.40492E-09| +| 9| -0.801529 +i* 0.598033| 1.00005| 7.19885E-09 +i* 8.43319E-09| +| 10| -0.604356 +i* -0.796695| 0.999985|-1.64091E-13 +i* 1.59084E-12| +| 11| 0.791937 +i* -0.610578| 0.999985| 6.0707E-13 +i* 1.52922E-12| +| 12| 0.616763 +i* 0.78713| 0.999985|-4.48042E-12 +i* -2.6295E-12| +| 13| -0.782301 +i* 0.622877| 0.999985|-2.15827E-12 +i*-6.27114E-12| +| 14| -0.628894 +i* -0.777551| 1.00005| 2.29838E-09 +i* 1.59417E-08| +| 15| 0.772474 +i* -0.635023| 0.999985| 1.54783E-11 +i*-1.81338E-12| +| 16| 0.641054 +i* 0.767476| 0.999985|-3.47633E-12 +i* 1.20617E-11| +| 17| -0.762458 +i* 0.647014| 0.999985|-7.74447E-12 +i* 7.566E-12| +| 18| -0.652967 +i* -0.757366| 0.999985|-6.31406E-12 +i* 8.49495E-12| +| 19| 0.752302 +i* -0.658888| 1.00005| 3.99107E-09 +i* 1.02117E-08| +| 20| 0.66472 +i* 0.747072| 0.999985|-1.93379E-12 +i*-1.29726E-11| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 0.999985 +50000 racines de module = 1.00005 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^150000 + (-10 +i*0)*x^250000 + (1 +i*0)*x^400000 + +(-15000 +i*0)*x^149999 + (-2.5E+06 +i*0)*x^249999 + (400000 +i*0)*x^399999 + +zone limite de 'log-exp' 1.00089 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 1 (of 3) uses CUDA device 1 +CPU thread 0 (of 3) uses CUDA device 0 +gpu 1 dimgrid 1563 dimblock 256 degrePoly 400000 +gpu 1 dimgrid2 521 start 133376 size 133376 +gpu 0 dimgrid 1563 dimblock 256 degrePoly 400000 +gpu 0 dimgrid2 521 start 0 size 133376 +gpu 2 dimgrid 1563 dimblock 256 degrePoly 400000 +gpu 2 dimgrid2 521 start 266752 size 133376 +gpu 0 iter : 1 Arret : 0.00053336 s/iter 4.015433 +gpu 0 iter : 2 Arret : 0.00165478 s/iter 4.015274 +gpu 0 iter : 3 Arret : 0.00149659 s/iter 4.015225 +gpu 0 iter : 4 Arret : 0.00476307 s/iter 4.014142 +gpu 0 iter : 5 Arret : 0.0270497 s/iter 4.020618 +gpu 0 iter : 6 Arret : 0.0269319 s/iter 4.340327 +gpu 0 iter : 7 Arret : 0.0180523 s/iter 4.298465 +gpu 0 iter : 8 Arret : 0.0146534 s/iter 4.308899 +gpu 0 iter : 9 Arret : 0.00619736 s/iter 4.011731 +gpu 0 iter : 10 Arret : 0.00299981 s/iter 4.010855 +gpu 0 iter : 11 Arret : 0.00111873 s/iter 4.009952 +gpu 0 iter : 12 Arret : 0.000851809 s/iter 4.011669 +gpu 0 iter : 13 Arret : 0.000757841 s/iter 4.011889 +gpu 0 iter : 14 Arret : 0.000509989 s/iter 4.011347 +gpu 0 iter : 15 Arret : 0.000667055 s/iter 4.011093 +gpu 0 iter : 16 Arret : 2.71105E-05 s/iter 4.000315 +gpu 0 iter : 17 Arret : 8.00906E-06 s/iter 3.991624 +gpu 0 iter : 18 Arret : 1.99192E-07 s/iter 3.991746 +gpu 0 iter : 19 Arret : 3.11567E-09 s/iter 3.991734 +gpu 0 iter : 20 Arret : 4.89263E-11 s/iter 3.991803 +gpu 0 iter : 21 Arret : 7.68172E-13 s/iter 3.991754 +temps : 86.1208 seconde(s) +Nb iterations : 21 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.49185E-08 +Stabilite : 7.68172E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540334 +i* 0.84144| 0.999991| 6.97609E-12 +i* 5.61207E-12| +| 2| -0.998329 +i* 0.057622| 0.999991| 4.43912E-12 +i* 1.27665E-12| +| 3| 0.43989 +i* -0.898041| 0.999991|-2.08855E-12 +i*-1.75276E-12| +| 4| -0.996033 +i* 0.0888768| 0.999991|-3.15592E-12 +i* 1.17456E-12| +| 5| 0.411533 +i* -0.911385| 0.999991|-2.45048E-12 +i* 4.6238E-12| +| 6| 0.59196 +i* 0.805956| 0.999991| 5.24358E-13 +i*-8.53073E-12| +| 7| -0.992759 +i* 0.120044| 0.999991| 2.58804E-12 +i* 2.47274E-12| +| 8| 0.382796 +i* -0.923823| 0.999991| 1.11042E-11 +i*-9.27687E-12| +| 9| 0.616925 +i* 0.78701| 0.999991| 4.27514E-12 +i*-1.13966E-11| +| 10| -0.98851 +i* 0.151094| 0.999991|-1.29017E-11 +i*-4.43427E-12| +| 11| 0.35366 +i* -0.935364| 0.999991|-1.92664E-11 +i* 1.19958E-11| +| 12| 0.641283 +i* 0.767292| 0.999991| 1.73468E-11 +i*-3.74729E-12| +| 13| -0.98329 +i* 0.181995| 0.999991|-6.62759E-12 +i*-5.46796E-12| +| 14| 0.324176 +i* -0.945987| 0.999991| 1.53594E-11 +i*-1.57324E-12| +| 15| 0.665012 +i* 0.746821| 0.999991| 5.27178E-12 +i*-4.27913E-12| +| 16| -0.977104 +i* 0.212717| 0.999991|-1.01148E-11 +i* 2.41479E-12| +| 17| 0.294374 +i* -0.955681| 0.999991| -1.2063E-11 +i* 1.32238E-11| +| 18| 0.688087 +i* 0.725616| 0.999991| 6.67011E-12 +i* 1.57173E-11| +| 19| -0.969965 +i* 0.243206| 0.999991| 6.88072E-12 +i* 3.20268E-13| +| 20| 0.264283 +i* -0.964436| 0.999991| 2.5573E-11 +i*-6.45539E-12| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 0.999991 +150000 racines de module = 1.00002 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^250000 + (-10 +i*0)*x^350000 + (1 +i*0)*x^600000 + +(-25000 +i*0)*x^249999 + (-3.5E+06 +i*0)*x^349999 + (600000 +i*0)*x^599999 + +zone limite de 'log-exp' 1.00059 +CPU thread 0 (of 3) uses CUDA device 0 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 1 (of 3) uses CUDA device 1 +gpu 1 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 1 dimgrid2 782 start 200021 size 200021 +gpu 2 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 2 dimgrid2 782 start 400042 size 200021 +gpu 0 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 0 dimgrid2 782 start 0 size 200021 +gpu 0 iter : 1 Arret : 0.00574299 s/iter 9.047838 +gpu 0 iter : 2 Arret : 0.00960381 s/iter 9.043639 +gpu 0 iter : 3 Arret : 0.130996 s/iter 9.471525 +gpu 0 iter : 4 Arret : 0.142079 s/iter 9.198199 +gpu 0 iter : 5 Arret : 0.0868349 s/iter 9.506055 +gpu 0 iter : 6 Arret : 0.0882721 s/iter 9.145065 +gpu 0 iter : 7 Arret : 0.114689 s/iter 9.172845 +gpu 0 iter : 8 Arret : 0.108656 s/iter 9.193791 +gpu 0 iter : 9 Arret : 0.0356399 s/iter 9.170752 +gpu 0 iter : 10 Arret : 0.0134072 s/iter 9.594206 +gpu 0 iter : 11 Arret : 0.00832588 s/iter 9.158565 +gpu 0 iter : 12 Arret : 0.00682235 s/iter 9.135471 +gpu 0 iter : 13 Arret : 0.00415856 s/iter 9.143664 +gpu 0 iter : 14 Arret : 0.00311193 s/iter 9.065571 +gpu 0 iter : 15 Arret : 0.000707097 s/iter 9.044745 +gpu 0 iter : 16 Arret : 0.000778409 s/iter 9.042087 +gpu 0 iter : 17 Arret : 0.000667704 s/iter 9.043931 +gpu 0 iter : 18 Arret : 9.33212E-06 s/iter 9.043636 +gpu 0 iter : 19 Arret : 7.71387E-08 s/iter 9.041264 +gpu 0 iter : 20 Arret : 1.09443E-09 s/iter 9.041736 +gpu 0 iter : 21 Arret : 1.56107E-11 s/iter 9.047621 +gpu 0 iter : 22 Arret : 2.22664E-13 s/iter 9.046678 +temps : 202.419 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 7.53549E-08 +Stabilite : 2.22043E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540302 +i* 0.841463| 0.999993| 8.34199E-12 +i* -1.9051E-11| +| 2| -0.553438 +i* -0.832883| 0.999993|-2.10654E-12 +i*-2.55273E-11| +| 3| -0.579282 +i* -0.815119| 0.999993| 1.33613E-11 +i*-1.98701E-11| +| 4| 0.592014 +i* 0.805919| 0.999993|-3.98037E-12 +i* 9.55808E-12| +| 5| -0.604557 +i* -0.796554| 0.999993|-2.82974E-12 +i* 9.99473E-12| +| 6| 0.61698 +i* 0.78697| 0.999993| 9.01823E-12 +i*-5.69156E-12| +| 7| -0.629237 +i* -0.777205| 0.999993|-2.92122E-12 +i*-4.85867E-12| +| 8| 0.641354 +i* 0.767237| 0.999993|-1.64209E-11 +i* 1.12904E-12| +| 9| -0.653299 +i* -0.757092| 0.999993|-8.22453E-13 +i* 2.82818E-12| +| 10| 0.665096 +i* 0.746749| 0.999993| -1.2145E-11 +i* 1.89129E-11| +| 11| -0.676717 +i* -0.736234| 0.999993|-1.26079E-11 +i*-1.25073E-11| +| 12| 0.688185 +i* 0.725526| 0.999993|-4.43978E-12 +i*-2.31382E-11| +| 13| -0.699466 +i* -0.714679| 1.00001| 3.92343E-10 +i*-3.02623E-09| +| 14| 0.710597 +i* 0.70359| 0.999993| 1.28564E-11 +i* 1.56626E-11| +| 15| -0.721517 +i* -0.69241| 1.00001| 2.88447E-09 +i* 3.69506E-09| +| 16| 0.73231 +i* 0.680962| 0.999993|-5.73186E-12 +i* 1.14335E-11| +| 17| -0.742904 +i* -0.669389| 0.999993|-7.78222E-12 +i* 1.50098E-11| +| 18| 0.7533 +i* 0.657691| 1.00001| 1.64587E-09 +i*-3.03669E-09| +| 19| -0.76354 +i* -0.64575| 0.999993| 2.24043E-11 +i*-1.30496E-12| +| 20| 0.773539 +i* 0.633763| 1.00001| 5.39271E-09 +i*-2.77636E-09| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 0.999993 +250000 racines de module = 1.00001 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^300000 + (-10 +i*0)*x^500000 + (1 +i*0)*x^800000 + +(-30000 +i*0)*x^299999 + (-5E+06 +i*0)*x^499999 + (800000 +i*0)*x^799999 + +zone limite de 'log-exp' 1.00044 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 0 (of 3) uses CUDA device 0 +CPU thread 1 (of 3) uses CUDA device 1 +gpu 1 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 1 dimgrid2 1042 start 266666 size 266666 +gpu 0 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 0 dimgrid2 1042 start 0 size 266666 +gpu 2 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 2 dimgrid2 1042 start 533332 size 266666 +gpu 0 iter : 1 Arret : 0.000985945 s/iter 15.851621 +gpu 0 iter : 2 Arret : 0.00155936 s/iter 15.788402 +gpu 0 iter : 3 Arret : 0.0129473 s/iter 15.851181 +gpu 0 iter : 4 Arret : 0.0558872 s/iter 16.300649 +gpu 0 iter : 5 Arret : 0.19954 s/iter 15.808251 +gpu 0 iter : 6 Arret : 0.377937 s/iter 15.879884 +gpu 0 iter : 7 Arret : 0.514814 s/iter 16.303367 +gpu 0 iter : 8 Arret : 0.338633 s/iter 15.914224 +gpu 0 iter : 9 Arret : 0.206607 s/iter 16.151496 +gpu 0 iter : 10 Arret : 0.138277 s/iter 16.399153 +gpu 0 iter : 11 Arret : 0.113953 s/iter 15.857365 +gpu 0 iter : 12 Arret : 0.0627751 s/iter 15.843953 +gpu 0 iter : 13 Arret : 0.0358213 s/iter 15.848470 +gpu 0 iter : 14 Arret : 0.0221421 s/iter 15.846627 +gpu 0 iter : 15 Arret : 0.00243723 s/iter 15.842171 +gpu 0 iter : 16 Arret : 0.000254217 s/iter 15.843580 +gpu 0 iter : 17 Arret : 0.000130358 s/iter 15.845033 +gpu 0 iter : 18 Arret : 0.00018532 s/iter 15.849105 +gpu 0 iter : 19 Arret : 1.35363E-05 s/iter 15.847663 +gpu 0 iter : 20 Arret : 2.14908E-09 s/iter 15.847042 +gpu 0 iter : 21 Arret : 4.62703E-12 s/iter 15.807436 +gpu 0 iter : 22 Arret : 9.97217E-15 s/iter 15.847751 +temps : 351.42 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 12.9528 +Stabilite : 7.80251E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540305 +i* 0.841464| 0.999995|-5.33817E-12 +i*-1.81878E-11| +| 2| 0.592014 +i* 0.805922| 0.999995| 2.33948E-11 +i*-2.13005E-11| +| 3| 0.617007 +i* 0.786952| 0.999995| 4.23442E-11 +i* -6.2147E-12| +| 4| 0.641392 +i* 0.767207| 0.999995|-4.99742E-11 +i* 1.43873E-11| +| 5| 0.665146 +i* 0.746707| 0.999995| 2.02977E-11 +i* 7.48579E-12| +| 6| 0.688245 +i* 0.725472| 0.999995|-1.73153E-11 +i* -1.2656E-11| +| 7| 0.710667 +i* 0.703522| 0.999995| 3.69782E-12 +i* 2.3081E-12| +| 8| 0.732388 +i* 0.68088| 0.999995| 9.45355E-12 +i* 2.09024E-11| +| 9| 0.753381 +i* 0.657577| 0.999995| 1.7531E-11 +i*-4.02243E-11| +| 10| 0.77364 +i* 0.633618| 0.999995|-1.72307E-11 +i* 1.22723E-11| +| 11| 0.793138 +i* 0.609034| 0.999995| 3.89222E-12 +i* 2.21356E-11| +| 12| 0.811855 +i* 0.583851| 0.999995|-1.28337E-11 +i*-5.47207E-12| +| 13| 0.829772 +i* 0.558094| 0.999995|-1.63114E-11 +i*-1.64246E-12| +| 14| 0.846873 +i* 0.531786| 0.999995|-3.30451E-11 +i*-8.10676E-12| +| 15| 0.86314 +i* 0.504956| 0.999995|-4.00413E-12 +i* 3.04823E-11| +| 16| 0.878557 +i* 0.477628| 0.999995|-2.16493E-12 +i* 1.10533E-11| +| 17| 0.893104 +i* 0.449841| 0.999995|-1.48552E-11 +i* 1.06063E-11| +| 18| 0.906777 +i* 0.4216| 0.999995|-1.38745E-11 +i* 5.33384E-12| +| 19| 0.919557 +i* 0.392944| 0.999995| 4.13796E-11 +i*-2.48189E-11| +| 20| 0.931433 +i* 0.363901| 0.999995| 4.93219E-11 +i*-2.82651E-11| ++---+----------------------------+------------+----------------------------+ +499998 racines de module = 0.999995 +300000 racines de module = 1.00001 + 2 racines de module = 1 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^400000 + (-10 +i*0)*x^600000 + (1 +i*0)*x^1000000 + +(-40000 +i*0)*x^399999 + (-6E+06 +i*0)*x^599999 + (1E+06 +i*0)*x^999999 + +zone limite de 'log-exp' 1.00035 +CPU thread 1 (of 3) uses CUDA device 1 +CPU thread 0 (of 3) uses CUDA device 0 +CPU thread 2 (of 3) uses CUDA device 2 +gpu 2 dimgrid 3907 dimblock 256 degrePoly 1000000 +gpu 2 dimgrid2 1303 start 666794 size 333397 +gpu 1 dimgrid 3907 dimblock 256 degrePoly 1000000 +gpu 1 dimgrid2 1303 start 333397 size 333397 +gpu 0 dimgrid 3907 dimblock 256 degrePoly 1000000 +gpu 0 dimgrid2 1303 start 0 size 333397 +gpu 0 iter : 1 Arret : 0.0011104 s/iter 24.284964 +gpu 0 iter : 2 Arret : 0.00309979 s/iter 24.283383 +gpu 0 iter : 3 Arret : 0.247623 s/iter 24.789931 +gpu 0 iter : 4 Arret : 0.461817 s/iter 24.581195 +gpu 0 iter : 5 Arret : 0.334336 s/iter 25.044367 +gpu 0 iter : 6 Arret : 0.274486 s/iter 25.665034 +gpu 0 iter : 7 Arret : 0.159668 s/iter 26.197375 +gpu 0 iter : 8 Arret : 0.0519691 s/iter 25.694996 +gpu 0 iter : 9 Arret : 0.0269291 s/iter 25.673851 +gpu 0 iter : 10 Arret : 0.0602316 s/iter 25.604792 +gpu 0 iter : 11 Arret : 0.0619642 s/iter 24.773954 +gpu 0 iter : 12 Arret : 0.0234 s/iter 24.787706 +gpu 0 iter : 13 Arret : 0.0244077 s/iter 24.353884 +gpu 0 iter : 14 Arret : 0.00963063 s/iter 24.344876 +gpu 0 iter : 15 Arret : 0.00340716 s/iter 24.345219 +gpu 0 iter : 16 Arret : 0.000234823 s/iter 24.297435 +gpu 0 iter : 17 Arret : 0.000256334 s/iter 24.352140 +gpu 0 iter : 18 Arret : 0.000224052 s/iter 24.290971 +gpu 0 iter : 19 Arret : 0.000781478 s/iter 24.296445 +gpu 0 iter : 20 Arret : 0.000194356 s/iter 24.291281 +gpu 0 iter : 21 Arret : 2.40806E-07 s/iter 24.291827 +gpu 0 iter : 22 Arret : 3.31687E-09 s/iter 24.291690 +gpu 0 iter : 23 Arret : 4.67724E-11 s/iter 24.290907 +gpu 0 iter : 24 Arret : 6.59569E-13 s/iter 24.293931 +temps : 598.968 seconde(s) +Nb iterations : 24 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.52682E-07 +Stabilite : 6.59569E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841468| 0.999996| 5.07216E-12 +i* 6.41236E-12| +| 2| 0.529701 +i* 0.84818| 0.999996|-4.61853E-13 +i*-4.17888E-12| +| 3| 0.524361 +i* 0.851491| 0.999996|-2.47296E-11 +i* 1.78327E-11| +| 4| 0.519015 +i* 0.854772| 1.00001| 2.38413E-09 +i*-5.89917E-09| +| 5| 0.513629 +i* 0.858008| 0.999996| 2.32483E-11 +i* 6.70747E-12| +| 6| 0.508237 +i* 0.861213| 0.999996|-1.34339E-11 +i* 9.87854E-12| +| 7| 0.502825 +i* 0.864384| 0.999996|-3.18459E-11 +i* 7.64744E-12| +| 8| 0.497384 +i* 0.867526| 0.999996| 2.97429E-11 +i*-6.06626E-13| +| 9| 0.491942 +i* 0.870624| 0.999996| -1.9825E-11 +i*-1.52329E-11| +| 10| 0.486452 +i* 0.873703| 0.999996| 3.0312E-11 +i* 1.02214E-11| +| 11| 0.480962 +i* 0.876737| 0.999996|-3.09397E-11 +i*-1.68578E-11| +| 12| 0.475453 +i* 0.879736| 0.999996| 3.09861E-11 +i* 4.093E-12| +| 13| 0.469917 +i* 0.882706| 0.999996|-1.29106E-11 +i*-2.31489E-11| +| 14| 0.46438 +i* 0.885632| 0.999996| 1.33844E-11 +i*-1.06731E-12| +| 15| 0.458797 +i* 0.888537| 0.999996| 2.78862E-11 +i* 1.10441E-11| +| 16| 0.453214 +i* 0.891397| 0.999996| 2.45506E-11 +i* 3.1726E-11| +| 17| 0.447614 +i* 0.894223| 0.999996|-1.08491E-12 +i*-2.12277E-11| +| 18| 0.441986 +i* 0.897017| 0.999996| 2.72476E-11 +i* 3.22485E-11| +| 19| 0.436355 +i* 0.899781| 1.00001| 4.84598E-09 +i*-1.12092E-09| +| 20| 0.430689 +i* 0.902496| 0.999996|-1.25435E-11 +i* 3.86925E-13| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 0.999996 +400000 racines de module = 1.00001 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^500000 + (-10 +i*0)*x^700000 + (1 +i*0)*x^1200000 + +(-50000 +i*0)*x^499999 + (-7E+06 +i*0)*x^699999 + (1.2E+06 +i*0)*x^1199999 + +zone limite de 'log-exp' 1.0003 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 0 (of 3) uses CUDA device 0 +CPU thread 1 (of 3) uses CUDA device 1 +gpu 0 dimgrid 4688 dimblock 256 degrePoly 1200000 +gpu 0 dimgrid2 1563 start 0 size 400042 +gpu 1 dimgrid 4688 dimblock 256 degrePoly 1200000 +gpu 1 dimgrid2 1563 start 400042 size 400042 +gpu 2 dimgrid 4688 dimblock 256 degrePoly 1200000 +gpu 2 dimgrid2 1563 start 800084 size 400042 +gpu 0 iter : 1 Arret : 0.0129118 s/iter 35.194295 +gpu 0 iter : 2 Arret : 1.14226 s/iter 37.357952 +gpu 0 iter : 3 Arret : 1.41831 s/iter 37.472613 +gpu 0 iter : 4 Arret : 1.98712 s/iter 37.475866 +gpu 0 iter : 5 Arret : 0.777118 s/iter 37.323598 +gpu 0 iter : 6 Arret : 0.414132 s/iter 38.133114 +gpu 0 iter : 7 Arret : 0.596053 s/iter 38.249814 +gpu 0 iter : 8 Arret : 0.923957 s/iter 38.214227 +gpu 0 iter : 9 Arret : 1.37764 s/iter 38.802357 +gpu 0 iter : 10 Arret : 3.75882 s/iter 38.537349 +gpu 0 iter : 11 Arret : 3.50583 s/iter 39.060169 +gpu 0 iter : 12 Arret : 3.46154 s/iter 38.314523 +gpu 0 iter : 13 Arret : 1.44838 s/iter 38.304672 +gpu 0 iter : 14 Arret : 2.97866 s/iter 38.101085 +gpu 0 iter : 15 Arret : 1.47363 s/iter 37.961455 +gpu 0 iter : 16 Arret : 3.02916 s/iter 37.963549 +gpu 0 iter : 17 Arret : 3.44273 s/iter 37.562647 +gpu 0 iter : 18 Arret : 9.75818 s/iter 37.462847 +gpu 0 iter : 19 Arret : 3.55089 s/iter 37.388809 +gpu 0 iter : 20 Arret : 1.23127 s/iter 37.253955 +gpu 0 iter : 21 Arret : 2.15757 s/iter 37.181593 +gpu 0 iter : 22 Arret : 1.41689 s/iter 37.239248 +gpu 0 iter : 23 Arret : 2.71181 s/iter 37.183043 +gpu 0 iter : 24 Arret : 1.74358 s/iter 37.093614 +gpu 0 iter : 25 Arret : 1.20275 s/iter 37.190846 +gpu 0 iter : 26 Arret : 4.12739 s/iter 37.151827 +gpu 0 iter : 27 Arret : 0.963355 s/iter 37.085124 +gpu 0 iter : 28 Arret : 0.780804 s/iter 37.089879 +gpu 0 iter : 29 Arret : 1.04543 s/iter 37.116299 +gpu 0 iter : 30 Arret : 0.861461 s/iter 36.766134 +gpu 0 iter : 31 Arret : 0.882203 s/iter 36.884355 +gpu 0 iter : 32 Arret : 1.2718 s/iter 36.769843 +gpu 0 iter : 33 Arret : 2.35224 s/iter 36.354615 +gpu 0 iter : 34 Arret : 0.727156 s/iter 36.255055 +gpu 0 iter : 35 Arret : 1.44624 s/iter 36.206611 +gpu 0 iter : 36 Arret : 0.991076 s/iter 36.090368 +gpu 0 iter : 37 Arret : 1.04914 s/iter 35.800864 +gpu 0 iter : 38 Arret : 1.8416 s/iter 35.547956 +gpu 0 iter : 39 Arret : 73.3357 s/iter 35.569370 +gpu 0 iter : 40 Arret : 1.27526 s/iter 35.589183 +gpu 0 iter : 41 Arret : 0.664432 s/iter 35.572552 +gpu 0 iter : 42 Arret : 2.02267 s/iter 35.596663 +gpu 0 iter : 43 Arret : 3.3247 s/iter 35.518933 +gpu 0 iter : 44 Arret : 0.753208 s/iter 35.558919 +gpu 0 iter : 45 Arret : 0.406779 s/iter 35.517839 +gpu 0 iter : 46 Arret : 0.190344 s/iter 35.499532 +gpu 0 iter : 47 Arret : 0.053701 s/iter 35.454469 +gpu 0 iter : 48 Arret : 0.0180092 s/iter 35.423771 +gpu 0 iter : 49 Arret : 0.0103853 s/iter 35.469037 +gpu 0 iter : 50 Arret : 0.00392672 s/iter 35.295894 +gpu 0 iter : 51 Arret : 0.00130348 s/iter 35.285682 +gpu 0 iter : 52 Arret : 5.94285E-05 s/iter 35.279833 +gpu 0 iter : 53 Arret : 3.66884E-07 s/iter 35.262013 +gpu 0 iter : 54 Arret : 1.24856E-09 s/iter 35.260448 +gpu 0 iter : 55 Arret : 1.23865E-11 s/iter 35.262868 +gpu 0 iter : 56 Arret : 1.69469E-13 s/iter 35.261163 +temps : 2056.31 seconde(s) +Nb iterations : 56 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.48302E-06 +Stabilite : 1.69469E-13 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.54031 +i* 0.841472| 1| 1.4588E-09 +i* 4.51768E-09| +| 2| 0.513633 +i* 0.858015| 1| 1.54651E-09 +i*-2.27023E-10| +| 3| 0.486464 +i* 0.873697| 0.999997| 5.22282E-12 +i* 2.0872E-11| +| 4| 0.458789 +i* 0.888542| 0.999997| 2.48135E-13 +i*-2.88822E-11| +| 5| 0.430701 +i* 0.902491| 0.999997| 1.55062E-11 +i*-3.45463E-12| +| 6| 0.402126 +i* 0.915589| 1| 2.50282E-09 +i*-6.10471E-09| +| 7| 0.3732 +i* 0.927747| 0.999997|-1.54374E-11 +i*-2.76083E-11| +| 8| 0.3439 +i* 0.939003| 0.999997|-1.12714E-11 +i* 1.5453E-11| +| 9| 0.314261 +i* 0.949333| 0.999997| 1.93628E-11 +i* 2.50909E-11| +| 10| 0.284313 +i* 0.958728| 0.999997| 2.69426E-11 +i* 2.77974E-11| +| 11| 0.254084 +i* 0.967179| 0.999997| 1.5277E-11 +i* 4.73027E-12| +| 12| 0.223605 +i* 0.974676| 0.999997| -8.1017E-11 +i*-3.77299E-11| +| 13| 0.192909 +i* 0.981221| 1|-1.95729E-09 +i* 4.84549E-09| +| 14| 0.162018 +i* 0.986792| 1| 1.18712E-08 +i* 5.95858E-09| +| 15| 0.128886 +i* 0.991664| 1|-2.36358E-09 +i* 3.79427E-11| +| 16| 0.099787 +i* 0.995013| 1|-7.20324E-09 +i* 2.86361E-09| +| 17| 0.0685404 +i* 0.997645| 0.999997| 1.01124E-11 +i* 3.1089E-12| +| 18| 0.0371504 +i* 0.999314| 1|-3.18728E-10 +i*-2.97119E-09| +| 19| 0.00578048 +i* 0.99998| 0.999997| 3.46787E-11 +i* 1.94857E-13| +| 20| -0.0256056 +i* 0.999669| 0.999997| 2.01068E-11 +i*-1.22213E-12| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +700000 racines de module = 0.999997 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^600000 + (-10 +i*0)*x^800000 + (1 +i*0)*x^1400000 + +(-60000 +i*0)*x^599999 + (-8E+06 +i*0)*x^799999 + (1.4E+06 +i*0)*x^1399999 + +zone limite de 'log-exp' 1.00025 +CPU thread 2 (of 3) uses CUDA device 2 +CPU thread 1 (of 3) uses CUDA device 1 +CPU thread 0 (of 3) uses CUDA device 0 +gpu 1 dimgrid 5469 dimblock 256 degrePoly 1400000 +gpu 1 dimgrid2 1823 start 466688 size 466688 +gpu 2 dimgrid 5469 dimblock 256 degrePoly 1400000 +gpu 2 dimgrid2 1823 start 933376 size 466688 +gpu 0 dimgrid 5469 dimblock 256 degrePoly 1400000 +gpu 0 dimgrid2 1823 start 0 size 466688 +gpu 0 iter : 1 Arret : 0.047657 s/iter 48.025151 +gpu 0 iter : 2 Arret : 0.964913 s/iter 49.123050 +gpu 0 iter : 3 Arret : 2.4727 s/iter 49.732738 +gpu 0 iter : 4 Arret : 2.06376 s/iter 50.210543 +gpu 0 iter : 5 Arret : 0.958099 s/iter 51.132618 +gpu 0 iter : 6 Arret : 0.828164 s/iter 51.281245 +gpu 0 iter : 7 Arret : 2.24981 s/iter 51.515152 +gpu 0 iter : 8 Arret : 1.27056 s/iter 52.721722 +gpu 0 iter : 9 Arret : 1.7356 s/iter 52.706102 +gpu 0 iter : 10 Arret : 0.542543 s/iter 52.785746 +gpu 0 iter : 11 Arret : 0.703757 s/iter 52.816724 +gpu 0 iter : 12 Arret : 0.310008 s/iter 52.461451 +gpu 0 iter : 13 Arret : 0.443499 s/iter 51.910352 +gpu 0 iter : 14 Arret : 0.600068 s/iter 51.409402 +gpu 0 iter : 15 Arret : 0.482174 s/iter 51.392959 +gpu 0 iter : 16 Arret : 0.771182 s/iter 50.626111 +gpu 0 iter : 17 Arret : 0.532518 s/iter 50.225728 +gpu 0 iter : 18 Arret : 0.257696 s/iter 49.125636 +gpu 0 iter : 19 Arret : 0.177381 s/iter 48.905491 +gpu 0 iter : 20 Arret : 0.130753 s/iter 48.447574 +gpu 0 iter : 21 Arret : 0.0607806 s/iter 48.417696 +gpu 0 iter : 22 Arret : 3.28538 s/iter 48.161859 +gpu 0 iter : 23 Arret : 1.32615 s/iter 48.015609 +gpu 0 iter : 24 Arret : 0.026712 s/iter 48.032029 +gpu 0 iter : 25 Arret : 0.0189921 s/iter 48.023109 +gpu 0 iter : 26 Arret : 0.0252448 s/iter 48.022355 +gpu 0 iter : 27 Arret : 0.0183014 s/iter 48.029077 +gpu 0 iter : 28 Arret : 0.0259939 s/iter 48.031196 +gpu 0 iter : 29 Arret : 0.0148008 s/iter 48.034595 +gpu 0 iter : 30 Arret : 0.00511391 s/iter 48.034650 +gpu 0 iter : 31 Arret : 0.000444388 s/iter 48.016595 +gpu 0 iter : 32 Arret : 1.35417E-05 s/iter 48.015821 +gpu 0 iter : 33 Arret : 5.22681E-07 s/iter 48.020076 +gpu 0 iter : 34 Arret : 2.63971E-09 s/iter 48.039932 +gpu 0 iter : 35 Arret : 1.22535E-11 s/iter 48.040535 +gpu 0 iter : 36 Arret : 5.68579E-14 s/iter 48.039757 +temps : 1786.83 seconde(s) +Nb iterations : 36 +Nb de depassements de capacite exponentielle : 0 +Precision : 3.48488E-08 +Stabilite : 5.68579E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841469| 0.999997|-8.47142E-11 +i* 1.92466E-11| +| 2| 0.513623 +i* 0.858013| 0.999997|-2.15776E-11 +i*-2.98557E-11| +| 3| -0.52703 +i* -0.849843| 0.999997|-6.50922E-11 +i* 8.44216E-12| +| 4| 0.486439 +i* 0.873711| 0.999997| 5.60277E-11 +i* 4.36779E-11| +| 5| -0.500096 +i* -0.865967| 0.999997| 3.56147E-11 +i*-3.12713E-11| +| 6| 0.458776 +i* 0.888549| 0.999997|-1.89702E-11 +i* 4.08274E-12| +| 7| -0.472669 +i* -0.881237| 0.999997|-1.66496E-11 +i*-3.61498E-11| +| 8| 0.430661 +i* 0.902511| 0.999997|-1.60558E-11 +i*-1.29949E-11| +| 9| -0.444791 +i* -0.895631| 0.999997|-8.89955E-13 +i* 2.61938E-12| +| 10| 0.402136 +i* 0.915577| 0.999997| 6.5834E-12 +i* -1.3935E-11| +| 11| -0.416432 +i* -0.909164| 0.999997| 1.97816E-11 +i* 3.10848E-11| +| 12| 0.373171 +i* 0.927759| 0.999997|-2.17995E-11 +i*-2.96867E-12| +| 13| -0.387698 +i* -0.921783| 0.999997|-1.86324E-11 +i* -4.6545E-11| +| 14| 0.343875 +i* 0.939012| 0.999997|-1.30287E-11 +i*-2.87501E-11| +| 15| -0.358575 +i* -0.933498| 0.999997|-4.93405E-11 +i*-7.15173E-13| +| 16| 0.314233 +i* 0.949343| 0.999997| 1.02587E-11 +i*-4.25648E-11| +| 17| -0.329098 +i* -0.944293| 0.999997|-1.57903E-11 +i* 2.05052E-11| +| 18| 0.284281 +i* 0.958738| 0.999997| 2.51592E-11 +i* 2.09243E-11| +| 19| -0.299297 +i* -0.954157| 0.999997| 5.03608E-12 +i* 1.70503E-11| +| 20| 0.254048 +i* 0.967189| 0.999997|-2.81228E-11 +i*-1.66302E-11| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 0.999997 +600000 racines de module = 1 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140098: line 23: 11749 Segmentation fault (core dumped) ./template -r -i 900000 700000 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140098: line 24: 11753 Segmentation fault (core dumped) ./template -r -i 1000000 800000 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140098: line 25: 11755 Segmentation fault (core dumped) ./template -r -i 1500000 500000 diff --git a/Simulations/sparse_openmp/sparse_openmp_3GPU.sge b/Simulations/sparse_openmp/sparse_openmp_3GPU.sge new file mode 100644 index 0000000..f3bb47b --- /dev/null +++ b/Simulations/sparse_openmp/sparse_openmp_3GPU.sge @@ -0,0 +1,27 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=3 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -pe openmp 3 +#$ -V +#$ -cwd +#$ -N sparse_openmp_3GPU + +module load gcc/4.9.0 +module load cuda/7.0 + + +./template -r -i 60000 40000 +./template -r -i 150000 50000 +./template -r -i 250000 150000 +./template -r -i 350000 250000 +./template -r -i 500000 300000 +./template -r -i 600000 400000 +./template -r -i 700000 500000 +./template -r -i 800000 600000 +./template -r -i 900000 700000 +./template -r -i 1000000 800000 +./template -r -i 1500000 500000 + + diff --git a/Simulations/sparse_openmp/sparse_openmp_4GPU.o140097 b/Simulations/sparse_openmp/sparse_openmp_4GPU.o140097 new file mode 100644 index 0000000..2edc5c1 --- /dev/null +++ b/Simulations/sparse_openmp/sparse_openmp_4GPU.o140097 @@ -0,0 +1,621 @@ +REMAINING: 4 +Taking GPU #0 +Taking GPU #1 +Taking GPU #2 +Taking GPU #3 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^40000 + (-10 +i*0)*x^60000 + (1 +i*0)*x^100000 + +(-4000 +i*0)*x^39999 + (-600000 +i*0)*x^59999 + (100000 +i*0)*x^99999 + +zone limite de 'log-exp' 1.00356 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 1 (of 4) uses CUDA device 1 +gpu 0 dimgrid 391 dimblock 256 degrePoly 100000 +gpu 0 dimgrid2 98 start 0 size 25024 +gpu 2 dimgrid 391 dimblock 256 degrePoly 100000 +gpu 2 dimgrid2 98 start 50048 size 25024 +gpu 3 dimgrid 391 dimblock 256 degrePoly 100000 +gpu 3 dimgrid2 98 start 75072 size 25024 +gpu 1 dimgrid 391 dimblock 256 degrePoly 100000 +gpu 1 dimgrid2 98 start 25024 size 25024 +gpu 0 iter : 1 Arret : 0.00317265 s/iter 0.236357 +gpu 0 iter : 2 Arret : 0.00227157 s/iter 0.222729 +gpu 0 iter : 3 Arret : 0.00205316 s/iter 0.222769 +gpu 0 iter : 4 Arret : 0.00128297 s/iter 0.222748 +gpu 0 iter : 5 Arret : 0.00112626 s/iter 0.222747 +gpu 0 iter : 6 Arret : 0.0020822 s/iter 0.222736 +gpu 0 iter : 7 Arret : 0.0115304 s/iter 0.222730 +gpu 0 iter : 8 Arret : 0.0115653 s/iter 0.295379 +gpu 0 iter : 9 Arret : 0.00182694 s/iter 0.222647 +gpu 0 iter : 10 Arret : 0.000971807 s/iter 0.222690 +gpu 0 iter : 11 Arret : 0.00050868 s/iter 0.222743 +gpu 0 iter : 12 Arret : 0.000554626 s/iter 0.222588 +gpu 0 iter : 13 Arret : 0.000773549 s/iter 0.222519 +gpu 0 iter : 14 Arret : 0.000652981 s/iter 0.222480 +gpu 0 iter : 15 Arret : 7.85268E-05 s/iter 0.222478 +gpu 0 iter : 16 Arret : 1.67519E-05 s/iter 0.222489 +gpu 0 iter : 17 Arret : 1.93862E-07 s/iter 0.222504 +gpu 0 iter : 18 Arret : 2.89153E-09 s/iter 0.222440 +gpu 0 iter : 19 Arret : 4.30769E-11 s/iter 0.222397 +gpu 0 iter : 20 Arret : 6.41743E-13 s/iter 0.222499 +temps : 5.86914 seconde(s) +Nb iterations : 20 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.09748E-08 +Stabilite : 1.57015E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540308 +i* 0.841422| 0.999962|-1.95866E-12 +i*-4.55465E-13| +| 2| -0.113164 +i* 0.993538| 0.999962|-4.34919E-12 +i* 9.60242E-13| +| 3| -0.226732 +i* -0.974016| 1.00006|-1.34468E-09 +i*-3.70749E-10| +| 4| -0.715763 +i* 0.698289| 0.999962| 9.11271E-13 +i* 2.47219E-12| +| 5| 0.439922 +i* -0.897993| 0.999962|-3.49498E-13 +i* 1.66432E-12| +| 6| -0.996122 +i* 0.0886386| 1.00006| 4.72785E-10 +i* 4.13616E-11| +| 7| 0.908546 +i* -0.417692| 0.999962| 4.78506E-13 +i* 1.54377E-13| +| 8| -0.827813 +i* -0.560935| 0.999962| 9.76996E-13 +i*-2.04309E-12| +| 9| 0.968129 +i* 0.250682| 1.00006|-2.31715E-10 +i* 1.34848E-10| +| 10| -0.286842 +i* -0.958038| 1.00006|-5.93554E-10 +i*-2.45345E-10| +| 11| 0.591653 +i* 0.806145| 0.999962|-9.87654E-13 +i*-3.03635E-12| +| 12| -0.0511836 +i* 0.998651| 0.999962|-2.22622E-12 +i*-3.69013E-14| +| 13| -0.67097 +i* 0.741432| 0.999962|-8.03801E-14 +i*-1.68204E-12| +| 14| 0.383249 +i* -0.923603| 0.999962|-1.29119E-12 +i*-1.37426E-12| +| 15| -0.988685 +i* 0.15039| 1.00006|-1.61051E-10 +i* 7.18515E-11| +| 16| 0.880824 +i* -0.473363| 0.999962|-4.03455E-13 +i* 2.85139E-12| +| 17| -0.861082 +i* -0.508391| 0.999962| 9.8066E-13 +i* 3.40478E-12| +| 18| 0.98184 +i* 0.190015| 1.00006| 8.88373E-10 +i*-2.66385E-10| +| 19| -0.345842 +i* -0.938354| 1.00006| 1.38421E-10 +i*-2.31696E-10| +| 20| 0.640621 +i* 0.767807| 0.999962|-6.98774E-13 +i* 1.13798E-12| ++---+----------------------------+------------+----------------------------+ +60000 racines de module = 0.999962 +40000 racines de module = 1.00006 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^50000 + (-10 +i*0)*x^150000 + (1 +i*0)*x^200000 + +(-5000 +i*0)*x^49999 + (-1.5E+06 +i*0)*x^149999 + (200000 +i*0)*x^199999 + +zone limite de 'log-exp' 1.00178 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 1 (of 4) uses CUDA device 1 +CPU thread 0 (of 4) uses CUDA device 0 +gpu 1 dimgrid 782 dimblock 256 degrePoly 200000 +gpu 1 dimgrid2 196 start 50048 size 50048 +gpu 2 dimgrid 782 dimblock 256 degrePoly 200000 +gpu 2 dimgrid2 196 start 100096 size 50048 +gpu 3 dimgrid 782 dimblock 256 degrePoly 200000 +gpu 3 dimgrid2 196 start 150144 size 50048 +gpu 0 dimgrid 782 dimblock 256 degrePoly 200000 +gpu 0 dimgrid2 196 start 0 size 50048 +gpu 0 iter : 1 Arret : 0.000151294 s/iter 0.873722 +gpu 0 iter : 2 Arret : 0.000148163 s/iter 0.876720 +gpu 0 iter : 3 Arret : 0.000156239 s/iter 0.876483 +gpu 0 iter : 4 Arret : 0.000917016 s/iter 0.876408 +gpu 0 iter : 5 Arret : 0.00193309 s/iter 0.877387 +gpu 0 iter : 6 Arret : 0.012901 s/iter 1.040793 +gpu 0 iter : 7 Arret : 0.0696679 s/iter 1.039198 +gpu 0 iter : 8 Arret : 0.0831135 s/iter 1.017396 +gpu 0 iter : 9 Arret : 0.655093 s/iter 1.021459 +gpu 0 iter : 10 Arret : 0.310762 s/iter 1.026425 +gpu 0 iter : 11 Arret : 0.25028 s/iter 1.016739 +gpu 0 iter : 12 Arret : 0.12787 s/iter 1.024487 +gpu 0 iter : 13 Arret : 0.174578 s/iter 0.991808 +gpu 0 iter : 14 Arret : 0.13471 s/iter 1.020582 +gpu 0 iter : 15 Arret : 0.260288 s/iter 0.881413 +gpu 0 iter : 16 Arret : 0.151424 s/iter 1.018801 +gpu 0 iter : 17 Arret : 0.070357 s/iter 0.881097 +gpu 0 iter : 18 Arret : 0.0196537 s/iter 0.881104 +gpu 0 iter : 19 Arret : 0.00113921 s/iter 0.878041 +gpu 0 iter : 20 Arret : 4.42128E-05 s/iter 0.877967 +gpu 0 iter : 21 Arret : 3.87634E-06 s/iter 0.878342 +gpu 0 iter : 22 Arret : 3.63936E-09 s/iter 0.878295 +gpu 0 iter : 23 Arret : 3.63838E-13 s/iter 0.878170 +temps : 22.9576 seconde(s) +Nb iterations : 23 +Nb de depassements de capacite exponentielle : 0 +Precision : 0.000181892 +Stabilite : 2.22061E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540303 +i* 0.841453| 0.999985| 1.08703E-11 +i*-2.49217E-12| +| 2| -0.837195 +i* 0.546877| 0.999985| -5.4492E-12 +i* 1.09163E-12| +| 3| -0.553418 +i* -0.832885| 0.999985| -1.9722E-12 +i*-7.40397E-12| +| 4| 0.828599 +i* -0.559925| 1.00005|-7.54521E-09 +i* 1.47059E-08| +| 5| -0.8197 +i* 0.572767| 0.999985|-4.21663E-13 +i* -2.8616E-12| +| 6| -0.57917 +i* -0.815188| 0.999985|-5.13034E-12 +i*-1.52645E-12| +| 7| 0.810626 +i* -0.585537| 0.999985|-6.36846E-12 +i*-5.86797E-12| +| 8| 0.591872 +i* 0.806089| 1.00005|-1.69803E-09 +i* 9.43795E-09| +| 9| -0.801454 +i* 0.598134| 1.00005| 5.92533E-09 +i* 3.55911E-08| +| 10| -0.604356 +i* -0.796695| 0.999985|-1.64091E-13 +i* 1.59084E-12| +| 11| 0.791937 +i* -0.610578| 0.999985| 6.0707E-13 +i* 1.52922E-12| +| 12| 0.616763 +i* 0.78713| 0.999985|-4.48042E-12 +i* -2.6295E-12| +| 13| -0.782301 +i* 0.622877| 0.999985|-2.15827E-12 +i*-6.27114E-12| +| 14| -0.628991 +i* -0.777472| 1.00005| 6.93065E-09 +i*-8.65443E-09| +| 15| 0.772474 +i* -0.635023| 0.999985| 1.54783E-11 +i*-1.81338E-12| +| 16| 0.641054 +i* 0.767476| 0.999985| 9.05009E-12 +i*-2.91295E-12| +| 17| -0.762458 +i* 0.647014| 0.999985| 5.81724E-12 +i*-9.99384E-12| +| 18| -0.652967 +i* -0.757366| 0.999985| 5.10392E-12 +i*-6.61069E-12| +| 19| 0.752302 +i* -0.658888| 1.00005| 3.99107E-09 +i* 1.02117E-08| +| 20| 0.66472 +i* 0.747072| 0.999985|-1.93379E-12 +i*-1.29726E-11| ++---+----------------------------+------------+----------------------------+ +150000 racines de module = 0.999985 +50000 racines de module = 1.00005 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^150000 + (-10 +i*0)*x^250000 + (1 +i*0)*x^400000 + +(-15000 +i*0)*x^149999 + (-2.5E+06 +i*0)*x^249999 + (400000 +i*0)*x^399999 + +zone limite de 'log-exp' 1.00089 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 1 (of 4) uses CUDA device 1 +gpu 0 dimgrid 1563 dimblock 256 degrePoly 400000 +gpu 0 dimgrid2 391 start 0 size 100032 +gpu 2 dimgrid 1563 dimblock 256 degrePoly 400000 +gpu 2 dimgrid2 391 start 200064 size 100032 +gpu 3 dimgrid 1563 dimblock 256 degrePoly 400000 +gpu 3 dimgrid2 391 start 300096 size 100032 +gpu 1 dimgrid 1563 dimblock 256 degrePoly 400000 +gpu 1 dimgrid2 391 start 100032 size 100032 +gpu 0 iter : 1 Arret : 0.00053336 s/iter 3.114080 +gpu 0 iter : 2 Arret : 0.00132869 s/iter 3.113006 +gpu 0 iter : 3 Arret : 0.00304211 s/iter 3.113002 +gpu 0 iter : 4 Arret : 0.0081892 s/iter 3.421884 +gpu 0 iter : 5 Arret : 0.0174091 s/iter 3.393637 +gpu 0 iter : 6 Arret : 0.0170263 s/iter 3.378163 +gpu 0 iter : 7 Arret : 0.00925735 s/iter 3.423651 +gpu 0 iter : 8 Arret : 0.00879968 s/iter 3.111951 +gpu 0 iter : 9 Arret : 0.0133997 s/iter 3.368852 +gpu 0 iter : 10 Arret : 0.00968114 s/iter 3.111774 +gpu 0 iter : 11 Arret : 0.00462525 s/iter 3.110863 +gpu 0 iter : 12 Arret : 0.00341319 s/iter 3.111132 +gpu 0 iter : 13 Arret : 0.00439696 s/iter 3.110364 +gpu 0 iter : 14 Arret : 0.000354857 s/iter 3.110007 +gpu 0 iter : 15 Arret : 0.00105657 s/iter 3.109831 +gpu 0 iter : 16 Arret : 0.000563123 s/iter 3.109784 +gpu 0 iter : 17 Arret : 2.74759E-05 s/iter 3.109683 +gpu 0 iter : 18 Arret : 3.06801E-07 s/iter 3.109172 +gpu 0 iter : 19 Arret : 7.06164E-10 s/iter 3.108923 +gpu 0 iter : 20 Arret : 1.07684E-11 s/iter 3.109509 +gpu 0 iter : 21 Arret : 1.64161E-13 s/iter 3.109378 +temps : 68.0633 seconde(s) +Nb iterations : 21 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.09466E-07 +Stabilite : 3.51078E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540313 +i* 0.841453| 0.999991| 9.34197E-12 +i*-1.23633E-11| +| 2| -0.998329 +i* 0.057622| 0.999991| 4.43912E-12 +i* 1.27665E-12| +| 3| 0.439867 +i* -0.898052| 0.999991|-8.50653E-12 +i*-8.85586E-12| +| 4| -0.996033 +i* 0.0888768| 0.999991|-3.15592E-12 +i* 1.17456E-12| +| 5| 0.411521 +i* -0.911417| 1.00002|-2.94737E-09 +i* 1.73005E-09| +| 6| 0.59196 +i* 0.805956| 0.999991| 5.24358E-13 +i*-8.53073E-12| +| 7| -0.992759 +i* 0.120044| 0.999991| 2.58804E-12 +i* 2.47274E-12| +| 8| 0.382796 +i* -0.923823| 0.999991|-1.63092E-11 +i* 4.26312E-12| +| 9| 0.616925 +i* 0.78701| 0.999991| 4.27514E-12 +i*-1.13966E-11| +| 10| -0.988534 +i* 0.151098| 1.00002|-8.27014E-10 +i* 9.44171E-10| +| 11| 0.35366 +i* -0.935364| 0.999991|-1.92664E-11 +i* 1.19958E-11| +| 12| 0.641299 +i* 0.767311| 1.00002|-2.44657E-09 +i* -6.7886E-11| +| 13| -0.983286 +i* 0.18202| 0.999991| 3.21676E-12 +i*-9.48297E-13| +| 14| 0.324176 +i* -0.945987| 0.999991|-5.20695E-12 +i*-7.06984E-12| +| 15| 0.66503 +i* 0.746804| 0.999991| 5.74873E-13 +i* 8.53884E-12| +| 16| -0.977123 +i* 0.212747| 1.00002| 1.09185E-09 +i* 2.38902E-10| +| 17| 0.294374 +i* -0.955681| 0.999991|-2.37395E-11 +i*-2.53098E-12| +| 18| 0.688122 +i* 0.725616| 1.00002|-2.54456E-09 +i* 8.15125E-10| +| 19| -0.969965 +i* 0.243206| 0.999991| 6.88072E-12 +i* 3.20268E-13| +| 20| 0.264283 +i* -0.964436| 0.999991| 2.5573E-11 +i*-6.45539E-12| ++---+----------------------------+------------+----------------------------+ +250000 racines de module = 0.999991 +150000 racines de module = 1.00002 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^250000 + (-10 +i*0)*x^350000 + (1 +i*0)*x^600000 + +(-25000 +i*0)*x^249999 + (-3.5E+06 +i*0)*x^349999 + (600000 +i*0)*x^599999 + +zone limite de 'log-exp' 1.00059 +CPU thread 1 (of 4) uses CUDA device 1 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 3 (of 4) uses CUDA device 3 +gpu 0 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 0 dimgrid2 586 start 0 size 150016 +gpu 2 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 2 dimgrid2 586 start 300032 size 150016 +gpu 1 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 1 dimgrid2 586 start 150016 size 150016 +gpu 3 dimgrid 2344 dimblock 256 degrePoly 600000 +gpu 3 dimgrid2 586 start 450048 size 150016 +gpu 0 iter : 1 Arret : 0.00166144 s/iter 6.733254 +gpu 0 iter : 2 Arret : 0.00663307 s/iter 6.721345 +gpu 0 iter : 3 Arret : 0.0196947 s/iter 6.725089 +gpu 0 iter : 4 Arret : 0.0354088 s/iter 7.044531 +gpu 0 iter : 5 Arret : 0.0344666 s/iter 7.231490 +gpu 0 iter : 6 Arret : 0.0255965 s/iter 7.223546 +gpu 0 iter : 7 Arret : 0.0250307 s/iter 7.248225 +gpu 0 iter : 8 Arret : 0.0220818 s/iter 7.524758 +gpu 0 iter : 9 Arret : 0.0193422 s/iter 7.217155 +gpu 0 iter : 10 Arret : 0.0384961 s/iter 7.206267 +gpu 0 iter : 11 Arret : 0.0308611 s/iter 7.198073 +gpu 0 iter : 12 Arret : 0.0139003 s/iter 7.227655 +gpu 0 iter : 13 Arret : 0.00821788 s/iter 6.730489 +gpu 0 iter : 14 Arret : 0.00366002 s/iter 7.146524 +gpu 0 iter : 15 Arret : 0.00103013 s/iter 6.725238 +gpu 0 iter : 16 Arret : 0.000538911 s/iter 6.724848 +gpu 0 iter : 17 Arret : 0.000270623 s/iter 6.725086 +gpu 0 iter : 18 Arret : 4.24795E-05 s/iter 6.724157 +gpu 0 iter : 19 Arret : 5.07342E-09 s/iter 6.723896 +gpu 0 iter : 20 Arret : 7.14369E-11 s/iter 6.724108 +gpu 0 iter : 21 Arret : 1.00557E-12 s/iter 6.725050 +gpu 0 iter : 22 Arret : 1.41479E-14 s/iter 6.724347 +temps : 154.313 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 1.37653E-08 +Stabilite : 2.77613E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540302 +i* 0.841463| 0.999993| 8.34199E-12 +i* -1.9051E-11| +| 2| -0.553438 +i* -0.832883| 0.999993|-2.10654E-12 +i*-2.55273E-11| +| 3| -0.579282 +i* -0.815119| 0.999993|-1.44751E-12 +i* 7.66798E-12| +| 4| 0.592014 +i* 0.805919| 0.999993|-3.98037E-12 +i* 9.55808E-12| +| 5| -0.604557 +i* -0.796554| 0.999993|-2.82974E-12 +i* 9.99473E-12| +| 6| 0.61698 +i* 0.78697| 0.999993| 9.01823E-12 +i*-5.69156E-12| +| 7| -0.629237 +i* -0.777205| 0.999993|-2.92122E-12 +i*-4.85867E-12| +| 8| 0.641354 +i* 0.767237| 0.999993|-1.64209E-11 +i* 1.12904E-12| +| 9| -0.653299 +i* -0.757092| 0.999993|-8.22453E-13 +i* 2.82818E-12| +| 10| 0.665096 +i* 0.746749| 0.999993| -1.2145E-11 +i* 1.89129E-11| +| 11| -0.676717 +i* -0.736234| 0.999993|-1.26079E-11 +i*-1.25073E-11| +| 12| 0.688185 +i* 0.725526| 0.999993| 2.69875E-11 +i* 1.65411E-11| +| 13| -0.699466 +i* -0.714679| 1.00001| 3.92343E-10 +i*-3.02623E-09| +| 14| 0.710597 +i* 0.70359| 0.999993| 1.28564E-11 +i* 1.56626E-11| +| 15| -0.721517 +i* -0.69241| 1.00001| 1.76709E-09 +i*-4.04041E-09| +| 16| 0.73231 +i* 0.680962| 0.999993| 1.34706E-11 +i*-4.43489E-12| +| 17| -0.742944 +i* -0.669367| 1.00001| 9.14394E-11 +i*-3.49261E-09| +| 18| 0.7533 +i* 0.657691| 1.00001| 1.64587E-09 +i*-3.03669E-09| +| 19| -0.763551 +i* -0.645737| 0.999993| 1.68299E-11 +i* 1.43271E-11| +| 20| 0.773539 +i* 0.633763| 1.00001| -4.2314E-09 +i* 1.86243E-09| ++---+----------------------------+------------+----------------------------+ +350000 racines de module = 0.999993 +250000 racines de module = 1.00001 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^300000 + (-10 +i*0)*x^500000 + (1 +i*0)*x^800000 + +(-30000 +i*0)*x^299999 + (-5E+06 +i*0)*x^499999 + (800000 +i*0)*x^799999 + +zone limite de 'log-exp' 1.00044 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 1 (of 4) uses CUDA device 1 +CPU thread 2 (of 4) uses CUDA device 2 +gpu 3 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 3 dimgrid2 782 start 600000 size 200000 +gpu 1 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 1 dimgrid2 782 start 200000 size 200000 +gpu 0 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 0 dimgrid2 782 start 0 size 200000 +gpu 2 dimgrid 3125 dimblock 256 degrePoly 800000 +gpu 2 dimgrid2 782 start 400000 size 200000 +gpu 0 iter : 1 Arret : 0.00108387 s/iter 12.149827 +gpu 0 iter : 2 Arret : 0.00154284 s/iter 12.327396 +gpu 0 iter : 3 Arret : 0.00442373 s/iter 12.172431 +gpu 0 iter : 4 Arret : 0.0484674 s/iter 12.229082 +gpu 0 iter : 5 Arret : 0.0462186 s/iter 12.248952 +gpu 0 iter : 6 Arret : 0.0672711 s/iter 12.235166 +gpu 0 iter : 7 Arret : 0.0371959 s/iter 12.355881 +gpu 0 iter : 8 Arret : 0.0332451 s/iter 12.399234 +gpu 0 iter : 9 Arret : 0.0347928 s/iter 12.369857 +gpu 0 iter : 10 Arret : 0.0382283 s/iter 12.701023 +gpu 0 iter : 11 Arret : 0.010893 s/iter 12.800482 +gpu 0 iter : 12 Arret : 0.0100182 s/iter 12.206749 +gpu 0 iter : 13 Arret : 0.000870471 s/iter 12.137340 +gpu 0 iter : 14 Arret : 0.00222619 s/iter 12.140578 +gpu 0 iter : 15 Arret : 0.000360359 s/iter 12.119427 +gpu 0 iter : 16 Arret : 0.000163251 s/iter 12.146378 +gpu 0 iter : 17 Arret : 8.3446E-05 s/iter 12.146441 +gpu 0 iter : 18 Arret : 5.95325E-07 s/iter 12.141680 +gpu 0 iter : 19 Arret : 1.07969E-09 s/iter 12.142666 +gpu 0 iter : 20 Arret : 2.37954E-12 s/iter 12.145013 +gpu 0 iter : 21 Arret : 3.63218E-14 s/iter 12.145853 +temps : 258.82 seconde(s) +Nb iterations : 21 +Nb de depassements de capacite exponentielle : 0 +Precision : 6.97756E-07 +Stabilite : 2.22043E-16 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.540305 +i* 0.841464| 0.999995| -2.03E-11 +i* 2.74701E-11| +| 2| 0.592014 +i* 0.805922| 0.999995|-1.82734E-11 +i* 2.10218E-11| +| 3| 0.617007 +i* 0.786952| 0.999995| 4.23442E-11 +i* -6.2147E-12| +| 4| 0.641392 +i* 0.767207| 0.999995| 6.90537E-12 +i*-5.12417E-11| +| 5| 0.665146 +i* 0.746707| 0.999995| 2.02977E-11 +i* 7.48579E-12| +| 6| 0.688245 +i* 0.725472| 0.999995|-1.73153E-11 +i* -1.2656E-11| +| 7| 0.710667 +i* 0.703522| 0.999995| 3.69782E-12 +i* 2.3081E-12| +| 8| 0.732388 +i* 0.68088| 0.999995| 9.45355E-12 +i* 2.09024E-11| +| 9| 0.753381 +i* 0.657577| 0.999995| 3.40094E-11 +i* 1.45989E-12| +| 10| 0.77364 +i* 0.633618| 0.999995|-1.72307E-11 +i* 1.22723E-11| +| 11| 0.793138 +i* 0.609034| 0.999995| 3.89222E-12 +i* 2.21356E-11| +| 12| 0.811855 +i* 0.583851| 0.999995|-1.28337E-11 +i*-5.47207E-12| +| 13| 0.829772 +i* 0.558094| 0.999995|-1.63114E-11 +i*-1.64246E-12| +| 14| 0.846873 +i* 0.531786| 0.999995|-3.30451E-11 +i*-8.10676E-12| +| 15| 0.86314 +i* 0.504956| 0.999995|-4.00413E-12 +i* 3.04823E-11| +| 16| 0.878557 +i* 0.477628| 0.999995|-2.16493E-12 +i* 1.10533E-11| +| 17| 0.893104 +i* 0.449841| 0.999995|-1.48552E-11 +i* 1.06063E-11| +| 18| 0.906777 +i* 0.4216| 0.999995|-1.38745E-11 +i* 5.33384E-12| +| 19| 0.919557 +i* 0.392944| 0.999995|-3.33245E-11 +i* 5.94386E-12| +| 20| 0.931433 +i* 0.363901| 0.999995| 4.93219E-11 +i*-2.82651E-11| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 0.999995 +300000 racines de module = 1.00001 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^400000 + (-10 +i*0)*x^600000 + (1 +i*0)*x^1000000 + +(-40000 +i*0)*x^399999 + (-6E+06 +i*0)*x^599999 + (1E+06 +i*0)*x^999999 + +zone limite de 'log-exp' 1.00035 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 1 (of 4) uses CUDA device 1 +CPU thread 2 (of 4) uses CUDA device 2 +gpu 3 dimgrid 3907 dimblock 256 degrePoly 1000000 +gpu 3 dimgrid2 977 start 750144 size 250048 +gpu 0 dimgrid 3907 dimblock 256 degrePoly 1000000 +gpu 0 dimgrid2 977 start 0 size 250048 +gpu 1 dimgrid 3907 dimblock 256 degrePoly 1000000 +gpu 1 dimgrid2 977 start 250048 size 250048 +gpu 2 dimgrid 3907 dimblock 256 degrePoly 1000000 +gpu 2 dimgrid2 977 start 500096 size 250048 +gpu 0 iter : 1 Arret : 0.000456228 s/iter 18.772328 +gpu 0 iter : 2 Arret : 0.00142575 s/iter 18.751830 +gpu 0 iter : 3 Arret : 0.00549425 s/iter 18.764447 +gpu 0 iter : 4 Arret : 0.0229296 s/iter 19.538754 +gpu 0 iter : 5 Arret : 0.0173741 s/iter 19.273977 +gpu 0 iter : 6 Arret : 0.0179817 s/iter 19.297823 +gpu 0 iter : 7 Arret : 0.0102999 s/iter 18.835443 +gpu 0 iter : 8 Arret : 0.00783109 s/iter 19.616467 +gpu 0 iter : 9 Arret : 0.00443683 s/iter 19.576776 +gpu 0 iter : 10 Arret : 0.00652305 s/iter 18.757222 +gpu 0 iter : 11 Arret : 0.00589396 s/iter 18.772725 +gpu 0 iter : 12 Arret : 0.00781914 s/iter 18.746761 +gpu 0 iter : 13 Arret : 0.00825508 s/iter 18.745513 +gpu 0 iter : 14 Arret : 0.00209831 s/iter 18.746669 +gpu 0 iter : 15 Arret : 0.000157396 s/iter 18.747760 +gpu 0 iter : 16 Arret : 0.000185725 s/iter 18.747416 +gpu 0 iter : 17 Arret : 0.000163905 s/iter 18.747056 +gpu 0 iter : 18 Arret : 6.34206E-05 s/iter 18.748309 +gpu 0 iter : 19 Arret : 5.65573E-06 s/iter 18.749904 +gpu 0 iter : 20 Arret : 7.0784E-09 s/iter 18.749738 +gpu 0 iter : 21 Arret : 2.24468E-11 s/iter 18.748487 +gpu 0 iter : 22 Arret : 7.09418E-14 s/iter 18.747345 +temps : 422.324 seconde(s) +Nb iterations : 22 +Nb de depassements de capacite exponentielle : 0 +Precision : 8.97857E-06 +Stabilite : 5.20859E-14 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841468| 0.999996| 5.07216E-12 +i* 6.41236E-12| +| 2| 0.529701 +i* 0.84818| 0.999996|-4.61853E-13 +i*-4.17888E-12| +| 3| 0.524361 +i* 0.851491| 0.999996|-2.47296E-11 +i* 1.78327E-11| +| 4| 0.51901 +i* 0.854764| 0.999996| 9.45599E-12 +i* 2.07434E-11| +| 5| 0.513629 +i* 0.858008| 0.999996| 2.32483E-11 +i* 6.70747E-12| +| 6| 0.508237 +i* 0.861213| 0.999996|-1.34339E-11 +i* 9.87854E-12| +| 7| 0.502825 +i* 0.864384| 0.999996|-3.18459E-11 +i* 7.64744E-12| +| 8| 0.497384 +i* 0.867526| 0.999996| 2.97429E-11 +i*-6.06626E-13| +| 9| 0.491932 +i* 0.870629| 0.999996|-2.65525E-11 +i* 1.22525E-11| +| 10| 0.486452 +i* 0.873703| 0.999996| 3.0312E-11 +i* 1.02214E-11| +| 11| 0.480962 +i* 0.876737| 0.999996| 1.81546E-11 +i* 8.04012E-12| +| 12| 0.475453 +i* 0.879736| 0.999996| 3.09861E-11 +i* 4.093E-12| +| 13| 0.469917 +i* 0.882706| 0.999996|-1.29106E-11 +i*-2.31489E-11| +| 14| 0.46437 +i* 0.885637| 0.999996| 1.38481E-11 +i* -1.517E-11| +| 15| 0.458797 +i* 0.888537| 0.999996| 2.78862E-11 +i* 1.10441E-11| +| 16| 0.453214 +i* 0.891397| 0.999996| 2.45506E-11 +i* 3.1726E-11| +| 17| 0.447614 +i* 0.894223| 0.999996|-1.08491E-12 +i*-2.12277E-11| +| 18| 0.441986 +i* 0.897017| 0.999996| 2.72476E-11 +i* 3.22485E-11| +| 19| 0.436351 +i* 0.899772| 0.999996|-1.24334E-11 +i*-2.66317E-11| +| 20| 0.430689 +i* 0.902496| 0.999996| 2.73914E-12 +i* 2.25153E-11| ++---+----------------------------+------------+----------------------------+ +600000 racines de module = 0.999996 +400000 racines de module = 1.00001 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^500000 + (-10 +i*0)*x^700000 + (1 +i*0)*x^1200000 + +(-50000 +i*0)*x^499999 + (-7E+06 +i*0)*x^699999 + (1.2E+06 +i*0)*x^1199999 + +zone limite de 'log-exp' 1.0003 +CPU thread 3 (of 4) uses CUDA device 3 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 1 (of 4) uses CUDA device 1 +gpu 0 dimgrid 4688 dimblock 256 degrePoly 1200000 +gpu 3 dimgrid 4688 dimblock 256 degrePoly 1200000 +gpu 3 dimgrid2 1172 start 900096 size 300032 +gpu 2 dimgrid 4688 dimblock 256 degrePoly 1200000 +gpu 0 dimgrid2 1172 start 0 size 300032 +gpu 2 dimgrid2 1172 start 600064 size 300032 +gpu 1 dimgrid 4688 dimblock 256 degrePoly 1200000 +gpu 1 dimgrid2 1172 start 300032 size 300032 +gpu 0 iter : 1 Arret : 0.00368442 s/iter 26.569710 +gpu 0 iter : 2 Arret : 3.704 s/iter 28.385681 +gpu 0 iter : 3 Arret : 1.74615 s/iter 28.502041 +gpu 0 iter : 4 Arret : 2.12336 s/iter 28.609424 +gpu 0 iter : 5 Arret : 2.13811 s/iter 29.338801 +gpu 0 iter : 6 Arret : 0.766739 s/iter 29.346300 +gpu 0 iter : 7 Arret : 0.657775 s/iter 29.516021 +gpu 0 iter : 8 Arret : 0.597705 s/iter 29.678298 +gpu 0 iter : 9 Arret : 0.573945 s/iter 29.579526 +gpu 0 iter : 10 Arret : 0.542611 s/iter 29.795670 +gpu 0 iter : 11 Arret : 0.488156 s/iter 29.717429 +gpu 0 iter : 12 Arret : 0.463721 s/iter 29.588883 +gpu 0 iter : 13 Arret : 0.442782 s/iter 29.618542 +gpu 0 iter : 14 Arret : 0.43109 s/iter 29.294507 +gpu 0 iter : 15 Arret : 0.427026 s/iter 29.324604 +gpu 0 iter : 16 Arret : 0.434845 s/iter 29.362199 +gpu 0 iter : 17 Arret : 0.442084 s/iter 29.279579 +gpu 0 iter : 18 Arret : 0.46093 s/iter 29.338081 +gpu 0 iter : 19 Arret : 0.48645 s/iter 29.333743 +gpu 0 iter : 20 Arret : 0.496349 s/iter 29.369982 +gpu 0 iter : 21 Arret : 1.56187 s/iter 28.940178 +gpu 0 iter : 22 Arret : 2.3748 s/iter 28.784866 +gpu 0 iter : 23 Arret : 1.09653 s/iter 28.933834 +gpu 0 iter : 24 Arret : 1.43739 s/iter 28.700919 +gpu 0 iter : 25 Arret : 2.22796 s/iter 28.722635 +gpu 0 iter : 26 Arret : 1.54855 s/iter 28.698877 +gpu 0 iter : 27 Arret : 1.95651 s/iter 28.629259 +gpu 0 iter : 28 Arret : 0.897983 s/iter 28.648379 +gpu 0 iter : 29 Arret : 7.34662 s/iter 28.534855 +gpu 0 iter : 30 Arret : 1.74621 s/iter 28.422914 +gpu 0 iter : 31 Arret : 0.597689 s/iter 28.621303 +gpu 0 iter : 32 Arret : 0.857922 s/iter 28.617561 +gpu 0 iter : 33 Arret : 1.33974 s/iter 28.328536 +gpu 0 iter : 34 Arret : 10.8161 s/iter 28.390666 +gpu 0 iter : 35 Arret : 6.6951 s/iter 28.507533 +gpu 0 iter : 36 Arret : 0.757761 s/iter 28.460493 +gpu 0 iter : 37 Arret : 0.588104 s/iter 28.489026 +gpu 0 iter : 38 Arret : 0.593958 s/iter 28.232970 +gpu 0 iter : 39 Arret : 0.333943 s/iter 27.617579 +gpu 0 iter : 40 Arret : 0.276517 s/iter 27.632546 +gpu 0 iter : 41 Arret : 0.137564 s/iter 27.552902 +gpu 0 iter : 42 Arret : 0.0648876 s/iter 27.307198 +gpu 0 iter : 43 Arret : 0.0511538 s/iter 27.320582 +gpu 0 iter : 44 Arret : 0.0242118 s/iter 26.798806 +gpu 0 iter : 45 Arret : 0.00922443 s/iter 26.583042 +gpu 0 iter : 46 Arret : 0.00927718 s/iter 26.616458 +gpu 0 iter : 47 Arret : 0.0412361 s/iter 26.563085 +gpu 0 iter : 48 Arret : 0.0405407 s/iter 26.561073 +gpu 0 iter : 49 Arret : 0.00788436 s/iter 26.567749 +gpu 0 iter : 50 Arret : 0.00128029 s/iter 26.567412 +gpu 0 iter : 51 Arret : 0.000171237 s/iter 26.567449 +gpu 0 iter : 52 Arret : 7.02979E-07 s/iter 26.567944 +gpu 0 iter : 53 Arret : 2.0296E-09 s/iter 26.567809 +gpu 0 iter : 54 Arret : 8.07801E-12 s/iter 26.567272 +gpu 0 iter : 55 Arret : 3.21626E-14 s/iter 26.572179 +temps : 1556.58 seconde(s) +Nb iterations : 55 +Nb de depassements de capacite exponentielle : 0 +Precision : 4.03717E-06 +Stabilite : 4.93017E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.54031 +i* 0.841472| 1| 1.4588E-09 +i* 4.51768E-09| +| 2| 0.513633 +i* 0.858015| 1| 1.54651E-09 +i*-2.27023E-10| +| 3| 0.486451 +i* 0.873713| 1| 1.95054E-09 +i* 6.77633E-10| +| 4| 0.458805 +i* 0.888533| 0.999997| 1.78773E-11 +i* 1.55684E-11| +| 5| 0.430685 +i* 0.902499| 0.999997| 2.12053E-13 +i*-1.16324E-11| +| 6| 0.402126 +i* 0.915589| 1| 2.50282E-09 +i*-6.10471E-09| +| 7| 0.3732 +i* 0.927747| 0.999997|-1.54374E-11 +i*-2.76083E-11| +| 8| 0.3439 +i* 0.939003| 0.999997|-1.12714E-11 +i* 1.5453E-11| +| 9| 0.314261 +i* 0.949333| 0.999997| 1.93628E-11 +i* 2.50909E-11| +| 10| 0.284313 +i* 0.958728| 0.999997| 2.69426E-11 +i* 2.77974E-11| +| 11| 0.254084 +i* 0.967179| 0.999997| 1.5277E-11 +i* 4.73027E-12| +| 12| 0.223605 +i* 0.974676| 0.999997| -8.1017E-11 +i*-3.77299E-11| +| 13| 0.192909 +i* 0.981221| 1|-1.95729E-09 +i* 4.84549E-09| +| 14| 0.162018 +i* 0.986792| 1| 1.80241E-09 +i* 1.03051E-10| +| 15| 0.130967 +i* 0.991391| 1|-1.93729E-10 +i*-4.06442E-10| +| 16| 0.0998077 +i* 0.995003| 0.999997| -4.5103E-11 +i*-6.66658E-12| +| 17| 0.0685404 +i* 0.997645| 0.999997| 1.01124E-11 +i* 3.1089E-12| +| 18| 0.0371504 +i* 0.999314| 1|-1.38879E-09 +i*-2.32658E-09| +| 19| 0.00578048 +i* 0.99998| 0.999997| 3.46787E-11 +i* 1.94857E-13| +| 20| -0.0256056 +i* 0.999669| 0.999997| 2.01068E-11 +i*-1.22213E-12| ++---+----------------------------+------------+----------------------------+ +500000 racines de module = 1 +700000 racines de module = 0.999997 +(1 +i*0)*x^0 + (-0.1 +i*0)*x^600000 + (-10 +i*0)*x^800000 + (1 +i*0)*x^1400000 + +(-60000 +i*0)*x^599999 + (-8E+06 +i*0)*x^799999 + (1.4E+06 +i*0)*x^1399999 + +zone limite de 'log-exp' 1.00025 +CPU thread 1 (of 4) uses CUDA device 1 +CPU thread 0 (of 4) uses CUDA device 0 +CPU thread 2 (of 4) uses CUDA device 2 +CPU thread 3 (of 4) uses CUDA device 3 +gpu 0 dimgrid 5469 dimblock 256 degrePoly 1400000 +gpu 0 dimgrid2 1368 start 0 size 350016 +gpu 1 dimgrid 5469 dimblock 256 degrePoly 1400000 +gpu 1 dimgrid2 1368 start 350016 size 350016 +gpu 2 dimgrid 5469 dimblock 256 degrePoly 1400000 +gpu 2 dimgrid2 1368 start 700032 size 350016 +gpu 3 dimgrid 5469 dimblock 256 degrePoly 1400000 +gpu 3 dimgrid2 1368 start 1050048 size 350016 +gpu 0 iter : 1 Arret : 0.00408309 s/iter 36.124369 +gpu 0 iter : 2 Arret : 0.208632 s/iter 36.641290 +gpu 0 iter : 3 Arret : 1.37702 s/iter 37.617641 +gpu 0 iter : 4 Arret : 1.45346 s/iter 37.349167 +gpu 0 iter : 5 Arret : 1.6393 s/iter 37.990887 +gpu 0 iter : 6 Arret : 3.4316 s/iter 38.064434 +gpu 0 iter : 7 Arret : 1.9865 s/iter 38.951955 +gpu 0 iter : 8 Arret : 4.57739 s/iter 39.092906 +gpu 0 iter : 9 Arret : 2.70182 s/iter 39.516603 +gpu 0 iter : 10 Arret : 2.54353 s/iter 40.448257 +gpu 0 iter : 11 Arret : 1.82865 s/iter 40.236603 +gpu 0 iter : 12 Arret : 0.783909 s/iter 39.432599 +gpu 0 iter : 13 Arret : 1.89333 s/iter 39.521084 +gpu 0 iter : 14 Arret : 1.37044 s/iter 39.264476 +gpu 0 iter : 15 Arret : 3.05361 s/iter 38.860385 +gpu 0 iter : 16 Arret : 2.08571 s/iter 38.971159 +gpu 0 iter : 17 Arret : 2.09101 s/iter 38.887096 +gpu 0 iter : 18 Arret : 1.02745 s/iter 38.910018 +gpu 0 iter : 19 Arret : 0.704384 s/iter 38.234669 +gpu 0 iter : 20 Arret : 0.741087 s/iter 38.350019 +gpu 0 iter : 21 Arret : 0.788627 s/iter 38.106199 +gpu 0 iter : 22 Arret : 1.04305 s/iter 37.990724 +gpu 0 iter : 23 Arret : 2.78018 s/iter 38.167968 +gpu 0 iter : 24 Arret : 3.62183 s/iter 38.203661 +gpu 0 iter : 25 Arret : 5.50084 s/iter 37.940466 +gpu 0 iter : 26 Arret : 0.606592 s/iter 38.122389 +gpu 0 iter : 27 Arret : 0.700038 s/iter 37.866885 +gpu 0 iter : 28 Arret : 0.418813 s/iter 37.840730 +gpu 0 iter : 29 Arret : 0.495401 s/iter 37.808439 +gpu 0 iter : 30 Arret : 0.988549 s/iter 37.865318 +gpu 0 iter : 31 Arret : 0.749386 s/iter 37.753243 +gpu 0 iter : 32 Arret : 0.852267 s/iter 37.713161 +gpu 0 iter : 33 Arret : 1.16501 s/iter 37.855558 +gpu 0 iter : 34 Arret : 0.385689 s/iter 37.935460 +gpu 0 iter : 35 Arret : 0.393423 s/iter 37.441807 +gpu 0 iter : 36 Arret : 0.317888 s/iter 36.669962 +gpu 0 iter : 37 Arret : 0.23539 s/iter 36.318606 +gpu 0 iter : 38 Arret : 0.0527559 s/iter 36.193597 +gpu 0 iter : 39 Arret : 0.0143793 s/iter 36.106964 +gpu 0 iter : 40 Arret : 0.00318939 s/iter 36.183822 +gpu 0 iter : 41 Arret : 2.64184E-05 s/iter 36.123292 +gpu 0 iter : 42 Arret : 1.30802E-08 s/iter 36.116093 +gpu 0 iter : 43 Arret : 1.80499E-10 s/iter 36.117759 +gpu 0 iter : 44 Arret : 2.48451E-12 s/iter 36.115451 +gpu 0 iter : 45 Arret : 3.41814E-14 s/iter 36.113705 +temps : 1704.89 seconde(s) +Nb iterations : 45 +Nb de depassements de capacite exponentielle : 0 +Precision : 2.68566E-08 +Stabilite : 7.85076E-15 ++---+----------------------------+------------+----------------------------+ +| i | Zi | mod(Zi) | P(Zi) | ++---+----------------------------+------------+----------------------------+ +| 1| 0.5403 +i* 0.841469| 0.999997|-5.74141E-12 +i*-6.39521E-11| +| 2| 0.513623 +i* 0.858013| 0.999997|-2.15776E-11 +i*-2.98557E-11| +| 3| -0.52703 +i* -0.849843| 0.999997|-6.50922E-11 +i* 8.44216E-12| +| 4| 0.486439 +i* 0.873711| 0.999997| 5.60277E-11 +i* 4.36779E-11| +| 5| -0.500096 +i* -0.865967| 0.999997| 3.56147E-11 +i*-3.12713E-11| +| 6| 0.458776 +i* 0.888549| 0.999997|-1.89702E-11 +i* 4.08274E-12| +| 7| -0.472669 +i* -0.881237| 0.999997|-1.66496E-11 +i*-3.61498E-11| +| 8| 0.430661 +i* 0.902511| 0.999997|-1.60558E-11 +i*-1.29949E-11| +| 9| -0.444791 +i* -0.895631| 0.999997| 3.68259E-11 +i* 1.36002E-12| +| 10| 0.402136 +i* 0.915577| 0.999997| 6.5834E-12 +i* -1.3935E-11| +| 11| -0.416432 +i* -0.909164| 0.999997| 1.97816E-11 +i* 3.10848E-11| +| 12| 0.373171 +i* 0.927759| 0.999997|-2.17995E-11 +i*-2.96867E-12| +| 13| -0.387698 +i* -0.921783| 0.999997|-1.86324E-11 +i* -4.6545E-11| +| 14| 0.343875 +i* 0.939012| 0.999997| 3.06317E-11 +i* 7.08794E-11| +| 15| -0.358575 +i* -0.933498| 0.999997| 8.13599E-11 +i*-1.42233E-11| +| 16| 0.314233 +i* 0.949343| 0.999997| 3.86503E-11 +i* 2.08775E-11| +| 17| -0.329098 +i* -0.944293| 0.999997|-1.57903E-11 +i* 2.05052E-11| +| 18| 0.284281 +i* 0.958738| 0.999997| 2.51592E-11 +i* 2.09243E-11| +| 19| -0.299297 +i* -0.954157| 0.999997| 5.03608E-12 +i* 1.70503E-11| +| 20| 0.254048 +i* 0.967189| 0.999997|-2.81228E-11 +i*-1.66302E-11| ++---+----------------------------+------------+----------------------------+ +800000 racines de module = 0.999997 +600000 racines de module = 1 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140097: line 23: 10309 Segmentation fault (core dumped) ./template -r -i 900000 700000 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140097: line 24: 10313 Segmentation fault (core dumped) ./template -r -i 1000000 800000 +/Softs/Sge/mesodell/spool/node1-50/job_scripts/140097: line 25: 10315 Segmentation fault (core dumped) ./template -r -i 1500000 500000 diff --git a/Simulations/sparse_openmp/sparse_openmp_4GPU.sge b/Simulations/sparse_openmp/sparse_openmp_4GPU.sge new file mode 100644 index 0000000..1b5ae2f --- /dev/null +++ b/Simulations/sparse_openmp/sparse_openmp_4GPU.sge @@ -0,0 +1,27 @@ +#!/bin/bash -l +#$ -q tesla.q +#$ -l gpu=4 +## adapter selon besoin +#$ -l h_vmem=15G +#$ -pe openmp 4 +#$ -V +#$ -cwd +#$ -N sparse_openmp_4GPU + +module load gcc/4.9.0 +module load cuda/7.0 + + +./template -r -i 60000 40000 +./template -r -i 150000 50000 +./template -r -i 250000 150000 +./template -r -i 350000 250000 +./template -r -i 500000 300000 +./template -r -i 600000 400000 +./template -r -i 700000 500000 +./template -r -i 800000 600000 +./template -r -i 900000 700000 +./template -r -i 1000000 800000 +./template -r -i 1500000 500000 + + diff --git a/Sparse_mpi.pdf b/Sparse_mpi.pdf new file mode 100644 index 0000000000000000000000000000000000000000..2bdfcfa55c079fdc392b0aa8603b5668548349f4 GIT binary patch literal 8094 zcmb_B2{=^i`z=>xgquRLbRt`pGmF7YmN2$t$+tICW&ld0Aq7lWP(48my&w!`Eie$ z4Ts-PI9x5$-JCy`KE?5cAKrDlSjpvqq*2m3DStsLkz+mG9^)=f6Wzp(CpM4Hxr}$# zV8`4)g66ufHcZ-vdwGK4)9JGLhMwNKa|i0EhI4^}H6@Ze6l5!!1EXaMWSQFr(No{$hs%6#0s`%S-=Rc02)U5oZEOiBH3pOa=W+AiUR z$#1q(eaz|9^xqgFBX4A4-dk>Wu50O!KI3%x@4YKki!3soB1crWERidrsU2Dnpt+s6 zPK@J$xU_|%Dj^=9=C(yxIH}ZBV1d6{>cK?$geKp_<}|jb+4ZOkrdu?oo`#*rgmwfq z>*BMY&XmifuKIEr=Y3Ay-<#$}8IqHTH;!?1N57Sbc`R>qU2Dr0j_~raJWk1OUObjk z;kDlvx!=OO?uww$wTfEm_N&?t6a@(iW6@b|cOT22keKx|e`MK&k+{z;Dw3(t)34Q5 z-0fVqJ1hD$TDuUYxZA>cw=v8uvadpAo13bjDoIegY+-cFN?|H>!|cPOgAa}l-c5UX zOeZ_7;pU;d9Bw>l~ zlcf{4G8ywx=%Fi?A+7qpo<7!$+0a;{54Kq+9Ag^r3R+6eY}lQvY18X*8E$IA*PE}w zQjLAhV%FqRF1N$5XjamV7PyeG8tq{WC0DD#xEfYk^is<=lOVChxw*C8=DPD1N;*NH zt3UjYrTwJUcC#s00TI;otoEr;m#l%oBF0=+Ws_D;uA^4JGb-OPH%&wSoaeT4!#;u( z@g(n2)J9?V#ywZWIU;i0iwTF_Xs$*~#BMb+`h69D#BMY$Yf-QW#;1f9TF35cb*-yu zC6ig=^F_TEiYJvd)!zBKE1ES9`Q9+->2$1V7|g2-n?bhWT^=RM*y=w%>)u#ycO#-W zjT9n~nH1fTqv5p;F@5q_#|}YMtB*kH^|h(A#q;2gc8Fi(M$@{Ci#mp~mEGxQqYsO7 z)I5K|EokOlNe67c^lnw&Xg+>&+Qq$Pu(!Y8;`82*ZsO&AsG&T@h)U}$Rb$z!SFh?P z-g_Q={iSn<`5UMH)3!-fFFuq_FvAZ_%uV%sG3P&i;6YJZ{VHS3lG}X<#d-50U(@T} ztLN|M2Josg`VIN(XY50x{Z3@iDt);5ab&ru#60_owr0QLmS0(gm;6;-W7}1Q@{%Q} zwOMEH%VNd@C6a+G$6>)-NuV>QFZ4>m;#&k_^92tWt8JA#6Lcd( z-DtX4Ov-FF$t6wSLVD|X=+0BIy88<&oCjP2-b)T-$i3WjV!`Ft^X1R)0pcML@{r&fEO#sRpENFcn$A}M!iriJ&|M#9}9p*I|GAv80)Kik|e>1&v4=cF(Wt*t3_`!T4E zO8BPJBNzpHHl=%BjcPxhl0E{Sr=QV%bk6OxK6Ur78dZ1iSjP5yb89UlBZ!hFCx-jI zZ)4RxUem3VGb&_>!%?v#xN@tyr)|acnZl*F_Fda=YZmrQtdYh9C$ec72MRCNn4Lb` zA%I>@8Is)8^t^RbR#l5Domo;Kk$wgp5nFW>Q2SUiBlBqZl*3lv_c}R=469``(B3t1tSAug!ERi@mYon!0gKk055li{k4Q&;D%cDQStQ z^^7(hXorx0QIBcGqZWm7a~*Q>!T-a{kKL39tIiCOlH5uV2_W=VZG{uxop>oqs#Qx$J~* zMg1G+)^pmnIjUVwt(XU)gk5Ogx+~chxtA+==thKg{^glMpLVU{aYokx_X~C0gB?x2 zbf?x^DOv4BS-J8}ez{WxVsTYHn$_qz^G-kEimUeAo_3dmWve;uF05SSeveM2d>!eI zyptby{5s(=yC+ZQO=RAuRE?`IDhEqrM?=^t&u;V=w|uPh^_UO2cEO-DR>H-&Yl1Vs zj~SZz=i$N%1-${Ek@D_aXUaMX?oWHz9z&7ht+w~fbW~I3M?Z~E*T3%`uX;mfkd~4H zXv9w>_~`@xjfA5yu%$JvZ%Kw@Z~z&!BT&hpHJL;w7&CbQ9u94z;aY$W67B(mHd$l_ z2SD-D5Ey7rW;3}gBAE>(D0VC+(SgjtgHQ?sfR1Dy2Ld5_;er?GbV(N zKrBq4oCP$2<`6|Tz|VE;VbIc&SbP?Xxer7Qk_%W6j17QRbP^lD!}wy`!#n_p0+&zn zJ5)aPrL<`g(}chw_%W%=B$lMNCUXcRXa_(n()z|*=SKqHjsXL0?W_TWfx(iH3#VFQ zWv>I{^jveE<5M7oRH} zKrZ3%-?}K&vMdk|96<5s5Dx!ri_l9n;Cvr7Wk3lrok0Z<3x)LTpZuTgZ4AX76m}X&gf5_?jRbVG5FY$gpUMWbV4xA3$d5p15egncfCZV) zdU49zekGr4^Na|mF{ea z&TFFPmW+fWws zC=L&EvRdQyw?2LD^eE}wjtFy9nm6`!mDz{j@|l*0;!@`X+~}&=A-8<}IOWM@Wi{b0 z<+HQ1eR!d{NqJExYF6gk*P5>tU2^Mc+j6*5E55)A@fns@r?O};q{H>ToYy4oN1SWQ z?hKp6BboFTBnrjq%Ts&t+Q8GZTd4LL&nYR$*QPi$b$6nM%fpOzRm>Krj(H9HO^WSg zmBPa6aZJuk#3j;r(&-}C6G6vbFwd7ImOPU8I__?ro4)TauH*W?-S_PS9oHr7%FQxX z6%aQIcG%#!{YKRBi_UvRHpQ_nxjsCfWOPggF^*MCCq)?^S4xh_4tl2uCQy@lbrpji z#?1tW%2wTPddev2vNnoH+ZEu}Y+BapRCH+MVmOh4lxo=9FB!BGzk0mZruK$3`|>K#TG!nps23Q)^KVd+M|zw8zV&j=C$sQF+UjN4*0It zmo%G**o@QJLqw*xZ#?(+HL2qb7atcy@5|0TjnX}enG{-Yc@slN* z5q^3pPd7oW%js4=D|~g?QG&K(lHSm|D^WLe` zPDhV!CG1fDB`kbwRpc0^LUvz4*RLYG3~12?AsH9ES4#jxx4rcn9(cx&9`rJSlCXDQ zBJfdXLuO4FVTo^vlPlJWnR?wu+->yc`KpGgY0co1Q(|{!RWRYF!(7#dDM4FbaA|A3 z9lAkg{K_z7_JD~^qH?L>3iCB*#^aB_WcB=7_3{s^KxqZ9tWl5bQl860gq45ZAMaBSuZar-XQ3GXsTd={s}3;LYXz0{UiHsN!oU~1po&-bJQEnHZ>jpq>pu( zfA-Y#;P4s8P}LEd^=I^(9gcfLK5vfk0QN;7KTA*s>a?w&b;u5;DzuLecS`%1?;usz z*ve$*{&uXtwzf}-7a(Y31#F6iNi@4gWfZKtC?KbG^>&{wO!}8c^neIl!0lrZfk`+* z>eH#xLp2yNi4Pb2SXh>9mj$Pf|{P6u*CQjDp4J)UOU z`q((1pSrZ+_*LVY`Az%uvx_;rZJ5#akw>52*}Erjw_SSO&-30X6S3O74=za=8^1l+ zhcqm$Wyb8-RB#@lKe|PCA4-3i(Y?i9GZ}cgiTL`o(mLc(AN2t4Z(kJF25u|q%t<(k zPwZ{w_)M3&3)JnbU;8Owg|jPMw7>RVbhwE>73`u`%OP&YJDhCH&{;LQUeDkEw)`Wf zIHPrUpT}LWk!u#(;PLXgT4^oaKS}wL>@C(4MWfm2yrJ^=&)Z+-NY{-N{+{M}I8i@! z^{3lmX+kswqg>JFXT=WnHeYU)Y7D**Had`g#gCr&`pIN&S>#c4kFeLiKaPuv+ZI=B zsMIn!cW#2S-t57bw5Xk8Drw9#D<{cHS|zVg;9&LLp^^h1@b;m@nL&T_rwpg9?>&3+ zv+&B5fzqK$@!lRf4QJD|+ku?xw-Y1pREYE%G{qbhZ#Y`>{;%%rn1Ba1-DmF`#at1$ z7AzD>-dXHrp8A&MZ>5}Em)5M0XK^t}8UpVD^lr7z3$^(#ra#Pu1POZdKPy{vSz+T; ze}k8_TVT(9wS-joK_y8`u~#!Hb+iNUpxY?#NXg*)d#2ou&~Zvp>fU=E=+)M};);AE z7#J0{QDo9`-FH^qiY#g_wPqIY7A{XmFy3vx;H#MP^x@``=Jv^iCynA%`%Kjv(ZX-B z^$8l=2cL|)*t&|`f%i$>w77*l{My{i_pd{prl$_X|5law?AX<~xtdy(vfSDala~?= z&%;eopC$%N%0@!dW8-@h!}l;RSb1U)eH7Fq@BC6#$6LM~R%qFr*1zv*)QGDDPAe%+ z(+aOx2RzsME!4Xg9k;7h<-&7Yq~t2;nH3HyzpA$F=yY9v}@9qG1EaNZTw$!y; zNqV~mnHj!+*Pq8awP3;-p?@hJ$;VycKJQRA8_-ws*v~YSh+NyCv+;4vuB11HtSB=&C;#b>n!GT){AX`a*~VmE zlf)Gr8WImIe0*)M_sBKbJ*VQ{9u~X9d)}{TfCxN4BAq`|WNW5*^X*4}r-3(j%N%Ns z#cMuNhqJYA_*UNTzzV{Wu$$Be`3zQhxSgPN=(A+F)BqpP^-l%G4J_wV1YxgVv;WKlr`27>|NNDztCfFLy3!3++8r@>$= zK>QX2p}T%XW3V+BWYQ!u{Xx1bh|q+C%Z!%m2s)Di@EH@lnOu&(GM7syVF}u3427(t ztwAE9i5dt51+D>y9t{edNY)|iP>2{E_%geI@5KCpAG856L_vChMp&q>Cvk~nmcFvN z-5$W4#$hS~Mi(D5_mmu{(zMa0)(7&xSLV&gP|Ex8Cf4*Du;jlO+k?RkYiI%wk zkJJ3yb|w+O3LL;?`7J~Ui3pPY$b8w@kf{-n#3Uk?!esdqApa%=1VH61fdjcc2>GS5 zfgZHUp>zDm1`F|LH8KY*@D4qz|Z z#E)*UI9R|2zfpunM82CaS&Kv+$brk$4gBbSbiz;g3;TThuUOESwA8qPME)n0W%uFx z(0@nl2Lk`Wi58ZiiwE*2@awf^00aJ|=iejr?JkG@L+C5-=ik)-_+Rl|$-jK*sQjlp zM-^&O@NEOBl^?_^{P>4Hf&vI_sArU5U2&=Lnd;*g76IqEgNw;Gzf9QNmRc!3VAFt z1!`R(&@ldey!ZgxXfz59P=KX1BuWQr$nhV5vAm|E#c$XBxQ0X_pl0b$YY6Rs;KHFJ z{}WE@A8<%56x6T!i5^-DYP9{hhJr&H{%H-VrTY&!B%0qA{RtO^f*OTCt|2kVf5-y$ zB)>Z^hed$8LoDd~Hvl@&L!d4)8UXE?(51`oVcG+rC4<5Q7FtJ8zY7Q8^~_9lkq9%C zE2{@En`1oy+8ZBf=R6fa4m~R$im=MM;OZIE4G4o-V&CFm@Q9>orB4o`{sO%9f zgt}5h+LWS&iey)otNZ(A(0YIW<$3OSJaf*wpZ9&wIq!K#(bmXB9gWmLC^q!RWg&0? z3SfHqA#`-W?GVF<>kDYY5IfL>O5;Lo05qYIxR4PO$MJp_l#hDdY-FE!2OUaUJ# z^kr93rKL;vn~@H;9F>I{$8S<3OER(ILJ!18R`1mt|NJRE!OT>ld0j`YJCw1dBe=7O zbP(4X_f>aY;$SHKV@jMz#CV1xecz2g>!xUp(5>>s>l=ht`hMKG@Z+84tNw#)r^ART z_O9Uc85ITErbZkyLy)CZqxuRA`3_K5!WoJae2QukT|VV z;pB%&%WW;u6ej|Q8g19BzC$ToV9aZY-7KAwS-ecft+;s6yX?}nh?KJ>LReXovZ{HD z@T!UjW-Vg8Y%@G7peCbbTi5NB6uej4o!9qvDn5txQj&)d6z>h1$_m0{kkMWIsRNlE?4fV`!ZG^y3I51Uf!hrp} zQ?Fy0fm4%1|2R*J@3wxGv6y_1*RB7IptyQ+_tfCa*Q2>t1~)vhVa5f2>^L<3_T}rB z^&jK9!ZYnmBVya3u=ax*WC%Zn5ig`dmGa|w9o6LBtlVG{D zsGsL~i=xys$$i&0p?jo4f;+Y^O7_r_xulpap_*{H-J-iHpB`mIvrMy1Dd#ynSrSPv ze|&Y)s#}VJq*M_xs&vsPXC?fY>->kE7^x4d$>httZ_{1#sEuo(=9a^1e<@SO|(jMP8u|KxLr zMULPuj7%8qZ+Dpt^{gl|8>N&c4wPagp2-`B8ICPh+OvFgd2CfqLn(2~tH|ZP6{?go z4nm1h_vj9Cr>XBMgW4*8o6t9Z^!611QxC*hA0u=XT&rSziP%6Z#(XwYGq5`9YW|3;P#}7wM3t- z8?aUF>9&1)y|nw?U)$-~eRaA_& zLy>-u5BMZGn=X567#MG>b97jtpzrajk8#SUWa8uYt&_#I{Jj-FCTd+T_E36yAYv;v zO-#-v%h^8Uc4goD^VK)sKJ#jf-=K%=IHSnS*%V!WF(=3LbSj&Ck(d*q-j$lhJ`LjA zJpv@wI+bp|Yb)_dp&3*Pd+|nb)mKp~g-=f>mNdUEN%$h7FS6!x-2s;dAw?G8SXtci z#nL7*X!z^BozbHyXv$Y*(dyEnd|YtOC+!~Rl`ssaOqiUkt{?7{rhx^uxM!T<;e>2vZvyY(GS(m7gT$xWfHlRZ8UZ`hr zvWBw2>qUyI{kz8r+Bka=>RzUSQ=2%wqLf_)dxp@n-CZf-BwJnCwhb~QiZ^3kWxA5I79TqHEM zP09zjF9{2qRwRrqqBxA8-@U&>Dp`_lEuG!b7_jM-)Jxx`GTAHo@UclDr*g*=D!KMY zeB}DKKX~Q**R8)%*PR=#{Wj+Q5eJ=Oym3g z=dhavfwm+c2(*GIRFWZ+2e_eNG!CT!;4vr<1dL=u3@(7>-;fB<4&pEa*<^?V-<`H> zCfOe1x`FWR3V;p}j|-C<^SGw=T=@P3(0n;CiwP5EN23K3_&NoN@En%N0r=Oj9Rdc; znZ;Kzdo9D#V7mZ;VH^Ooq*6G58-j1P9l`^EB?R(C{=mwYK6j(fauP{g5{>CIFJjJm zD~L;?z!(5M3;3=Z|FeMa%RqoOwpIXIPjAjh!K&s|+2Ijm&69J z7;rmjZj8pDKxZn2>&tONVDNlJ|J$Dci@@PDfnWb;Irz|@coE-cnwtFe;sx?&wah}a zuvj=-FnkPR7Bb7jhkfV%HWEk_Xh*@BHfPDa)tGNQe5rF-fxRdI%ZI=`eA;lW%$5OU>Gns)Ngb9Krb#o$N6aiM{z#a_-_3nVSe$tU}{aGL;oHgLwK9OyF?v> z)&lUF@Uk_~9{i%whXY_W5TF5v%-=CE6i#*$%M7CW_|8rFf#u`)tO(E?&QU7afZ;=f z02BhW=R$NRc-z1ttf(9gyc$77`Kv{ME^}gVSZ!D;9DaD`ses0yDQFH_f>xk4Xam}U zj-VGv1}Pu}3Y3E0pf|i-K`KZG86Xp6G9ZuzvLH5e+M(c zK#&K9Ky2n_fe+w{7{UT*eiVPqa{heId$Tq3k0mp_kRN?coUgGlSZz1}->PXxM-c~c zXPNZl6z>a5alK|@RvSOtc7i40Y7+8G+W|zlv4PRjxMX1Ah~KB@PZ+1g=pMyS%9Vt6 zmg|OJjXnyT%`5OXc0IdT=H{*T519py!T+Ri>U%q1^*;ODlv>3Ze6jV*bj|ck7kJjl zI$j@0I+6Fp;eu-PD0{tbShu|XXlm;Ywjad#7I4P|Las$p6MAuXscuyonMi0eap zPL!Fc5>%2`*C6#&G^2Ars7#4Zp|Ekwc6CCrrOU6Ky0J8ucS5A^iE~!?0`q@ZV_N;| zIj3BwPo$q(*)jf>l|DK6`0KT<)E4{3Atu?ZHp$6-{G@roj=kqKw1>e{3|Ul1?plN0x7yeAGPI*l(t> zsC>&ngRJE+O^4IdwyTQEd(gLoCG^xk+q>$h`eA&XrveRcq4q@Ifmviqz;6zJx+|P0 z67yN8c)gG;wO4n~OuSU@9of=`HY6+2w)BZw6>+H2TzNoiqVnylw<`6k*7s@!kF=l2 zmhO*J-JL?8n9C`zJWh!g=p)@)U_&e>iOsM7M`D~882l^WFHA{yBL3C--j7um_M}U!Sv9j>c^;zTQhGa3QVI? zMMUE6D#UI2JG&cO{dlG=(th6+H;X5a?zz)Ux5O0RTiS5!q^9bJOnlu3rScApSi|ei zr79P*hS$~n(O<1L%$qiOHdVM@?VPmW0I<$#MQh`RHn&>Yqe`qza(5dXbG+4$ z?2Nmu6GRRWYHFxGJ~?Xk@y?Y}rJciphE4g=3%Wa$Cl?33QQ3Ifv^axRChdu605^+Q zm#cn=k@}>bR`|7EyfoCiq43Jb&hBS*!7^?=`vL=%{%cSbJyoU9f3G#bJLsIONCwdNuVrZ_&T^7^( zgHngaJ{)#5<9-fa>3#Cz13lt$YmEUDiw_aj=%Dk%%%BqKBa3n`J2i+6hd7)QziI6I zPJfx)kww00wfQa!^S#1k-mny`{~`<%WnRe3zF<}GPNqBc%IMmy1zeST*G8{Bh}`)2 z?uKy4;+~oRA;!Zt5!IH!#O1vGO$)saM}D|%Q=&F7-sU*T)@t0p<_YJCkE@lZ%-^P& zUy;f7M(C8+Vqa=|*6(ymQ|q@)i%~57Q#8U@OUm?5iC4?YOru^!noO<^nLc@}$|8M* zD|T_qLASWqp%u(};xS}08He<<5Q?HhN)=4fafod%+M!ufqO0p_)MaBa|p5AKtpN z1nWdPr%YWK&}ztvGBVq1n5;i}*=~oS9B;Xqp5l?!y6=ip7j4>67c)kEnd|d;u;*j! zodMM2>7f4no@XEWQ>AzN?lr8@^H`sQ_6 zZpZ!g)c4FXR9G)6)I4g>;T&qWeE5<(y9NS_;$oUyDTR2Xt5n=PFV#L|yk*L{U zC11kAcdfmSuwHf3GD>FYo!V{j$LtzDDW#X3P{cmmgY5U$8#*&U za~qXR$6fYmpgi#%?TSyV$({tNVgqmG3TKGrY-H$I_)16mt~5=NpXxoV{Jb)}miXBr z09fRqunw7>xttO0u_gJqr*I>|QJkKHMn4?NEE_dCII0#sCHH6Ura$=Q?a%K&!As}I zN_YMZ^u0`TvD!XgqoHvqt#37&&Nd!g9{NLEzzg!BGIW&(uhl36REn;$GtLTS#Uet! zRI?B^WFKPfKo0RIYg3fB=^=Esk>H0Xq|PI;)V&1_RSp1Gy}BETcH2!h@(FkZ9-T#p zpJD)yPGfKgJY8i03jrSU!JslAAmRG!D!W+O0$e7O=1=7U7^F55t&Ya30p4u5HVx6gaPF{&hxWG623}k{2_OtE(IsNTm?G zyvW`dEj(VGLdKER(P(d!Itu=%lgK1*99avE^Y$Xmt7H9O=1=-y1gsDX`vD#i;Ab`^ zkPNYPl}&B81E#)A4tMr-2xucwIAw5d`TvzwaBTkF3vfW^+@J%~5Uk+$miKNW_@%Gs z3{e1eBS@VLIG{BN0EU1e;4lON3eW+6p@f4Evl8KkI^1CYe_;KA@&{HX+W}4qJs(CO zi^k*v8c0omMdFfuX;2VE15mSC1*~(FIv_tzKX~ZB_8Ey~W%Ymd8lBEhYd#&ph)E8l z!>>SdqyL|z`LE+lA%8QN709Lub_j(GLNthP8wUO$wxOmG$gdBsK@yNoP@m zI7~VV39&e{fuT|LW(NWh;CHd`h|JFwCVN)0JrppnLXSqJQAxk>3-EmYZ(Q)0GS^Ij z?fzZLd=Bvw>3AT xYZ#*N7(7l3Z-~<}!4dJsSS<~#-v6D#gWt~Oa7k>gAV7Gu78;?bXl!GG_#Xsy14{q^ literal 0 HcmV?d00001 diff --git a/Sparse_openmp.pdf b/Sparse_openmp.pdf new file mode 100644 index 0000000000000000000000000000000000000000..3c41967b5b042a95a7620b570c545a0a3b749ab6 GIT binary patch literal 8085 zcmb_B2{=^i``x+~qjFm)6^^a3G|sHXOpL}ZOW7il#uzgbW~NyfvfOA>_r_Irq9`|! zP?U&POIZscDmRKE5?PY}IhN|)e*f)x?wQAPzUAG%clo^Ud(?Iqo1!q%1VTQ8=8F&~rzE&W z%HNkc{JbvrP0=qVcu`r2vQmcmAHW$sC50$`XH!byl?Y&(a_v)F9GMBwvh(yV`G<;n zv#$Az+6@$6{$`e@I6n0uaJ(yZN<1~R>h926wbZ}HD%3W*yKhVBU3YDxQ>EPGkZgWU zBjMQtb*(QR*8+ma6Ub*3$45Q{28~~tP&C_IaX0crM8#`7hwYsfay78Wp>c>;8svAc zjPhAH-uLoD|M?8Eh!vaOSg$H#y?Lsx;9{Go#){r%giB%WGc>~1*s&VY%$_7{4cl}P zkAHJUR0U8^IjmnVykx|VO|#HkzPz|L8*f>!8goRJ?4NFdD9vcdrpD2{4Oh9=*s+_7 zn?eJVS^#FBSw9m+Eh0UoymszSaQ28*742r7VI=k-%rERhpw@phx1FbFmLjPNOAyZK zQ8KTu(N|qB%;`gz!z`A#9VuS83U6`#?BUwc)0+?1emPyAHY~C2)ICapL*humr-1Ik z)(P95R_}+!b+;Nc)*Miejo)M;zb-LT?r7`6Xm+gOi6tF$$Jrx>bEwRPl8G6O^=aOX zi^G4mwqvvE&;N;vvVe zHvd4`VD+7PmUh_9s&#p5b9Q9MtE#E0ouDEOE_OSBPP|$#f%{$k&9#T7 zbBi4u)=N$Y+qnFad4!#*Ht{*f#yj^^>gVmB$Z@U03)z^$L+lHy7U!H)Z9^rD zuq4+ritp|9ez5-Pp@>-ZHya;`vJacavyG`-1=K)8mjWuu%u=d>H7i)!WZ-#+dDb=4 z_ov*SO*4i=&*m#1a4WfI9zW`GuI~BU#-8f8N(ZLKit0HH@@E0rP(*KQRvdJ*L`Yq?8Ec2l7Q)fvF@6YA@T6Q*x1;IshduU?4Z={ zjrfPjA9gi!_l?y|7EK3y`ZCdTv?z33ToM>G^>XNs_Kd>Xaz+PX^wLA-(AY#$XluH| zgu(@l}!scf~sy*%3@Cry;&(KKFK-+DQ7^hR#>slxq!#Y!^R+I1rc ze|FDVB1fw(F|#lyCc~lp`jRJF&$^o`;|q3MrwFVf*bdj%xl(*f_f+;>YiN-5-W6WB zJRYa%yez&z7Lz?1Xk_S`9o+ERx8#b<(NJG1_(oy$f&-^=t+#xJn>1d6+Y&ha$Oyc? zy{%GLx#;fYSml1KLFlEFOLo$Mw?9?xx%NV7{G3Vf1B2AmMK|o&dG{uIA3S-UBftB- zZpEh)AtH_Y?`rJcxe3q*B1hUZM=jW;?5t8VU$6IxnXLy1g{RcA^E|0$?VqPomZfUg z`-8dFex28MshFCdsCgeA*P^e#DCcF*zTej=p>&iTtL29Ms`K)PYdY3r3|)M_C`JUc z6cl})c67sYUE6>Q10&T6tsUAck@X%b{H|r_y4MFkqg%Z1NnU+=tb8YNGIt~W?tvvN zXwLIc{aJPO1LJCEZS(ShMV}_sl=W3rw!MBblpOVI$I>s7q{oeqldJqm1*RLJb5tu@tw%EdN+_RWfr*e{gjC|$=(hLNIGo3qV2_uD~h(x zzLs{`rO3Sc5O)aCI63M|ip0Au2O5}Vtr+B%&63(qv7M&v!M)xpsvd`~K0PkMj8}+B z8Lo@m<`*NgRQ$*?yxz}!l5eQo8UC?M23SKOaURA8s#OF%Lr4YnGfY@zU@%E(rOMS% zl?$nj4h|DH18T42ir zW~)l`o(Y}3!Ntj=%{$)KxGr)6at;Q)l-Xf>L#tyfxZlaOWqVGV)~+)S^?WC)lVaYs zd+h+WlXy+0tTX!-etCdp=H!J!YD-d$;bT&vkGRpUXgILw+LQd6 zn)m*wR%Rt|%KX;IA4iW)b-Zupg42s9RBr8Ma6IR-0B8hf4sgBzzp-dM9x=Cu|CUua z1n?N(4jPjIS~EP^G()Z!a79Dg1T-EXV$p60Xp_(22mu_NcOXDJhJY*L(-{INBiX^{ z((M^SR}jis0MLOU7DC`AVxgJ65Xwpb3`_??G37$&7|hHBN>V^0Xbw>n0B~|+hk%ym z#DZDOCOZ%{NG@PTFaZEsvONWWD*_hV4&eqs6htt|?@(dtb9vG%rV&j@^Wie*Nz6%a z%@EQ&p&bA-OY0kN;@=5;I|c&WzQY>8P$+Xk&YWtFl^qcQK-z%79Wy(SI@x@I(1=Cj z12`;bMVlLAuo%#Z?I~mlToG6z%;?(>i-pw#{|LJ9xo3U|0zn7(=N|+yw>k&)75dv; zM+ZJL@gF>(eZ=g}EF=+&oyYzDjhN*C``7opV6JEYJBI_mb#b_PSs)xVfP?1{4t%y* z=s6l_*hft`PzKEAFagYrp+S3*hY)sb*cTwv%{$o4?ssnT6%T~XF;4{2BZtZnu)ofY z*MoO1{}lmeB1RZP-rVlZK7^&5Sd)v!VGi{4u!?& z0z@4wK*VF*;M|@m0PqNqDxkv=2rWXvL*tnCbw`2`q%IkzWtv{vNyCmI()g7nNu_n`03Vx+79k}!DzRwpS`+5 zB#~g4Q|0*fakRr~oOEqMMNQ(JnjV$x0);|Z2`~HVtjxzz`iiaXj&+HBnqg+RG!OEt zGSi`elFyCRGI9xvcd<1t2Hx=Y5tby~yjc`L5{}meH9k1lGQwJL{FF=!3Cy^0suFxTELUjaVFx-+fu@*(=JPJ)KgO zSHzBqe%>~PK`GnfP)^n9O&X;2j?L33yESS}4E6l{yCbBm&tVy!BZ;T4I{)q$@r--s zW?WI7viort>zuQ@{}eea>)v+XZoh*>%+{PtLyg5UrUCXV9aOI!I(}}a?TR&#{0!&n zGl|p)b<7A^?X2e^gX5c$PF(csQv+j|iCwyCe$|nm1A^qs?$@?*iaM;RVQE`=yXsAD zK6bo%aNt}h-3u%C$hK##-xk+JBb7Fl*ER@l_)42}lv2Za;&Q59bB&x@*Pf*PzpPJq zPA*Or>TJ?DKjywDIXTbR@4ESY`ayMS(z-h4S8K>ov#vtjeyDI1qNeV24$t*&t9Tb}1U#_SH7e&8v#*1~l^-<(xzvM+Pw?epcW8JBfqv^pGbx&8j_pUMF*DtMdDp5E}3v5v7%gp z__=0L=6VJ8$B;->>CerJro}}WyA@IdqW>vuymD) zdpYJ#jfdDug}k+x$=b$PPX%i+U@G(R}O5yp2@Z@v0oI$?|o2; zWS;)-a+3KQmz?hz*nMN|_KsaVAh;!KbB*bm+T+9eWT)x2);+=fu?|5R11#%N!fQ$Yb3w<#)3BmFHK_L*sV-mTca@nX*2h@Q&IZaFbe(#8^4 za}pt2?|djdPvYES1$=gSw=QDC&vk5Gm@%(BB5Z%6F)gKaqWEA1X_f3ys*i$r(`%){ zvsBt88~0*w*AQDxexS5WjO<2Q9LDiL){109rmb7+#qIlScAlBYSb03#uwr`6ZvBge zLa`EQuxX%fxX;cdMx>PSsz>axWnnrrgTVDtyq>+Z(s z_j5Ye+i52Ot!wD7PH&RH9^1E>C)zu%vUI;vQA<|LG1s`R$HIM+#V(7hwme)q%v-S2 z87ons_b;!b;Hs*OUu)JnG(?OMf^ zY~Ms=hWriwQ#I<;%A(=&kTfZl3N=T%J$}`}uKEj) zdr!DJ>|6_FdPe1M75VR@E!;SbTK24_y z$SNq03%^~uqKi^{;+V{%V-@fJ?7Vn__rRtz{yz1@B^hhUe5s@@h3;l4Z}`5J$fT;Y zdVN>Eh?Iz0{2m}|(`rer%zZXF^d-d`+j!HV%^p?{^eU_V60P_^qfqmocx_C}aoJLKBm8Q8 zu{F1F+wzjL7*5~1RByGc*6MXd^-W_jPithDcIP#&9bW#1{4fTk`u6FF({|?-x6$2l z*UfKWkGwK7_5SlsJ&%zZ4ud#Un(kbNQI?CV;OM2VYs*q9NKe$U-uiIYb@;&daY7hriG74CYNSb3GW z>|FS8%a`$m9aQTo#iIooW3rY<+FHb8*(ZbA4YJ<$4z?7b4&4dlZ|ZG+zq#aL^2s{K zU8_}fQb6Q|{Xpm1BW{23R!;tQYe9g@FVeT79w2Bp9R~~EbUwY{#g}`ga!g_%v%+hwTwenfz+W*gphUCUKamMV@3b`$LpQN9@e{K0f(Z`GxOCpU>}bN3$Y zz3X(cSw8nNr+D|{lTW|oriZtb-lQfd5C2wiImA_Y)B{A?7)@(?ilpDYli8o&aK+YR z;EKFebmW^Ot8RTBKNg zK3C8)T*zgH4fY>>Dpw}A@mPoSwxhk#7gRD0$c*dtK@(&TYgEL;RfwxqTRdCed#^B- z_dv=lE~402Y`&gaUoTBvwGqFJTK2J~yU-YWy+Rh{Tv^^kk*qzZBsG9IG_kLi^{aY# zexi=Gd|=bZv!zoz5~lFSCx|_Al4)>i{r7@%rnLG#6P_=+zNK)^)>iZR8-{?^`I^7! z8Hl0e(VHOzJQz$iM<4nAW*HJ-d+H;d2-aw8o)Lq^HV@=8>;r8a=z-pJk|)xDg3vRd zL6t58C8qIEUNe1h0RW}N`pQOjR;J1@fS4@y<@rLjA0YPi;RwiLedG)Z85+aOAQG4X z5qj$*ovn8OLN3?Gn=J&e+9YiZ3WM7Wc=4g!-Ji?%1~A$>NQflg(~E2emA$hBp_x9C zB^2_=An5P!ukDZ1=JJ^!hD0KPXe@}uq96#AAb=yJiBTMZ3dC$-fMkZ}K z*B4|vgBWczIL~Olj$m^+0L+-?!4(Phks=Y>lT2e^NHnY$5#>oI&`}tS7aE0z9u%J8 z<%OXW7(_flcb*;ZJ2C&p588kj;vhXhBQjLidy41`zCO}yhZSJP;tGVbvM!(p z{sR&+K7?uneHVegll&i0zk~b^mCJX4T!O;nhmg@}a z9Hbry+vz(E{o6XD@vN=?XRZ1A!fp-2k&U@@kuOvxS{VO-oaW!QvnTzlz&sJ(XC^{C z=^(?00m~+UOpSpg_N0@&xO`t4L z*l;|NeP|q}K2nVGWO&g;K0+kLo=4*g817sigX7E7X7B{FX7OQDW(P9_z;8sM5gqmv zE`OG;J!Aho1BwsZhfVtj{>(m%{}l@wd(QQ4AgO<(GVejK8~u00{zl+G_|eP~boW3m z1%AERC!4$pM*ZrAHJ-A_;>ML)jxmlsQ;&HM+53oz_x+Z3dgZJd<8%s zJ^_pl)Hi~oAFm5w(HH^*2VE31AjV{P0qTtDV6g;UEI|v6L88$}2*Lq&BK05KW1a_> zuRd?6e}*~)0yQG`G3dgtAh0c=WvWQXf)Ho?MB{6_P|Rm|K@BVn0Ri92vk#y{Am9jq z7cjSm#Sx(H5&Qt0`86UQ{lgj-2SNM;4vWG60EdQ7{UaRq2RJMq3$+9P&KFC-{(uXy zg&K(efWzzj0Efkseptid;HKU`a7jO&4YCi^0-T2v@@Y_yh!1`C20(juAk<4H0H7Tg zx_W2Y$N*@;@!|qA4J4@RWem9Lnd+bo2^gY@iHckSsGY>fo>lH8qp%rilLnyiDQy literal 0 HcmV?d00001 diff --git a/paper.tex b/paper.tex index 6c21bfa..c4f142d 100644 --- a/paper.tex +++ b/paper.tex @@ -571,18 +571,46 @@ Algorithm~\ref{alg2-cuda} shows a sketch of the Ehrlich-Aberth method using CUDA \begin{figure}[htbp] \centering - \includegraphics[angle=-90,width=0.6\textwidth]{GPU_openmp} -\caption{Execution times in seconds of the Ehrlich-Aberth method on GPUs using shared memory paradigm with OpenMP} + \includegraphics[angle=-90,width=0.5\textwidth]{Sparse_openmp} +\caption{Execution times in seconds of the Ehrlich-Aberth method for solving sparse polynomials on GPUs using shared memory paradigm with OpenMP} \label{fig:01} \end{figure} \begin{figure}[htbp] \centering - \includegraphics[angle=-90,width=0.6\textwidth]{GPU_mpi} -\caption{Execution times in seconds of the Ehrlich-Aberth method on GPUs using distributed memory paradigm with MPI} + \includegraphics[angle=-90,width=0.5\textwidth]{Sparse_mpi} +\caption{Execution times in seconds of the Ehrlich-Aberth method for solving sparse polynomials on GPUs using distributed memory paradigm with MPI} \label{fig:02} \end{figure} +\begin{figure}[htbp] +\centering + \includegraphics[angle=-90,width=0.5\textwidth]{Full_openmp} +\caption{Execution times in seconds of the Ehrlich-Aberth method for solving full polynomials on GPUs using shared memory paradigm with OpenMP} +\label{fig:03} +\end{figure} + +\begin{figure}[htbp] +\centering + \includegraphics[angle=-90,width=0.5\textwidth]{Full_mpi} +\caption{Execution times in seconds of the Ehrlich-Aberth method for full polynomials on GPUs using distributed memory paradigm with MPI} +\label{fig:04} +\end{figure} + +\begin{figure}[htbp] +\centering + \includegraphics[angle=-90,width=0.5\textwidth]{Sparse_mpivsomp} +\caption{Comparaison between MPI and OpenMP versions of the Ehrlich-Aberth method for solving sparse plynomials on GPUs} +\label{fig:05} +\end{figure} + +\begin{figure}[htbp] +\centering + \includegraphics[angle=-90,width=0.5\textwidth]{Full_mpivsomp} +\caption{Comparaison between MPI and OpenMP versions of the Ehrlich-Aberth method for solving full polynomials on GPUs} +\label{fig:06} +\end{figure} + % An example of a floating figure using the graphicx package. % Note that \label must occur AFTER (or within) \caption. % For figures, \caption should occur after the \includegraphics. -- 2.39.5