From e6206cbc48d80bf6ff86c59ba812f861c2b1cb17 Mon Sep 17 00:00:00 2001 From: Kahina Date: Fri, 30 Oct 2015 17:49:18 +0100 Subject: [PATCH 1/1] MAJ --- figures/EA_DK.pdf | Bin 8559 -> 8590 bytes figures/EA_DK.plot | 7 +++- figures/EA_DK.txt | 30 +++++++------- paper.tex | 95 +++++++++++++++++---------------------------- 4 files changed, 56 insertions(+), 76 deletions(-) diff --git a/figures/EA_DK.pdf b/figures/EA_DK.pdf index f992927f22752539856d3fbcaddb9c5f08199899..2bfe0281810c4546f86934142798541ded15de17 100644 GIT binary patch delta 2411 zcma)(c|6qX9>*C=H8?3U3~91gCi9zp#&C)mk?o2xX0i>&HeoPPp|PA>F3j@8|n`p68jeI%9qA=z6#I z*?}QQzaQQ5S}=>cw*uHlIka!L2k;yJe;S73PjxUU};+m z{GU!995E(*x?-2;R9cBRxnyEtMDf|ePlGWjxop(G!K{%JP5ZKT5~9YzqS$9Gy^Eo# zo!42&%#24K-{o2wKTwk*kh_GQ%GngTc4T73@t-*k$IZa;0tTbbprDO6RNbV^uNb0H z3f?zCKpShR6A80m6Ft=muGfw*9sdcZ8$qVxyV*}{& z2>0rUQ}H;2V@r%oIIX3_ST4{diA5EVL584^H~|}kQ}SU3_}RvFa=Vw#3(7!H-hcw~ zrtI>Qv94O5h-Qo9-=2M%ojaTFz5B(-I4z%tBs1yn41;S=y%{4L?Ey}i&30;)a*mK( z)6uI>^U_UduuI{mZf?5U8!$?WAI*yGC&K<%U#<9IkUJ~AVshA{^WqsCZelB1mOgp< zty`D-b9!=bq}sucUB$a;XS8>O)bdQHV61-_c<2pONJz8QSit1XOQY!bx}N(jQJHzF z`J>w@%_o)f>>I*6Yv<~FJ^R&n`pk^18`w9;F1zo{g|}`bYV$a4>FFJ$#)(ZLYE@Y) zgexC+C3$Jq^*RmVGeDdvP+`I;VEWm2B%^Cfe&qV$T(86k^{`vhl+ztWy!O&kRlhcJ}M=K2@9NjKhQMAExW z6aze^sPp6dsm+jT_x6SM>;OpJ7u($HlX_`0rK6f3<422riEILl`!|SaeVGR4N#hpm zuMA7EYtEuh5%d9VHfP)kO`p?JhzK%pK77Sx@_DLW5V_98+~p%Ly=VJn=~WU27kci9 zFhHkPRT|iVM_;&IbD?m`)ES;0>vU;sFxrFfux}lay|FS--#H;hn@C!`bYhss0XZ(K zh?*#KT5!{|@lMtIouX*|VHYn~>1I`q(0i*s&)B}OXmHiI=qMZd(}8cA@?zC5QC5ITGv2kk?*NUh4Gk6N+E+vy314M#~!yg&Y~# z=BGK;UcN`mbH{I_Jz8GuvJw4AQT4zRwas7mn-gIN#u@AcUUBmY_RC)zmfYRvx*Cfm zj}FaOca<-VSu_hJrVFBm;u`d)Tg6j1qxADq;p-Nk?3HrAy%^%`#ifjrcaq=f0Z1$B?sbat}-0O+!pY*&CJ|=pVCDeQ`z-se9Ep zzmdn!3GPXe$U~DfOwl!Rkqa}Kb@o%aPrVKfU#I0u+Ri5DxG0{ZmwEJgL_Zc&TCzR} zb=BODO*MdncX`iG(;d+7T0=pn_b6#V;}B{`Cz-uBzS~aa)0DO<@Vyh<1&ARQ8Mw-< z_8s%J3#ltypMR&m=;34z?IMtNV%4Xip%dxI#Lm!G(59HN7Jfqg=mVngG{n3S;(RZI z>m#&-E+cO^z^WPL((i$H7qy?py;l1!_e*1fkQE*f&5dF)!@w(DgkLBa3q!zGSAc*6 zZqKi?-E6?b;Q@p{5CHeXp^dUD+R}3acC?H5ypm<$A|zjlglz86ITTQfkFT{G#-N%*lbI) z#IL;VYQe%`;J+FKj<7Q0ZyFMb#I4Z~IIQ3&m=O=NW&{$20oLGX404S|K>wG$gtZ(R zxkf{wfPZQF|B)TJa;?7~f<@u60x8VGlY+HI?L{FFSPYgxwn158@B|wK7Hy3NuvRu0 jyd}x{{}EnbOG|Jxml?%962%Gx;{g;7Y-mVvwgLYM2?*{< delta 2350 zcma)&YdDmP7RNP=G&qT{3wdMQj)wPr=S~RY7P2vJ<9->rY-3`O*o{l2Fv3LSnqA}` zv!{-u#&i?8H5Dp~5``U-OOiTu&T~GT-8s)`eOc@IuiyGVYpop1d5hdcsgTaaIyg8H zpOt>*Db5+!M;p5?t$W{;%Rt*_qtD7PXu%1ZYxBl;-GDvt>7d{!4?jx#)& zJ$S}Ki+G(%jK-&zL}LF9o}D-$usQoza?A{>DPdSBT8lW*01)FDY6ppB&4*k&6o~H4N=Kl8m$d|@iu#&Zz_}3GUj1*@vT4^ zvGuCk?5~R`T@ASwY1^*Vp!l1MT9~33o;0(+KgEk0@Wd@3Zyvb<&56z;Nj{raM`eqw zkcGZTr8UO*xfP~Zj?K87y=%a>P1(L;mI7tchimKN%)cX=;>38Dgst^LjWOBM9z~`p z!e*=vktG%IhbiKx#b-k5l{qn=rj%Gi$=)hNPZJ_5*^rqXH@|uOh(tAafDqy(0mk#A zPbL#VM`64e!$a7uBOdCUO84MW5L$@o!`w&&QCdAPB*-?Ymo@M)m)nTg$u>g5HJjES zPWN5)kM1xz`gwR|@%`xvKZB8_q#e;+dku%4)6nN1`Ozkn?IC8P^=`M{Ws9pRSGq-- z9=^MNy=Ir5bxK~)E()16O`gn1cwz*+mf}m!jk4YkmFvcN_7*e|iL+|BOZUN#i+;yq}q+* zno7a7{Yz3)_BJ{K7SM3fcK57e*BYE5&p2*gU4q9HYQYr`%q=q7si)$rmH-T zpa%=;1cnif*{d9=TQ6oUk6=Z%+CJgc1HIX}S9k1C2c$#Z(&X`=5UrCsV-mSRGwrGC zP0pcmUh1zo#Oa)CSj$ekYMk#@mayIUKvkETv%x*P?bkKgEU6m2ZvB+Cto*>4>Z>Oyh9Nd~`*#j5130Fi{&8Q#eK$?g%HOh=kZ*wg5RX>VMG z=;mVAYij)~bOL_Jz1wc~ke+e5qGOi2z0ur@verw#pni_cUAzl;o)|x?P$xLpWahtY zIWqOI-M^xo?N@OiNx!W9{D_)!nss{D+of%j)2_cb=zWw|bIqJA(L0`q##~V@aj|nz z#5ggwsWlKwT-rE#Rs#X9_uA9+zpzhR9}`wf%<&(Fb(-B)f6j4EL3g<1FivZ<4bjYO zXg-nrV4Vx^_(Mlxjt+XXGmb9jH8v}q+2Fey*Cc$#v&ZxH3to9VT76iX=W^RKJy~$j zv9@DlV^we9EV^J8TkBI{hnGy6E~HZ93#oD1ZnFLPb=|M>FU(x`c1heRu33NWQw zOP#`V)!3>}?$<6;H6P8Gq}>WSWv2T8?XcswXf20iEEjxHUhS@?B!1hNQY3fT%lSiR zmaOgQ7u8(%OKy@Ewl&v@$ArBAWpU3Vc>BU~k;h#dshaHk!}NT!sLiEWT;Xo4GDfvJ zwbMIFNlLc0l9@AXK82o8hHD&awiIJE9-rxz#jyVcXdgp*>1ir^tVo|C)7(krIbW6m6u9myVYn`Mj$=sK#ZTTOOhBxirH&2fTsqiNW=X_IC@4 zD+kV4HJgm|jFC8V5&E>{JLPvAaBprzAUOM^m3EG#?p;6JQ+{#P@nb_HQ&c|?@se$G zqgPkFtHFIwcthLkhx#L z>+A=l}s2D_ZI*opl0eG~_ z`>cJ9n64F!w%VNViRuF#jyf-Fj~I|1qB*g}&f2*&jOQ#n?%5}`Hzw~+ec9wK6H-NI zgv7F9=z&qFuT^wV1d0HFz_$#MaUgHIl&w6Pj13|XLWAj;AY34bfuK+j1AYw*9R~%` zaiMT9K9Iys*%|d?;5HRwMaO6cfN=`OumCDdFajVWf)R-42C8WPk4~vd%8!}vQ?>Xp zux}^uLm+QP)fR#Mwy#q#3xEj#^leomED3-?2(O1Sbc_z61hVM56r*nf1j0m+3}bO1 zm#&^^ipK-rJ_P~{0QJuTB$CMFKWi{V{`&O) \Delta z_{max}$ }{ $\Delta z_{max}$=c\;} } } @@ -514,51 +513,26 @@ In this sequential algorithm, one CPU thread executes all the steps. Let us loo There exists two ways to execute the iterative function that we call a Jacobi one and a Gauss-Seidel one. With the Jacobi iteration, at iteration $k+1$ we need all the previous values $z^{(k)}_{i}$ to compute the new values $z^{(k+1)}_{i}$, that is : \begin{equation} -z^{k+1}_{i}=\frac{p(z^{k}_{i})}{p'(z^{k}_{i})-p(z^{k}_{i})\sum^{n}_{j=1 j\neq i}\frac{1}{z^{k}_{i}-z^{k}_{j}}}, i=1,...,n. +EAJ: z^{k+1}_{i}=\frac{p(z^{k}_{i})}{p'(z^{k}_{i})-p(z^{k}_{i})\sum^{n}_{j=1 j\neq i}\frac{1}{z^{k}_{i}-z^{k}_{j}}}, i=1,...,n. \end{equation} With the Gauss-Seidel iteration, we have: \begin{equation} \label{eq:Aberth-H-GS} -z^{k+1}_{i}=\frac{p(z^{k}_{i})}{p'(z^{k}_{i})-p(z^{k}_{i})(\sum^{i-1}_{j=1}\frac{1}{z^{k}_{i}-z^{k+1}_{j}}+\sum^{n}_{j=i+1}\frac{1}{z^{k}_{i}-z^{k}_{j}})}, i=1,...,n. +EAGS: z^{k+1}_{i}=\frac{p(z^{k}_{i})}{p'(z^{k}_{i})-p(z^{k}_{i})(\sum^{i-1}_{j=1}\frac{1}{z^{k}_{i}-z^{k+1}_{j}}+\sum^{n}_{j=i+1}\frac{1}{z^{k}_{i}-z^{k}_{j}})}, i=1,...,n. \end{equation} %%Here a finiched my revision %% -Using Equation.~\ref{eq:Aberth-H-GS} for the update sub-step of $H(i,z^{k+1})$, we expect the Gauss-Seidel iteration to converge more quickly because, just as its ancestor (for solving linear systems of equations), it uses the most fresh computed roots $z^{k+1}_{i}$. +Using Equation.~\ref{eq:Aberth-H-GS} to update the vector solution \textit{Z}, we expect the Gauss-Seidel iteration to converge more quickly because, just as its ancestor (for solving linear systems of equations), it uses the most fresh computed roots $z^{k+1}_{i}$. The $4^{th}$ step of the algorithm checks the convergence condition using Equation.~\ref{eq:Aberth-Conv-Cond}. Both steps 3 and 4 use 1 thread to compute all the $n$ roots on CPU, which is very harmful for performance in case of the large degree polynomials. -\paragraph{The execution time} -Let $T_{i}(n)$ be the time to compute one new root value at step 3, $T_{i}$ depends on the polynomial's degree $n$. When $n$ increase $T_{i}(n)$ increases too. We need $n.T_{i}(n)$ to compute all the new values in one iteration at step 3. - -Let $T_{j}$ be the time needed to check the convergence of one root value at the step 4, so we need $n.T_{j}$ to compute global convergence condition in each iteration at step 4. - -Thus, the execution time for both steps 3 and 4 is: -\begin{equation} -T_{iter}=n(T_{i}(n)+T_{j})+O(n). -\end{equation} -Let $K$ be the number of iterations necessary to compute all the roots, so the total execution time $T$ can be given as: - -\begin{equation} -\label{eq:T-global} -T=\left[n\left(T_{i}(n)+T_{j}\right)+O(n)\right].K -\end{equation} -The execution time increases with the increasing of the polynomial degree, which justifies to parallelize these steps in order to reduce the global execution time. In the following, we explain how we did parallelize these steps on a GPU architecture using the CUDA platform. -\subsubsection{A Parallel implementation with CUDA } +\subsection{A Parallel implementation with CUDA } On the CPU, both steps 3 and 4 contain the loop \verb=for= and a single thread executes all the instructions in the loop $n$ times. In this subsection, we explain how the GPU architecture can compute this loop and reduce the execution time. In the GPU, the schduler assigns the execution of this loop to a group of threads organised as a grid of blocks with block containing a number of threads. All threads within a block are executed concurrently in parallel. The instructions run on the GPU are grouped in special function called kernels. It's up to the programmer, to describe the execution context, that is the size of the Grid, the number of blocks and the number of threads per block upon the call of a given kernel, according to a special syntax defined by CUDA. -Let N be the number of threads executed in parallel, Equation.~\ref{eq:T-global} becomes then : - -\begin{equation} -T=\left[\frac{n}{N}\left(T_{i}(n)+T_{j}\right)+O(n)\right].K. -\end{equation} - -In theory, total execution time $T$ on GPU is speed up $N$ times as $T$ on CPU. We will see at what extent this is true in the experimental study hereafter. -~\\ -~\\ -In CUDA programming, all the instructions of the \verb=for= loop are executed by the GPU as a kernel. A kernel is a function written in CUDA and defined by the \verb=__global__= qualifier added before a usual ``C`` function, which instructs the compiler to generate appropriate code to pass it to the CUDA runtime in order to be executed on the GPU. +In CUDA programming, all the instructions of the \verb=for= loop are executed by the GPU as a kernel. A kernel is a function written in CUDA and defined by the \verb=__global__= qualifier added before a usual \verb=C= function, which instructs the compiler to generate appropriate code to pass it to the CUDA runtime in order to be executed on the GPU. Algorithm~\ref{alg2-cuda} shows a sketch of the Aberth algorithm usind CUDA. @@ -594,7 +568,7 @@ The second kernel executes the iterative function $H$ and updates $z^{k}$, accor \begin{algorithm}[H] \label{alg3-update} %\LinesNumbered -\caption{A global Algorithm for the iterative function} +\caption{Kernel update} \eIf{$(\left|Z^{(k)}\right|<= R)$}{ $kernel\_update(d\_z^{k})$\;} @@ -614,15 +588,15 @@ or from GPU memory to CPU memory \verb=(cudaMemcpyDeviceToHost))=. %%HIER END MY REVISIONS (SIDER) \section{Experimental study} \label{sec6} -\subsection{Definition of the used polynomials } +%\subsection{Definition of the used polynomials } We study two categories of polynomials : the sparse polynomials and the full polynomials. -\paragraph{A sparse polynomial}: is a polynomial for which only some coefficients are not null. We use in the following polonymial for which the roots are distributed on 2 distinct circles : +\paragraph{A sparse polynomial}:is a polynomial for which only some coefficients are not null. We use in the following polynomial for which the roots are distributed on 2 distinct circles : \begin{equation} \forall \alpha_{1} \alpha_{2} \in C,\forall n_{1},n_{2} \in N^{*}; P(z)= (z^{n_{1}}-\alpha_{1})(z^{n_{2}}-\alpha_{2}) \end{equation} -\paragraph{A full polynomial} is in contrast, a polynomial for which all the coefficients are not null. the second form used to obtain a full polynomial is: +\paragraph{A full polynomial}:is in contrast, a polynomial for which all the coefficients are not null. the second form used to obtain a full polynomial is: %%\begin{equation} %%\forall \alpha_{i} \in C,\forall n_{i}\in N^{*}; P(z)= \sum^{n}_{i=1}(z^{n^{i}}.a_{i}) %%\end{equation} @@ -632,7 +606,7 @@ We study two categories of polynomials : the sparse polynomials and the full pol \end{equation} With this form, we can have until \textit{n} non zero terms whereas the sparse ones have just two non zero terms. -\subsection{The study condition} +%\subsection{The study condition} The our experiences results concern two parameters which are the polynomial degree and the execution time of our program to converge on the solution. The polynomial degree allows us @@ -643,13 +617,13 @@ element-key which justifies our work of parallelization. E5620@2.40GHz and a GPU K40 (with 6 Go of ram). -\subsection{Comparative study} +%\subsection{Comparative study} In this section, we discuss the performance Ehrlich-Aberth method of root finding polynomials implemented on CPUs and on GPUs. We performed a set of experiments on the sequential and the parallel algorithms, for both sparse and full polynomials and different sizes. We took into account the execution time, the polynomial size and the number of threads per block performed by sum or each experiment on CPUs and on GPUs. All experimental results obtained from the simulations are made in double precision data, for a convergence tolerance of the methods set to $10^{-7}$. Since we were more interested in the comparison of the performance behaviors of Ehrlich-Aberth and Durand-Kerner methods on CPUs versus on GPUs. The initialization values of the vector solution of the Ehrlich-Aberth method are given in section 2.2. -\subsubsection{The execution time in seconds of Ehrlich-Aberth algorithm on CPU OpenMP (1 core, 4 cores) vs. on a Tesla GPU} +\subsection{The execution time in seconds of Ehrlich-Aberth algorithm on CPU OpenMP (1 core, 4 cores) vs. on a Tesla GPU} %\begin{figure}[H] @@ -670,7 +644,7 @@ We report respectively the execution time of the Ehrlich-Aberth method implement %We notice that the convergence precision is a round $10^{-7}$ for the both implementation on CPU and GPU. Consequently, we can conclude that Ehrlich-Aberth on GPU are faster and accurately then CPU implementation. -\subsubsection{Influence of the number of threads on the execution times of different polynomials (sparse and full)} +\subsection{Influence of the number of threads on the execution times of different polynomials (sparse and full)} To optimize the performances of an algorithm on a GPU, it is necessary to maximize the use of cores GPU (maximize the number of threads executed in parallel) and to optimize the use of the various memoirs GPU. In fact, it is interesting to see the influence of the number of threads per block on the execution time of Ehrlich-Aberth algorithm. For that, we notice that the maximum number of threads per block for the Nvidia Tesla K40 GPU is 1024, so we varied the number of threads per block from 8 to 1024. We took into account the execution time for both sparse and full of 10 different polynomials of size 50000 and 10 different polynomials of size 500000 degrees. @@ -683,7 +657,7 @@ For that, we notice that the maximum number of threads per block for the Nvidia The figure 2 show that, the best execution time for both sparse and full polynomial are given when the threads number varies between 64 and 256 threads per bloc. We notice that with small polynomials the best number of threads per block is 64, Whereas, the large polynomials the best number of threads per block is 256. However,In the following experiments we specify that the number of thread by block is 256. -\subsubsection{The impact of exp-log solution to compute very high degrees of polynomial} +\subsection{The impact of exp-log solution to compute very high degrees of polynomial} In this experiment we report the performance of log.exp solution describe in ~\ref{sec2} to compute very high degrees polynomials. \begin{figure}[H] @@ -708,7 +682,7 @@ in fact, when the modulus of the roots are up than \textit{R} given in ~\ref{R}, %we report the performances of the exp.log for the Ehrlich-Aberth algorithm for solving very high degree of polynomial. -\subsubsection{A comparative study between Ehrlich-Aberth algorithm and Durand-kerner algorithm} +\subsection{A comparative study between Ehrlich-Aberth algorithm and Durand-kerner algorithm} In this part, we are interesting to compare the simultaneous methods, Ehrlich-Aberth and Durand-Kerner in parallel computer using GPU. We took into account the execution time, the number of iteration and the polynomial's size. for the both sparse and full polynomials. \begin{figure}[H] @@ -735,6 +709,7 @@ This figure show the execution time of the both algorithm EA and DK with sparse \section{Conclusion and perspective} + \label{sec7} \bibliography{mybibfile} -- 2.39.5