From: couturie Date: Sun, 5 May 2013 15:54:18 +0000 (+0200) Subject: correct X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/book_gpu.git/commitdiff_plain/8db670a863cf32ab3e5fbd99ecc161d6317c763f correct --- diff --git a/BookGPU/BookGPU.tex b/BookGPU/BookGPU.tex index 77937b8..1ca9c1a 100755 --- a/BookGPU/BookGPU.tex +++ b/BookGPU/BookGPU.tex @@ -147,7 +147,7 @@ \makeindex -%\includeonly{Chapters/chapter19/ch19} +%\includeonly{Chapters/chapter15/ch15} \begin{document} @@ -189,7 +189,7 @@ \part{Optimization} \include{Chapters/chapter8/ch8} \include{Chapters/chapter9/ch9} -\include{Chapters/chapter10/ch10} +\include{Chapters/chapter10/ch10} %revoir ce chapitre \part{Numerical applications} \include{Chapters/chapter7/ch7} diff --git a/BookGPU/Chapters/chapter11/biblio11.bib b/BookGPU/Chapters/chapter11/biblio11.bib index a39c5ce..c6d75ac 100644 --- a/BookGPU/Chapters/chapter11/biblio11.bib +++ b/BookGPU/Chapters/chapter11/biblio11.bib @@ -17,7 +17,7 @@ } @article{tridiag_GPU, - author = {G\"ddeke , D. and Strzodka, R.}, + author = {G\"oddeke , D. and Strzodka, R.}, title = {Cyclic Reduction Tridiagonal Solvers on {GPU}s Applied to Mixed Precision Multigrid}, journal = { IEEE Transactions on Parallel and Distributed Systems}, volume = {22}, @@ -56,7 +56,7 @@ } @inproceedings{Abbas2011, - author = {Abbas, M. and Majid, A.A. and Awang, M.N.H. and Ali, J.M.}, + author = {Abbas, M. and Majid, A. A. and Awang, M. N. H. and Ali, J. M.}, title = {Monotonicity Preserving Interpolation using Rational Spline}, booktitle = {International MultiConference of Engineers and Computer Scientists (IMECS '11)}, address = {Hong Kong}, @@ -66,7 +66,7 @@ } @article{abel1826, - author = {Abel, N.H.}, + author = {Abel, N. H.}, title = {Untersuchungen der Funktionen zweier unabh\"angigen ver\"anderlichen Gr\"ossen $x$ und $y$ wie $f(x, y)$, welche die Eigenschaft haben, dass $f(z, f(x, y))$ eine symmetrische Funktion von $x, y$ und $z$ ist.}, journal = {J. Reine Angew. Math.}, volume = {1}, @@ -143,7 +143,7 @@ year = {1984} } - author = {Adams, M.J.}, + author = {Adams, M. J.}, title = {Chemometrics in Analytical Spectroscopy}, publisher = {Royal Society of Chemistry}, address = {London}, @@ -2557,7 +2557,7 @@ Contents(R)/Clinical Medicine. } @article{Bellman1973, - author = {Bellman, R.E. and Giertz, M.}, + author = {Bellman, R. E. and Giertz, M.}, title = {On the analytic formalism of the theory of fuzzy sets}, journal = {Inform. Sci.}, volume = {5}, @@ -2566,7 +2566,7 @@ Contents(R)/Clinical Medicine. } @article{Bellman1970_MS, - author = {Bellman, R.E. and Zadeh, L.}, + author = {Bellman, R. E. and Zadeh, L.}, title = {Decisionmaking in a fuzzy environment}, journal = {Management Science}, volume = {17}, @@ -2894,7 +2894,7 @@ constraint}, } @article{Blum1973, - author = {Blum, M. and Floyd, R.W. and Watt, V. and Rive, R.L. and Tarjan, R.E.}, + author = {Blum, M. and Floyd, R. W. and Watt, V. and Rive, R. L. and Tarjan, R. E.}, title = {Time Bounds for Selection}, journal = {Journal of Computer and System Sciences}, volume = {7}, @@ -3524,7 +3524,7 @@ Royal Australian Chemical Institute; RACI}, } @article{Carlson1985_SIAM, - author = {Carlson, R.E. and Fritsch, F.N.}, + author = {Carlson, R. E. and Fritsch, F. N.}, title = {Monotone piecewise bicubic interpolation}, journal = {SIAM J. Numer. Anal.}, volume = {22}, @@ -6672,7 +6672,7 @@ Schrödinger equation}, } @article{Fritsch1980, - author = {Fritsch, F.N. and Carlson, R.E.}, + author = {Fritsch, F. N. and Carlson, R. E.}, title = {Monotone pieceuiuse cubic interpolation}, journal = {SIAM J. Numer. Anal.}, volume = {17 }, @@ -7443,7 +7443,7 @@ Genetic algorithms.}, } @article{Gregory1982, - author = {Gregory, J.A. and Delbourgo, R.}, + author = {Gregory, J. A. and Delbourgo, R.}, title = {Piecewise rational quadratic interpolation to monotonic data}, journal = {IMA Journal of Numerical Analysis}, volume = {2}, @@ -9120,7 +9120,7 @@ review}, } @article{Jupp_1978, - author = {Jupp, D.L.B.}, + author = {Jupp, D. L. B.}, title = {Approximation to data by splines with free knots}, journal = {SIAM J. Numer. Anal.}, volume = {15 }, @@ -9302,7 +9302,7 @@ ELECTR STRUCT and LASER, POB 1527, GR-71110 IRAKLION.}, } @article{Kearsley_2006, - author = {Kearsley, A.J.}, + author = {Kearsley, A. J.}, title = {Projections Onto Order Simplexes and Isotonic Regression}, journal = {J. Res. Natl. Inst. Stand. Technol.}, volume = {111}, @@ -9311,7 +9311,7 @@ ELECTR STRUCT and LASER, POB 1527, GR-71110 IRAKLION.}, } @article{Kelley1960_siam, - author = {Kelley, J.E.}, + author = {Kelley, J. E.}, title = {The cutting-plane method for solving convex programs}, journal = {J. of SIAM}, volume = {8}, @@ -10825,7 +10825,7 @@ PRINCETON, NJ 08544, USA.}, } @article{Lyche1973, - author = {Lyche, T. and Schumaker, L.L.}, + author = {Lyche, T. and Schumaker, L. L.}, title = {Computation of smoothing and interpolating naturel splines via local bases}, journal = {SIAM J. Numer. Anal.}, volume = {10}, @@ -11342,7 +11342,7 @@ undergraduate text}, } @article{McAllister1981_ACM, - author = {McAllister, D.F. and Roulier, J.A.}, + author = {McAllister, D. F. and Roulier, J. A.}, title = {An algorithm for computing a shape-preserving oscillatory quadratic spline}, journal = {ACM Trans. Math. Software }, volume = {7}, @@ -13486,7 +13486,7 @@ IRAKLION, GREECE.}, } @book{Robertson_book, - author = {Robertson, T. and Wright, F.T. and Dykstra, R.L.}, + author = {Robertson, T. and Wright, F. T. and Dykstra, R. L.}, title = {Order Restricted Statistical Inference}, publisher = {Wiley}, address = {Chichester ; New York}, @@ -14261,7 +14261,7 @@ Reprint available from: Schoen F UNIV FLORENCE FLORENCE ITALY}, } @book{Schumaker1981_book, - author = {Schumaker, L.L.}, + author = {Schumaker, L. L.}, title = {Spline functions: Basic theory}, publisher = {Wiley}, address = {New York}, @@ -14269,7 +14269,7 @@ Reprint available from: Schoen F UNIV FLORENCE FLORENCE ITALY}, } @article{Schumaker1983, - author = {Schumaker, L.L.}, + author = {Schumaker, L. L.}, title = {On Shape Preserving Quadratic Spline Interpolation}, journal = {SIAM Journal on Numerical Analysis}, volume = {20}, @@ -14298,7 +14298,7 @@ Princeton, NJ 08544, USA, .}, } @article{Sch, - author = {Schweikert, D.G.}, + author = {Schweikert, D. G.}, title = {An interpolation curve using a spline in tension}, journal = {J. Math. Phys. }, volume = {45}, @@ -14307,7 +14307,7 @@ Princeton, NJ 08544, USA, .}, } @article{Schweikert1966, - author = {Schweikert, D.G.}, + author = {Schweikert, D. G.}, title = {An interpolation curve using a spline in tension}, journal = {J. Math. Phys.}, volume = {45}, @@ -15640,7 +15640,7 @@ United States}, year = {2000} } - author = {Warren, J. and Noone, J. and Smith, B. and Ruffin, R. and Frith, P. and van der Zwaag, B. and Beliakov, G. and Frankel, H.}, + author = {Warren, J. and Noone, J. and Smith, B. and Ruffin, R. and Frith, P. and Van der Zwaag, B. and Beliakov, G. and Frankel, H.}, title = {Automated Attention Flags in Chronic Disease Care Planning}, journal = {Ausralian Medical Journal}, volume = {175}, diff --git a/BookGPU/Chapters/chapter11/code3.cu b/BookGPU/Chapters/chapter11/code3.cu index 37d8409..5da77e6 100644 --- a/BookGPU/Chapters/chapter11/code3.cu +++ b/BookGPU/Chapters/chapter11/code3.cu @@ -11,8 +11,9 @@ __device__ void Bisection_device(T z, T* t, int mi,int ma,int* l) *l = mi-1; } -/* Kernel to evaluates monotone spline for a sequence of query points residing in the array z of size m -*/ +// Kernel to evaluate monotone spline for a sequence of query points +// residing in the array z of size m + template __global__ void d_MonSplineValue(Tx* z, int K, double* t, double * alpha, double * beta, double * gamma, int T, Ty *value) { diff --git a/BookGPU/Chapters/chapter14/biblio14.bib b/BookGPU/Chapters/chapter14/biblio14.bib index b5e4141..ec060bc 100644 --- a/BookGPU/Chapters/chapter14/biblio14.bib +++ b/BookGPU/Chapters/chapter14/biblio14.bib @@ -16,7 +16,7 @@ } @Article{aidun2010, - author = { Aidun, C.K. and Clausen, J.R.}, + author = { Aidun, C. K. and Clausen, J. R.}, title = {Lattice Boltzmann method for complex flows}, journal = {Ann. Rev. Fluid Mech.}, year = {2010}, @@ -35,7 +35,7 @@ } @Article{wei2004, - author = {Wei, X. and Li, W. and M\"uller, K. and Kaufman, A.E.}, + author = {Wei, X. and Li, W. and M\"uller, K. and Kaufman, A. E.}, title = {The lattice Boltzmann method for simulating gaseous phenomena}, journal = {IEEE Transactions on Visualization and Computer Graphics}, year = {2004}, @@ -83,7 +83,7 @@ @Article{myre2011, - author = { Myre, J. and Walsh, S.D.C. and Lilja, D. and Saar, M.O.}, + author = { Myre, J. and Walsh, S. D. C. and Lilja, D. and Saar, M. O.}, title = {Performance analysis of single-phase, multiphase, and multicomponent lattice Boltzmann fluid flow simulations on GPU clusters}, journal = {Concurrency Computat.: Pract. Exper.}, year = {2011}, @@ -102,7 +102,7 @@ } @Article{bernaschi2010, - author = {Bernaschi, M. and Fatica, M. and Melchionna, S. and Succi, S; and Kaxiras, E.}, + author = {Bernaschi, M. and Fatica, M. and Melchionna, S. and Succi, S. and Kaxiras, E.}, title = {A flexible high-performance lattice Boltzmann GPU code for the simulations of fluid flow in complex geometries}, journal = {Concurrency Computat.: Pract. Exper.}, @@ -170,7 +170,7 @@ lattice Boltzmann method on GPU cluster}, } @Article{walshsaar2012, - author = {Walsh, S.D.C. and Saar, M.O.}, + author = {Walsh, S. D. C. and Saar, M. O.}, title = {Developing extensible lattice Boltzmann simulators for general-purpose graphics-processing units}, journal = {Comm. Comput. Phys.}, year = {2013}, @@ -203,7 +203,7 @@ hierarchical and distributed auto-tuning}, @Article{ladd1994, - author = {Ladd, A.J.C.}, + author = {Ladd, A. J. C.}, title = {Numerical simulations of particle suspensions via a discretized Boltzmann equation. Part 1. Theoretical foundation and Part II. Numerical results}, journal = {J. Fluid Mech.}, year = {1994}, @@ -214,7 +214,7 @@ hierarchical and distributed auto-tuning}, @Article{nguyen2002, - author = {Nguyen, N.-Q. and Ladd, A.J.C.}, + author = {Nguyen, N.-Q. and Ladd, A. J. C.}, title = {Lubrication corrections for lattice Boltzmann simulations of particle suspensions}, journal = {Phys. Rev. E}, year = {2002}, @@ -223,7 +223,7 @@ hierarchical and distributed auto-tuning}, } @Article{ch14:immersed1, - author = {Peskin, C.S.}, + author = {Peskin, C. S.}, title = {Flow patterns around heart valves; a numerical method}, journal = {J. Comp. Phys.}, year = {1972}, @@ -233,7 +233,7 @@ hierarchical and distributed auto-tuning}, } @Article{ch14:immersed2, - author = {Peskin, C.S.}, + author = {Peskin, C. S.}, title = {The immersed boundary method}, journal = {Acta Nummerica}, year = {2002}, @@ -243,7 +243,7 @@ hierarchical and distributed auto-tuning}, } @Article{ch14:immersed-lb, - author = {Feng, Z.-G. and Michaelides, E.E}, + author = {Feng, Z.-G. and Michaelides, E. E}, title = {The immersed boundary-lattice Boltzmann method for solving fluid-particles interaction problem}, journal = {J. Comp. Phys.}, diff --git a/BookGPU/Chapters/chapter15/biblio.bib b/BookGPU/Chapters/chapter15/biblio.bib index d0bb53f..8cb390d 100644 --- a/BookGPU/Chapters/chapter15/biblio.bib +++ b/BookGPU/Chapters/chapter15/biblio.bib @@ -1,5 +1,5 @@ @Inproceedings{PF_PDSEC2011, - author ={P. Fortin and R. Habel and F.~J\'ez\'equel and J.-L. Lamotte and N.S. Scott}, + author ={P. Fortin and R. Habel and F.~J\'ez\'equel and J.-L. Lamotte and N. S. Scott}, title = {Deployment on GPUs of an application in computational atomic physics}, booktitle = {{12th IEEE International Workshop on Parallel and Distributed Scientific and Engineering Computing (PDSEC) in conjunction with the 25th International Parallel and Distributed Processing Symposium (IPDPS)}}, @@ -10,7 +10,7 @@ year = 2011} @article{Burke_1987, -author={P.G. Burke and C.J. Noble and M.P. Scott}, +author={P. G. Burke and C. J. Noble and M. P. Scott}, title={{R-matrix theory of electron scattering at intermediate energies}}, journal={Proceedings of the Royal Society of London A}, volume=410, @@ -20,7 +20,7 @@ pages={287--310} % %Proc. Roy. Soc. A } @Article{2DRMP, -author ={N.S. Scott and M.P. Scott and P.G. Burke and T. Stitt and V. Faro-Maza and C. Denis and A. Maniopoulou}, +author ={N. S. Scott and M. P. Scott and P. G. Burke and T. Stitt and V. Faro-Maza and C. Denis and A. Maniopoulou}, title ={{2DRMP: A~suite of two-dimensional R-matrix propagation codes}}, journal ={Computer Physics Communications}, volume={180}, @@ -30,7 +30,7 @@ pages={2424--2449} %note={ISSN: {0010-4655}, doi:10.1016/j.cpc.2009.07.017} @Article{FARM_2DRMP, -author ={ V.M. Burke and C.J. Noble and V. Faro-Maza and A. Maniopoulou and N.S. Scott}, +author ={V. M. Burke and C. J. Noble and V. Faro-Maza and A. Maniopoulou and N. S. Scott}, title ={ {FARM\_2DRMP: a version of FARM for use with 2DRMP}}, journal ={Computer Physics Communications}, volume={180}, @@ -41,9 +41,9 @@ pages={2450--2451} @INPROCEEDINGS{VECPAR, author = {T. Stitt and - N.S. Scott and - M.P. Scott and - P.G. Burke}, + N. S. Scott and + M. P. Scott and + P. G. Burke}, title = {{2-D R-Matrix Propagation: A Large Scale Electron Scattering Simulation Dominated by the Multiplication of Dynamically Changing Matrices}}, diff --git a/BookGPU/Chapters/chapter15/ch15.tex b/BookGPU/Chapters/chapter15/ch15.tex index 9b0bf27..cf464c7 100644 --- a/BookGPU/Chapters/chapter15/ch15.tex +++ b/BookGPU/Chapters/chapter15/ch15.tex @@ -825,7 +825,7 @@ as the matrices increase in size during the propagation \section{Performance results} \subsection{PROP deployment on GPU} -\begin{table*}[ht] +\begin{table}[ht] \begin{center} \begin{tabular}{|c||c|c||} \hline @@ -849,13 +849,13 @@ GPU version & C1060 & C2050 \\ GPU V5 (\S~\ref{gpuv5}) & 24m27s & 12m39s \\ \hline \end{tabular} -\caption{\label{table:time} -Execution time of PROP on CPU and GPU} \end{center} -\end{table*} +\caption{Execution time of PROP on CPU and GPU} +\label{table:time} +\end{table} -\begin{comment} -\begin{table*}[ht] + +\begin{table}[ht] \begin{center} \begin{tabular}{|c||c|c||} \hline @@ -876,11 +876,10 @@ GPU version & C1060 & C2050 \\ GPU V5 (\ref{gpuv5}) & 24m27s & 12m39s \\ \hline \end{tabular} -\caption{\label{table:time} -Execution time of the successive GPU versions} \end{center} -\end{table*} -\end{comment} +\caption{Execution time of the successive GPU versions} +\label{table:time} +\end{table} \begin{figure}[h] \centering diff --git a/BookGPU/Chapters/chapter19/code.cu b/BookGPU/Chapters/chapter19/code.cu index 3a95e55..c7bad40 100644 --- a/BookGPU/Chapters/chapter19/code.cu +++ b/BookGPU/Chapters/chapter19/code.cu @@ -1,4 +1,5 @@ -// compute y = B*x (B is stored in SCOO formats [ cols, rows, values, offsets, numPacks, numRows ]) +// compute y = B*x (B is stored in SCOO formats [ cols, rows, values, +//offsets, numPacks, numRows ]) // LANE_SIZE = 2^k // NUM_ROWS_PER_SLICE is computed based on sparsity template @@ -13,7 +14,9 @@ sliced_coo_kernel( const float * x, float * y) { - const int thread_lane = threadIdx.x & (LANE_SIZE-1); // ~ threadIdx.x % LANE_SIZE + // ~ threadIdx.x % LANE_SIZE + const int thread_lane = threadIdx.x & (LANE_SIZE-1); + const int row_lane = threadIdx.x/(LANE_SIZE); __shared__ float sdata[NUM_ROWS_PER_SLICE][LANE_SIZE]; diff --git a/BookGPU/Chapters/chapter7/biblio7.bib b/BookGPU/Chapters/chapter7/biblio7.bib index 6d7e3f9..e48f2ce 100644 --- a/BookGPU/Chapters/chapter7/biblio7.bib +++ b/BookGPU/Chapters/chapter7/biblio7.bib @@ -37,7 +37,7 @@ DOI = "10.1002/fld.2675" } @ARTICLE{ch7:EHBM06, -AUTHOR = "Engsig-Karup, A.P. and Hesthaven, J.S. and Bingham, H.B. and Madsen, P.", +AUTHOR = "Engsig-Karup, A. P. and Hesthaven, J. S. and Bingham, H. B. and Madsen, P.", TITLE = "Nodal {DG-FEM} solutions of high-order {B}oussinesq-type equations", JOURNAL = JEM, YEAR = "2006", @@ -46,7 +46,7 @@ PAGES = "351--370" } @ARTICLE{ch7:EHBW08, -AUTHOR = "Engsig-Karup, A.P. and Hesthaven, J.S. and Bingham, H.B. and Warburton, T.", +AUTHOR = "Engsig-Karup, A. P. and Hesthaven, J. S. and Bingham, H. B. and Warburton, T.", TITLE = "{DG-FEM} solution for nonlinear wave-structure interaction using Boussinesq-type equations", JOURNAL = CE, YEAR = "2008", @@ -55,7 +55,7 @@ PAGES = "197--208" } @INPROCEEDINGS{ch7:Glimberg2011, - AUTHOR = {Stefan L. Glimberg and Allan P. Engsig-Karup and Morten G. Madsen}, + AUTHOR = {S. L. Glimberg and A. P. Engsig-Karup and M. G. Madsen}, TITLE = {A Fast GPU-accelerated Mixed-precision Strategy for Fully Nonlinear Water Wave Computations}, BOOKTITLE = {Numerical Mathematics and Advanced Applications 2011, Proceedings of ENUMATH 2011, the 9th European Conference on Numerical Mathematics and Advanced Applications, Leicester, September 2011}, YEAR = {2011}, @@ -64,7 +64,7 @@ PAGES = "197--208" } @ARTICLE{ch7:EBL08, -AUTHOR = "Engsig-Karup, A.P. and Bingham, H.B. and Lindberg, O.", +AUTHOR = "Engsig-Karup, A. P. and Bingham, H. B. and Lindberg, O.", TITLE = "An efficient flexible-order model for {3D} nonlinear water waves", YEAR = "2009", JOURNAL = JCP, @@ -141,7 +141,7 @@ PAGES = "211--228" } @ARTICLE{ch7:MBS03, -AUTHOR = "Madsen, P.A. and Bingham, H.B. and Sch{\"a}ffer, H. A.", +AUTHOR = "Madsen, P. A. and Bingham, H. B. and Sch{\"a}ffer, H. A.", TITLE = "Boussinesq-type formulations for fully nonlinear and extremely dispersive water waves: derivation and analysis", JOURNAL = RSL, YEAR = "2003", @@ -150,7 +150,7 @@ PAGES = "1075--1104" } @ARTICLE{ch7:MBL02, -AUTHOR = "Madsen, P.A. and Bingham, H.B. and Liu, H.", +AUTHOR = "Madsen, P. A. and Bingham, H. B. and Liu, H.", TITLE = "A new Boussinesq method for fully nonlinear waves from shallow to deep water", JOURNAL = JFM, YEAR = "2002", @@ -168,7 +168,7 @@ PAGES = "{319--333}" } @article {ch7:LynettEtAl2004a, - AUTHOR = {Lynett, P. and Liu, P.L.-F.}, + AUTHOR = {Lynett, P. and Liu, P. L.-F.}, TITLE = {A two-layer approach to wave modelling}, JOURNAL = {Proc. Roy. Soc. London Ser. A}, FJOURNAL = {Proceedings of the Royal Society. London. Series A. @@ -179,7 +179,7 @@ PAGES = "{319--333}" } @incollection {ch7:TsaiYue1996, - AUTHOR = {Tsai, Wu-ting and Yue, Dick K. P.}, + AUTHOR = {Tsai, W. and Yue, D. K. P.}, TITLE = {Computation of nonlinear free-surface flows}, BOOKTITLE = {Annual review of fluid mechanics, Vol.\ 28}, PAGES = {249--278}, @@ -191,7 +191,7 @@ PAGES = "{319--333}" } @article {ch7:LynettEtAl2004b, - AUTHOR = {Lynett, P. and Liu, P.L.-F.}, + AUTHOR = {Lynett, P. and Liu, P. L.-F.}, TITLE = {Linear analysis of the multi-layer model}, JOURNAL = CE, VOLUME = {51}, @@ -200,7 +200,7 @@ PAGES = "{319--333}" } @article {ch7:DiasBridges2006, - AUTHOR = {Dias, Fr{\'e}d{\'e}ric and Bridges, Thomas J.}, + AUTHOR = {Dias, F. and Bridges, T. J.}, TITLE = {The numerical computation of freely propagating time-dependent irrotational water waves}, JOURNAL = {Fluid Dynam. Res.}, @@ -240,7 +240,7 @@ PAGES = "285--297" @incollection {ch7:Yeung1982, - AUTHOR = {Yeung, Ronald W.}, + AUTHOR = {Yeung, R. W.}, TITLE = {Numerical methods in free-surface flows}, BOOKTITLE = {Annual review of fluid mechanics, Vol. 14}, PAGES = {395--442}, @@ -263,13 +263,13 @@ note = "", issn = "0079-6611", doi = "10.1016/j.pocean.2007.05.005", url = "http://www.sciencedirect.com/science/article/pii/S0079661107001206", -author = "L. Cavaleri and J.-H.G.M. Alves and F. Ardhuin and A. Babanin and M. Banner and K. Belibassakis and M. Benoit and M. Donelan and J. Groeneweg and T.H.C. Herbers and P. Hwang and P.A.E.M. Janssen and T. Janssen and I.V. Lavrenov and R. Magne and J. Monbaliu and M. Onorato and V. Polnikov and D. Resio and W.E. Rogers and A. Sheremet and J. McKee Smith and H.L. Tolman and G. van Vledder and J. Wolf and I. Young", +author = "L. Cavaleri and J.-H. G. M. Alves and F. Ardhuin and A. Babanin and M. Banner and K. Belibassakis and M. Benoit and M. Donelan and J. Groeneweg and T.H.C. Herbers and P. Hwang and P. A. E. M. Janssen and T. Janssen and I. V. Lavrenov and R. Magne and J. Monbaliu and M. Onorato and V. Polnikov and D. Resio and W. E. Rogers and A. Sheremet and J. McKee Smith and H. L. Tolman and G. van Vledder and J. Wolf and I. Young", keywords = "Wind waves", -keywords = "Wind‰ÛÒwave generation", -keywords = "Wave‰ÛÒwave interaction", +keywords = "WindﾛÒwave generation", +keywords = "WaveﾛÒwave interaction", keywords = "Wave propagation", keywords = "Wave dissipation", -keywords = "Wave‰ÛÒcurrent interaction", +keywords = "WaveﾛÒcurrent interaction", keywords = "Numerics" } @@ -303,7 +303,7 @@ YEAR = "1982" } @BOOK{ch7:Hackbusch1982, -AUTHOR = "Hackbusch W.", +AUTHOR = "Hackbusch, W.", TITLE = "On multigrid iterations with defect correction. In: Hackbusch, W.; Trottenberg, U. (eds): Lecture Notes in Math.", BOOKTITLE = "Multigrid Methods", VOLUME = "960", @@ -313,7 +313,7 @@ YEAR = "1982" } @article {ch7:MR744926, - AUTHOR = {Schaffer, Steve}, + AUTHOR = {Schaffer, S.}, TITLE = {Higher order multigrid methods}, JOURNAL = {Math. Comp.}, FJOURNAL = {Mathematics of Computation}, @@ -352,7 +352,7 @@ year = "2011", issn = "1631-0721", doi = "10.1016/j.crme.2010.11.002", url = "http://www.sciencedirect.com/science/article/pii/S1631072110002032", -author = "David E. Keyes", +author = "D. E. Keyes", keywords = "Computer science", keywords = "Exaflop", keywords = "Informatiquealgorithmique", @@ -375,7 +375,7 @@ YEAR = "2006" @book{ch7:Whalin1971, title={The Limit of Applicability of Linear Wave Refraction Theory in a Convergence Zone}, - author={Whalin, R.W. and United States. Army. Corps of Engineers and Waterways Experiment Station (U.S.)}, + author={Whalin, R. W. and United States. Army. Corps of Engineers and Waterways Experiment Station (U.S.)}, series={Research report}, url={http://books.google.dk/books?id=wwvWSgAACAAJ}, year={1971}, @@ -383,7 +383,7 @@ YEAR = "2006" } @article{ch7:AbottEtAl1984, -author = "Abott, M.B. and McCowan, A.D. and Warren, I.R.", +author = "Abott, M. B. and McCowan, A. D. and Warren, I. R.", title = "Accuracy of short-wave numerical models", journal = "ASCE Journal of Hydraulic Engineering", volume = "110", @@ -393,7 +393,7 @@ year = "1984" } @article{ch7:AbottEtAl1978, -author = "Abott, M.B. Petersens, H.M. and Skovgaard, O.", +author = "Abott, M. B. Petersens, H. M. and Skovgaard, O.", title = "On the numerical modelling of short waves in shallow water", journal = "Journal of Hydraulic Research", volume = "16", @@ -403,7 +403,7 @@ year = "1978" } @ARTICLE{ch7:MS98, -AUTHOR = "Madsen, P.A. and Sch{\"{a}}ffer, H. A.", +AUTHOR = "Madsen, P. A. and Sch{\"{a}}ffer, H. A.", TITLE = "Higher order Boussinesq-type equations for surface gravity waves - derivation and analysis.", JOURNAL = "In Advances in Coastal and Ocean Engineering", VOLUME = "356", @@ -412,7 +412,7 @@ PAGES = "3123--3181" } @article{ch7:Peregrine1967, -author = "Peregrine, D.H.", +author = "Peregrine, D. H.", title = "Long waves on a beach", journal = "Journal of Fluid Mechanics", volume = "27", @@ -430,7 +430,7 @@ published = {SIAM} @ARTICLE{ch7:GlimbergEtAl2012, - AUTHOR = {Stefan L. Glimberg and Allan P. Engsig-Karup}, + AUTHOR = {S. L. Glimberg and A. P. Engsig-Karup}, TITLE = {On a Multi-GPU Implementation of a Free Surface Water Wave Model for Large-scale Simulations}, JOURNAL = {Submitted to: Special Issue of the Journal Parallel Computing}, YEAR = {2012}, @@ -479,7 +479,7 @@ published = {SIAM} @mastersthesis{ch7:ASNP12, - author = {Allan S. Nielsen}, + author = {A. S. Nielsen}, title = {Feasibility study of the Parareal algorithm}, school = {Technical University of Denmark, Department of Informatics and Mathematical Modeling}, year = {2012}, @@ -487,7 +487,7 @@ published = {SIAM} } @Book{ch7:Higham:2002:ASN, - author = "Nicholas J. Higham", + author = "N. J. Higham", title = "Accuracy and Stability of Numerical Algorithms", publisher = "Society for Industrial and Applied Mathematics", address = "Philadelphia, PA, USA", @@ -526,7 +526,7 @@ note = "", issn = "0378-3839", doi = "10.1016/j.coastaleng.2008.10.012", url = "http://www.sciencedirect.com/science/article/pii/S0378383908001865", -author = "Harry B. Bingham and Per A. Madsen and David R. Fuhrman", +author = "H. B. Bingham and P. A. Madsen and D. R. Fuhrman", keywords = "Boussinesq-type equations", keywords = "Nonlinear waves", keywords = "Potential flow", diff --git a/BookGPU/Chapters/chapter7/ch7.tex b/BookGPU/Chapters/chapter7/ch7.tex index c18d417..45fc453 100644 --- a/BookGPU/Chapters/chapter7/ch7.tex +++ b/BookGPU/Chapters/chapter7/ch7.tex @@ -535,7 +535,8 @@ __global__ void laplace_sigma_transformed( { size_type offset_i = i < alpha ? 2*alpha-i : i >= Ns-alpha ? Ns-1-i : alpha; size_type row_i = offset_i*rank; - size_type offset_j = alpha; // Always centered stencils in x-dir + // Always centered stencils in x-dir + size_type offset_j = alpha; size_type row_j = alpha*rank; value_type dhdx = hx[j]; diff --git a/BookGPU/Chapters/chapter8/biblio8.bib b/BookGPU/Chapters/chapter8/biblio8.bib index 78424f2..3e10526 100644 --- a/BookGPU/Chapters/chapter8/biblio8.bib +++ b/BookGPU/Chapters/chapter8/biblio8.bib @@ -7,14 +7,14 @@ } @InProceedings{ch8:Carneiro_2011, - author = {T. Carneiro and A. Einstein Muritibab and M. Negreirosc and G. Augusto Lima de Campos}, + author = {T. Carneiro and A. E. Muritibab and M. Negreirosc and G. A. Lima de Campos}, title = {A New Parallel Schema for Branch-and-Bound Algorithms Using GPGPU}, booktitle = {23rd International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)}, year = {2011} } @ARTICLE{ch8:Casadoa_2008, - author = "L.G. Casadoa and J.A. Martíneza and I. Garcíaa and E.M.T. Hendrixb.", + author = "L. G. Casadoa and J. A. Martíneza and I. Garcíaa and E. M. T. Hendrixb.", title = "Branch-and-Bound interval global optimization on shared memory multiprocessors", journal = "Optimization Methods and Software", volume = "23, No.5", @@ -32,7 +32,7 @@ } @Article{ch8:Garey_1976, - author = {M.R. Garey and D.S. Johnson and R. Sethi}, + author = {M. R. Garey and D. S. Johnson and R. Sethi}, title = {{The complexity of flow-shop and job-shop scheduling}}, journal = {Mathematics of Operations Research}, year = {1976}, @@ -42,7 +42,7 @@ } @Article{ch8:Gendron_1994, - author = {B. Gendron and T.G. Crainic}, + author = {B. Gendron and T. G. Crainic}, title = {Parallel {B}ranch and {B}ound {A}lgorithms: {S}urvey and {S}ynthesis}, journal = {Operations Research}, year = {1994}, @@ -52,7 +52,7 @@ } @InProceedings{ch8:Han, - author = {T. Han and T.S. Abdelrahman}, + author = {T. Han and T. S. Abdelrahman}, title = {Reducing branch divergence in GPU programs}, booktitle = {{In Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units (GPGPU-4), ACM}}, year = {2011}, @@ -60,7 +60,7 @@ } @Article{ch8:Johnson_1954, - author = {S.M. Johnson}, + author = {S. M. Johnson}, title = {{Optimal two and three-stage production schedules with setup times included}}, journal = {Naval Research Logistis Quarterly}, year = {1954}, @@ -77,7 +77,7 @@ } @Article{ch8:Lenstra_1978, - author = {J.K. Lenstra and B.J. Lageweg and A.H.G. Rinnooy Kan}, + author = {J. K. Lenstra and B. J. Lageweg and A. H. G. Rinnooy Kan}, title = {{A General bounding scheme for the permutation flow-shop problem}}, journal = {Operations Research}, year = {1978}, @@ -108,7 +108,7 @@ NOTE = "Th\`ese HDR" } @ARTICLE{ch8:JRJackson_1956, - AUTHOR ="J.R.Jackson", + AUTHOR ="J. R. Jackson", TITLE ="An Extension of Johnson's results on Job-Lot Scheduling", JOURNAL ="Naval Research Logistis Quarterly", YEAR ="1956", @@ -116,7 +116,7 @@ NOTE = "Th\`ese HDR" } @ARTICLE{ch8:LGMitten_1959, - AUTHOR ="L.G.Mitten", + AUTHOR ="L. G. Mitten", TITLE ="Sequencing n jobs on two machines with arbitrary time lags", JOURNAL ="Management Science", YEAR ="1959" @@ -141,7 +141,7 @@ NOTE = "Th\`ese HDR" } @InProceedings{ch8:Zhang, - author = {E.Z. Zhang and Y. Jiang and Z. Guo and X. Shen}, + author = {E. Z. Zhang and Y. Jiang and Z. Guo and X. Shen}, title = {Streamlining GPU applications on the fly: thread divergence elimination through runtime thread-data remapping}, booktitle = {{In Proceedings of the 24th ACM International Conference on Supercomputing (ICS'10), ACM.}}, year = {2010}, diff --git a/BookGPU/Chapters/chapter9/biblio9.bib b/BookGPU/Chapters/chapter9/biblio9.bib index 5c32a72..041c461 100644 --- a/BookGPU/Chapters/chapter9/biblio9.bib +++ b/BookGPU/Chapters/chapter9/biblio9.bib @@ -228,7 +228,7 @@ year = {2013} } @incollection{paradiseoGPU, -author={Melab, N. and Luong, T.V. and Boufaras, K. and Talbi, E.G.}, +author={Melab, N. and Luong, T. V. and Boufaras, K. and Talbi, E.-G.}, title={{Towards ParadisEO-MO-GPU: A Framework for GPU-Based Local Search Metaheuristics}}, booktitle={Advances in Computational Intelligence}, series={Lecture Notes in Computer Science}, @@ -238,7 +238,7 @@ year={2011} } @incollection{luongMultiStart, -author={T. V. Luong and N. Melab and E-G. Talbi}, +author={T. V. Luong and N. Melab and E.-G. Talbi}, title={{GPU-Based Multi-start Local Search Algorithms}}, booktitle={Learning and Intelligent Optimization}, series={Lecture Notes in Computer Science},