-\@writefile{toc}{\contentsline {section}{\numberline {3.1}Introduction}{24}}
-\newlabel{ch6:intro}{{3.1}{24}}
-\@writefile{toc}{\contentsline {section}{\numberline {3.2}General scheme of synchronous code with computation/communication overlapping in GPU clusters}{24}}
-\newlabel{ch6:part1}{{3.2}{24}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.2.1}Synchronous parallel algorithms on GPU clusters}{24}}
-\@writefile{lof}{\contentsline {figure}{\numberline {3.1}{\ignorespaces Native overlap of internode CPU communications with GPU computations.\relax }}{26}}
-\newlabel{fig:ch6p1overlapnative}{{3.1}{26}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.2.2}Native overlap of CPU communications and GPU computations}{26}}
-\newlabel{algo:ch6p1overlapnative}{{3.1}{27}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.1}Generic scheme implicitly overlapping MPI communications with CUDA GPU computations}{27}}
-\@writefile{lof}{\contentsline {figure}{\numberline {3.2}{\ignorespaces Overlap of internode CPU communications with a sequence of CPU/GPU data transfers and GPU computations.\relax }}{28}}
-\newlabel{fig:ch6p1overlapseqsequence}{{3.2}{28}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.2.3}Overlapping with sequences of transfers and computations}{28}}
-\newlabel{algo:ch6p1overlapseqsequence}{{3.2}{29}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.2}Generic scheme explicitly overlapping MPI communications with sequences of CUDA CPU/GPU transfers and CUDA GPU computations}{29}}
-\@writefile{lof}{\contentsline {figure}{\numberline {3.3}{\ignorespaces Overlap of internode CPU communications with a streamed sequence of CPU/GPU data transfers and GPU computations.\relax }}{30}}
-\newlabel{fig:ch6p1overlapstreamsequence}{{3.3}{30}}
-\newlabel{algo:ch6p1overlapstreamsequence}{{3.3}{31}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.3}Generic scheme explicitly overlapping MPI communications with streamed sequences of CUDA CPU/GPU transfers and CUDA GPU computations}{31}}
-\@writefile{lof}{\contentsline {figure}{\numberline {3.4}{\ignorespaces Complete overlap of internode CPU communications, CPU/GPU data transfers and GPU computations, interleaving computation-communication iterations\relax }}{33}}
-\newlabel{fig:ch6p1overlapinterleaved}{{3.4}{33}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.2.4}Interleaved communications-transfers-computations overlapping}{33}}
-\newlabel{algo:ch6p1overlapinterleaved}{{3.4}{34}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.4}Generic scheme explicitly overlapping MPI communications, CUDA CPU/GPU transfers and CUDA GPU computations, interleaving computation-communication iterations}{34}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.2.5}Experimental validation}{36}}
-\newlabel{ch6:p1expes}{{3.2.5}{36}}
-\newlabel{ch6:p1block-cyclic}{{3.2.5}{36}}
-\@writefile{lof}{\contentsline {figure}{\numberline {3.5}{\ignorespaces Experimental performances of different synchronous algorithms computing a dense matrix product\relax }}{37}}
-\newlabel{fig:ch6p1syncexpematrixprod}{{3.5}{37}}
-\@writefile{toc}{\contentsline {section}{\numberline {3.3}General scheme of asynchronous parallel code with computation/communication overlapping}{38}}
-\newlabel{ch6:part2}{{3.3}{38}}
-\@writefile{loa}{\contentsline {algorithm}{\numberline {1}{\ignorespaces Synchronous iterative scheme\relax }}{38}}
-\newlabel{algo:ch6p2sync}{{1}{38}}
-\@writefile{loa}{\contentsline {algorithm}{\numberline {2}{\ignorespaces Asynchronous iterative scheme\relax }}{38}}
-\newlabel{algo:ch6p2async}{{2}{38}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.3.1}A basic asynchronous scheme}{40}}
-\newlabel{ch6:p2BasicAsync}{{3.3.1}{40}}
-\newlabel{algo:ch6p2BasicAsync}{{3.5}{40}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.5}Initialization of the basic asynchronous scheme}{40}}
-\newlabel{algo:ch6p2BasicAsyncComp}{{3.6}{41}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.6}Computing function in the basic asynchronous scheme}{41}}
-\newlabel{algo:ch6p2BasicAsyncSendings}{{3.7}{42}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.7}Sending function in the basic asynchronous scheme}{42}}
-\newlabel{algo:ch6p2BasicAsyncReceptions}{{3.8}{43}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.8}Reception function in the basic asynchronous scheme}{43}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.3.2}Synchronization of the asynchronous scheme}{44}}
-\newlabel{ch6:p2SsyncOverAsync}{{3.3.2}{44}}
-\newlabel{algo:ch6p2Sync}{{3.9}{45}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.9}Initialization of the synchronized scheme}{45}}
-\newlabel{algo:ch6p2SyncComp}{{3.10}{46}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.10}Computing function in the synchronized scheme}{46}}
-\newlabel{algo:ch6p2SyncReceptions}{{3.11}{47}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.11}Reception function in the synchronized scheme}{47}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.3.3}Asynchronous scheme using MPI, OpenMP and CUDA}{48}}
-\newlabel{ch6:p2GPUAsync}{{3.3.3}{48}}
-\newlabel{algo:ch6p2AsyncSyncComp}{{3.12}{50}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.12}Computing function in the final asynchronous scheme}{50}}
-\newlabel{algo:ch6p2syncGPU}{{3.13}{51}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.13}Computing function in the final asynchronous scheme}{51}}
-\newlabel{algo:ch6p2FullOverAsyncMain}{{3.14}{53}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.14}Initialization of the main process of complete overlap with asynchronism}{53}}
-\newlabel{algo:ch6p2FullOverAsyncComp1}{{3.15}{54}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.15}Computing function in the final asynchronous scheme with CPU/GPU overlap}{54}}
-\newlabel{algo:ch6p2FullOverAsyncComp2}{{3.16}{55}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.16}Auxiliary computing function in the final asynchronous scheme with CPU/GPU overlap}{55}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.3.4}Experimental validation}{56}}
-\newlabel{sec:ch6p2expes}{{3.3.4}{56}}
-\@writefile{lof}{\contentsline {figure}{\numberline {3.6}{\ignorespaces Computation times of the test application in synchronous and asynchronous modes.\relax }}{57}}
-\newlabel{fig:ch6p2syncasync}{{3.6}{57}}
-\@writefile{lof}{\contentsline {figure}{\numberline {3.7}{\ignorespaces Computation times with or without overlap of Jacobian updatings in asynchronous mode.\relax }}{58}}
-\newlabel{fig:ch6p2aux}{{3.7}{58}}
-\@writefile{toc}{\contentsline {section}{\numberline {3.4}Perspective: A unifying programming model}{59}}
-\newlabel{sec:ch6p3unify}{{3.4}{59}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.4.1}Resources}{59}}
-\newlabel{sec:ch6p3resources}{{3.4.1}{59}}
-\newlabel{algo:ch6p3ORWLresources}{{3.17}{60}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.17}Declaration of ORWL resources for a block-cyclic matrix multiplication}{60}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.4.2}Control}{60}}
-\newlabel{sec:ch6p3ORWLcontrol}{{3.4.2}{60}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.4.3}Example: block-cyclic matrix multiplication (MM)}{61}}
-\newlabel{sec:ch6p3ORWLMM}{{3.4.3}{61}}
-\newlabel{algo:ch6p3ORWLBCCMM}{{3.18}{61}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.18}Block-cyclic matrix multiplication, high level per task view}{61}}
-\newlabel{algo:ch6p3ORWLlcopy}{{3.19}{62}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.19}An iterative local copy operation}{62}}
-\newlabel{algo:ch6p3ORWLrcopy}{{3.20}{62}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.20}An iterative remote copy operation as part of a block cyclic matrix multiplication task}{62}}
-\newlabel{algo:ch6p3ORWLtrans}{{3.21}{62}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.21}An iterative GPU transfer and compute operation as part of a block cyclic matrix multiplication task}{62}}
-\newlabel{algo:ch6p3ORWLdecl}{{3.22}{63}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.22}Dynamic declaration of handles to represent the resources}{63}}
-\newlabel{algo:ch6p3ORWLinit}{{3.23}{64}}
-\@writefile{lol}{\contentsline {lstlisting}{\numberline {3.23}Dynamic initialization of access mode and priorities}{64}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.4.4}Tasks and operations}{64}}
-\newlabel{sec:ch6p3tasks}{{3.4.4}{64}}
-\@writefile{toc}{\contentsline {section}{\numberline {3.5}Conclusion}{65}}
-\newlabel{ch6:conclu}{{3.5}{65}}
-\@writefile{toc}{\contentsline {section}{\numberline {3.6}Glossary}{65}}
-\@writefile{toc}{\contentsline {section}{Bibliography}{66}}
+\@writefile{toc}{\contentsline {section}{\numberline {5.1}Introduction}{50}}
+\newlabel{ch6:intro}{{5.1}{50}}
+\@writefile{toc}{\contentsline {section}{\numberline {5.2}General scheme of synchronous code with computation/communication overlapping in GPU clusters}{50}}
+\newlabel{ch6:part1}{{5.2}{50}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.2.1}Synchronous parallel algorithms on GPU clusters}{50}}
+\@writefile{lof}{\contentsline {figure}{\numberline {5.1}{\ignorespaces Native overlap of internode CPU communications with GPU computations.\relax }}{52}}
+\newlabel{fig:ch6p1overlapnative}{{5.1}{52}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.2.2}Native overlap of CPU communications and GPU computations}{52}}
+\newlabel{algo:ch6p1overlapnative}{{5.1}{53}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.1}Generic scheme implicitly overlapping MPI communications with CUDA GPU computations}{53}}
+\@writefile{lof}{\contentsline {figure}{\numberline {5.2}{\ignorespaces Overlap of internode CPU communications with a sequence of CPU/GPU data transfers and GPU computations.\relax }}{54}}
+\newlabel{fig:ch6p1overlapseqsequence}{{5.2}{54}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.2.3}Overlapping with sequences of transfers and computations}{54}}
+\newlabel{algo:ch6p1overlapseqsequence}{{5.2}{55}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.2}Generic scheme explicitly overlapping MPI communications with sequences of CUDA CPU/GPU transfers and CUDA GPU computations}{55}}
+\@writefile{lof}{\contentsline {figure}{\numberline {5.3}{\ignorespaces Overlap of internode CPU communications with a streamed sequence of CPU/GPU data transfers and GPU computations.\relax }}{56}}
+\newlabel{fig:ch6p1overlapstreamsequence}{{5.3}{56}}
+\newlabel{algo:ch6p1overlapstreamsequence}{{5.3}{57}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.3}Generic scheme explicitly overlapping MPI communications with streamed sequences of CUDA CPU/GPU transfers and CUDA GPU computations}{57}}
+\@writefile{lof}{\contentsline {figure}{\numberline {5.4}{\ignorespaces Complete overlap of internode CPU communications, CPU/GPU data transfers and GPU computations, interleaving computation-communication iterations\relax }}{59}}
+\newlabel{fig:ch6p1overlapinterleaved}{{5.4}{59}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.2.4}Interleaved communications-transfers-computations overlapping}{59}}
+\newlabel{algo:ch6p1overlapinterleaved}{{5.4}{60}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.4}Generic scheme explicitly overlapping MPI communications, CUDA CPU/GPU transfers and CUDA GPU computations, interleaving computation-communication iterations}{60}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.2.5}Experimental validation}{62}}
+\newlabel{ch6:p1expes}{{5.2.5}{62}}
+\newlabel{ch6:p1block-cyclic}{{5.2.5}{62}}
+\@writefile{lof}{\contentsline {figure}{\numberline {5.5}{\ignorespaces Experimental performances of different synchronous algorithms computing a dense matrix product\relax }}{63}}
+\newlabel{fig:ch6p1syncexpematrixprod}{{5.5}{63}}
+\@writefile{toc}{\contentsline {section}{\numberline {5.3}General scheme of asynchronous parallel code with computation/communication overlapping}{64}}
+\newlabel{ch6:part2}{{5.3}{64}}
+\@writefile{loa}{\contentsline {algorithm}{\numberline {3}{\ignorespaces Synchronous iterative scheme\relax }}{64}}
+\newlabel{algo:ch6p2sync}{{3}{64}}
+\@writefile{loa}{\contentsline {algorithm}{\numberline {4}{\ignorespaces Asynchronous iterative scheme\relax }}{64}}
+\newlabel{algo:ch6p2async}{{4}{64}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.3.1}A basic asynchronous scheme}{66}}
+\newlabel{ch6:p2BasicAsync}{{5.3.1}{66}}
+\newlabel{algo:ch6p2BasicAsync}{{5.5}{66}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.5}Initialization of the basic asynchronous scheme}{66}}
+\newlabel{algo:ch6p2BasicAsyncComp}{{5.6}{67}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.6}Computing function in the basic asynchronous scheme}{67}}
+\newlabel{algo:ch6p2BasicAsyncSendings}{{5.7}{68}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.7}Sending function in the basic asynchronous scheme}{68}}
+\newlabel{algo:ch6p2BasicAsyncReceptions}{{5.8}{69}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.8}Reception function in the basic asynchronous scheme}{69}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.3.2}Synchronization of the asynchronous scheme}{70}}
+\newlabel{ch6:p2SsyncOverAsync}{{5.3.2}{70}}
+\newlabel{algo:ch6p2Sync}{{5.9}{71}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.9}Initialization of the synchronized scheme}{71}}
+\newlabel{algo:ch6p2SyncComp}{{5.10}{72}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.10}Computing function in the synchronized scheme}{72}}
+\newlabel{algo:ch6p2SyncReceptions}{{5.11}{73}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.11}Reception function in the synchronized scheme}{73}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.3.3}Asynchronous scheme using MPI, OpenMP and CUDA}{74}}
+\newlabel{ch6:p2GPUAsync}{{5.3.3}{74}}
+\newlabel{algo:ch6p2AsyncSyncComp}{{5.12}{76}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.12}Computing function in the final asynchronous scheme}{76}}
+\newlabel{algo:ch6p2syncGPU}{{5.13}{77}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.13}Computing function in the final asynchronous scheme}{77}}
+\newlabel{algo:ch6p2FullOverAsyncMain}{{5.14}{79}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.14}Initialization of the main process of complete overlap with asynchronism}{79}}
+\newlabel{algo:ch6p2FullOverAsyncComp1}{{5.15}{80}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.15}Computing function in the final asynchronous scheme with CPU/GPU overlap}{80}}
+\newlabel{algo:ch6p2FullOverAsyncComp2}{{5.16}{81}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.16}Auxiliary computing function in the final asynchronous scheme with CPU/GPU overlap}{81}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.3.4}Experimental validation}{82}}
+\newlabel{sec:ch6p2expes}{{5.3.4}{82}}
+\@writefile{lof}{\contentsline {figure}{\numberline {5.6}{\ignorespaces Computation times of the test application in synchronous and asynchronous modes.\relax }}{83}}
+\newlabel{fig:ch6p2syncasync}{{5.6}{83}}
+\@writefile{lof}{\contentsline {figure}{\numberline {5.7}{\ignorespaces Computation times with or without overlap of Jacobian updatings in asynchronous mode.\relax }}{84}}
+\newlabel{fig:ch6p2aux}{{5.7}{84}}
+\@writefile{toc}{\contentsline {section}{\numberline {5.4}Perspective: A unifying programming model}{85}}
+\newlabel{sec:ch6p3unify}{{5.4}{85}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.4.1}Resources}{85}}
+\newlabel{sec:ch6p3resources}{{5.4.1}{85}}
+\newlabel{algo:ch6p3ORWLresources}{{5.17}{86}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.17}Declaration of ORWL resources for a block-cyclic matrix multiplication}{86}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.4.2}Control}{86}}
+\newlabel{sec:ch6p3ORWLcontrol}{{5.4.2}{86}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.4.3}Example: block-cyclic matrix multiplication (MM)}{87}}
+\newlabel{sec:ch6p3ORWLMM}{{5.4.3}{87}}
+\newlabel{algo:ch6p3ORWLBCCMM}{{5.18}{87}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.18}Block-cyclic matrix multiplication, high level per task view}{87}}
+\newlabel{algo:ch6p3ORWLlcopy}{{5.19}{88}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.19}An iterative local copy operation}{88}}
+\newlabel{algo:ch6p3ORWLrcopy}{{5.20}{88}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.20}An iterative remote copy operation as part of a block cyclic matrix multiplication task}{88}}
+\newlabel{algo:ch6p3ORWLtrans}{{5.21}{88}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.21}An iterative GPU transfer and compute operation as part of a block cyclic matrix multiplication task}{88}}
+\newlabel{algo:ch6p3ORWLdecl}{{5.22}{89}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.22}Dynamic declaration of handles to represent the resources}{89}}
+\newlabel{algo:ch6p3ORWLinit}{{5.23}{90}}
+\@writefile{lol}{\contentsline {lstlisting}{\numberline {5.23}Dynamic initialization of access mode and priorities}{90}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {5.4.4}Tasks and operations}{90}}
+\newlabel{sec:ch6p3tasks}{{5.4.4}{90}}
+\@writefile{toc}{\contentsline {section}{\numberline {5.5}Conclusion}{91}}
+\newlabel{ch6:conclu}{{5.5}{91}}
+\@writefile{toc}{\contentsline {section}{\numberline {5.6}Glossary}{91}}
+\@writefile{toc}{\contentsline {section}{Bibliography}{92}}
