BookGPU/Chapters/chapter13/ch13.aux

   1 \relax
   2 \@writefile{toc}{\author{}{}}
   3 \@writefile{loa}{\addvspace {10\p@ }}
   4 \@writefile{toc}{\contentsline {chapter}{\numberline {12}Solving sparse nonlinear systems of obstacle problems on GPU clusters}{277}}
   5 \@writefile{lof}{\addvspace {10\p@ }}
   6 \@writefile{lot}{\addvspace {10\p@ }}
   7 \@writefile{toc}{\contentsline {section}{\numberline {12.1}Introduction}{277}}
   8 \newlabel{sec:01}{{12.1}{277}}
   9 \@writefile{toc}{\contentsline {section}{\numberline {12.2}Obstacle problems}{278}}
  10 \newlabel{sec:02}{{12.2}{278}}
  11 \@writefile{toc}{\contentsline {subsection}{\numberline {12.2.1}Mathematical model}{278}}
  12 \newlabel{sec:02.01}{{12.2.1}{278}}
  13 \newlabel{eq:01}{{12.1}{278}}
  14 \newlabel{eq:02}{{12.2}{279}}
  15 \@writefile{toc}{\contentsline {subsection}{\numberline {12.2.2}Discretization}{279}}
  16 \newlabel{sec:02.02}{{12.2.2}{279}}
  17 \newlabel{eq:03}{{12.3}{279}}
  18 \newlabel{eq:04}{{12.4}{279}}
  19 \newlabel{eq:05}{{12.5}{280}}
  20 \@writefile{toc}{\contentsline {section}{\numberline {12.3}Parallel iterative method}{280}}
  21 \newlabel{sec:03}{{12.3}{280}}
  22 \newlabel{eq:06}{{12.6}{280}}
  23 \newlabel{eq:07}{{12.7}{280}}
  24 \newlabel{eq:08}{{12.8}{281}}
  25 \newlabel{eq:09}{{12.9}{281}}
  26 \newlabel{eq:10}{{12.10}{281}}
  27 \newlabel{eq:11}{{12.11}{281}}
  28 \newlabel{eq:12}{{12.12}{281}}
  29 \newlabel{eq:13}{{12.13}{282}}
  30 \newlabel{eq:14}{{12.14}{282}}
  31 \newlabel{eq:15}{{12.15}{282}}
  32 \newlabel{eq:16}{{12.16}{282}}
  33 \@writefile{toc}{\contentsline {section}{\numberline {12.4}Parallel implementation on a GPU cluster}{283}}
  34 \newlabel{sec:04}{{12.4}{283}}
  35 \@writefile{lof}{\contentsline {figure}{\numberline {12.1}{\ignorespaces Data partitioning of a problem to be solved among $S=3\times 4$ computing nodes.\relax }}{283}}
  36 \newlabel{fig:01}{{12.1}{283}}
  37 \@writefile{loa}{\contentsline {algocf}{\numberline {11}{\ignorespaces Parallel solving of the obstacle problem on a GPU cluster\relax }}{284}}
  38 \newlabel{alg:01}{{11}{284}}
  39 \newlabel{eq:18}{{12.17}{284}}
  40 \@writefile{loa}{\contentsline {algocf}{\numberline {12}{\ignorespaces Parallel iterative solving of the nonlinear systems on a GPU cluster ($Solve()$ function)\relax }}{285}}
  41 \newlabel{alg:02}{{12}{285}}
  42 \@writefile{lof}{\contentsline {figure}{\numberline {12.2}{\ignorespaces Decomposition of a sub-problem in a GPU into $nz$ slices.\relax }}{286}}
  43 \newlabel{fig:02}{{12.2}{286}}
  44 \newlabel{list:01}{{12.1}{286}}
  45 \@writefile{lol}{\contentsline {lstlisting}{\numberline {12.1}Skeleton codes of a GPU kernel and a CPU function}{286}}
  46 \@writefile{lof}{\contentsline {figure}{\numberline {12.3}{\ignorespaces Matrix constant coefficients in a three-dimensional domain.\relax }}{288}}
  47 \newlabel{fig:03}{{12.3}{288}}
  48 \newlabel{eq:17}{{12.18}{288}}
  49 \newlabel{list:02}{{12.2}{289}}
  50 \@writefile{lol}{\contentsline {lstlisting}{\numberline {12.2}GPU kernels of the projected Richardson method}{289}}
  51 \@writefile{lof}{\contentsline {figure}{\numberline {12.4}{\ignorespaces Computation of a vector element with the projected Richardson method.\relax }}{290}}
  52 \newlabel{fig:04}{{12.4}{290}}
  53 \newlabel{list:03}{{12.3}{290}}
  54 \@writefile{lol}{\contentsline {lstlisting}{\numberline {12.3}Memory access to the cache texture memory}{290}}
  55 \@writefile{toc}{\contentsline {section}{\numberline {12.5}Experimental tests on a GPU cluster}{291}}
  56 \newlabel{sec:05}{{12.5}{291}}
  57 \@writefile{lof}{\contentsline {figure}{\numberline {12.5}{\ignorespaces GPU cluster of tests composed of 12 computing nodes (six machines, each with two GPUs.\relax }}{292}}
  58 \newlabel{fig:05}{{12.5}{292}}
  59 \@writefile{lot}{\contentsline {table}{\numberline {12.1}{\ignorespaces Execution times in seconds of the parallel projected Richardson method implemented on a cluster of 24 CPU cores.\relax }}{293}}
  60 \newlabel{tab:01}{{12.1}{293}}
  61 \@writefile{lot}{\contentsline {table}{\numberline {12.2}{\ignorespaces Execution times in seconds of the parallel projected Richardson method implemented on a cluster of 12 GPUs.\relax }}{293}}
  62 \newlabel{tab:02}{{12.2}{293}}
  63 \@writefile{toc}{\contentsline {section}{\numberline {12.6}Red-Black ordering technique}{294}}
  64 \newlabel{sec:06}{{12.6}{294}}
  65 \newlabel{fig:06.01}{{12.6(a)}{295}}
  66 \newlabel{sub@fig:06.01}{{(a)}{295}}
  67 \newlabel{fig:06.02}{{12.6(b)}{295}}
  68 \newlabel{sub@fig:06.02}{{(b)}{295}}
  69 \@writefile{lof}{\contentsline {figure}{\numberline {12.6}{\ignorespaces Red-black ordering for computing the iterate vector elements in a three-dimensional space.\relax }}{295}}
  70 \@writefile{lof}{\contentsline {subfigure}{\numberline{(a)}{\ignorespaces {Red-black ordering on x, y and z axises}}}{295}}
  71 \@writefile{lof}{\contentsline {subfigure}{\numberline{(b)}{\ignorespaces {Red-black ordering on y axis}}}{295}}
  72 \newlabel{list:04}{{12.4}{296}}
  73 \@writefile{lol}{\contentsline {lstlisting}{\numberline {12.4}GPU kernels of the projected Richardson method using the red-black technique}{296}}
  74 \@writefile{lot}{\contentsline {table}{\numberline {12.3}{\ignorespaces Execution times in seconds of the parallel projected Richardson method using read-black ordering technique implemented on a cluster of 12 GPUs.\relax }}{297}}
  75 \newlabel{tab:03}{{12.3}{297}}
  76 \@writefile{lof}{\contentsline {figure}{\numberline {12.7}{\ignorespaces Weak scaling of both synchronous and asynchronous algorithms of the projected Richardson method using red-black ordering technique.\relax }}{298}}
  77 \newlabel{fig:07}{{12.7}{298}}
  78 \@writefile{toc}{\contentsline {section}{\numberline {12.7}Conclusion}{299}}
  79 \newlabel{sec:07}{{12.7}{299}}
  80 \@writefile{toc}{\contentsline {section}{Bibliography}{299}}
  81 \@setckpt{Chapters/chapter13/ch13}{
  82 \setcounter{page}{301}
  83 \setcounter{equation}{18}
  84 \setcounter{enumi}{4}
  85 \setcounter{enumii}{0}
  86 \setcounter{enumiii}{0}
  87 \setcounter{enumiv}{15}
  88 \setcounter{footnote}{0}
  89 \setcounter{mpfootnote}{0}
  90 \setcounter{part}{1}
  91 \setcounter{chapter}{12}
  92 \setcounter{section}{7}
  93 \setcounter{subsection}{0}
  94 \setcounter{subsubsection}{0}
  95 \setcounter{paragraph}{0}
  96 \setcounter{subparagraph}{0}
  97 \setcounter{figure}{7}
  98 \setcounter{table}{3}
  99 \setcounter{numauthors}{0}
 100 \setcounter{parentequation}{46}
 101 \setcounter{subfigure}{0}
 102 \setcounter{lofdepth}{1}
 103 \setcounter{subtable}{0}
 104 \setcounter{lotdepth}{1}
 105 \setcounter{lstnumber}{55}
 106 \setcounter{ContinuedFloat}{0}
 107 \setcounter{AlgoLine}{12}
 108 \setcounter{algocfline}{12}
 109 \setcounter{algocfproc}{12}
 110 \setcounter{algocf}{12}
 111 \setcounter{proposition}{1}
 112 \setcounter{theorem}{0}
 113 \setcounter{exercise}{0}
 114 \setcounter{example}{0}
 115 \setcounter{definition}{0}
 116 \setcounter{proof}{1}
 117 \setcounter{lstlisting}{4}
 118 }