new

[book_gpu.git] / BookGPU / Chapters / chapter15 / ch15.tex

diff --git a/BookGPU/Chapters/chapter15/ch15.tex b/BookGPU/Chapters/chapter15/ch15.tex
index 5dae9b22fdb97d2982d3e8f1eff38ec0cb84548d..1b3a58062544cdb21b2b1b2b73d2fd942f040eb4 100644 (file)
--- a/BookGPU/Chapters/chapter15/ch15.tex
+++ b/BookGPU/Chapters/chapter15/ch15.tex
@@ -1,13 +1,14 @@
-\chapterauthor{Pierre Fortin}{Laboratoire d'Informatique de Paris 6, University Paris 6}
-\chapterauthor{Rachid Habel}{T\'el\'ecom SudParis}
-\chapterauthor{Fabienne J\'ez\'equel}{Laboratoire d'Informatique de Paris 6, University Paris 6}
-\chapterauthor{Jean-Luc Lamotte}{Laboratoire d'Informatique de Paris 6, University Paris 6}
+\chapterauthor{Rachid Habel}{T\'el\'ecom SudParis, France}
+\chapterauthor{Pierre Fortin, Fabienne J\'ez\'equel and Jean-Luc Lamotte}{Laboratoire d'Informatique de Paris 6, Université Pierre et Marie Curie, France}
+
+%\chapterauthor{Fabienne J\'ez\'equel}{Laboratoire d'Informatique de Paris 6, University Paris 6}
+%\chapterauthor{Jean-Luc Lamotte}{Laboratoire d'Informatique de Paris 6, University Paris 6}

 \chapterauthor{Stan Scott}{School of Electronics, Electrical Engineering \& Computer Science,
 \chapterauthor{Stan Scott}{School of Electronics, Electrical Engineering \& Computer Science,

-The Queen's University of Belfast}
+The Queen's University of Belfast, United Kingdom}

 
 

-\newcommand{\fixme}[1]{{\bf #1}}
+%\newcommand{\fixme}[1]{{\bf #1}}

 
 

-\chapter[Numerical validation and performance optimization on GPUs in atomic physics]{Numerical validation and performance optimization on GPUs of an application in atomic physics} 
+\chapter[Numerical validation and GPU performance in atomic physics]{Numerical validation and performance optimization on GPUs of an application in atomic physics} 

 \label{chapter15}
 
 \section{Introduction}\label{ch15:intro}
 \label{chapter15}
 
 \section{Introduction}\label{ch15:intro}


@@ -275,20 +276,36 @@ $\Re^{O}$.
 the output $R$-matrix becomes  the input $R$-matrix 
 for the next evaluation.  
 
 the output $R$-matrix becomes  the input $R$-matrix 
 for the next evaluation.  
 

+%% \begin{algorithm}
+%% \caption{\label{prop-algo}PROP algorithm}
+%% \begin{algorithmic}
+%% \FOR{all scattering energies}
+%%  \FOR{all sectors}
+%%  \STATE Read amplitude arrays
+%%  \STATE Read correction data
+%% \STATE Construct local $R$-matrices
+%% \STATE From $\Re^{I}$ and local $R$-matrices, compute $\Re^{O}$
+%% \STATE $\Re^{O}$ becomes $\Re^{I}$ for the next sector 
+%%  \ENDFOR
+%%  \STATE Compute physical $R$-Matrix 
+%% \ENDFOR
+%% \end{algorithmic}
+%% \end{algorithm}
+

 \begin{algorithm}
 \caption{\label{prop-algo}PROP algorithm}
 \begin{algorithm}
 \caption{\label{prop-algo}PROP algorithm}

-\begin{algorithmic}
-\FOR{all scattering energies}
- \FOR{all sectors}
- \STATE Read amplitude arrays
- \STATE Read correction data
-\STATE Construct local $R$-matrices
-\STATE From $\Re^{I}$ and local $R$-matrices, compute $\Re^{O}$
-\STATE $\Re^{O}$ becomes $\Re^{I}$ for the next sector 
- \ENDFOR
- \STATE Compute physical $R$-Matrix 
-\ENDFOR
-\end{algorithmic}
+%\begin{algorithmic}
+\For{all scattering energies} {
+ \For{all sectors}{
+  Read amplitude arrays\;
+  Read correction data\;
+  Construct local $R$-matrices\;
+  From $\Re^{I}$ and local $R$-matrices, compute $\Re^{O}$\;
+ $\Re^{O}$ becomes $\Re^{I}$ for the next sector\;
+ }
+ Compute physical $R$-Matrix \;
+}
+%\end{algorithmic}

 \end{algorithm}
 
 
 \end{algorithm}
 
 


@@ -809,7 +826,7 @@ as the matrices increase in size during the propagation
 \section{Performance results}
 \subsection{PROP deployment on GPU}
 
 \section{Performance results}
 \subsection{PROP deployment on GPU}
 

-\begin{table*}[ht]
+\begin{table}[ht]

 \begin{center}
 \begin{tabular}{|c||c|c||}
  \hline
 \begin{center}
 \begin{tabular}{|c||c|c||}
  \hline


@@ -833,38 +850,37 @@ GPU version  & C1060 & C2050 \\
   GPU V5 (\S~\ref{gpuv5}) & 24m27s & 12m39s  \\
   \hline
 \end{tabular}
   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{center}

-\end{table*}
+\caption{Execution time of PROP on CPU and GPU}
+\label{table:time} 
+\end{table}

 
 

-\begin{comment}
-\begin{table*}[ht]
-\begin{center}
-\begin{tabular}{|c||c|c||}
- \hline
-  PROP version & \multicolumn{2}{c|}{Execution time} \\
-  \hline  \hline
-CPU version & 1 core & 4 cores  \\\hline
-& {201m32s} & {113m28s} \\ \hline  \hline
-GPU version  & C1060 & C2050 \\
-  \hline\hline
-  GPU V1 (\ref{gpuv1}) & 79m25s & 66m22s  \\
-  \hline
-  GPU V2 (\ref{gpuv2}) & 47m58s & 29m52s \\
-  \hline
-  GPU V3 (\ref{gpuv3}) & 41m28s & 23m46s \\
-  \hline
-  GPU V4 (\ref{gpuv4}) & 27m21s & 13m55s\\
-  \hline
-  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}
+
+%% \begin{table}[ht]
+%% \begin{center}
+%% \begin{tabular}{|c||c|c||}
+%%  \hline
+%%   PROP version & \multicolumn{2}{c|}{Execution time} \\
+%%   \hline  \hline
+%% CPU version & 1 core & 4 cores  \\\hline
+%% & {201m32s} & {113m28s} \\ \hline  \hline
+%% GPU version  & C1060 & C2050 \\
+%%   \hline\hline
+%%   GPU V1 (\ref{gpuv1}) & 79m25s & 66m22s  \\
+%%   \hline
+%%   GPU V2 (\ref{gpuv2}) & 47m58s & 29m52s \\
+%%   \hline
+%%   GPU V3 (\ref{gpuv3}) & 41m28s & 23m46s \\
+%%   \hline
+%%   GPU V4 (\ref{gpuv4}) & 27m21s & 13m55s\\
+%%   \hline
+%%   GPU V5 (\ref{gpuv5}) & 24m27s & 12m39s  \\
+%%   \hline
+%% \end{tabular}
+%% \end{center}
+%% \caption{Execution time of the successive GPU versions}
+%% \label{table:time} 
+%% \end{table}

 
 \begin{figure}[h]
 \centering
 
 \begin{figure}[h]
 \centering