X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/rce2015.git/blobdiff_plain/f463119047e7f3b45c777e90a8702e74aba0f520..b0694e2563db1ac6146d29848f55971b9b021fd2:/paper.tex?ds=inline

diff --git a/paper.tex b/paper.tex
index f3ef835..8583e51 100644
--- a/paper.tex
+++ b/paper.tex
@@ -1,4 +1,13 @@
-\documentclass[conference]{IEEEtran}
+\documentclass[times]{cpeauth}
+
+\usepackage{moreverb}
+
+%\usepackage[dvips,colorlinks,bookmarksopen,bookmarksnumbered,citecolor=red,urlcolor=red]{hyperref}
+
+%\newcommand\BibTeX{{\rmfamily B\kern-.05em \textsc{i\kern-.025em b}\kern-.08em
+%T\kern-.1667em\lower.7ex\hbox{E}\kern-.125emX}}
+
+\def\volumeyear{2015}
 
 \usepackage{graphicx}
 \usepackage{wrapfig}
@@ -27,6 +36,7 @@
 
 \usepackage{xspace}
 \usepackage[textsize=footnotesize]{todonotes}
+
 \newcommand{\AG}[2][inline]{%
   \todo[color=green!50,#1]{\sffamily\textbf{AG:} #2}\xspace}
 \newcommand{\RC}[2][inline]{%
@@ -53,36 +63,34 @@
 \definecolor{Gray}{gray}{0.9}
 
 
+
 \begin{document}
 \RCE{Titre a confirmer.}
-
 \title{Comparative performance analysis of simulated grid-enabled numerical iterative algorithms}
+%\itshape{\journalnamelc}\footnotemark[2]}
 
-\author{%
-  \IEEEauthorblockN{%
-    Charles Emile Ramamonjisoa and
+\author{    Charles Emile Ramamonjisoa and
     David Laiymani and
     Arnaud Giersch and
     Lilia Ziane Khodja and
     Raphaël Couturier
-  }
-  \IEEEauthorblockA{%
+}
+
+\address{
+	\centering    
     Femto-ST Institute - DISC Department\\
     Université de Franche-Comté\\
     Belfort\\
     Email: \email{{raphael.couturier,arnaud.giersch,david.laiymani,charles.ramamonjisoa}@univ-fcomte.fr}
-  }
 }
 
-\maketitle
-
 \begin{abstract}
 ABSTRACT
+\end{abstract}
 
+\keywords{Algorithm; distributed; iterative; asynchronous; simulation; simgrid; performance}
 
-Keywords : Algorithm distributed iterative asynchronous simulation simgrid performance
-
-\end{abstract}
+\maketitle
 
 \section{Introduction}
 
@@ -194,7 +202,7 @@ and our comments.
 
 \textit{3.a Executing the algorithms on various computational grid 
 architecture scaling up the input matrix size}
-
+\\
 
 % environment
 \begin{footnotesize}
@@ -209,18 +217,24 @@ architecture scaling up the input matrix size}
 
 
  Table 1 : Clusters x Nodes with NX=150 or NX=170
-\RCE{J'ai voulu mettre les tableaux des données mais je pense que c'est inutile et ça va surcharger}
 
-\begin{wrapfigure}{l}{50mm}
-\centering
-\includegraphics[width=50mm]{Cluster x Nodes NX=150 and NX=170.jpg}
-\caption{Cluster x Nodes NX=150 and NX=170 \label{overflow}}
-\end{wrapfigure}
+\RCE{J'ai voulu mettre les tableaux des données mais je pense que c'est inutile et ça va surcharger}
 
 
 The results in figure 1 show the non-variation of the number of 
 iterations of classical GMRES for a given input matrix size; it is not 
-the case for the multisplitting method. Unless the 8x8 cluster, the time 
+the case for the multisplitting method. 
+
+%\begin{wrapfigure}{l}{60mm}
+\begin{figure} [ht!]
+\centering
+\includegraphics[width=60mm]{cluster_x_nodes_nx_150_and_nx_170.pdf}
+\caption{Cluster x Nodes NX=150 and NX=170} 
+%\label{overflow}}
+\end{figure}
+%\end{wrapfigure}
+
+Unless the 8x8 cluster, the time 
 execution difference between the two algorithms is important when 
 comparing between different grid architectures, even with the same number of 
 processors (like 2x16 and 4x8 = 32 processors for example). The 
@@ -237,7 +251,7 @@ matrix size.
  Grid & 2x16, 4x8\\ %\hline
  Network & N1 : bw=10Gbs-lat=8E-06 \\ %\hline
  - & N2 : bw=1Gbs-lat=5E-05 \\
- Input matrix size & N$_{x}$ =150 x 150 x 150\\ \hline
+ Input matrix size & N$_{x}$ =150 x 150 x 150\\ \hline \\
  \end{tabular}
 \end{footnotesize}
 
@@ -245,11 +259,14 @@ matrix size.
 %\RCE{idem pour tous les tableaux de donnees}
 
 
-\begin{wrapfigure}{l}{45mm}
+%\begin{wrapfigure}{l}{60mm}
+\begin{figure} [ht!]
 \centering
-\includegraphics[width=50mm]{Cluster x Nodes N1 x N2.jpg}
-\caption{Cluster x Nodes N1 x N2\label{overflow}}
-\end{wrapfigure}
+\includegraphics[width=60mm]{cluster_x_nodes_n1_x_n2.pdf}
+\caption{Cluster x Nodes N1 x N2}
+%\label{overflow}}
+\end{figure}
+%\end{wrapfigure}
 
 The experiments compare the behavior of the algorithms running first on 
 speed inter- cluster network (N1) and a less performant network (N2). 
@@ -259,7 +276,7 @@ performance was increased in a factor of 2. The results depict also that
 when the network speed drops down, the difference between the execution 
 times can reach more than 25\%. 
 
-\textit{3.c Network latency impacts on performance}
+\textit{\\\\\\\\\\\\\\\\\\3.c Network latency impacts on performance}
 
 % environment
 \begin{footnotesize}
@@ -267,18 +284,19 @@ times can reach more than 25\%.
  \hline  
  Grid & 2x16\\ %\hline
  Network & N1 : bw=1Gbs \\ %\hline
- Input matrix size & N$_{x}$ =150 x 150 x 150\\ \hline
+ Input matrix size & N$_{x}$ =150 x 150 x 150\\ \hline\\
  \end{tabular}
 \end{footnotesize}
 
 Table 3 : Network latency impact
 
 
-\begin{wrapfigure}{l}{60mm}
+\begin{figure} [ht!]
 \centering
-\includegraphics[width=60mm]{Network latency impact on execution time.jpg}
-\caption{Network latency impact on execution time\label{overflow}}
-\end{wrapfigure}
+\includegraphics[width=60mm]{network_latency_impact_on_execution_time.pdf}
+\caption{Network latency impact on execution time}
+%\label{overflow}}
+\end{figure}
 
 
 According the results in table and figure 3, degradation of the network 
@@ -305,11 +323,12 @@ of magnitude with a latency of 8.10$^{-6}$.
 
 Table 4 : Network bandwidth impact
 
-\begin{wrapfigure}{l}{60mm}
+\begin{figure} [ht!]
 \centering
-\includegraphics[width=60mm]{Network bandwith impact on execution time.jpg}
-\caption{Network bandwith impact on execution time\label{overflow}}
-\end{wrapfigure}
+\includegraphics[width=60mm]{network_bandwith_impact_on_execution_time.pdf}
+\caption{Network bandwith impact on execution time}
+%\label{overflow}
+\end{figure}
 
 
 
@@ -333,11 +352,12 @@ a gain of 40\% which is only around 24\% for classical GMRES.
 
 Table 5 : Input matrix size impact
 
-\begin{wrapfigure}{l}{50mm}
+\begin{figure} [ht!]
 \centering
-\includegraphics[width=60mm]{Pb size impact on execution time.jpg}
-\caption{Pb size impact on execution time\label{overflow}}
-\end{wrapfigure}
+\includegraphics[width=60mm]{pb_size_impact_on_execution_time.pdf}
+\caption{Pb size impact on execution time}
+%\label{overflow}}
+\end{figure}
 
 In this experimentation, the input matrix size has been set from 
 Nx=Ny=Nz=40 to 200 side elements that is from 40$^{3}$ = 64.000 to 
@@ -367,11 +387,12 @@ same test has been done with the grid 2x16 getting the same conclusion.
 
 Table 6 : CPU Power impact
 
-\begin{wrapfigure}{l}{60mm}
+\begin{figure} [ht!]
 \centering
-\includegraphics[width=60mm]{CPU Power impact on execution time.jpg}
-\caption{CPU Power impact on execution time\label{overflow}}
-\end{wrapfigure}
+\includegraphics[width=60mm]{cpu_power_impact_on_execution_time.pdf}
+\caption{CPU Power impact on execution time}
+%\label{overflow}}
+\end{figure}
 
 Using the SIMGRID simulator flexibility, we have tried to determine the 
 impact on the algorithms performance in varying the CPU power of the