Commentaires sur la contribution

[rce2015.git] / paper.tex

diff --git a/paper.tex b/paper.tex
index 46ecc39896759d726aae43c489435194d4d27558..5b8ada3eb4a39c28943053fe5ec0d6e434ec5b3b 100644 (file)
--- a/paper.tex
+++ b/paper.tex
@@ -174,10 +174,22 @@ applications (i.e. large linear system solvers) can help developers to better
 tune their application for a given multi-core architecture. To show the validity
 of this approach we first compare the simulated execution of the multisplitting
 algorithm  with  the  GMRES   (Generalized   Minimal  Residual)
 tune their application for a given multi-core architecture. To show the validity
 of this approach we first compare the simulated execution of the multisplitting
 algorithm  with  the  GMRES   (Generalized   Minimal  Residual)

-solver~\cite{saad86} in synchronous mode. The obtained results on different
+solver~\cite{saad86} in synchronous mode. 
+
+\LZK{Pas trop convainquant comme argument pour valider l'approche de simulation. \\On peut dire par exemple: on a pu simuler différents algos itératifs à large échelle (le plus connu GMRES et deux variantes de multisplitting) et la simulation nous a permis (sans avoir le vrai matériel) de déterminer quelle serait la meilleure solution pour une telle configuration de l'archi ou vice versa.\\A revoir...}
+
+The obtained results on different

 simulated multi-core architectures confirm the real results previously obtained
 simulated multi-core architectures confirm the real results previously obtained

-on non simulated architectures.  We also confirm  the efficiency  of the
-asynchronous  multisplitting algorithm  compared to the synchronous  GMRES. In
+on non simulated architectures.  
+
+\LZK{Il n y a pas dans la partie expé cette comparaison et confirmation des résultats entre la simulation et l'exécution réelle des algos sur les vrais clusters.\\ Sinon on pourrait ajouter dans la partie expé une référence vers le journal supercomput de krylov multi pour confirmer que cette méthode est meilleure que GMRES sur les clusters large échelle.}
+
+We also confirm  the efficiency  of the
+asynchronous  multisplitting algorithm  compared to the synchronous  GMRES. 
+
+\LZK{P.S.: Pour tout le papier, le principal objectif n'est pas de faire des comparaisons entre des méthodes itératives!!\\Sinon, les deux algorithmes Krylov multisplitting synchrone et multisplitting asynchrone sont plus efficaces que GMRES sur des clusters à large échelle.\\Et préciser, si c'est vraiment le cas, que le multisplitting asynchrone est plus efficace et adapté aux clusters distants par rapport aux deux autres algos (je n'ai pas encore lu la partie expé)}
+
+In

 this way and with a simple computing architecture (a laptop) SimGrid allows us
 to run a test campaign  of  a  real parallel iterative  applications on
 different simulated multi-core architectures.  To our knowledge, there is no
 this way and with a simple computing architecture (a laptop) SimGrid allows us
 to run a test campaign  of  a  real parallel iterative  applications on
 different simulated multi-core architectures.  To our knowledge, there is no


@@ -191,8 +203,10 @@ Section~\ref{sec:04} details the different solvers that we use.  Finally our
 experimental results are presented in section~\ref{sec:expe} followed by some
 concluding remarks and perspectives.
 
 experimental results are presented in section~\ref{sec:expe} followed by some
 concluding remarks and perspectives.
 

+\LZK{Proposition d'un titre pour le papier: Grid-enabled simulation of large-scale linear iterative solvers.}
+

 
 

-\section{The asynchronous iteration model}
+\section{The asynchronous iteration model and the motivations of our work}

 \label{sec:asynchro}
 
 Asynchronous iterative methods have been  studied for many years theoritecally and
 \label{sec:asynchro}
 
 Asynchronous iterative methods have been  studied for many years theoritecally and


@@ -216,6 +230,21 @@ point. In the  asynchronous model, the convergence detection is  more tricky as
 it   must  not   synchronize  all   the  processors.   Interested  readers   can
 consult~\cite{myBCCV05c,bahi07,ccl09:ij}.
 
 it   must  not   synchronize  all   the  processors.   Interested  readers   can
 consult~\cite{myBCCV05c,bahi07,ccl09:ij}.
 

+The number of iterations required to reach the convergence is generally greater
+for the asynchronous scheme (this number depends depends on  the delay of the
+messages). Note that, it is not the case in the synchronous mode where the
+number of iterations is the same than in the sequential mode. In this way, the
+set of the parameters  of the  platform (number  of nodes,  power of nodes,
+inter and  intra clusters  bandwidth  and  latency \ldots) and  of  the
+application can drastically change the number of iterations required to get the
+convergence. It follows that asynchronous iterative algorithms are difficult to
+optimize since the financial and deployment costs on large scale multi-core
+architecture are often very important. So, prior to delpoyment and tests it
+seems very promising to be able to simulate the behavior of asynchronous
+iterative algorithms. The problematic is then to show that the results produce
+by simulation are in accordance with reality i.e. of the same order of
+magnitude. To our knowledge, there is no study on this problematic.
+

 \section{SimGrid}
  \label{sec:simgrid}
 
 \section{SimGrid}
  \label{sec:simgrid}
 


@@ -241,7 +270,7 @@ where $x_\ell$ are sub-vectors of the solution $x$, $b_\ell$ are the sub-vectors
 A_{\ell\ell} x_\ell = c_\ell,\mbox{~for~}\ell=1,\ldots,L,
 \label{eq:03}
 \end{equation}
 A_{\ell\ell} x_\ell = c_\ell,\mbox{~for~}\ell=1,\ldots,L,
 \label{eq:03}
 \end{equation}

-where right-hand sides $c_\ell=b_\ell-\sum_{m\neq\ell}A_{\ell m}x_m$ are computed using the shared vectors $x_m$. In this paper, we use the well-known iterative method GMRES ({\it Generalized Minimal RESidual})~\cite{saad86} as an inner iteration to approximate the solutions of the different splittings arising from the block Jacobi multisplitting of matrix $A$. The algorithm in Figure~\ref{alg:01} shows the main key points of our block Jacobi two-stage method executed by a cluster of processors. In line~\ref{solve}, the linear sub-system~(\ref{eq:03}) is solved in parallel using GMRES method where $\MIG$ and $\TOLG$ are the maximum number of inner iterations and the tolerance threshold for GMRES respectively. The convergence of the two-stage multisplitting methods, based on synchronous or asynchronous iterations, has been studied by many authors for example~\cite{Bru95,bahi07}.
+where right-hand sides $c_\ell=b_\ell-\sum_{m\neq\ell}A_{\ell m}x_m$ are computed using the shared vectors $x_m$. In this paper, we use the well-known iterative method GMRES ({\it Generalized Minimal RESidual})~\cite{saad86} as an inner iteration to approximate the solutions of the different splittings arising from the block Jacobi multisplitting of matrix $A$. The algorithm in Figure~\ref{01} shows the main key points of our block Jacobi two-stage method executed by a cluster of processors. In line~\ref{solve}, the linear sub-system~(\ref{eq:03}) is solved in parallel using GMRES method where $\MIG$ and $\TOLG$ are the maximum number of inner iterations and the tolerance threshold for GMRES respectively. The convergence of the two-stage multisplitting methods, based on synchronous or asynchronous iterations, has been studied by many authors for example~\cite{Bru95,bahi07}.

 
 \begin{figure}[t]
 %\begin{algorithm}[t]
 
 \begin{figure}[t]
 %\begin{algorithm}[t]


@@ -358,6 +387,7 @@ In addition, the following arguments are given to the programs at runtime:
        \item execution mode: synchronous or asynchronous.
 \end{itemize}
 \LZK{CE pourrais tu vérifier et confirmer les valeurs des éléments diag et off-diag de la matrice?}
        \item execution mode: synchronous or asynchronous.
 \end{itemize}
 \LZK{CE pourrais tu vérifier et confirmer les valeurs des éléments diag et off-diag de la matrice?}

+\RCE{oui, les valeurs de diag et off-diag donnees sont ok}

 
 It should also be noticed that both solvers have been executed with the Simgrid selector \texttt{-cfg=smpi/running\_power} which determines the computational power (here 19GFlops) of the simulator host machine.
 
 
 It should also be noticed that both solvers have been executed with the Simgrid selector \texttt{-cfg=smpi/running\_power} which determines the computational power (here 19GFlops) of the simulator host machine.
 


@@ -433,13 +463,13 @@ input data.  \\
 a grid environment}
 
 When running a distributed application in a computational grid, many factors may
 a grid environment}
 
 When running a distributed application in a computational grid, many factors may

-have a strong impact on the performances.  First of all, the architecture of the
+have a strong impact on the performance.  First of all, the architecture of the

 grid itself can obviously influence the  performance results of the program. The
 performance gain  might be important  theoretically when the number  of clusters
 and/or  the  number  of  nodes (processors/cores)  in  each  individual  cluster
 increase.
 
 grid itself can obviously influence the  performance results of the program. The
 performance gain  might be important  theoretically when the number  of clusters
 and/or  the  number  of  nodes (processors/cores)  in  each  individual  cluster
 increase.
 

-Another important factor  impacting the overall performances  of the application
+Another important factor  impacting the overall performance  of the application

 is the network configuration. Two main network parameters can modify drastically
 the program output results:
 \begin{enumerate}
 is the network configuration. Two main network parameters can modify drastically
 the program output results:
 \begin{enumerate}


@@ -465,8 +495,8 @@ and  between distant  clusters.  This parameter is application dependent.
 \subsection{Comparison of GMRES and Krylov Multisplitting algorithms in synchronous mode}
 
 In the scope  of this paper, our  first objective is to analyze  when the Krylov
 \subsection{Comparison of GMRES and Krylov Multisplitting algorithms in synchronous mode}
 
 In the scope  of this paper, our  first objective is to analyze  when the Krylov

-Multisplitting  method   has  better  performances  than   the  classical  GMRES
-method. With a synchronous  iterative method, better performances mean a
+Multisplitting  method   has  better  performance  than   the  classical  GMRES
+method. With a synchronous  iterative method, better performance mean a

 smaller number of iterations and execution time before reaching the convergence.
 For a systematic study,  the experiments  should figure  out  that, for  various
 grid  parameters values, the simulator will confirm  the targeted outcomes,
 smaller number of iterations and execution time before reaching the convergence.
 For a systematic study,  the experiments  should figure  out  that, for  various
 grid  parameters values, the simulator will confirm  the targeted outcomes,


@@ -482,18 +512,19 @@ architectures and scaling up the input matrix size}
 \ \\
 % environment
 
 \ \\
 % environment
 

-\begin{figure} [ht!]
+\begin{table} [ht!]

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

- Grid & 2x16, 4x8, 4x16 and 8x8\\ %\hline
+ Grid Architecture & 2x16, 4x8, 4x16 and 8x8\\ %\hline

  Network & N2 : bw=1Gbits/s - lat=5.10$^{-5}$ \\ %\hline
  Input matrix size & N$_{x}$ x N$_{y}$ x N$_{z}$ =150 x 150 x 150\\ %\hline
  - &  N$_{x}$ x N$_{y}$ x N$_{z}$  =170 x 170 x 170    \\ \hline
  \end{tabular}
  Network & N2 : bw=1Gbits/s - lat=5.10$^{-5}$ \\ %\hline
  Input matrix size & N$_{x}$ x N$_{y}$ x N$_{z}$ =150 x 150 x 150\\ %\hline
  - &  N$_{x}$ x N$_{y}$ x N$_{z}$  =170 x 170 x 170    \\ \hline
  \end{tabular}

-\caption{Clusters x Nodes with N$_{x}$=150 or N$_{x}$=170 \RC{je ne comprends pas la légende... Ca ne serait pas plutot Characteristics of cluster (mais il faudrait lui donner un nom)}}
+\caption{Test conditions: Various grid configurations with the input matix size N$_{x}$=150 or N$_{x}$=170 \RC{je ne comprends pas la légende... Ca ne serait pas plutot Characteristics of cluster (mais il faudrait lui donner un nom)}}
+\label{tab:01}

 \end{center}
 \end{center}

-\end{figure}
+\end{table}

 
 
 
 
 
 


@@ -501,7 +532,7 @@ architectures and scaling up the input matrix size}
 %\RCE{J'ai voulu mettre les tableaux des données mais je pense que c'est inutile et ça va surcharger}
 
 
 %\RCE{J'ai voulu mettre les tableaux des données mais je pense que c'est inutile et ça va surcharger}
 
 

-In this  section, we analyze the  performences of algorithms running  on various
+In this  section, we analyze the  performance of algorithms running  on various

 grid configurations  (2x16, 4x8, 4x16  and 8x8). First,  the results in  Figure~\ref{fig:01}
 show for all grid configurations the non-variation of the number of iterations of
 classical  GMRES for  a given  input matrix  size; it is not  the case  for the
 grid configurations  (2x16, 4x8, 4x16  and 8x8). First,  the results in  Figure~\ref{fig:01}
 show for all grid configurations the non-variation of the number of iterations of
 classical  GMRES for  a given  input matrix  size; it is not  the case  for the


@@ -515,7 +546,7 @@ multisplitting method.
   \begin{center}
     \includegraphics[width=100mm]{cluster_x_nodes_nx_150_and_nx_170.pdf}
   \end{center}
   \begin{center}
     \includegraphics[width=100mm]{cluster_x_nodes_nx_150_and_nx_170.pdf}
   \end{center}

-  \caption{Cluster x Nodes N$_{x}$=150 and N$_{x}$=170}
+  \caption{Various grid configurations with the input matrix size N$_{x}$=150 and N$_{x}$=170}

   \label{fig:01}
 \end{figure}
 
   \label{fig:01}
 \end{figure}
 


@@ -527,54 +558,56 @@ and  4x8). We  can  observ  the low  sensitivity  of  the Krylov multisplitting
 in the  grid: in  average, the GMRES  (resp. Multisplitting)  algorithm performs
 $40\%$ better (resp. $48\%$) when running from 2x16=32 to 8x8=64 processors.
 
 in the  grid: in  average, the GMRES  (resp. Multisplitting)  algorithm performs
 $40\%$ better (resp. $48\%$) when running from 2x16=32 to 8x8=64 processors.
 

-\subsubsection{Running on two different inter-clusters network speed}
-\ \\
+\subsubsection{Running on two different inter-clusters network speeds \\}

 
 

-\begin{figure} [ht!]
+\begin{table} [ht!]

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

- Grid & 2x16, 4x8\\ %\hline
+ Grid Architecture & 2x16, 4x8\\ %\hline

  Network & N1 : bw=10Gbs-lat=8.10$^{-6}$ \\ %\hline
  - & N2 : bw=1Gbs-lat=5.10$^{-5}$ \\
  Input matrix size & N$_{x}$ x N$_{y}$ x N$_{z}$ =150 x 150 x 150\\ \hline
  \end{tabular}
  Network & N1 : bw=10Gbs-lat=8.10$^{-6}$ \\ %\hline
  - & N2 : bw=1Gbs-lat=5.10$^{-5}$ \\
  Input matrix size & N$_{x}$ x N$_{y}$ x N$_{z}$ =150 x 150 x 150\\ \hline
  \end{tabular}

-\caption{Clusters x Nodes - Networks N1 x N2}
+\caption{Test conditions: Grid 2x16 and 4x8 - Networks N1 vs N2}
+\label{tab:02}

 \end{center}
 \end{center}

-\end{figure}
+\end{table}

 
 

+These experiments  compare the  behavior of  the algorithms  running first  on a
+speed inter-cluster  network (N1) and  also on  a less performant  network (N2).
+Figure~\ref{fig:02} shows that end users will  gain to reduce the execution time
+for  both  algorithms  in using  a  grid  architecture  like  4x16 or  8x8:  the
+performance was increased  by a factor of  $2$. The results depict  also that when
+the  network speed  drops down (variation of 12.5\%), the  difference between  the two Multisplitting algorithms execution times can reach more than 25\%.
+%\RC{c'est pas clair : la différence entre quoi et quoi?}
+%\DL{pas clair}
+%\RCE{Modifie}

 
 
 %\begin{wrapfigure}{l}{100mm}
 \begin{figure} [ht!]
 \centering
 \includegraphics[width=100mm]{cluster_x_nodes_n1_x_n2.pdf}
 
 
 %\begin{wrapfigure}{l}{100mm}
 \begin{figure} [ht!]
 \centering
 \includegraphics[width=100mm]{cluster_x_nodes_n1_x_n2.pdf}

-\caption{Cluster x Nodes N1 x N2}
+\caption{Grid 2x16 and 4x8 - Networks N1 vs N2}

 \label{fig:02}
 \end{figure}
 %\end{wrapfigure}
 
 \label{fig:02}
 \end{figure}
 %\end{wrapfigure}
 

-These experiments  compare the  behavior of  the algorithms  running first  on a
-speed inter-cluster  network (N1) and  also on  a less performant  network (N2).
-Figure~\ref{fig:02} shows that end users will  gain to reduce the execution time
-for  both  algorithms  in using  a  grid  architecture  like  4x16 or  8x8:  the
-performance was increased  by a factor of  $2$. The results depict  also that when
-the  network speed  drops down  (12.5\%), the  difference between  the execution
-times can reach more than 25\%. \RC{c'est pas clair : la différence entre quoi et quoi?}
-\DL{pas clair}

 
 \subsubsection{Network latency impacts on performance}
 \ \\
 
 \subsubsection{Network latency impacts on performance}
 \ \\

-\begin{figure} [ht!]
+\begin{table} [ht!]

 \centering
 \begin{tabular}{r c }
  \hline
 \centering
 \begin{tabular}{r c }
  \hline

- Grid & 2x16\\ %\hline
+ Grid Architecture & 2x16\\ %\hline

  Network & N1 : bw=1Gbs \\ %\hline
  Input matrix size & N$_{x}$ x N$_{y}$ x N$_{z}$ =150 x 150 x 150\\ \hline
  \end{tabular}
  Network & N1 : bw=1Gbs \\ %\hline
  Input matrix size & N$_{x}$ x N$_{y}$ x N$_{z}$ =150 x 150 x 150\\ \hline
  \end{tabular}

-\caption{Network latency impacts}
-\end{figure}
+\caption{Test conditions: Network latency impacts}
+\label{tab:03}
+\end{table}

 
 
 
 
 
 


@@ -598,16 +631,17 @@ order of magnitude with a latency of $8.10^{-6}$.
 
 \subsubsection{Network bandwidth impacts on performance}
 \ \\
 
 \subsubsection{Network bandwidth impacts on performance}
 \ \\

-\begin{figure} [ht!]
+\begin{table} [ht!]

 \centering
 \begin{tabular}{r c }
  \hline
 \centering
 \begin{tabular}{r c }
  \hline

- Grid & 2x16\\ %\hline
+ Grid Architecture & 2x16\\ %\hline

  Network & N1 : bw=1Gbs - lat=5.10$^{-5}$ \\ %\hline
  Input matrix size & N$_{x}$ x N$_{y}$ x N$_{z}$ =150 x 150 x 150\\ \hline \\
  \end{tabular}
  Network & N1 : bw=1Gbs - lat=5.10$^{-5}$ \\ %\hline
  Input matrix size & N$_{x}$ x N$_{y}$ x N$_{z}$ =150 x 150 x 150\\ \hline \\
  \end{tabular}

-\caption{Network bandwidth impacts}
-\end{figure}
+\caption{Test conditions: Network bandwidth impacts}
+\label{tab:04}
+\end{table}

 
 
 \begin{figure} [ht!]
 
 
 \begin{figure} [ht!]


@@ -625,16 +659,17 @@ of $40\%$ which is only around $24\%$ for the classical GMRES.
 
 \subsubsection{Input matrix size impacts on performance}
 \ \\
 
 \subsubsection{Input matrix size impacts on performance}
 \ \\

-\begin{figure} [ht!]
+\begin{table} [ht!]

 \centering
 \begin{tabular}{r c }
  \hline
 \centering
 \begin{tabular}{r c }
  \hline

- Grid & 4x8\\ %\hline
+ Grid Architecture & 4x8\\ %\hline

  Network & N2 : bw=1Gbs - lat=5.10$^{-5}$ \\
  Input matrix size & N$_{x}$ = From 40 to 200\\ \hline
  \end{tabular}
  Network & N2 : bw=1Gbs - lat=5.10$^{-5}$ \\
  Input matrix size & N$_{x}$ = From 40 to 200\\ \hline
  \end{tabular}

-\caption{Input matrix size impacts}
-\end{figure}
+\caption{Test conditions: Input matrix size impacts}
+\label{tab:05}
+\end{table}

 
 
 \begin{figure} [ht!]
 
 
 \begin{figure} [ht!]


@@ -650,8 +685,8 @@ In these experiments, the input matrix size  has been set from $N_{x} = N_{y}
 time for  both algorithms increases when  the input matrix size  also increases.
 But the interesting results are:
 \begin{enumerate}
 time for  both algorithms increases when  the input matrix size  also increases.
 But the interesting results are:
 \begin{enumerate}

-  \item the drastic increase ($300$ times) \RC{Je ne vois pas cela sur la figure}
-of the  number of  iterations needed  to reach the  convergence for  the classical
+  \item the drastic increase ($10$ times) \RC{Je ne vois pas cela sur la figure}
+\RCE{Corrige} of the  number of  iterations needed  to reach the  convergence for  the classical

 GMRES algorithm when  the matrix size go beyond $N_{x}=150$;
 \item the  classical GMRES execution time  is almost the double  for $N_{x}=140$
   compared with the Krylov multisplitting method.
 GMRES algorithm when  the matrix size go beyond $N_{x}=150$;
 \item the  classical GMRES execution time  is almost the double  for $N_{x}=140$
   compared with the Krylov multisplitting method.


@@ -664,16 +699,17 @@ grid 2x16 leading to the same conclusion.
 
 \subsubsection{CPU Power impacts on performance}
 
 
 \subsubsection{CPU Power impacts on performance}
 

-\begin{figure} [ht!]
+\begin{table} [ht!]

 \centering
 \begin{tabular}{r c }
  \hline
 \centering
 \begin{tabular}{r c }
  \hline

- Grid & 2x16\\ %\hline
+ Grid architecture & 2x16\\ %\hline

  Network & N2 : bw=1Gbs - lat=5.10$^{-5}$ \\ %\hline
  Input matrix size & N$_{x}$ = 150 x 150 x 150\\ \hline
  \end{tabular}
  Network & N2 : bw=1Gbs - lat=5.10$^{-5}$ \\ %\hline
  Input matrix size & N$_{x}$ = 150 x 150 x 150\\ \hline
  \end{tabular}

-\caption{CPU Power impacts}
-\end{figure}
+\caption{Test conditions: CPU Power impacts}
+\label{tab:06}
+\end{table}

 
 \begin{figure} [ht!]
 \centering
 
 \begin{figure} [ht!]
 \centering


@@ -692,12 +728,13 @@ powerful CPU.
 obtenus en grandeur réelle. Donc c'est une aide précieuse pour les dev. Pas
 besoin de déployer sur une archi réelle}
 
 obtenus en grandeur réelle. Donc c'est une aide précieuse pour les dev. Pas
 besoin de déployer sur une archi réelle}
 

+

 \subsection{Comparing GMRES in native synchronous mode and the multisplitting algorithm in asynchronous mode}
 
 The previous paragraphs  put in evidence the interests to  simulate the behavior
 of  the application  before  any  deployment in  a  real  environment.  In  this
 section, following  the same previous  methodology, our  goal is to  compare the
 \subsection{Comparing GMRES in native synchronous mode and the multisplitting algorithm in asynchronous mode}
 
 The previous paragraphs  put in evidence the interests to  simulate the behavior
 of  the application  before  any  deployment in  a  real  environment.  In  this
 section, following  the same previous  methodology, our  goal is to  compare the

-efficiency of the multisplitting method  in \textit{ asynchronous mode} with the
+efficiency of the multisplitting method  in \textit{ asynchronous mode} compared with the

 classical GMRES in \textit{synchronous mode}.
 
 The  interest of  using  an asynchronous  algorithm  is that  there  is no  more
 classical GMRES in \textit{synchronous mode}.
 
 The  interest of  using  an asynchronous  algorithm  is that  there  is no  more


@@ -708,33 +745,35 @@ theoretically reduce  the overall execution  time and can improve  the algorithm
 performance.
 
 \RC{la phrase suivante est bizarre, je ne comprends pas pourquoi elle vient ici}
 performance.
 
 \RC{la phrase suivante est bizarre, je ne comprends pas pourquoi elle vient ici}

-As stated before, the Simgrid simulator tool has been successfully used to show
+In this section, Simgrid simulator tool has been successfully used to show

 the efficiency of  the multisplitting in asynchronous mode and  to find the best
 combination of the grid resources (CPU,  Network, input matrix size, \ldots ) to
 get    the   highest    \textit{"relative    gain"}   (exec\_time$_{GMRES}$    /
 exec\_time$_{multisplitting}$) in comparison with the classical GMRES time.
 
 
 the efficiency of  the multisplitting in asynchronous mode and  to find the best
 combination of the grid resources (CPU,  Network, input matrix size, \ldots ) to
 get    the   highest    \textit{"relative    gain"}   (exec\_time$_{GMRES}$    /
 exec\_time$_{multisplitting}$) in comparison with the classical GMRES time.
 
 

-The test conditions are summarized in the table below: \\
+The test conditions are summarized in the table~\ref{tab:07}: \\

 
 

-\begin{figure} [ht!]
+\begin{table} [ht!]

 \centering
 \begin{tabular}{r c }
  \hline
 \centering
 \begin{tabular}{r c }
  \hline

- Grid & 2x50 totaling 100 processors\\ %\hline
+ Grid Architecture & 2x50 totaling 100 processors\\ %\hline

  Processors Power & 1 GFlops to 1.5 GFlops\\
    Intra-Network & bw=1.25 Gbits - lat=5.10$^{-5}$ \\ %\hline
    Inter-Network & bw=5 Mbits - lat=2.10$^{-2}$\\
  Input matrix size & N$_{x}$ = From 62 to 150\\ %\hline
  Residual error precision & 10$^{-5}$ to 10$^{-9}$\\ \hline \\
  \end{tabular}
  Processors Power & 1 GFlops to 1.5 GFlops\\
    Intra-Network & bw=1.25 Gbits - lat=5.10$^{-5}$ \\ %\hline
    Inter-Network & bw=5 Mbits - lat=2.10$^{-2}$\\
  Input matrix size & N$_{x}$ = From 62 to 150\\ %\hline
  Residual error precision & 10$^{-5}$ to 10$^{-9}$\\ \hline \\
  \end{tabular}

-\end{figure}
+\caption{Test conditions: GMRES in synchronous mode vs Krylov Multisplitting in asynchronous mode}
+\label{tab:07}
+\end{table}

 
 Again,  comprehensive and  extensive tests  have been  conducted with  different
 parameters as  the CPU power, the  network parameters (bandwidth and  latency)
 and with different problem size. The  relative gains greater than $1$  between the
 two algorithms have  been captured after  each step  of the test.   In
 
 Again,  comprehensive and  extensive tests  have been  conducted with  different
 parameters as  the CPU power, the  network parameters (bandwidth and  latency)
 and with different problem size. The  relative gains greater than $1$  between the
 two algorithms have  been captured after  each step  of the test.   In

-Figure~\ref{table:01}  are  reported the  best  grid  configurations allowing
+Figure~\ref{fig:07}  are  reported the  best  grid  configurations allowing

 the  multisplitting method to  be more than  $2.5$ times faster  than the
 classical  GMRES.  These  experiments also  show the  relative tolerance  of the
 multisplitting algorithm when using a low speed network as usually observed with
 the  multisplitting method to  be more than  $2.5$ times faster  than the
 classical  GMRES.  These  experiments also  show the  relative tolerance  of the
 multisplitting algorithm when using a low speed network as usually observed with


@@ -777,7 +816,7 @@ geographically distant clusters through the internet.
   \end{mytable}
 %\end{table}
  \caption{Relative gain of the multisplitting algorithm compared with the classical GMRES}
   \end{mytable}
 %\end{table}
  \caption{Relative gain of the multisplitting algorithm compared with the classical GMRES}

- \label{table:01}
+ \label{fig:07}

 \end{figure}
 
 
 \end{figure}