X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/rce2015.git/blobdiff_plain/49ee5215a4f7de973138cd830c4b5506e6497a34..976b793822811b4335b31747dc0e5542a41fc62b:/paper.tex?ds=sidebyside diff --git a/paper.tex b/paper.tex index fab2e82..0e69066 100644 --- a/paper.tex +++ b/paper.tex @@ -407,10 +407,10 @@ in which several clusters are geographically distant, so there are intra and inter-cluster communications. In the following, these parameters are described: \begin{itemize} - \item hostfile: hosts description file. + \item hostfile: hosts description file, \item platform: file describing the platform architecture: clusters (CPU power, \dots{}), intra cluster network description, inter cluster network (bandwidth $bw$, -latency $lat$, \dots{}). +latency $lat$, \dots{}), \item archi : grid computational description (number of clusters, number of nodes/processors in each cluster). \end{itemize} @@ -485,7 +485,7 @@ results comparison and analysis. In the scope of this study, we retain on the one hand the algorithm execution mode (synchronous and asynchronous) and on the other hand the execution time and the number of iterations to reach the convergence. \\ -\textbf{Step 4 }: Set up the different grid testbed environments that will be +\textbf{Step 4}: Set up the different grid testbed environments that will be simulated in the simulator tool to run the program. The following architectures have been configured in SimGrid : 2$\times$16, 4$\times$8, 4$\times$16, 8$\times$8 and 2$\times$50. The first number represents the number of clusters in the grid and the second number represents @@ -495,6 +495,7 @@ latency of 8.10$^{-6}$ seconds (resp. 5.10$^{-5}$) for the intra-clusters links (resp. inter-clusters backbone links). \\ \LZK{Il me semble que le bw et lat des deux réseaux varient dans les expés d'une simu à l'autre. On vire la dernière phrase?} +\RC{il me semble qu'on peut laisser ca} \textbf{Step 5}: Conduct an extensive and comprehensive testings within these configurations by varying the key parameters, especially @@ -540,61 +541,79 @@ and between distant clusters. This parameter is application dependent. In the scope of this paper, our first objective is to analyze when the Krylov two-stage method has better performance than the classical GMRES method. With a synchronous iterative method, better performance means 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, -particularly for poor and slow networks, focusing on the impact on the -communication performance on the chosen class of algorithm. -\LZK{Pas du tout claire la dernière phrase (For a systematic...)!!} +In what follows, we will present the test conditions, the output results and our comments. + +%%RAPH : on vire ca, c'est pas clair et pas important +%For a systematic study, the experiments should figure out that, for various +%grid parameters values, the simulator will confirm Multisplitting method better performance compared to classical GMRES, particularly on poor and slow networks. +%\LZK{Pas du tout claire la dernière phrase (For a systematic...)!!} +%\RCE { Reformule autrement} + -In what follows, we will present the test conditions, the output results and our comments.\\ %\subsubsection{Execution of the algorithms on various computational grid architectures and scaling up the input matrix size} \subsubsection{Simulations for various grid architectures and scaling-up matrix sizes} \ \\ % environment +\RC{Je ne comprends plus rien CE : pourquoi dans 5.4.1 il y a 2 network et aussi dans 5.4.2. Quelle est la différence? Dans la figure 3 de la section 5.4.1 pourquoi il n'y a pas N1 et N2?} + \begin{table} [ht!] \begin{center} \begin{tabular}{ll } \hline Grid architecture & 2$\times$16, 4$\times$8, 4$\times$16 and 8$\times$8\\ %\hline - Network & N1 : $bw$=1Gbits/s, $lat$=5$\times$10$^{-5}$ \\ %\hline + \multirow{2}{*}{Network} & Inter (N2): $bw$=1Gbs, $lat$=5$\times$10$^{-5}$ \\ %\hline + & Intra (N1): $bw$=10Gbs, $lat$=8$\times$10$^{-6}$ \\ \multirow{2}{*}{Matrix size} & N$_{x}$ $\times$ N$_{y}$ $\times$ N$_{z}$ =150 $\times$ 150 $\times$ 150\\ %\hline & N$_{x}$ $\times$ N$_{y}$ $\times$ N$_{z}$ =170 $\times$ 170 $\times$ 170 \\ \hline \end{tabular} \caption{Test conditions: various grid configurations with the matrix sizes 150$^3$ or 170$^3$} -\LZK{Ce sont les caractéristiques du réseau intra ou inter clusters? Ce n'est pas précisé...} +%\LZK{Ce sont les caractéristiques du réseau intra ou inter clusters? Ce n'est pas précisé...} +%\RCE{oui c est precise} \label{tab:01} \end{center} \end{table} -In this section, we analyze the simulations conducted on various grid configurations presented in Table~\ref{tab:01}. Figure~\ref{fig:01} shows, for all grid configurations and a given matrix size, a non-variation in the number of iterations for the classical GMRES algorithm, which is not the case of the Krylov two-stage algorithm. +In this section, we analyze the simulations conducted on various grid +configurations presented in Table~\ref{tab:01}. It should be noticed that two +networks are considered: N1 is the network between clusters (inter-cluster) and +N2 is the network inside a cluster (intra-cluster). Figure~\ref{fig:01} shows, +for all grid configurations and a given matrix size, a non-variation in the +number of iterations for the classical GMRES algorithm, which is not the case of +the Krylov two-stage algorithm. %% 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 %% multisplitting method. -\RC{CE attention tu n'as pas mis de label dans tes figures, donc c'est le bordel, j'en mets mais vérifie...} -\RC{Les légendes ne sont pas explicites...} +%\RC{CE attention tu n'as pas mis de label dans tes figures, donc c'est le bordel, j'en mets mais vérifie...} +%\RC{Les légendes ne sont pas explicites...} +%\RCE{Corrige} \begin{figure} [ht!] \begin{center} \includegraphics[width=100mm]{cluster_x_nodes_nx_150_and_nx_170.pdf} \end{center} - \caption{Various grid configurations with the matrix sizes 150$^3$ and 170$^3$ -\AG{Utiliser le point comme séparateur décimal et non la virgule. Idem dans les autres figures.}} -\LZK{Pour quelle taille du problème sont calculés les nombres d'itérations? Que représente le 2 Clusters x 16 Nodes with Nx=150 and Nx=170 en haut de la figure?} + \caption{Various grid configurations with the matrix sizes 150$^3$ and 170$^3$} +%\AG{Utiliser le point comme séparateur décimal et non la virgule. Idem dans les autres figures.} +%\LZK{Pour quelle taille du problème sont calculés les nombres d'itérations? Que représente le 2 Clusters x 16 Nodes with Nx=150 and Nx=170 en haut de la figure?} + %\RCE {Corrige} + \RC{Idéalement dans la légende il faudrait insiquer Pb size=$150^3$ ou $170^3$ car pour l'instant Nx=150 ca n'indique rien concernant Ny et Nz} \label{fig:01} \end{figure} + + The execution times between the two algorithms is significant with different -grid architectures, even with the same number of processors (for example, 2x16 -and 4x8). We can observe the low sensitivity of the Krylov multisplitting method +grid architectures, even with the same number of processors (for example, 2 $\times$ 16 +and 4 $\times 8$). We can observe a better sensitivity of the Krylov multisplitting method (compared with the classical GMRES) when scaling up the number of the 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. +$40\%$ better (resp. $48\%$) when running from 32 (grid 2 $\times$ 16) to 64 processors/cores (grid 8 $\times$ 8). Note that even with a grid 8 $\times$ 8 having the maximum number of clusters, the execution time of the multisplitting method is in average 32\% less compared to GMRES. \RC{pas très clair, c'est pas précis de dire qu'un algo perform mieux qu'un autre, selon quel critère?} \LZK{A revoir toute cette analyse... Le multi est plus performant que GMRES. Les temps d'exécution de multi sont sensibles au nombre de CLUSTERS. Il est moins performant pour un nombre grand de cluster. Avez vous d'autres remarques?} +\RCE{Remarquez que meme avec une grille 8x8, le multi est toujours plus performant} \subsubsection{Simulations for two different inter-clusters network speeds \\} @@ -603,7 +622,7 @@ $40\%$ better (resp. $48\%$) when running from 2x16=32 to 8x8=64 processors. \begin{tabular}{ll} \hline Grid architecture & 2$\times$16, 4$\times$8\\ %\hline - \multirow{2}{*}{Network} & N1: $bw$=1Gbs, $lat$=5$\times$10$^{-5}$ \\ %\hline + \multirow{2}{*}{Inter Network} & N1: $bw$=1Gbs, $lat$=5$\times$10$^{-5}$ \\ %\hline & N2: $bw$=10Gbs, $lat$=8$\times$10$^{-6}$ \\ Matrix size & $N_{x} \times N_{y} \times N_{z} =150 \times 150 \times 150$\\ \hline \end{tabular} @@ -613,9 +632,10 @@ $40\%$ better (resp. $48\%$) when running from 2x16=32 to 8x8=64 processors. \end{table} In this section, the experiments compare the behavior of the algorithms running on a -speeder inter-cluster network (N2) and also on a less performant network (N1) respectively defined in the test conditions Table~\ref{tab:02}. \RC{Il faut définir cela avant...} +speeder inter-cluster network (N2) and also on a less performant network (N1) respectively defined in the test conditions Table~\ref{tab:02}. +%\RC{Il faut définir cela avant...} Figure~\ref{fig:02} shows that end users will reduce the execution time -for both algorithms when using a grid architecture like 4 $\times$ 16 or 8 $\times$ 8: the reduction is about $2$. The results depict also that when +for both algorithms when using a grid architecture like 4 $\times$ 16 or 8 $\times$ 8: the reduction factor is around $2$. 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\%. @@ -624,8 +644,9 @@ the network speed drops down (variation of 12.5\%), the difference between t \begin{figure} [ht!] \centering \includegraphics[width=100mm]{cluster_x_nodes_n1_x_n2.pdf} -\caption{Grid 2 $\times$ 16 and 4 $\times$ 8 with networks N1 vs N2 +\caption{Various grid configurations with networks N1 vs N2 \AG{\np{8E-6}, \np{5E-6} au lieu de 8E-6, 5E-6}} +\RCE{Corrige} \label{fig:02} \end{figure} %\end{wrapfigure} @@ -638,15 +659,14 @@ the network speed drops down (variation of 12.5\%), the difference between t \begin{tabular}{r c } \hline Grid Architecture & 2 $\times$ 16\\ %\hline - Network & N1 : bw=1Gbs \\ %\hline + \multirow{2}{*}{Inter Network N1} & $bw$=1Gbs, \\ %\hline + & $lat$= From 8$\times$10$^{-6}$ to $6.10^{-5}$ second \\ Input matrix size & $N_{x} \times N_{y} \times N_{z} = 150 \times 150 \times 150$\\ \hline \end{tabular} \caption{Test conditions: network latency impacts} \label{tab:03} \end{table} - - \begin{figure} [ht!] \centering \includegraphics[width=100mm]{network_latency_impact_on_execution_time.pdf} @@ -655,17 +675,13 @@ the network speed drops down (variation of 12.5\%), the difference between t \label{fig:03} \end{figure} - According to the results of Figure~\ref{fig:03}, a degradation of the network latency from $8.10^{-6}$ to $6.10^{-5}$ implies an absolute time increase of more than $75\%$ (resp. $82\%$) of the execution for the classical GMRES -(resp. Krylov multisplitting) algorithm. In addition, it appears that the -Krylov multisplitting method tolerates more the network latency variation with a -less rate increase of the execution time.\RC{Les 2 précédentes phrases me - semblent en contradiction....} Consequently, in the worst case ($lat=6.10^{-5 -}$), the execution time for GMRES is almost the double than the time of the -Krylov multisplitting, even though, the performance was on the same order of -magnitude with a latency of $8.10^{-6}$. +(resp. Krylov multisplitting) algorithm which means that the GMRES seems tolerate more the network latency variation with a less rate increase of the execution time. However, the execution time factor between the two algorithms varies from 2.2 to 1.5 times with a network latency decreasing from $8.10^{-6}$ to $6.10^{-5}$. + +\RC{Les 2 précédentes phrases me semblent en contradiction....} +\RCE{Reformule} \subsubsection{Network bandwidth impacts on performance} \ \\ @@ -674,10 +690,12 @@ magnitude with a latency of $8.10^{-6}$. \begin{tabular}{r c } \hline Grid Architecture & 2 $\times$ 16\\ %\hline - Network & N1 : bw=1Gbs - lat=5.10$^{-5}$ \\ %\hline +\multirow{2}{*}{Inter Network N1} & $bw$=From 1Gbs to 10 Gbs \\ %\hline + & $lat$= 5.10$^{-5}$ second \\ Input matrix size & $N_{x} \times N_{y} \times N_{z} =150 \times 150 \times 150$\\ \hline \\ \end{tabular} \caption{Test conditions: Network bandwidth impacts\RC{Qu'est ce qui varie ici? Il n'y a pas de variation dans le tableau}} +\RCE{C est le bw} \label{tab:04} \end{table} @@ -687,6 +705,7 @@ magnitude with a latency of $8.10^{-6}$. \includegraphics[width=100mm]{network_bandwith_impact_on_execution_time.pdf} \caption{Network bandwith impacts on execution time \AG{``Execution time'' avec un 't' minuscule}. Idem autres figures.} +\RCE{Corrige} \label{fig:04} \end{figure} @@ -703,8 +722,8 @@ of $40\%$ which is only around $24\%$ for the classical GMRES. \begin{tabular}{r c } \hline Grid Architecture & 4 $\times$ 8\\ %\hline - Network & N2 : bw=1Gbs - lat=5.10$^{-5}$ \\ - Input matrix size & $N_{x}$ = From 40 to 200\\ \hline + Inter Network & $bw$=1Gbs - $lat$=5.10$^{-5}$ \\ + Input matrix size & $N_{x} \times N_{y} \times N_{z}$ = From 40$^{3}$ to 200$^{3}$\\ \hline \end{tabular} \caption{Test conditions: Input matrix size impacts} \label{tab:05} @@ -724,9 +743,11 @@ 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} - \item the drastic increase ($10$ times) of the number of iterations needed to - reach the convergence for the classical GMRES algorithm when the matrix size + \item the important increase ($10$ times) of the number of iterations needed to + reach the convergence for the classical GMRES algorithm particularly, when the matrix size go beyond $N_{x}=150$; \RC{C'est toujours pas clair... ok le nommbre d'itérations est 10 fois plus long mais la suite de la phrase ne veut rien dire} + \RCE{Le nombre d'iterations augmente de 10 fois, cela surtout a partir de N=150} + \item the classical GMRES execution time is almost the double for $N_{x}=140$ compared with the Krylov multisplitting method. \end{enumerate} @@ -743,8 +764,9 @@ grid 2 $\times$ 16 leading to the same conclusion. \begin{tabular}{r c } \hline Grid architecture & 2 $\times$ 16\\ %\hline - Network & N2 : bw=1Gbs - lat=5.10$^{-5}$ \\ %\hline - Input matrix size & $N_{x} = 150 \times 150 \times 150$\\ \hline + Inter Network & N2 : $bw$=1Gbs - $lat$=5.10$^{-5}$ \\ %\hline + Input matrix size & $N_{x} = 150 \times 150 \times 150$\\ + CPU Power & From 3 to 19 GFlops \\ \hline \end{tabular} \caption{Test conditions: CPU Power impacts} \label{tab:06} @@ -790,6 +812,7 @@ 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} +\RCE{C est la description du dernier test sync/async avec l'introduction de la notion de relative gain} 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