X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/hpcc2014.git/blobdiff_plain/c9066e476a4a5b2bdba5c2eb18ad0aa2ad1d2bb3..42e7f35fe290785950e094b86fd73c998719025f:/hpcc.tex diff --git a/hpcc.tex b/hpcc.tex index e043c78..5a03bb2 100644 --- a/hpcc.tex +++ b/hpcc.tex @@ -1,3 +1,4 @@ + \documentclass[conference]{IEEEtran} \usepackage[T1]{fontenc} @@ -81,8 +82,8 @@ what parameters could influence or not the behaviors of an algorithm. In this paper, we show that it is interesting to use SimGrid to simulate the behaviors of asynchronous iterative algorithms. For that, we compare the behaviour of a synchronous GMRES algorithm with an asynchronous multisplitting one with -simulations in which we choose some parameters. Both codes are real MPI -codes. Simulations allow us to see when the multisplitting algorithm can be more +simulations which let us easily choose some parameters. Both codes are real MPI +codes and simulations allow us to see when the asynchronous multisplitting algorithm can be more efficient than the GMRES one to solve a 3D Poisson problem. @@ -102,50 +103,57 @@ suggests, these algorithms solve a given problem by successive iterations ($X_{n $X_{0}$ to find an approximate value $X^*$ of the solution with a very low residual error. Several well-known methods demonstrate the convergence of these algorithms~\cite{BT89,Bahi07}. -Parallelization of such algorithms generally involve the division of the problem into several \emph{blocks} that will -be solved in parallel on multiple processing units. The latter will communicate each intermediate results before a new -iteration starts and until the approximate solution is reached. These parallel computations can be performed either in -\emph{synchronous} mode where a new iteration begins only when all nodes communications are completed, -or in \emph{asynchronous} mode where processors can continue independently with few or no synchronization points. For -instance in the \textit{Asynchronous Iterations~-- Asynchronous Communications (AIAC)} model~\cite{bcvc06:ij}, local -computations do not need to wait for required data. Processors can then perform their iterations with the data present -at that time. Even if the number of iterations required before the convergence is generally greater than for the -synchronous case, AIAC algorithms can significantly reduce overall execution times by suppressing idle times due to -synchronizations especially in a grid computing context (see~\cite{Bahi07} for more details). - -Parallel (synchronous or asynchronous) applications may have different -configuration and deployment requirements. Quantifying their resource -allocation policies and application scheduling algorithms in grid computing -environments under varying load, CPU power and network speeds is very costly, -very labor intensive and very time -consuming~\cite{Calheiros:2011:CTM:1951445.1951450}. The case of AIAC -algorithms is even more problematic since they are very sensible to the -execution environment context. For instance, variations in the network bandwidth -(intra and inter-clusters), in the number and the power of nodes, in the number -of clusters\dots{} can lead to very different number of iterations and so to -very different execution times. Then, it appears that the use of simulation -tools to explore various platform scenarios and to run large numbers of -experiments quickly can be very promising. In this way, the use of a simulation -environment to execute parallel iterative algorithms found some interests in -reducing the highly cost of access to computing resources: (1) for the -applications development life cycle and in code debugging (2) and in production -to get results in a reasonable execution time with a simulated infrastructure -not accessible with physical resources. Indeed, the launch of distributed -iterative asynchronous algorithms to solve a given problem on a large-scale -simulated environment challenges to find optimal configurations giving the best -results with a lowest residual error and in the best of execution time. +Parallelization of such algorithms generally involves the division of the problem +into several \emph{blocks} that will be solved in parallel on multiple +processing units. The latter will communicate each intermediate results before a +new iteration starts and until the approximate solution is reached. These +parallel computations can be performed either in \emph{synchronous} mode where a +new iteration begins only when all nodes communications are completed, or in +\emph{asynchronous} mode where processors can continue independently with no +synchronization points~\cite{bcvc06:ij}. In this case, local computations do not +need to wait for required data. Processors can then perform their iterations +with the data present at that time. Even if the number of iterations required +before the convergence is generally greater than for the synchronous case, +asynchronous iterative algorithms can significantly reduce overall execution +times by suppressing idle times due to synchronizations especially in a grid +computing context (see~\cite{Bahi07} for more details). + +Parallel applications based on a (synchronous or asynchronous) iteration model +may have different configuration and deployment requirements. Quantifying their +resource allocation policies and application scheduling algorithms in grid +computing environments under varying load, CPU power and network speeds is very +costly, very labor intensive and very time +consuming~\cite{Calheiros:2011:CTM:1951445.1951450}. The case of asynchronous +iterative algorithms is even more problematic since they are very sensible to +the execution environment context. For instance, variations in the network +bandwidth (intra and inter-clusters), in the number and the power of nodes, in +the number of clusters\dots{} can lead to very different number of iterations +and so to very different execution times. Then, it appears that the use of +simulation tools to explore various platform scenarios and to run large numbers +of experiments quickly can be very promising. In this way, the use of a +simulation environment to execute parallel iterative algorithms found some +interests in reducing the highly cost of access to computing resources: (1) for +the applications development life cycle and in code debugging (2) and in +production to get results in a reasonable execution time with a simulated +infrastructure not accessible with physical resources. Indeed, the launch of +distributed iterative asynchronous algorithms to solve a given problem on a +large-scale simulated environment challenges to find optimal configurations +giving the best results with a lowest residual error and in the best of +execution time. + To our knowledge, there is no existing work on the large-scale simulation of a -real AIAC application. {\bf The contribution of the present paper can be - summarised in two main points}. First we give a first approach of the -simulation of AIAC algorithms using a simulation tool (i.e. the SimGrid -toolkit~\cite{SimGrid}). Second, we confirm the effectiveness of the -asynchronous multisplitting algorithm by comparing its performance with the -synchronous GMRES (Generalized Minimal Residual) \cite{ref1}. Both these codes -can be used to solve large linear systems. In this paper, we focus on a 3D -Poisson problem. We show, that with minor modifications of the initial MPI -code, the SimGrid toolkit allows us to perform a test campaign of a real AIAC -application on different computing architectures. +real asynchronous iterative application. {\bf The contribution of the present + paper can be summarized in two main points}. First we give a first approach +of the simulation of asynchronous iterative algorithms using a simulation tool +(i.e. the SimGrid toolkit~\cite{SimGrid}). Second, we confirm the +effectiveness of the asynchronous multisplitting algorithm by comparing its +performance with the synchronous GMRES (Generalized Minimal Residual) method +\cite{ref1}. Both these codes can be used to solve large linear systems. In +this paper, we focus on a 3D Poisson problem. We show, that with minor +modifications of the initial MPI code, the SimGrid toolkit allows us to perform +a test campaign of a real asynchronous iterative application on different +computing architectures. % The simulated results we %obtained are in line with real results exposed in ??\AG[]{ref?}. SimGrid had allowed us to launch the application from a modest computing @@ -167,43 +175,41 @@ based on GMRES to solve each block obtained of the splitting. This code is written with MPI primitives and its adaptation to SimGrid with SMPI (Simulated MPI) is detailed in the next section. At last, the simulation results carried out will be presented before some concluding remarks and future works. + \section{Motivations and scientific context} As exposed in the introduction, parallel iterative methods are now widely used -in many scientific domains. They can be classified in three main classes +in many scientific domains. They can be classified in three main classes depending on how iterations and communications are managed (for more details -readers can refer to~\cite{bcvc06:ij}). In the \textit{Synchronous Iterations~-- - Synchronous Communications (SISC)} model data are exchanged at the end of each -iteration. All the processors must begin the same iteration at the same time and -important idle times on processors are generated. The \textit{Synchronous - Iterations~-- Asynchronous Communications (SIAC)} model can be compared to the -previous one except that data required on another processor are sent -asynchronously i.e. without stopping current computations. This technique -allows to partially overlap communications by computations but unfortunately, -the overlapping is only partial and important idle times remain. It is clear -that, in a grid computing context, where the number of computational nodes is -large, heterogeneous and widely distributed, the idle times generated by -synchronizations are very penalizing. One way to overcome this problem is to use -the \textit{Asynchronous Iterations~-- Asynchronous Communications (AIAC)} -model. Here, local computations do not need to wait for required -data. Processors can then perform their iterations with the data present at that -time. Figure~\ref{fig:aiac} illustrates this model where the gray blocks -represent the computation phases. With this algorithmic model, the number of -iterations required before the convergence is generally greater than for the two -former classes. But, and as detailed in~\cite{bcvc06:ij}, AIAC algorithms can -significantly reduce overall execution times by suppressing idle times due to -synchronizations especially in a grid computing context. -%\LZK{Répétition par rapport à l'intro} +readers can refer to~\cite{bcvc06:ij}). In the synchronous iterations model, +data are exchanged at the end of each iteration. All the processors must begin +the same iteration at the same time and important idle times on processors are +generated. It is possible to use asynchronous communications, in this case, the +model can be compared to the previous one except that data required on another +processor are sent asynchronously i.e. without stopping current computations. +This technique allows to partially overlap communications by computations but +unfortunately, the overlapping is only partial and important idle times remain. +It is clear that, in a grid computing context, where the number of computational +nodes is large, heterogeneous and widely distributed, the idle times generated +by synchronizations are very penalizing. One way to overcome this problem is to +use the asynchronous iterations model. Here, local computations do not need to +wait for required data. Processors can then perform their iterations with the +data present at that time. Figure~\ref{fig:aiac} illustrates this model where +the gray blocks represent the computation phases. With this algorithmic model, +the number of iterations required before the convergence is generally greater +than for the two former classes. But, and as detailed in~\cite{bcvc06:ij}, +asynchronous iterative algorithms can significantly reduce overall execution +times by suppressing idle times due to synchronizations especially in a grid +computing context. \begin{figure}[!t] \centering \includegraphics[width=8cm]{AIAC.pdf} - \caption{The Asynchronous Iterations~-- Asynchronous Communications model} + \caption{The asynchronous iterations model} \label{fig:aiac} \end{figure} -\RC{Je serais partant de virer AIAC et laisser asynchronous algorithms... à voir} %% It is very challenging to develop efficient applications for large scale, %% heterogeneous and distributed platforms such as computing grids. Researchers and @@ -222,11 +228,11 @@ In the context of asynchronous algorithms, the number of iterations to reach the convergence depends on the delay of messages. With synchronous iterations, the number of iterations is exactly the same than in the sequential mode (if the parallelization process does not change the algorithm). So the difficulty with -asynchronous algorithms comes from the fact it is necessary to run the algorithm +asynchronous iterative algorithms comes from the fact it is necessary to run the algorithm with real data. In fact, from an execution to another the order of messages will change and the number of iterations to reach the convergence will also change. According to all the parameters of the platform (number of nodes, power of -nodes, inter and intra clusrters bandwith and latency, ....) and of the +nodes, inter and intra clusrters bandwith and latency, etc.) and of the algorithm (number of splitting with the multisplitting algorithm), the multisplitting code will obtain the solution more or less quickly. Or course, the GMRES method also depends of the same parameters. As it is difficult to have @@ -282,6 +288,8 @@ These two techniques can help to run simulations at a very large scale. %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% \section{Simulation of the multisplitting method} + +\subsection{The multisplitting method} %Décrire le problème (algo) traité ainsi que le processus d'adaptation à SimGrid. Let $Ax=b$ be a large sparse system of $n$ linear equations in $\mathbb{R}$, where $A$ is a sparse square and nonsingular matrix, $x$ is the solution vector and $b$ is the right-hand side vector. We use a multisplitting method based on the block Jacobi splitting to solve this linear system on a large scale platform composed of $L$ clusters of processors~\cite{o1985multi}. In this case, we apply a row-by-row splitting without overlapping \begin{equation*} @@ -375,8 +383,8 @@ exchanged by message passing using MPI non-blocking communication routines. \begin{figure}[!t] \centering - \includegraphics[width=60mm,keepaspectratio]{clustering} -\caption{Example of three clusters of processors interconnected by a virtual unidirectional ring network.} + \includegraphics[width=60mm,keepaspectratio]{clustering2} +\caption{Example of two distant clusters of processors.} \label{fig:4.1} \end{figure} @@ -387,9 +395,9 @@ processor is designated (for example the processor with rank 1) and masters of all clusters are interconnected by a virtual unidirectional ring network (see Figure~\ref{fig:4.1}). During the resolution, a Boolean token circulates around the virtual ring from a master processor to another until the global convergence -is achieved. So starting from the cluster with rank 1, each master processor $i$ +is achieved. So starting from the cluster with rank 1, each master processor $\ell$ sets the token to \textit{True} if the local convergence is achieved or to -\textit{False} otherwise, and sends it to master processor $i+1$. Finally, the +\textit{False} otherwise, and sends it to master processor $\ell+1$. Finally, the global convergence is detected when the master of cluster 1 receives from the master of cluster $L$ a token set to \textit{True}. In this case, the master of cluster 1 broadcasts a stop message to masters of other clusters. In this work, @@ -402,59 +410,8 @@ where $\MI$ is the maximum number of outer iterations and $\epsilon$ is the tolerance threshold of the error computed between two successive local solution $X_\ell^k$ and $X_\ell^{k+1}$. -%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% -We did not encounter major blocking problems when adapting the multisplitting algorithm previously described to a simulation environment like SimGrid unless some code -debugging. Indeed, apart from the review of the program sequence for asynchronous exchanges between processors within a cluster or between clusters, the algorithm was executed successfully with SMPI and provided identical outputs as those obtained with direct execution under MPI. In synchronous -mode, the execution of the program raised no particular issue but in asynchronous mode, the review of the sequence of MPI\_Isend, MPI\_Irecv and MPI\_Waitall instructions -and with the addition of the primitive MPI\_Test was needed to avoid a memory fault due to an infinite loop resulting from the non-convergence of the algorithm. -\CER{On voulait en fait montrer la simplicité de l'adaptation de l'algo a SimGrid. Les problèmes rencontrés décrits dans ce paragraphe concerne surtout le mode async}\LZK{OK. J'aurais préféré avoir un peu plus de détails sur l'adaptation de la version async} -Note here that the use of SMPI functions optimizer for memory footprint and CPU usage is not recommended knowing that one wants to get real results by simulation. -As mentioned, upon this adaptation, the algorithm is executed as in the real life in the simulated environment after the following minor changes. First, all declared -global variables have been moved to local variables for each subroutine. In fact, global variables generate side effects arising from the concurrent access of -shared memory used by threads simulating each computing unit in the SimGrid architecture. Second, the alignment of certain types of variables such as ``long int'' had -also to be reviewed. -\AG{À propos de ces problèmes d'alignement, en dire plus si ça a un intérêt, ou l'enlever.} - Finally, some compilation errors on MPI\_Waitall and MPI\_Finalize primitives have been fixed with the latest version of SimGrid. -In total, the initial MPI program running on the simulation environment SMPI gave after a very simple adaptation the same results as those obtained in a real -environment. We have successfully executed the code in synchronous mode using parallel GMRES algorithm compared with our multisplitting algorithm in asynchronous mode after few modifications. - - - -\section{Experimental results} -When the \textit{real} application runs in the simulation environment and produces the expected results, varying the input -parameters and the program arguments allows us to compare outputs from the code execution. We have noticed from this -study that the results depend on the following parameters: -\begin{itemize} -\item At the network level, we found that the most critical values are the - bandwidth and the network latency. -\item Hosts power (GFlops) can also influence on the results. -\item Finally, when submitting job batches for execution, the arguments values - passed to the program like the maximum number of iterations or the external - precision are critical. They allow to ensure not only the convergence of the - algorithm but also to get the main objective of the experimentation of the - simulation in having an execution time in asynchronous less than in - synchronous mode. The ratio between the execution time of asynchronous - compared to the synchronous mode is defined as the \emph{relative gain}. So, - our objective running the algorithm in SimGrid is to obtain a relative gain - greater than 1. - \AG{$t_\text{async} / t_\text{sync} > 1$, l'objectif est donc que ça dure plus - longtemps (que ça aille moins vite) en asynchrone qu'en synchrone ? - Ce n'est pas plutôt l'inverse ?} -\end{itemize} - -A priori, obtaining a relative gain greater than 1 would be difficult in a local -area network configuration where the synchronous mode will take advantage on the -rapid exchange of information on such high-speed links. Thus, the methodology -adopted was to launch the application on clustered network. In this last -configuration, degrading the inter-cluster network performance will penalize the -synchronous mode allowing to get a relative gain greater than 1. This action -simulates the case of distant clusters linked with long distance network like -Internet. -\AG{Cette partie sur le poisson 3D - % on sait donc que ce n'est pas une plie ou une sole (/me fatigué) - n'est pas à sa place. Elle devrait être placée plus tôt.} In this paper, we solve the 3D Poisson problem whose the mathematical model is \begin{equation} \left\{ @@ -465,17 +422,17 @@ u =0 \text{~on~} \Gamma =\partial\Omega \right. \label{eq:02} \end{equation} -where $\nabla^2$ is the Laplace operator, $f$ and $u$ are real-valued functions, and $\Omega=[0,1]^3$. The spatial discretization with a finite difference scheme reduces problem~(\ref{eq:02}) to a system of sparse linear equations. The general iteration scheme of our multisplitting method in a 3D domain using a seven point stencil could be written as +where $\nabla^2$ is the Laplace operator, $f$ and $u$ are real-valued functions, and $\Omega=[0,1]^3$. The spatial discretization with a finite difference scheme reduces problem~(\ref{eq:02}) to a system of sparse linear equations. Our multisplitting method solves the 3D Poisson problem using a seven point stencil whose the general expression could be written as \begin{equation} -\begin{array}{ll} -u^{k+1}(x,y,z)= & u^k(x,y,z) - \frac{1}{6}\times\\ - & (u^k(x-1,y,z) + u^k(x+1,y,z) + \\ - & u^k(x,y-1,z) + u^k(x,y+1,z) + \\ - & u^k(x,y,z-1) + u^k(x,y,z+1)), +\begin{array}{l} +u(x-1,y,z) + u(x,y-1,z) + u(x,y,z-1)\\+u(x+1,y,z)+u(x,y+1,z)+u(x,y,z+1) \\ -6u(x,y,z)=h^2f(x,y,z), +%u(x,y,z)= & \frac{1}{6}\times [u(x-1,y,z) + u(x+1,y,z) + \\ + % & u(x,y-1,z) + u(x,y+1,z) + \\ + % & u(x,y,z-1) + u(x,y,z+1) - \\ & h^2f(x,y,z)], \end{array} \label{eq:03} \end{equation} -where the iteration matrix $A$ of size $N_x\times N_y\times N_z$ of the discretized linear system is sparse, symmetric and positive definite. +where $h$ is the distance between two adjacent elements in the spatial discretization scheme and the iteration matrix $A$ of size $N_x\times N_y\times N_z$ of the discretized linear system is sparse, symmetric and positive definite. The parallel solving of the 3D Poisson problem with our multisplitting method requires a data partitioning of the problem between clusters and between processors within a cluster. We have chosen the 3D partitioning instead of the row-by-row partitioning in order to reduce the data exchanges at sub-domain boundaries. Figure~\ref{fig:4.2} shows an example of the data partitioning of the 3D Poisson problem between two clusters of processors, where each sub-problem is assigned to a processor. In this context, a processor has at most six neighbors within a cluster or in distant clusters with which it shares data at sub-domain boundaries. @@ -487,14 +444,60 @@ The parallel solving of the 3D Poisson problem with our multisplitting method re \end{figure} -As a first step, the algorithm was run on a network consisting of two clusters -containing 50 hosts each, totaling 100 hosts. Various combinations of the above -factors have provided the results shown in Table~\ref{tab.cluster.2x50} with a -matrix size ranging from $N_x = N_y = N_z = \text{62}$ to 171 elements or from -$\text{62}^\text{3} = \text{\np{238328}}$ to $\text{171}^\text{3} = -\text{\np{5000211}}$ entries. -\AG{Expliquer comment lire les tableaux.} +\subsection{Simulation of the multisplitting method using SimGrid and SMPI} + + + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +We did not encounter major blocking problems when adapting the multisplitting algorithm previously described to a simulation environment like SimGrid unless some code +debugging. Indeed, apart from the review of the program sequence for asynchronous exchanges between processors within a cluster or between clusters, the algorithm was executed successfully with SMPI and provided identical outputs as those obtained with direct execution under MPI. For the synchronous GMRES method, the execution of the program raised no particular issue but in the asynchronous multisplitting method , the review of the sequence of \texttt{MPI\_Isend, MPI\_Irecv} and \texttt{MPI\_Waitall} instructions +and with the addition of the primitive \texttt{MPI\_Test} was needed to avoid a memory fault due to an infinite loop resulting from the non-convergence of the algorithm. +%\CER{On voulait en fait montrer la simplicité de l'adaptation de l'algo a SimGrid. Les problèmes rencontrés décrits dans ce paragraphe concerne surtout le mode async}\LZK{OK. J'aurais préféré avoir un peu plus de détails sur l'adaptation de la version async} +%\CER{Le problème majeur sur l'adaptation MPI vers SMPI pour la partie asynchrone de l'algorithme a été le plantage en SMPI de Waitall après un Isend et Irecv. J'avais proposé un workaround en utilisant un MPI\_wait séparé pour chaque échange a la place d'un waitall unique pour TOUTES les échanges, une instruction qui semble bien fonctionner en MPI. Ce workaround aussi fonctionne bien. Mais après, tu as modifié le programme avec l'ajout d'un MPI\_Test, au niveau de la routine de détection de la convergence et du coup, l'échange global avec waitall a aussi fonctionné.} +Note here that the use of SMPI functions optimizer for memory footprint and CPU usage is not recommended knowing that one wants to get real results by simulation. +As mentioned, upon this adaptation, the algorithm is executed as in the real life in the simulated environment after the following minor changes. The scope of all declared +global variables have been moved to local to subroutine. Indeed, global variables generate side effects arising from the concurrent access of +shared memory used by threads simulating each computing unit in the SimGrid architecture. +%Second, some compilation errors on MPI\_Waitall and MPI\_Finalize primitives have been fixed with the latest version of SimGrid. +%\AG{compilation or run-time error?} +In total, the initial MPI program running on the simulation environment SMPI gave after a very simple adaptation the same results as those obtained in a real +environment. We have successfully executed the code for the synchronous GMRES algorithm compared with our asynchronous multisplitting algorithm after few modifications. + + +\section{Simulation results} + +When the \textit{real} application runs in the simulation environment and produces the expected results, varying the input +parameters and the program arguments allows us to compare outputs from the code execution. We have noticed from this +study that the results depend on the following parameters: +\begin{itemize} +\item At the network level, we found that the most critical values are the + bandwidth and the network latency. +\item Hosts processors power (GFlops) can also influence on the results. +\item Finally, when submitting job batches for execution, the arguments values + passed to the program like the maximum number of iterations or the precision are critical. They allow us to ensure not only the convergence of the + algorithm but also to get the main objective in getting an execution time with the asynchronous multisplitting less than with synchronous GMRES. + \end{itemize} + +The ratio between the simulated execution time of synchronous GMRES algorithm +compared to the asynchronous multisplitting algorithm ($t_\text{GMRES} / t_\text{Multisplitting}$) is defined as the \emph{relative gain}. So, +our objective running the algorithm in SimGrid is to obtain a relative gain greater than 1. +A priori, obtaining a relative gain greater than 1 would be difficult in a local +area network configuration where the synchronous GMRES method will take advantage on the +rapid exchange of information on such high-speed links. Thus, the methodology +adopted was to launch the application on a clustered network. In this +configuration, degrading the inter-cluster network performance will penalize the +synchronous mode allowing to get a relative gain greater than 1. This action +simulates the case of distant clusters linked with long distance network as in grid computing context. + + + +Both codes were simulated on a two clusters based network with 50 hosts each, totaling 100 hosts. Various combinations of the above +factors have provided the results shown in Table~\ref{tab.cluster.2x50}. The problem size of the 3D Poisson problem ranges from $N_x = N_y = N_z = \text{62}$ to 150 elements (that is from +$\text{62}^\text{3} = \text{\np{238328}}$ to $\text{150}^\text{3} = +\text{\np{3375000}}$ entries). With the asynchronous multisplitting algorithm the simulated execution time is in average 2.5 times faster than with the synchronous GMRES one. +%\AG{Expliquer comment lire les tableaux.} +%\CER{J'ai reformulé la phrase par la lecture du tableau. Plus de détails seront lus dans la partie Interprétations et commentaires} % use the same column width for the following three tables \newlength{\mytablew}\settowidth{\mytablew}{\footnotesize\np{E-11}} \newenvironment{mytable}[1]{% #1: number of columns for data @@ -505,220 +508,219 @@ $\text{62}^\text{3} = \text{\np{238328}}$ to $\text{171}^\text{3} = \begin{table}[!t] \centering - \caption{2 clusters, each with 50 nodes} + \caption{Relative gain of the multisplitting algorithm compared to GMRES for + different configurations with 2 clusters, each one composed of 50 nodes.} \label{tab.cluster.2x50} - \begin{mytable}{6} + \begin{mytable}{5} \hline - bandwidth - & 5 & 5 & 5 & 5 & 5 & 50 \\ + bandwidth (Mbit/s) + & 5 & 5 & 5 & 5 & 5 \\ \hline - latency - & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 \\ + latency (ms) + & 20 & 20 & 20 & 20 & 20 \\ \hline - power - & 1 & 1 & 1 & 1.5 & 1.5 & 1.5 \\ + power (GFlops) + & 1 & 1 & 1 & 1.5 & 1.5 \\ \hline - size - & 62 & 62 & 62 & 100 & 100 & 110 \\ + size $(n^3)$ + & 62 & 62 & 62 & 100 & 100 \\ \hline - Prec/Eprec - & \np{E-5} & \np{E-8} & \np{E-9} & \np{E-11} & \np{E-11} & \np{E-11} \\ + Precision + & \np{E-5} & \np{E-8} & \np{E-9} & \np{E-11} & \np{E-11} \\ \hline \hline Relative gain - & 2.52 & 2.55 & 2.52 & 2.57 & 2.54 & 2.53 \\ + & 2.52 & 2.55 & 2.52 & 2.57 & 2.54 \\ \hline \end{mytable} \bigskip - \begin{mytable}{6} + \begin{mytable}{5} \hline - bandwidth - & 50 & 50 & 50 & 50 & 10 & 10 \\ + bandwidth (Mbit/s) + & 50 & 50 & 50 & 50 & 50 \\ % & 10 & 10 \\ \hline - latency - & 0.02 & 0.02 & 0.02 & 0.02 & 0.03 & 0.01 \\ + latency (ms) + & 20 & 20 & 20 & 20 & 20 \\ % & 0.03 & 0.01 \\ \hline - power - & 1.5 & 1.5 & 1.5 & 1.5 & 1 & 1.5 \\ + Power (GFlops) + & 1.5 & 1.5 & 1.5 & 1.5 & 1.5 \\ % & 1 & 1.5 \\ \hline - size - & 120 & 130 & 140 & 150 & 171 & 171 \\ + size $(n^3)$ + & 110 & 120 & 130 & 140 & 150 \\ % & 171 & 171 \\ \hline - Prec/Eprec - & \np{E-11} & \np{E-11} & \np{E-11} & \np{E-11} & \np{E-5} & \np{E-5} \\ + Precision + & \np{E-11} & \np{E-11} & \np{E-11} & \np{E-11} & \np{E-11} \\ % & \np{E-5} & \np{E-5} \\ \hline \hline Relative gain - & 2.51 & 2.58 & 2.55 & 2.54 & 1.59 & 1.29 \\ + & 2.53 & 2.51 & 2.58 & 2.55 & 2.54 \\ % & 1.59 & 1.29 \\ \hline \end{mytable} \end{table} -Then we have changed the network configuration using three clusters containing -respectively 33, 33 and 34 hosts, or again by on hundred hosts for all the -clusters. In the same way as above, a judicious choice of key parameters has -permitted to get the results in Table~\ref{tab.cluster.3x33} which shows the -relative gains greater than 1 with a matrix size from 62 to 100 elements. - -\begin{table}[!t] - \centering - \caption{3 clusters, each with 33 nodes} - \label{tab.cluster.3x33} - - \begin{mytable}{6} - \hline - bandwidth - & 10 & 5 & 4 & 3 & 2 & 6 \\ - \hline - latency - & 0.01 & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 \\ - \hline - power - & 1 & 1 & 1 & 1 & 1 & 1 \\ - \hline - size - & 62 & 100 & 100 & 100 & 100 & 171 \\ - \hline - Prec/Eprec - & \np{E-5} & \np{E-5} & \np{E-5} & \np{E-5} & \np{E-5} & \np{E-5} \\ - \hline - \hline - Relative gain - & 1.003 & 1.01 & 1.08 & 1.19 & 1.28 & 1.01 \\ - \hline - \end{mytable} -\end{table} - -In a final step, results of an execution attempt to scale up the three clustered -configuration but increasing by two hundreds hosts has been recorded in -Table~\ref{tab.cluster.3x67}. - -\begin{table}[!t] - \centering - \caption{3 clusters, each with 66 nodes} - \label{tab.cluster.3x67} - - \begin{mytable}{1} - \hline - bandwidth & 1 \\ - \hline - latency & 0.02 \\ - \hline - power & 1 \\ - \hline - size & 62 \\ - \hline - Prec/Eprec & \np{E-5} \\ - \hline - \hline - Relative gain & 1.11 \\ - \hline - \end{mytable} -\end{table} +\RC{Du coup la latence est toujours la même, pourquoi la mettre dans la table?} + +%Then we have changed the network configuration using three clusters containing +%respectively 33, 33 and 34 hosts, or again by on hundred hosts for all the +%clusters. In the same way as above, a judicious choice of key parameters has +%permitted to get the results in Table~\ref{tab.cluster.3x33} which shows the +%relative gains greater than 1 with a matrix size from 62 to 100 elements. + +%\CER{En accord avec RC, on a pour le moment enlevé les tableaux 2 et 3 sachant que les résultats obtenus sont limites. De même, on a enlevé aussi les deux dernières colonnes du tableau I en attendant une meilleure performance et une meilleure precision} +%\begin{table}[!t] +% \centering +% \caption{3 clusters, each with 33 nodes} +% \label{tab.cluster.3x33} +% +% \begin{mytable}{6} +% \hline +% bandwidth +% & 10 & 5 & 4 & 3 & 2 & 6 \\ +% \hline +% latency +% & 0.01 & 0.02 & 0.02 & 0.02 & 0.02 & 0.02 \\ +% \hline +% power +% & 1 & 1 & 1 & 1 & 1 & 1 \\ +% \hline +% size +% & 62 & 100 & 100 & 100 & 100 & 171 \\ +% \hline +% Prec/Eprec +% & \np{E-5} & \np{E-5} & \np{E-5} & \np{E-5} & \np{E-5} & \np{E-5} \\ +% \hline +% \hline +% Relative gain +% & 1.003 & 1.01 & 1.08 & 1.19 & 1.28 & 1.01 \\ +% \hline +% \end{mytable} +%\end{table} + +%In a final step, results of an execution attempt to scale up the three clustered +%configuration but increasing by two hundreds hosts has been recorded in +%Table~\ref{tab.cluster.3x67}. + +%\begin{table}[!t] +% \centering +% \caption{3 clusters, each with 66 nodes} +% \label{tab.cluster.3x67} +% +% \begin{mytable}{1} +% \hline +% bandwidth & 1 \\ +% \hline +% latency & 0.02 \\ +% \hline +% power & 1 \\ +% \hline +% size & 62 \\ +% \hline +% Prec/Eprec & \np{E-5} \\ +% \hline +% \hline +% Relative gain & 1.11 \\ +% \hline +% \end{mytable} +%\end{table} Note that the program was run with the following parameters: \paragraph*{SMPI parameters} -~\\{}\AG{Donner un peu plus de précisions (plateforme en particulier).} \begin{itemize} -\item HOSTFILE: Hosts file description. -\item PLATFORM: file description of the platform architecture : clusters (CPU - power, \dots{}), intra cluster network description, inter cluster network - (bandwidth, latency, \dots{}). +\item HOSTFILE: Text file containing the list of the processors units name. Here 100 hosts; +\item PLATFORM: XML file description of the platform architecture whith the following characteristics: %two clusters (cluster1 and cluster2) with the following characteristics : + \begin{itemize} + \item 2 clusters of 50 hosts each; + \item Processor unit power: \np[GFlops]{1} or \np[GFlops]{1.5}; + \item Intra-cluster network bandwidth: \np[Gbit/s]{1.25} and latency: \np[$\mu$s]{50}; + \item Inter-cluster network bandwidth: \np[Mbit/s]{5} or \np[Mbit/s]{50} and latency: \np[ms]{20}; + \end{itemize} \end{itemize} \paragraph*{Arguments of the program} \begin{itemize} - \item Description of the cluster architecture; - \item Maximum number of internal and external iterations; - \item Internal and external precisions; - \item Matrix size $N_x$, $N_y$ and $N_z$; - \item Matrix diagonal value: \np{6.0}; - \item Matrix off-diagonal value: \np{-1.0}; - \item Execution Mode: synchronous or asynchronous. +\item Description of the cluster architecture matching the format ; +\item Maximum number of iterations; +\item Precisions on the residual error; +\item Matrix size $N_x$, $N_y$ and $N_z$; +\item Matrix diagonal value: $6$ (See Equation~(\ref{eq:03})); +\item Matrix off-diagonal value: $-1$; +\item Communication mode: asynchronous. \end{itemize} \paragraph*{Interpretations and comments} -After analyzing the outputs, generally, for the configuration with two or three -clusters including one hundred hosts (Tables~\ref{tab.cluster.2x50} -and~\ref{tab.cluster.3x33}), some combinations of the used parameters affecting +After analyzing the outputs, generally, for the two clusters including one hundred hosts configuration (Tables~\ref{tab.cluster.2x50}), some combinations of parameters affecting the results have given a relative gain more than 2.5, showing the effectiveness of the -asynchronous performance compared to the synchronous mode. - -In the case of a two clusters configuration, Table~\ref{tab.cluster.2x50} shows -that with a deterioration of inter cluster network set with \np[Mbit/s]{5} of -bandwidth, a latency in order of a hundredth of a millisecond and a system power -of one GFlops, an efficiency of about \np[\%]{40} in asynchronous mode is -obtained for a matrix size of 62 elements. It is noticed that the result remains -stable even if we vary the external precision from \np{E-5} to \np{E-9}. By +asynchronous multisplitting compared to GMRES with two distant clusters. + +With these settings, Table~\ref{tab.cluster.2x50} shows +that after setting the bandwidth of the inter cluster network to \np[Mbit/s]{5} and a latency in order of one hundredth of millisecond and a processor power +of one GFlops, an efficiency of about \np[\%]{40} is +obtained in asynchronous mode for a matrix size of 62 elements. It is noticed that the result remains +stable even we vary the residual error precision from \np{E-5} to \np{E-9}. By increasing the matrix size up to 100 elements, it was necessary to increase the -CPU power of \np[\%]{50} to \np[GFlops]{1.5} for a convergence of the algorithm -with the same order of asynchronous mode efficiency. Maintaining such a system -power but this time, increasing network throughput inter cluster up to -\np[Mbit/s]{50}, the result of efficiency with a relative gain of 1.5\AG[]{2.5 ?} is obtained with +CPU power of \np[\%]{50} to \np[GFlops]{1.5} to get the algorithm convergence and the same order of asynchronous mode efficiency. Maintaining such processor power but increasing network throughput inter cluster up to +\np[Mbit/s]{50}, the result of efficiency with a relative gain of 2.5 is obtained with high external precision of \np{E-11} for a matrix size from 110 to 150 side elements. -For the 3 clusters architecture including a total of 100 hosts, -Table~\ref{tab.cluster.3x33} shows that it was difficult to have a combination -which gives a relative gain of asynchronous mode more than 1.2. Indeed, for a -matrix size of 62 elements, equality between the performance of the two modes -(synchronous and asynchronous) is achieved with an inter cluster of -\np[Mbit/s]{10} and a latency of \np[ms]{E-1}. To challenge an efficiency greater than 1.2 with a matrix size of 100 points, it was necessary to degrade the -inter cluster network bandwidth from 5 to \np[Mbit/s]{2}. +%For the 3 clusters architecture including a total of 100 hosts, +%Table~\ref{tab.cluster.3x33} shows that it was difficult to have a combination +%which gives a relative gain of asynchronous mode more than 1.2. Indeed, for a +%matrix size of 62 elements, equality between the performance of the two modes +%(synchronous and asynchronous) is achieved with an inter cluster of +%\np[Mbit/s]{10} and a latency of \np[ms]{E-1}. To challenge an efficiency greater than 1.2 with a matrix %size of 100 points, it was necessary to degrade the +%inter cluster network bandwidth from 5 to \np[Mbit/s]{2}. \AG{Conclusion, on prend une plateforme pourrie pour avoir un bon ratio sync/async ??? Quelle est la perte de perfs en faisant ça ?} -A last attempt was made for a configuration of three clusters but more powerful -with 200 nodes in total. The convergence with a relative gain around 1.1 was -obtained with a bandwidth of \np[Mbit/s]{1} as shown in -Table~\ref{tab.cluster.3x67}. - -\RC{Est ce qu'on sait expliquer pourquoi il y a une telle différence entre les résultats avec 2 et 3 clusters... Avec 3 clusters, ils sont pas très bons... Je me demande s'il ne faut pas les enlever...} -\RC{En fait je pense avoir la réponse à ma remarque... On voit avec les 2 clusters que le gain est d'autant plus grand qu'on choisit une bonne précision. Donc, plusieurs solutions, lancer rapidement un long test pour confirmer ca, ou enlever des tests... ou on ne change rien :-)} -\LZK{Ma question est: le bandwidth et latency sont ceux inter-clusters ou pour les deux inter et intra cluster??} +%A last attempt was made for a configuration of three clusters but more powerful +%with 200 nodes in total. The convergence with a relative gain around 1.1 was +%obtained with a bandwidth of \np[Mbit/s]{1} as shown in +%Table~\ref{tab.cluster.3x67}. +%\RC{Est ce qu'on sait expliquer pourquoi il y a une telle différence entre les résultats avec 2 et 3 clusters... Avec 3 clusters, ils sont pas très bons... Je me demande s'il ne faut pas les enlever...} +%\RC{En fait je pense avoir la réponse à ma remarque... On voit avec les 2 clusters que le gain est d'autant plus grand qu'on choisit une bonne précision. Donc, plusieurs solutions, lancer rapidement un long test pour confirmer ca, ou enlever des tests... ou on ne change rien :-)} +%\LZK{Ma question est: le bandwidth et latency sont ceux inter-clusters ou pour les deux inter et intra cluster??} +%\CER{Définitivement, les paramètres réseaux variables ici se rapportent au réseau INTER cluster.} \section{Conclusion} -The experimental results on executing a parallel iterative algorithm in -asynchronous mode on an environment simulating a large scale of virtual -computers organized with interconnected clusters have been presented. -Our work has demonstrated that using such a simulation tool allow us to -reach the following three objectives: +The simulation of the execution of parallel asynchronous iterative algorithms on large scale clusters has been presented. +In this work, we show that SIMGRID is an efficient simulation tool that allows us to +reach the following two objectives: \begin{enumerate} -\item To have a flexible configurable execution platform resolving the -hard exercise to access to very limited but so solicited physical -resources; -\item to ensure the algorithm convergence with a reasonable time and -iteration number ; -\item and finally and more importantly, to find the correct combination -of the cluster and network specifications permitting to save time in -executing the algorithm in asynchronous mode. +\item To have a flexible configurable execution platform that allows us to + simulate algorithms for which execution of all parts of + the code is necessary. Using simulations before real executions is a nice + solution to detect potential scalability problems. + +\item To test the combination of the cluster and network specifications permitting to execute an asynchronous algorithm faster than a synchronous one. \end{enumerate} -Our results have shown that in certain conditions, asynchronous mode is -speeder up to \np[\%]{40} than executing the algorithm in synchronous mode +Our results have shown that with two distant clusters, the asynchronous multisplitting is faster to \np[\%]{40} compared to the synchronous GMRES method which is not negligible for solving complex practical problems with more and more increasing size. - Several studies have already addressed the performance execution time of +Several studies have already addressed the performance execution time of this class of algorithm. The work presented in this paper has demonstrated an original solution to optimize the use of a simulation tool to run efficiently an iterative parallel algorithm in asynchronous mode in a grid architecture. -\LZK{Perspectives???} +In future works, we plan to extend our experimentations to larger scale platforms by increasing the number of computing cores and the number of clusters. +We will also have to increase the size of the input problem which will require the use of a more powerful simulation platform. At last, we expect to compare our simulation results to real execution results on real architectures in order to experimentally validate our study. \section*{Acknowledgment} This work is partially funded by the Labex ACTION program (contract ANR-11-LABX-01-01). -\todo[inline]{The authors would like to thank\dots{}} +%\todo[inline]{The authors would like to thank\dots{}} % trigger a \newpage just before the given reference % number - used to balance the columns on the last page