X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/GMRES2stage.git/blobdiff_plain/af93eecf8bd45d51b68e4c9ac79d9e2bf7100db4..a71cbaf8deace5aa6be2f43f9c2f97dab867a9b1:/paper.tex diff --git a/paper.tex b/paper.tex index 2d34b8f..98f208f 100644 --- a/paper.tex +++ b/paper.tex @@ -601,29 +601,29 @@ is summarized while intended perspectives are provided. %%%********************************************************* \section{Related works} \label{sec:02} -Krylov subspace iteration methods have increasingly become useful and successful -techniques for solving linear, nonlinear systems and eigenvalue problems, -especially since the increase development of the +Krylov subspace iteration methods have increasingly become key +techniques for solving linear and nonlinear systems, or eigenvalue problems, +especially since the increasing development of preconditioners~\cite{Saad2003,Meijerink77}. One reason of the popularity of -these methods is their generality, simplicity and efficiency to solve systems of +these methods is their generality, simplicity, and efficiency to solve systems of equations arising from very large and complex problems. GMRES is one of the most widely used Krylov iterative method for solving sparse -and large linear systems. It is developed by Saad and al.~\cite{Saad86} as a +and large linear systems. It has been developed by Saad \emph{et al.}~\cite{Saad86} as a generalized method to deal with unsymmetric and non-Hermitian problems, and -indefinite symmetric problems too. In its original version called full GMRES, it +indefinite symmetric problems too. In its original version called full GMRES, this algorithm minimizes the residual over the current Krylov subspace until convergence in at -most $n$ iterations, where $n$ is the size of the sparse matrix. It should be -noticed that full GMRES is too expensive in the case of large matrices since the +most $n$ iterations, where $n$ is the size of the sparse matrix. +Full GMRES is however too much expensive in the case of large matrices, since the required orthogonalization process per iteration grows quadratically with the -number of iterations. For that reason, in practice GMRES is restarted after each -$m\ll n$ iterations to avoid the storage of a large orthonormal basis. However, +number of iterations. For that reason, GMRES is restarted in practice after each +$m\ll n$ iterations, to avoid the storage of a large orthonormal basis. However, the convergence behavior of the restarted GMRES, called GMRES($m$), in many -cases depends quite critically on the value of $m$~\cite{Huang89}. Therefore in +cases depends quite critically on the $m$ value~\cite{Huang89}. Therefore in most cases, a preconditioning technique is applied to the restarted GMRES method in order to improve its convergence. -In order to enhance the robustness of Krylov iterative solvers, some techniques have been proposed allowing the use of different preconditioners, if necessary, within the iteration instead of restarting. Those techniques may lead to considerable savings in CPU time and memory requirements. Van der Vorst in~\cite{Vorst94} has proposed variants of the GMRES algorithm in which a different preconditioner is applied in each iteration, so-called GMRESR family of nested methods. In fact, the GMRES method is effectively preconditioned with other iterative schemes (or GMRES itself), where the iterations of the GMRES method are called outer iterations while the iterations of the preconditioning process referred to as inner iterations. Saad in~\cite{Saad:1993} has proposed FGMRES which is another variant of the GMRES algorithm using a variable preconditioner. In FGMRES the search directions are preconditioned whereas in GMRESR the residuals are preconditioned. However in practice the good preconditioners are those based on direct methods, as ILU preconditioners, which are not easy to parallelize and suffer from the scalability problems on large clusters of thousands of cores. +To enhance the robustness of Krylov iterative solvers, some techniques have been proposed allowing the use of different preconditioners, if necessary, within the iteration instead of restarting. Those techniques may lead to considerable savings in CPU time and memory requirements. Van der Vorst in~\cite{Vorst94} has for instance proposed variants of the GMRES algorithm in which a different preconditioner is applied in each iteration, leading to the so-called GMRESR family of nested methods. In fact, the GMRES method is effectively preconditioned with other iterative schemes (or GMRES itself), where the iterations of the GMRES method are called outer iterations while the iterations of the preconditioning process is referred to as inner iterations. Saad in~\cite{Saad:1993} has proposed FGMRES which is another variant of the GMRES algorithm using a variable preconditioner. In FGMRES the search directions are preconditioned whereas in GMRESR the residuals are preconditioned. However, in practice, good preconditioners are those based on direct methods, as ILU preconditioners, which are not easy to parallelize and suffer from the scalability problems on large clusters of thousands of cores. Recently, communication-avoiding methods have been developed to reduce the communication overheads in Krylov subspace iterative solvers. On modern computer architectures, communications between processors are much slower than floating-point arithmetic operations on a given processor. Communication-avoiding techniques reduce either communications between processors or data movements between levels of the memory hierarchy, by reformulating the communication-bound kernels (more frequently SpMV kernels) and the orthogonalization operations within the Krylov iterative solver. Different works have studied the communication-avoiding techniques for the GMRES method, so-called CA-GMRES, on multicore processors and multi-GPU machines~\cite{Mohiyuddin2009,Hoemmen2010,Yamazaki2014}. @@ -705,7 +705,7 @@ method. Moreover, a tolerance threshold must be specified for the solver. In practice, this threshold must be much smaller than the convergence threshold of the TSIRM algorithm (\emph{i.e.}, $\epsilon_{tsirm}$). We also consider that after the call of the $Solve$ function, we obtain the vector $x_k$ and the -$error$ which is defined by $||Ax_k-b||_2$. +$error$, which is defined by $||Ax_k-b||_2$. Line~\ref{algo:store}, $S_{k \mod s}=x_k$ consists in copying the solution $x_k$ into the column $k \mod s$ of $S$. After the minimization, the matrix @@ -716,7 +716,7 @@ $error$ which is defined by $||Ax_k-b||_2$. Let us summarize the most important parameters of TSIRM: \begin{itemize} -\item $\epsilon_{tsirm}$: the threshold to stop the TSIRM method; +\item $\epsilon_{tsirm}$: the threshold that stops the TSIRM method; \item $max\_iter_{kryl}$: the maximum number of iterations for the Krylov method; \item $s$: the number of outer iterations before applying the minimization step; \item $max\_iter_{ls}$: the maximum number of iterations for the iterative least-squares method; @@ -727,9 +727,9 @@ Let us summarize the most important parameters of TSIRM: The parallelization of TSIRM relies on the parallelization of all its parts. More precisely, except the least-squares step, all the other parts are obvious to achieve out in parallel. In order to develop a parallel version of -our code, we have chosen to use PETSc~\cite{petsc-web-page}. For -line~\ref{algo:matrix_mul} the matrix-matrix multiplication is implemented and -efficient since the matrix $A$ is sparse and since the matrix $S$ contains few +our code, we have chosen to use PETSc~\cite{petsc-web-page}. In +line~\ref{algo:matrix_mul}, the matrix-matrix multiplication is implemented and +efficient since the matrix $A$ is sparse and the matrix $S$ contains few columns in practice. As explained previously, at least two methods seem to be interesting to solve the least-squares minimization, CGLS and LSQR. @@ -764,7 +764,7 @@ the parallelization of CGLS which is similar to LSQR. In each iteration of CGLS, there is two matrix-vector multiplications and some -classical operations: dot product, norm, multiplication and addition on +classical operations: dot product, norm, multiplication, and addition on vectors. All these operations are easy to implement in PETSc or similar environment. It should be noticed that LSQR follows the same principle, it is a little bit longer but it performs more or less the same operations. @@ -846,8 +846,11 @@ $\begin{array}{ll} which concludes the induction and the proof. \end{proof} -%We can remark that, at each iterate, the residue of the TSIRM algorithm is lower -%than the one of the GMRES method. +Remark that a similar proposition can be formulated at each time +the given solver satisfies an inequality of the form $||r_n|| \leqslant \mu^n ||r_0||$, +with $|\mu|<1$. Furthermore, it is \emph{a priori} possible in some particular cases +regarding $A$, +that the proposed TSIRM converges while the GMRES($m$) does not. %%%********************************************************* %%%********************************************************* @@ -947,16 +950,16 @@ to read the codes available in the PETSc sources. Those problems have been chosen because they are scalable with many cores. In the following larger experiments are described on two large scale -architectures: Curie and Juqeen. Both these architectures are supercomputer -composed of 80,640 cores for Curie and 458,752 cores for Juqueen. Those machines -are respectively hosted by GENCI in France and Jülich Supercomputing Centre in -Germany. They belongs with other similar architectures of the PRACE initiative ( -Partnership for Advanced Computing in Europe) which aims at proposing high -performance supercomputing architecture to enhance research in Europe. The Curie -architecture is composed of Intel E5-2680 processors at 2.7 GHz with 2Gb memory -by core. The Juqueen architecture is composed of IBM PowerPC A2 at 1.6 GHz with -1Gb memory per core. Both those architecture are equiped with a dedicated high -speed network. +architectures: Curie and Juqueen. Both these architectures are supercomputer +respectively composed of 80,640 cores for Curie and 458,752 cores for +Juqueen. Those machines are respectively hosted by GENCI in France and Jülich +Supercomputing Centre in Germany. They belongs with other similar architectures +of the PRACE initiative (Partnership for Advanced Computing in Europe) which +aims at proposing high performance supercomputing architecture to enhance +research in Europe. The Curie architecture is composed of Intel E5-2680 +processors at 2.7 GHz with 2Gb memory by core. The Juqueen architecture is +composed of IBM PowerPC A2 at 1.6 GHz with 1Gb memory per core. Both those +architecture are equiped with a dedicated high speed network. In many situations, using preconditioners is essential in order to find the @@ -964,7 +967,7 @@ solution of a linear system. There are many preconditioners available in PETSc. For parallel applications all the preconditioners based on matrix factorization are not available. In our experiments, we have tested different kinds of preconditioners, however as it is not the subject of this paper, we will not -present results with many preconditioners. In practise, we have chosen to use a +present results with many preconditioners. In practice, we have chosen to use a multigrid (mg) and successive over-relaxation (sor). For more details on the preconditioner in PETSc please consult~\cite{petsc-web-page}. @@ -996,26 +999,29 @@ preconditioner in PETSc please consult~\cite{petsc-web-page}. Table~\ref{tab:03} shows the execution times and the number of iterations of example ex15 of PETSc on the Juqueen architecture. Different numbers of cores -are studied ranging from 2,048 up-to 16,383 with the two preconditioners {\it mg} and {\it sor}. For those experiments, the number of components (or unknowns of the -problems) per core is fixed to 25,000, also called weak scaling. This -number can seem relatively small. In fact, for some applications that need a lot -of memory, the number of components per processor requires sometimes to be -small. - - - -In Table~\ref{tab:03}, we can notice that TSIRM is always faster than FGMRES. The last -column shows the ratio between FGMRES and the best version of TSIRM according to -the minimization procedure: CGLS or LSQR. Even if we have computed the worst -case between CGLS and LSQR, it is clear that TSIRM is always faster than -FGMRES. For this example, the multigrid preconditioner is faster than SOR. The -gain between TSIRM and FGMRES is more or less similar for the two +are studied ranging from 2,048 up-to 16,383 with the two preconditioners {\it + mg} and {\it sor}. For those experiments, the number of components (or +unknowns of the problems) per core is fixed to 25,000, also called weak +scaling. This number can seem relatively small. In fact, for some applications +that need a lot of memory, the number of components per processor requires +sometimes to be small. Other parameters for this application are described in +the legend of this Table. + + + +In Table~\ref{tab:03}, we can notice that TSIRM is always faster than +FGMRES. The last column shows the ratio between FGMRES and the best version of +TSIRM according to the minimization procedure: CGLS or LSQR. Even if we have +computed the worst case between CGLS and LSQR, it is clear that TSIRM is always +faster than FGMRES. For this example, the multigrid preconditioner is faster +than SOR. The gain between TSIRM and FGMRES is more or less similar for the two preconditioners. Looking at the number of iterations to reach the convergence, it is obvious that TSIRM allows the reduction of the number of iterations. It should be noticed that for TSIRM, in those experiments, only the iterations of the Krylov solver are taken into account. Iterations of CGLS or LSQR were not -recorded but they are time-consuming. In general each $max\_iter_{kryl}*s$ which -corresponds to 30*12, there are $max\_iter_{ls}$ which corresponds to 15. +recorded but they are time-consuming. In general each $max\_iter_{kryl}*s$ +iterations which corresponds to 30*12, there are $max\_iter_{ls}$ iterations for +the least-squares method which corresponds to 15. \begin{figure}[htbp] \centering @@ -1068,10 +1074,10 @@ architecture are reported. For this application, we fixed $\alpha=0.6$. As it can be seen in that Table, the size of the problem has a strong influence on the number of iterations to reach the convergence. That is why we have preferred to change the threshold. If we set it to $1e-3$ as with the previous application, -only one iteration is necessray to reach the convergence. So Table~\ref{tab:04} -shows the results of differents executions with differents number of cores and -differents thresholds. As with the previous example, we can observe that TSIRM -is faster than FGMRES. The ratio greatly depends on the number of iterations for +only one iteration is necessary to reach the convergence. So Table~\ref{tab:04} +shows the results of different executions with different number of cores and +different thresholds. As with the previous example, we can observe that TSIRM is +faster than FGMRES. The ratio greatly depends on the number of iterations for FMGRES to reach the threshold. The greater the number of iterations to reach the convergence is, the better the ratio between our algorithm and FMGRES is. This experiment is also a weak scaling with approximately $25,000$ components per @@ -1083,19 +1089,20 @@ Table~\ref{tab:05} show a strong scaling experiment with the exemple ex54 on the Curie architecture. So in this case, the number of unknownws is fixed to $204,919,225$ and the number of cores ranges from $512$ to $8192$ with the power of two. The threshold is fixed to $5e-5$ and only the $mg$ preconditioner has -been tested. Here again we can see that TSIRM is faster that FGMRES. Efficiecy -of each algorithms is reported. It can be noticed that FGMRES is more efficient -than TSIRM except with $8,192$ cores and that its efficiency is greater that one -whereas the efficiency of TSIRM is lower than one. Nevertheless, the ratio of -TSIRM with any version of the least-squares method is always faster. With -$8,192$ cores when the number of iterations is far more important for FGMRES, we -can see that it is only slightly more important for TSIRM. +been tested. Here again we can see that TSIRM is faster that FGMRES. Efficiency +of each algorithm is reported. It can be noticed that the efficiency of FGMRES +is better than the TSIRM one except with $8,192$ cores and that its efficiency +is greater that one whereas the efficiency of TSIRM is lower than +one. Nevertheless, the ratio of TSIRM with any version of the least-squares +method is always faster. With $8,192$ cores when the number of iterations is +far more important for FGMRES, we can see that it is only slightly more +important for TSIRM. In Figure~\ref{fig:02} we report the number of iterations per second for -experiments reported in Table~\ref{tab:05}. This Figure highlights that the -number of iterations per seconds is more of less the same for FGMRES and TSIRM +experiments reported in Table~\ref{tab:05}. This Figure highlights that the +number of iterations per second is more of less the same for FGMRES and TSIRM with a little advantage for FGMRES. It can be explained by the fact that, as we -have previously explained, that the iterations of the least-sqaure steps are not +have previously explained, that the iterations of the least-squares steps are not taken into account with TSIRM. \begin{table*}[htbp] @@ -1115,7 +1122,7 @@ taken into account with TSIRM. \hline \end{tabular} -\caption{Comparison of FGMRES and TSIRM with FGMRES for ex54 of Petsc (both with the MG preconditioner) with 204,919,225 components on Curie with different number of cores ($\epsilon_{tsirm}=5e-5$, $max\_iter_{kryl}=30$, $s=12$, $max\_iter_{ls}=15$, $\epsilon_{ls}=1e-40$), time is expressed in seconds.} +\caption{Comparison of FGMRES and TSIRM for ex54 of PETSc (both with the MG preconditioner) with 204,919,225 components on Curie with different number of cores ($\epsilon_{tsirm}=5e-5$, $max\_iter_{kryl}=30$, $s=12$, $max\_iter_{ls}=15$, $\epsilon_{ls}=1e-40$), time is expressed in seconds.} \label{tab:05} \end{center} \end{table*} @@ -1130,16 +1137,16 @@ taken into account with TSIRM. Concerning the experiments some other remarks are interesting. \begin{itemize} -\item We can tested other examples of PETSc (ex29, ex45, ex49). For all these +\item We have tested other examples of PETSc (ex29, ex45, ex49). For all these examples, we also obtained similar gain between GMRES and TSIRM but those examples are not scalable with many cores. In general, we had some problems with more than $4,096$ cores. -\item We have tested many iterative solvers available in PETSc. In fast, it is +\item We have tested many iterative solvers available in PETSc. In fact, it is possible to use most of them with TSIRM. From our point of view, the condition to use a solver inside TSIRM is that the solver must have a restart - feature. More precisely, the solver must support to be stoped and restarted + feature. More precisely, the solver must support to be stopped and restarted without decrease its converge. That is why with GMRES we stop it when it is - naturraly restarted (i.e. with $m$ the restart parameter). The Conjugate + naturally restarted (i.e. with $m$ the restart parameter). The Conjugate Gradient (CG) and all its variants do not have ``restarted'' version in PETSc, so they are not efficient. They will converge with TSIRM but not quickly because if we compare a normal CG with a CG for which we stop it each 16 @@ -1170,11 +1177,13 @@ experiments up to 16,394 cores have been led to verify that TSIRM runs For future work, the authors' intention is to investigate other kinds of -matrices, problems, and inner solvers. The influence of all parameters must be +matrices, problems, and inner solvers. In particular, the possibility +to obtain a convergence of TSIRM in situations where the GMRES is divergent will be +investigated. The influence of all parameters must be tested too, while other methods to minimize the residuals must be regarded. The number of outer iterations to minimize should become adaptative to improve the overall performances of the proposal. Finally, this solver will be implemented -inside PETSc. This would be very interesting because it would allow us to test +inside PETSc, which would be of interest as it would allow us to test all the non-linear examples and compare our algorithm with the other algorithm implemented in PETSc.