ویراساینس.
سند علمی

Kernels for Distributed Memory Sparse Iterative Solvers ?

Yousef Saad, Andrei V. Malevsky

چکیده

Domain Decomposition techniques constitute an important class of methods especially appropriate in a parallel computing environment, but only a few general purpose codes based on these techniques have been developed so far. In this work, we attempt to develop not only algorithms but also software libraries and tools to help in the parallel implementation of such techniques. These algorithms and tools form P-SPARSLIB, a library of distributed sparse iterative solvers.

اسناد مشابه

  • P-sparslib: a Portable Library of Distributed Memory Sparse Iterative Solvers

    سند علمی۱۹۹۵Yousef Saad, Andrei V. Malevsky

    Domain Decomposition techniques constitute an important class of methods which are especially appropriate in a parallel computing environment. However, few general purpose computational codes based on these techniques have been developed so far. In this paper, we propose one such

  • Inner product computation for sparse iterative solvers on distributed supercomputer

    سند علمی۲۰۱۲Sheng-Xin Zhu, Tong-Xiang Gu, Xing-Ping Liu

    Recent years have witnessed that iterative Krylov methods without re-designing are not suitable for distribute supercomputers because of intensive global communications. It is well accepted that re-engineering Krylov methods for prescribed computer architecture is necessary and i

  • Minimizing synchronizations in sparse iterative solvers for distributed supercomputers

    سند علمی۲۰۱۴Computers & Mathematics with ApplicationsSheng-Xin Zhu, Tongxiang Gu, Xing-Ping Liu

    Eliminating synchronizations is one of the important techniques related to minimizing communications for modern high performance computing. This paper discusses principles of reducing communications due to global synchronizations in sparse iterative solvers on distributed superco

  • MUMPS : A General Purpose Distributed Memory Sparse Solver

    سند علمی۲۰۰۰PARAPatrick Amestoy, Iain S. Duff, Jean-Yves L'Excellent, Jacko Koster

    MUMPS is a software package for the multifrontal solution of large sparse linear systems on distributed memory computers. The matrices can be symmetric positive definite, general symmetric, or unsymmetric, and possibly rank deficient. MUMPS exploits parallelism coming from the sp

  • Sparsifying Synchronization for High-Performance Shared-Memory Sparse Triangular Solver

    سند علمی۲۰۱۴ISCJongsoo Park, Mikhail Smelyanskiy, Narayanan Sundaram, Pradeep Dubey

    The last decade has seen rapid growth of single-chip multiprocessors (CMPs), which have been leveraging Moore’s law to deliver high concurrency via increases in the number of cores and vector width. Modern CMPs execute from several hundreds to several thousands concurrent operati

  • Performance and tuning of two distributed memory sparse solvers

    سند علمی۲۰۰۱PPSCPatrick Amestoy, Iain S. Duff, Jean-Yves L'Excellent, Xiaoye S. Li

    We examine the performance of two codes using direct methods to solve large sparse linear equations on distributed memory computers. The code SuperLU is a right-looking supernodal code, written in C, while MUMPS is written in Fortran 90 and uses a multifrontal technique. Both cod