Techniques for Parallel Manipulation of Sparse Matrices
نویسندگان
چکیده
New techniques are presented forthe manipulation of sparse matrices on parallel MIMD computers. We consider the following problems: matrix addition, matrix multiplication, row and column permutation, matrix transpose, matrix vector multiplication, and Gaussian elimination.
منابع مشابه
P-sparslib: a Portable Library of Distributed Memory Sparse Iterative Solvers
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 solver developed around the idea of `distributed sparse matrices'. We explore issues related to data structures for ...
متن کاملA Parallel Gauss-Seidel Algorithm for Sparse Power Systems Matrices
We describe the implementation and performance of an e cient parallel Gauss-Seidel algorithm that has been developed for irregular, sparse matrices from electrical power systems applications. Although, Gauss-Seidel algorithms are inherently sequential, by performing specialized orderings on sparse matrices, it is possible to eliminate much of the data dependencies caused by precedence in the ca...
متن کاملData Structures and Algorithms for Domain Decomposition and Distributed Sparse Matrices
Although Domain Decomposition (DD) techniques constitute an important class of methods few actual general purpose codes based on these techniques have been developed so far. It is important to develop algorithms as well as software libraries and tools to facilitate parallel implementations of such techniques. In this paper we explore these ideas and propose a data structure for implementing`dis...
متن کاملAlgorithms and Data Structures for Very Large Sparse Matrices
Sparse matrix-vector multiplication (SpMV) is one of the most important numerical core methods in scientific and engineering computing. On today’s petascale and future exascale systems, the three principal problems related to SpMV are the minimization of communication between processors in distributed-memory environments, the maximization of the efficiency of local SpMV performed by a single pr...
متن کاملMSP: A Class of Parallel Multistep Successive Sparse Approximate Inverse Preconditioning Strategies
We develop a class of parallel multistep successive preconditioning strategies to enhance efficiency and robustness of standard sparse approximate inverse preconditioning techniques. The key idea is to compute a series of simple sparse matrices to approximate the inverse of the original matrix. Studies are conducted to show the advantages of such an approach in terms of both improving precondit...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Theor. Comput. Sci.
دوره 64 شماره
صفحات -
تاریخ انتشار 1989