A Scalable Sparse Direct Solver Using Static Pivoting
نویسندگان
چکیده
We propose several techniques as alternatives to partial pivoting to stabilize sparse Gaussian elimination. From numerical experiments we demonstrate that for a wide range of problems the new method is as stable as partial pivoting. The main advantage of the new method over partial pivoting is that it permits a priori determination of data structures and communication pattern, which makes it more scalable. We demonstrate the scalability of our algorithms on large-scale distributed memory computers.
منابع مشابه
A Distributed CPU-GPU Sparse Direct Solver
This paper presents the first hybrid MPI+OpenMP+CUDA implementation of a distributed memory right-looking unsymmetric sparse direct solver (i.e., sparse LU factorization) that uses static pivoting. While BLAS calls can account for more than 40% of the overall factorization time, the difficulty is that small problem sizes dominate the workload, making efficient GPU utilization challenging. This ...
متن کاملHSL_MA57 - Sparse symmetric system: multifrontal method
The method used is a direct method based on a sparse variant of Gaussian elimination and is discussed further by Duff and Reid, ACM Trans. Math. Software 9 (1983), 302-325. A detailed discussion on the MA57 strategy and performance is given by Duff, ACM Trans. Math. Software 30 (2004), 118-144. Relevant work on pivoting and scaling strategies is given by Duff and Pralet, SIAM Journal Matrix Ana...
متن کاملTowards a stable static pivoting strategy for the sequential and parallel solution of sparse symmetric indefinite systems
We consider the direct solution of sparse symmetric indefinite matrices. We develop new pivoting strategies that combine numerical and static pivoting. Furthermore, we propose original approaches that are designed for parallel distributed factorization. We show that our pivoting strategies are numerically robust and that the factorization is significantly faster because of this static/numerical...
متن کاملA Comparison of D and D Data Mapping for Sparse LU Factorization with Partial Pivoting
This paper presents a comparative study of two data mapping schemes for parallel sparse LU factorization with partial pivoting on distributed memory machines Our previous work has developed an approach that incorporates static symbolic factoriza tion nonsymmetric L U supernode partitioning and graph scheduling for this problem with D column block mapping The D mapping is commonly considered mor...
متن کاملBIT ? ? ( 199 ? ) , ? ? ? { ? ? ? . An Assessment of Incomplete - LU Preconditioners forNonsymmetric Linear Systems
We report on an extensive experiment to compare an iterative solver preconditioned by several versions of incomplete LU factorization with a sparse direct solver using LU factorization with partial pivoting. Our test suite is 24 nonsymmetric matrices drawn from benchmark sets in the literature. On a few matrices, the best iterative method is more than 5 times as fast and more than 10 times as m...
متن کامل