Distributed O(N) Linear Solver for Dense Symmetric Hierarchical Semi-Separable Matrices
Distributed O(N) Linear Solver for Dense Symmetric Hierarchical Semi-Separable Matrices
复制标题
密集对称分层半可分离矩阵的分布式 O(N) 线性求解器
DOI:
10.1109/mcsoc.2019.00008
复制
发表时间:
2019
期刊:
影响因子:
--
通讯作者:
Biros, George
中科院分区:
文献类型:
--
作者:
Yu, Chenhan D.;Reiz, Severin;Biros, George
We present a distributed memory algorithm for the approximate hierarchical factorization of symmetric positive definite (SPD) matrices. Our method is based on the distributed memory GOFMM, an algorithm that appeared in SC18 (doi:10.1109/SC.2018.00018). GOFMM constructs a hierarchical matrix approximation of an arbitrary SPD matrix that compresses the matrix by creating low-rank approximations of the off-diagonal blocks. GOFMM method has no guarantees of success for arbitrary SPD matrices. (This is similar to the SVD; not every matrix admits a good low-rank approximation.) But for many SPD matrices, GOFMM does enable compression that results in fast matrix-vector multiplication that can reach N logN time—as opposed to N2 required for a dense matrix. GOFMM supports shared and distributed memory parallelism. In this paper, we build an approximate "ULV" factorization based on the Hierarchically Semi-Separable (HSS) compression of the GOFMM. This factorization requires O(N) work (given the compressed matrix) and O(N=p) + O(log p) time on p MPI processes (assuming a hypercube topology). The previous state-of-the-art required O(N logN) work. We present the factorization algorithm, discuss its complexity, and present weak and strong scaling results for the "factorization" and "solve" phases of our algorithm. We also discuss the performance of the inexact ULV factorization as a preconditioner for a few exemplary large dense linear systems. In our largest run, we were able to factorize a 67M-by-67M matrix in less than one second; and solve a system with 64 right-hand sides in less than one-tenth of a second. This run was on 6,144 Intel "Skylake" cores on the SKX partition of the Stampede2 system at the Texas Advanced Computing Center.
登录
查看更多内容
DOI:
--
发表时间:
2017
期刊:
International Conference for High Performance Computing, Networking, Storage and Analysis
影响因子:
--
作者:
Chenhan D. Yu;James Levitt;Severin Reiz;G. Biros
通讯作者:
G. Biros
影响因子:
3.1
作者:
William B. March;Bo Xiao;Chenhan D. Yu;G. Biros
通讯作者:
G. Biros
DOI:
--
发表时间:
2018
期刊:
European Conference on Parallel Processing
影响因子:
--
作者:
Kadir Akbudak;H. Ltaief;A. Mikhalev;A. Charara;Aniello Esposito;D. Keyes
通讯作者:
D. Keyes
DOI:
10.1109/sc.2018.00018
发表时间:
2018
期刊:
SC18: International Conference for High Performance Computing, Networking, Storage and Analysis
影响因子:
--
作者:
Chenhan D. Yu;Severin Reiz;G. Biros
通讯作者:
G. Biros
DOI:
--
发表时间:
2017
期刊:
IEEE International Parallel and Distributed Processing Symposium
影响因子:
--
作者:
Chenhan D. Yu;William B. March;G. Biros
通讯作者:
G. Biros