PaStiX: A Parallel Direct Solver for Sparse SPD Matrices based on Efficient Static Scheduling and Memory Managment

Abstract

Solving large sparse symmetric positive definite systems of linear equations is a crucial and time-consuming step, arising in many scientific and engineering applications. In this work, we consider the block partitioning and scheduling problem for sparse parallel factorization without pivoting. We focus on the scalability of the parallel solver, and on the compromise between memory overhead and efficiency. We validate this study with parallel experiments on a large collection of irregular industrial problems.

Publication
Tenth SIAM Conference on Parallel Processing for Scientific Computing

Related