PaStiX: a high-performance parallel direct solver for sparse symmetric positive definite systems

摘要

Solving large sparse symmetric positive definite systems of linear equations is a crucial and time-consuming step, arising in many scientific and engineering applications. The block parti- tioning and scheduling problem for sparse parallel factorization without pivoting is consid- ered. There are tow major aims to this study: the scalability of the parallel solver, and the compromise between memory overhead and efficiency. Parallel experiments on a large collec- tion of irregular industrial problems validate out approach.