PaStiX: A Parallel Sparse Direct Solver Based on a Static Scheduling for Mixed 1D/2D Block Distributions

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

Dynamic scheduling for sparse direct solver on NUMA architectures

Over the past few years, parallel sparse direct solvers made significant progress and are now able to efficiently work on problems with several millions of equations. This paper presents some improvements on our sparse direct solver PaStiX for distributed Non-Uniform Memory Access architectures. We show results on two preliminary works: a memory allocation scheme more adapted to these architect...

A NUMA Aware Scheduler for a Parallel Sparse Direct Solver

Over the past few years, parallel sparse direct solvers have made significant progress [1, 3, 4]. They are now able to solve efficiently real-life three-dimensional problems with several millions of equations. Since the last decade, most of the supercomputer architectures are based on clusters of SMP (Symmetric Multi-Processor) nodes. In [5], the authors proposed a hybrid MPI-thread implementat...

Sparse direct solvers with accelerators over DAG runtimes

The current trend in the high performance computing shows a dramatic increase in the number of cores on the shared memory compute nodes. Algorithms, especially those related to linear algebra, need to be adapted to these new computer architectures in order to be efficient. PASTIX* is a sparse parallel direct solver, that incorporates a dynamic scheduler for strongly hierarchical modern architec...

A Scalable Parallel Assembly for Irregular Meshes Based on a Block Distribution for a Parallel Block Direct Solver

This paper describes a distribution of elements for irregular nite element meshes as well as the associated parallel assembly algorithm , in the context of parallel solving of the resulting sparse linear system using a direct block solver. These algorithms are integrated in the software processing chain EMILIO being developped at LaBRI for structural mechanics applications. Some illustrative nu...