Performance evaluation of accelerated real and complex multiple-precision sparse matrix-vector multiplication

TL;DR

This paper evaluates the performance of accelerated sparse matrix-vector multiplication using SIMD instructions with multiple-precision arithmetic, highlighting its effectiveness in scientific computing and Krylov subspace methods.

Contribution

It introduces an accelerated SpMV method employing SIMD instructions with multiple-precision arithmetic, demonstrating improved stability and performance in scientific applications.

Findings

Accelerated SpMV with SIMD improves computational speed.

Multiple-precision arithmetic reduces round-off errors.

Effective in Krylov subspace methods.

Abstract

Sparse matrices have recently played a significant and impactful role in scientific computing, including artificial intelligence-related fields. According to historical studies on sparse matrix--vector multiplication (SpMV), Krylov subspace methods are particularly sensitive to the effects of round-off errors when using floating-point arithmetic. By employing multiple-precision linear computation, convergence can be stabilized by reducing these round-off errors. In this paper, we present the performance of our accelerated SpMV using SIMD instructions, demonstrating its effectiveness through various examples, including Krylov subspace methods.