Verification Challenges in Sparse Matrix Vector Multiplication in High Performance Computing: Part I
arXiv:2510.13427 · doi:10.4204/EPTCS.432.11
Abstract
Sparse matrix vector multiplication (SpMV) is a fundamental kernel in scientific codes that rely on iterative solvers. In this first part of our work, we present both a sequential and a basic MPI parallel implementations of SpMV, aiming to provide a challenge problem for the scientific software verification community. The implementations are described in the context of the PETSc library.
In Proceedings VSS 2025, arXiv:2510.12314