A survey of sparse matrix-vector multiplication performance on large matrices

Abstract

We contribute a third-party survey of sparse matrix-vector (SpMV) product performance on industrial-strength, large matrices using: (1) The SpMV implementations in Intel MKL, the Trilinos project (Tpetra subpackage), the CUSPARSE library, and the CUSP library, each running on modern architectures. (2) NVIDIA GPUs and Intel multi-core CPUs (supported by each software package). (3) The CSR, BSR, COO, HYB, and ELL matrix formats (supported by each software package).

Rice Oil & Gas High Performance Computing Workshop. March 2016

Cited by in corpus (4)

• A Parallel, Distributed Memory Implementation of the Adaptive Sampling Configuration Interaction Method
• Computation on Sparse Neural Networks: an Inspiration for Future Hardware
• A finite volume/discontinuous Galerkin method for the advective Cahn-Hilliard equation with degenerate mobility on porous domains stemming from micro-CT imaging
• Accelerating Radiation Therapy Dose Calculation with Nvidia GPUs