Effect of GPU communication-hiding for SpMV using OpenACC

DOI10.1142/S0219876216400119MaRDI QIDQ2972093zbMATHOpenAlexFDO

Authors Olav Aanes Fagerlund, Takeshi Kitayama, Gaku Hashimoto, H. Okuda

Publication date 7 April 2017

Published in International Journal of Computational Methods (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/s0219876216400119

zbMATH Keywords

overlappingFEMGPGPUblock KrylovOpenACCSpMVcommunication-hidingRHS-vector

Mathematics Subject Classification ID

Computational methods for sparse matrices (65F50) Numerical algorithms for specific classes of architectures (65Y10)

Recommendations

• Efficient CSR-based sparse matrix-vector multiplication on GPU
• Sparse matrix-vector multiplication on GPGPUs
• A novel CSR-based sparse matrix-vector multiplication on GPUs
• Sparse matrix-vector multiply algorithm based on overlapping computation and communication and application in AMG
• Sparse matrix-vector product

Describes a project that uses

Uses Software

• CUDA
• OpenACC

This page was built for publication: Effect of GPU communication-hiding for SpMV using OpenACC

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2972093)