Improved row-grouped CSR format for storing of sparse matrices on GPU

zbMATH Open1278.65051MaRDI QIDQ2867836FDOQ2867836

Authors Tomáš Oberhuber, Martin Heller

Publication date 20 December 2013

Full work available at URL https://arxiv.org/abs/1203.5737

zbMATH Keywords

sparse matricesparallel computingCUDAGPUSpMVcircuit simulationsoptimizations problemsthread computing

Mathematics Subject Classification ID

Computational methods for sparse matrices (65F50) Parallel numerical computation (65Y05) Iterative numerical methods for linear systems (65F10)

Recommendations

• Compressed multirow storage format for sparse matrices on graphics processing units
• A novel CSR-based sparse matrix-vector multiplication on GPUs
• Sparse matrix-vector multiplication on NVIDIA GPU
• Efficient CSR-based sparse matrix-vector multiplication on GPU
• A new sparse matrix storage format for improving SpMV performance by SIMD

Cited in

(5)

• A Hilbert-order multiplication scheme for unstructured sparse matrices
• A novel CSR-based sparse matrix-vector multiplication on GPUs
• MPI-CUDA sparse matrix-vector multiplication for the conjugate gradient method with an approximate inverse preconditioner
• A new sparse matrix storage format for improving SpMV performance by SIMD
• Compressed multirow storage format for sparse matrices on graphics processing units

Describes a project that uses

Uses Software

• CUDA
• CUSPARSE

This page was built for publication: Improved row-grouped CSR format for storing of sparse matrices on GPU

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2867836)