Exploiting parallelism in matrix-computation kernels for symmetric multiprocessor systems: matrix-multiplication and matrix-addition algorithm optimizations by software pipelining and threads allocation

DOI10.1145/2049662.2049664zbMATH Open1365.65109OpenAlexW2045822279WikidataQ113310428 ScholiaQ113310428MaRDI QIDQ2989138FDOQ2989138

Authors: Paolo D'Alberto, Marco Bodrato, Alexandru Nicolau 

Publication date: 19 May 2017

Published in: ACM Transactions on Mathematical Software (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1145/2049662.2049664

Recommendations

• Adaptive Winograd's matrix multiplications
• Efficient Matrix Multiplication on SIMD Computers
• A memetic algorithm to schedule planned maintenance for the national grid
• scientific article; zbMATH DE number 1728263
• Emmerald: a fast matrix–matrix multiply using Intel's SSE instructions

zbMATH Keywords

parallelismfast algorithmsmatrix multiplicationssoftware pipeline

Mathematics Subject Classification ID

Parallel numerical computation (65Y05)

Cited In (5)

• Improving the Complexity of Block Low-Rank Factorizations with Fast Matrix Arithmetic
• Strassen's Algorithm for Tensor Contraction
• Computational Science - ICCS 2004
• Pebbling Game and Alternative Basis for High Performance Matrix Multiplication
• Adaptive Winograd's matrix multiplications

Uses Software

• FLAME
• LAPACK
• SPIRAL
• FFTW
• Algorithm 679
• Algorithm 784

This page was built for publication: Exploiting parallelism in matrix-computation kernels for symmetric multiprocessor systems: matrix-multiplication and matrix-addition algorithm optimizations by software pipelining and threads allocation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2989138)