Analytical modeling of matrix–vector multiplication on multicore processors

DOI10.1002/MMA.7045zbMATH Open1527.65028OpenAlexW3121314575MaRDI QIDQ6139033FDOQ6139033

Authors: E. N. Akimova 

Publication date: 18 December 2023

Published in: Mathematical Methods in the Applied Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/mma.7045

Recommendations

• Anatomy of high-performance matrix multiplication
• A framework for high-performance matrix multiplication based on hierarchical abstractions, algorithms and optimized low-level kernels
• scientific article; zbMATH DE number 1728263
• Analytical modeling is enough for high-performance BLIS
• SparseX: a library for high-performance sparse matrix-vector multiplication on multicore platforms

zbMATH Keywords

parallel computationmatrix-vector multiplicationanalytical modelingmulticore processors

Mathematics Subject Classification ID

Parallel numerical computation (65Y05) Numerical linear algebra (65F99)

Cites Work

• Automated empirical optimizations of software and the ATLAS project
• BLIS: a framework for rapidly instantiating BLAS functionality
• Basic Linear Algebra Subprograms for Fortran Usage
• A set of level 3 basic linear algebra subprograms
• Communication lower bounds and optimal algorithms for numerical linear algebra
• Title not available (Why is that?)
• Analytical modeling is enough for high-performance BLIS
• Embedded processor design challenges. Systems, architectures, modeling, and simulation - SAMOS

Cited In (1)

• Parameter estimation via time modeling for MLIR implementation of GEMM

This page was built for publication: Analytical modeling of matrix–vector multiplication on multicore processors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6139033)