The Use of BLAS3 in Linear Algebra on a Parallel Processor with a Hierarchical Memory

DOI10.1137/0908086MaRDI QIDQ3769849zbMATH OpenOpenAlexFDO

Authors K. A. Gallivan, William Jalby, Ulrike Meier

Publication date 1987

Published in SIAM Journal on Scientific and Statistical Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/0908086

zbMATH Keywords

parallel computingBlock algorithmsGram-Schmidt algorithmcache managementLU- decompositionBLAS3ALLIANT FX/8small cache size

Mathematics Subject Classification ID

Direct numerical methods for linear systems and matrix inversion (65F05) Parallel numerical computation (65Y05) Data structures (68P05) Orthogonalization in numerical linear algebra (65F25)

Recommendations

• Exploiting fast matrix multiplication within the level 3 BLAS
• Designing linear algebra algorithms on the IBM 3090 vector multiprocessor with a hierarchical memory system
• Parallelly solving linear systems on a hierarchy memory multiprocessor
• A parallel block implementation of Level-3 BLAS for MIMD vector processors
• scientific article; zbMATH DE number 878999
• scientific article; zbMATH DE number 954666
• scientific article; zbMATH DE number 431981
• Performance of parallel Cholesky factorization algorithms using BLAS

Cited in

(11)

• Adaptive blocking in the QR factorization
• An overview of parallel algorithms for the singular value and symmetric eigenvalue problems
• Gaussian variant of Freivalds' algorithm for efficient and reliable matrix product verification
• Vector processing in simplex and interior methods for linear programming
• Fast parallel solution of the Poisson equation on irregular domains
• Block-Cholesky for parallel processing
• A locally optimized reordering algorithm and its application to a parallel sparse linear system solver
• Designing linear algebra algorithms on the IBM 3090 vector multiprocessor with a hierarchical memory system
• Block conjugate gradient algorithms for least squares problems
• scientific article; zbMATH DE number 1136274 (Why is no real title available?)
• A pseudospectral matrix element method for solution of three-dimensional incompressible flows and its parallel implementation

This page was built for publication: The Use of BLAS3 in Linear Algebra on a Parallel Processor with a Hierarchical Memory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3769849)