Efficient address generation for affine subscripts in data-parallel programs

DOI10.1023/A:1008190606079MaRDI QIDQ5938647zbMATH OpenFDO

Authors Kuei-Ping Shih, Chih-Yung Chang, Jang-Ping Sheu, Jang-Ping Sheu

Publication date 1 October 2001

Published in The Journal of Supercomputing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1023/A:1008190606079

zbMATH Keywords

address generationaffine subscriptsdata distributiondata-parallel languagesdistributed-memory multicomputersmultiple induction variables (MIVs)single program multiple data (SPMD)

Mathematics Subject Classification ID

Other programming paradigms (object-oriented, sequential, concurrent, automatic, etc.) (68N19) Computing methodologies and applications (68U99)

Recommendations

• Generating efficient local memory access sequences for coupled subscripts in data-parallel programs.
• Generating local addresses and communication sets for data-parallel programs
• scientific article; zbMATH DE number 1262842
• The local memory access sequence of multiple induction variables on distributed memory machines
• Compiling for efficient communication of aligned arrays with block-cyclic distribution

Cited in

(5)

• Generating efficient local memory access sequences for coupled subscripts in data-parallel programs.
• Generating local addresses and communication sets for data-parallel programs
• Efficient index generation for compiling two-level mappings in data-parallel programs
• Compiling for efficient communication of aligned arrays with block-cyclic distribution
• Efficient address generation in a parallel processor

This page was built for publication: Efficient address generation for affine subscripts in data-parallel programs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5938647)