DocumentCode
2748496
Title
Optimization rules for programming with collective operations
Author
Gorlatch, Sergei ; Wedler, Christoph ; Lengauer, Christian
Author_Institution
Fakultat fur Math. und Inf., Passau Univ., Germany
fYear
1999
fDate
12-16 Apr 1999
Firstpage
492
Lastpage
499
Abstract
We study how several collective operations like broadcast, reduction, scan, etc. can be composed efficiently in complex parallel programs. Our specific contributions are: (1) a formal framework for reasoning about collective operations; (2) a set of optimization rules which save communications by fusing several collective operations into one; (3) performance estimates, which guide the application of optimization rules depending on the machine characteristics; (4) a simple case study with machine experiments
Keywords
parallel programming; broadcast; collective operations; optimization rules; performance estimates; reduction; scan; Broadcasting; Computer architecture; Concurrent computing; Functional programming; Hardware; Libraries; Parallel languages; Parallel processing; Parallel programming; Programming environments;
fLanguage
English
Publisher
ieee
Conference_Titel
Parallel Processing, 1999. 13th International and 10th Symposium on Parallel and Distributed Processing, 1999. 1999 IPPS/SPDP. Proceedings
Conference_Location
San Juan
Print_ISBN
0-7695-0143-5
Type
conf
DOI
10.1109/IPPS.1999.760522
Filename
760522
Link To Document