DocumentCode
862615
Title
Multiprocessor synchronization for concurrent loops
Author
Wolfe, Michael
Author_Institution
Kuck & Associates Inc., Savoy, IL, USA
Volume
5
Issue
1
fYear
1988
Firstpage
34
Lastpage
42
Abstract
Execution of concurrent loops on multiprocessor computers often requires synchronizing the processors. Synchronization schemes are surveyed that are suitable for automatic problem decomposition. The model of a shared-memory multiprocessor is used, as is the concurrent-loop paradigm, which is to compile a loop so each processor is assigned a different loop iteration. The discussion covers data dependence, removing synchronization points, random synchronization, pipelining, barrier synchronization, and critical sections.<>
Keywords
multiprocessing programs; parallel programming; synchronisation; automatic problem decomposition; barrier synchronization; concurrent loops; critical sections; data dependence; loop iteration; multiprocessor computers; pipelining; random synchronization; shared-memory multiprocessor; synchronization points; Concurrent computing; Data mining; Delay; Multitasking; Operating systems; Parallel processing; Registers; Throughput; Vector processors;
fLanguage
English
Journal_Title
Software, IEEE
Publisher
ieee
ISSN
0740-7459
Type
jour
DOI
10.1109/52.1992
Filename
1992
Link To Document