Cluster-Enabled OpenMP: An OpenMP Compiler for the SCASH Software Distributed Shared Memory System
OpenMP is attracting wide-spread interest because of its easy-to-use parallel programming model for shared memory multiprocessors. We have implemented a "cluster-enabled" OpenMP compiler for a page-based software distributed shared memory system, SCASH, which works on a cluster of PCs. It...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2001-01-01
|
Series: | Scientific Programming |
Online Access: | http://dx.doi.org/10.1155/2001/605217 |
id |
doaj-74e93ef9cdd5469c9c4a9f5d93d6ac25 |
---|---|
record_format |
Article |
spelling |
doaj-74e93ef9cdd5469c9c4a9f5d93d6ac252021-07-02T13:47:19ZengHindawi LimitedScientific Programming1058-92441875-919X2001-01-0192-312313010.1155/2001/605217Cluster-Enabled OpenMP: An OpenMP Compiler for the SCASH Software Distributed Shared Memory SystemMitsuhisa Sato0Hiroshi Harada1Atsushi Hasegawa2Yutaka Ishikawa3Real World Computing Partnership, 1-6-1 Takezono, Tsukuba Mitsui-Blg. 16F, Tsukuba, Ibaraki 305-0032, JapanReal World Computing Partnership, 1-6-1 Takezono, Tsukuba Mitsui-Blg. 16F, Tsukuba, Ibaraki 305-0032, JapanNEC Informatec Systems, Ltd., JapanReal World Computing Partnership, 1-6-1 Takezono, Tsukuba Mitsui-Blg. 16F, Tsukuba, Ibaraki 305-0032, JapanOpenMP is attracting wide-spread interest because of its easy-to-use parallel programming model for shared memory multiprocessors. We have implemented a "cluster-enabled" OpenMP compiler for a page-based software distributed shared memory system, SCASH, which works on a cluster of PCs. It allows OpenMP programs to run transparently in a distributed memory environment. The compiler transforms OpenMP programs into parallel programs using SCASH so that shared global variables are allocated at run time in the shared address space of SCASH. A set of directives is added to specify data mapping and loop scheduling method which schedules iterations onto threads associated with the data mapping. Our experimental results show that the data mapping may greatly impact on the performance of OpenMP programs in the software distributed shared memory system. The performance of some NAS parallel benchmark programs in OpenMP is improved by using our extended directives.http://dx.doi.org/10.1155/2001/605217 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mitsuhisa Sato Hiroshi Harada Atsushi Hasegawa Yutaka Ishikawa |
spellingShingle |
Mitsuhisa Sato Hiroshi Harada Atsushi Hasegawa Yutaka Ishikawa Cluster-Enabled OpenMP: An OpenMP Compiler for the SCASH Software Distributed Shared Memory System Scientific Programming |
author_facet |
Mitsuhisa Sato Hiroshi Harada Atsushi Hasegawa Yutaka Ishikawa |
author_sort |
Mitsuhisa Sato |
title |
Cluster-Enabled OpenMP: An OpenMP Compiler for the SCASH Software Distributed Shared Memory System |
title_short |
Cluster-Enabled OpenMP: An OpenMP Compiler for the SCASH Software Distributed Shared Memory System |
title_full |
Cluster-Enabled OpenMP: An OpenMP Compiler for the SCASH Software Distributed Shared Memory System |
title_fullStr |
Cluster-Enabled OpenMP: An OpenMP Compiler for the SCASH Software Distributed Shared Memory System |
title_full_unstemmed |
Cluster-Enabled OpenMP: An OpenMP Compiler for the SCASH Software Distributed Shared Memory System |
title_sort |
cluster-enabled openmp: an openmp compiler for the scash software distributed shared memory system |
publisher |
Hindawi Limited |
series |
Scientific Programming |
issn |
1058-9244 1875-919X |
publishDate |
2001-01-01 |
description |
OpenMP is attracting wide-spread interest because of its easy-to-use parallel programming model for shared memory multiprocessors. We have implemented a "cluster-enabled" OpenMP compiler for a page-based software distributed shared memory system, SCASH, which works on a cluster of PCs. It allows OpenMP programs to run transparently in a distributed memory environment. The compiler transforms OpenMP programs into parallel programs using SCASH so that shared global variables are allocated at run time in the shared address space of SCASH. A set of directives is added to specify data mapping and loop scheduling method which schedules iterations onto threads associated with the data mapping. Our experimental results show that the data mapping may greatly impact on the performance of OpenMP programs in the software distributed shared memory system. The performance of some NAS parallel benchmark programs in OpenMP is improved by using our extended directives. |
url |
http://dx.doi.org/10.1155/2001/605217 |
work_keys_str_mv |
AT mitsuhisasato clusterenabledopenmpanopenmpcompilerforthescashsoftwaredistributedsharedmemorysystem AT hiroshiharada clusterenabledopenmpanopenmpcompilerforthescashsoftwaredistributedsharedmemorysystem AT atsushihasegawa clusterenabledopenmpanopenmpcompilerforthescashsoftwaredistributedsharedmemorysystem AT yutakaishikawa clusterenabledopenmpanopenmpcompilerforthescashsoftwaredistributedsharedmemorysystem |
_version_ |
1721328768701693952 |