Compiler Optimization Techniques for OpenMP Programs

We have developed compiler optimization techniques for explicit parallel programs using the OpenMP API. To enable optimization across threads, we designed dataflow analysis techniques in which interactions between threads are effectively modeled. Structured description of parallelism and relaxed mem...

Full description

Saved in:
Bibliographic Details
Published in:Scientific programming 2001-01, Vol.9 (2-3), p.131-142
Main Authors: Satoh, Shigehisa, Kusano, Kazuhiro, Sato, Mitsuhisa
Format: Article
Language:English
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c1834-aca8b790921d25d4da69a61123990f191855e9872dca8f05827d6e55af8ad98f3
cites
container_end_page 142
container_issue 2-3
container_start_page 131
container_title Scientific programming
container_volume 9
creator Satoh, Shigehisa
Kusano, Kazuhiro
Sato, Mitsuhisa
description We have developed compiler optimization techniques for explicit parallel programs using the OpenMP API. To enable optimization across threads, we designed dataflow analysis techniques in which interactions between threads are effectively modeled. Structured description of parallelism and relaxed memory consistency in OpenMP make the analyses effective and efficient. We developed algorithms for reaching definitions analysis, memory synchronization analysis, and cross‐loop data dependence analysis for parallel loops. Our primary target is compiler‐directed software distributed shared memory systems in which aggressive compiler optimizations for software‐implemented coherence schemes are crucial to obtaining good performance. We also developed optimizations applicable to general OpenMP implementations, namely redundant barrier removal and privatization of dynamically allocated objects. Experimental results for the coherency optimization show that aggressive compiler optimizations are quite effective for a shared‐write intensive program because the coherence‐induced communication volume in such a program is much larger than that in shared‐read intensive programs.
doi_str_mv 10.1155/2001/189054
format article
fullrecord <record><control><sourceid>crossref</sourceid><recordid>TN_cdi_crossref_primary_10_1155_2001_189054</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1155_2001_189054</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1834-aca8b790921d25d4da69a61123990f191855e9872dca8f05827d6e55af8ad98f3</originalsourceid><addsrcrecordid>eNotj0FLAzEUhINYsLae_AN7l9i8bLKbd5RFrVBpDxW8hbhJNNLdrEk96K93l3qagRmG-Qi5BnYLIOWKMwYrUMikOCNzULWkCPh6PnomFUUuxAW5zPlz7ClgbE5EE7shHFwqtsMxdOHXHEPsi71rP_rw9e1y4eOUuf55V-xSfE-my0sy8-aQ3dW_LsjLw_2-WdPN9vGpudvQFlQpqGmNequRIQfLpRXWVGgqAF4iMg8ISkqHquZ2LPrxIK9t5aQ0XhmLypcLcnPabVPMOTmvhxQ6k340MD0B6wlYn4DLP-qqRwM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Compiler Optimization Techniques for OpenMP Programs</title><source>Wiley-Blackwell Titles (Open access)</source><creator>Satoh, Shigehisa ; Kusano, Kazuhiro ; Sato, Mitsuhisa</creator><creatorcontrib>Satoh, Shigehisa ; Kusano, Kazuhiro ; Sato, Mitsuhisa</creatorcontrib><description>We have developed compiler optimization techniques for explicit parallel programs using the OpenMP API. To enable optimization across threads, we designed dataflow analysis techniques in which interactions between threads are effectively modeled. Structured description of parallelism and relaxed memory consistency in OpenMP make the analyses effective and efficient. We developed algorithms for reaching definitions analysis, memory synchronization analysis, and cross‐loop data dependence analysis for parallel loops. Our primary target is compiler‐directed software distributed shared memory systems in which aggressive compiler optimizations for software‐implemented coherence schemes are crucial to obtaining good performance. We also developed optimizations applicable to general OpenMP implementations, namely redundant barrier removal and privatization of dynamically allocated objects. Experimental results for the coherency optimization show that aggressive compiler optimizations are quite effective for a shared‐write intensive program because the coherence‐induced communication volume in such a program is much larger than that in shared‐read intensive programs.</description><identifier>ISSN: 1058-9244</identifier><identifier>EISSN: 1875-919X</identifier><identifier>DOI: 10.1155/2001/189054</identifier><language>eng</language><ispartof>Scientific programming, 2001-01, Vol.9 (2-3), p.131-142</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c1834-aca8b790921d25d4da69a61123990f191855e9872dca8f05827d6e55af8ad98f3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Satoh, Shigehisa</creatorcontrib><creatorcontrib>Kusano, Kazuhiro</creatorcontrib><creatorcontrib>Sato, Mitsuhisa</creatorcontrib><title>Compiler Optimization Techniques for OpenMP Programs</title><title>Scientific programming</title><description>We have developed compiler optimization techniques for explicit parallel programs using the OpenMP API. To enable optimization across threads, we designed dataflow analysis techniques in which interactions between threads are effectively modeled. Structured description of parallelism and relaxed memory consistency in OpenMP make the analyses effective and efficient. We developed algorithms for reaching definitions analysis, memory synchronization analysis, and cross‐loop data dependence analysis for parallel loops. Our primary target is compiler‐directed software distributed shared memory systems in which aggressive compiler optimizations for software‐implemented coherence schemes are crucial to obtaining good performance. We also developed optimizations applicable to general OpenMP implementations, namely redundant barrier removal and privatization of dynamically allocated objects. Experimental results for the coherency optimization show that aggressive compiler optimizations are quite effective for a shared‐write intensive program because the coherence‐induced communication volume in such a program is much larger than that in shared‐read intensive programs.</description><issn>1058-9244</issn><issn>1875-919X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2001</creationdate><recordtype>article</recordtype><recordid>eNotj0FLAzEUhINYsLae_AN7l9i8bLKbd5RFrVBpDxW8hbhJNNLdrEk96K93l3qagRmG-Qi5BnYLIOWKMwYrUMikOCNzULWkCPh6PnomFUUuxAW5zPlz7ClgbE5EE7shHFwqtsMxdOHXHEPsi71rP_rw9e1y4eOUuf55V-xSfE-my0sy8-aQ3dW_LsjLw_2-WdPN9vGpudvQFlQpqGmNequRIQfLpRXWVGgqAF4iMg8ISkqHquZ2LPrxIK9t5aQ0XhmLypcLcnPabVPMOTmvhxQ6k340MD0B6wlYn4DLP-qqRwM</recordid><startdate>200101</startdate><enddate>200101</enddate><creator>Satoh, Shigehisa</creator><creator>Kusano, Kazuhiro</creator><creator>Sato, Mitsuhisa</creator><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>200101</creationdate><title>Compiler Optimization Techniques for OpenMP Programs</title><author>Satoh, Shigehisa ; Kusano, Kazuhiro ; Sato, Mitsuhisa</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1834-aca8b790921d25d4da69a61123990f191855e9872dca8f05827d6e55af8ad98f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2001</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Satoh, Shigehisa</creatorcontrib><creatorcontrib>Kusano, Kazuhiro</creatorcontrib><creatorcontrib>Sato, Mitsuhisa</creatorcontrib><collection>CrossRef</collection><jtitle>Scientific programming</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Satoh, Shigehisa</au><au>Kusano, Kazuhiro</au><au>Sato, Mitsuhisa</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Compiler Optimization Techniques for OpenMP Programs</atitle><jtitle>Scientific programming</jtitle><date>2001-01</date><risdate>2001</risdate><volume>9</volume><issue>2-3</issue><spage>131</spage><epage>142</epage><pages>131-142</pages><issn>1058-9244</issn><eissn>1875-919X</eissn><abstract>We have developed compiler optimization techniques for explicit parallel programs using the OpenMP API. To enable optimization across threads, we designed dataflow analysis techniques in which interactions between threads are effectively modeled. Structured description of parallelism and relaxed memory consistency in OpenMP make the analyses effective and efficient. We developed algorithms for reaching definitions analysis, memory synchronization analysis, and cross‐loop data dependence analysis for parallel loops. Our primary target is compiler‐directed software distributed shared memory systems in which aggressive compiler optimizations for software‐implemented coherence schemes are crucial to obtaining good performance. We also developed optimizations applicable to general OpenMP implementations, namely redundant barrier removal and privatization of dynamically allocated objects. Experimental results for the coherency optimization show that aggressive compiler optimizations are quite effective for a shared‐write intensive program because the coherence‐induced communication volume in such a program is much larger than that in shared‐read intensive programs.</abstract><doi>10.1155/2001/189054</doi><tpages>12</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1058-9244
ispartof Scientific programming, 2001-01, Vol.9 (2-3), p.131-142
issn 1058-9244
1875-919X
language eng
recordid cdi_crossref_primary_10_1155_2001_189054
source Wiley-Blackwell Titles (Open access)
title Compiler Optimization Techniques for OpenMP Programs
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T08%3A26%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Compiler%20Optimization%20Techniques%20for%20OpenMP%20Programs&rft.jtitle=Scientific%20programming&rft.au=Satoh,%20Shigehisa&rft.date=2001-01&rft.volume=9&rft.issue=2-3&rft.spage=131&rft.epage=142&rft.pages=131-142&rft.issn=1058-9244&rft.eissn=1875-919X&rft_id=info:doi/10.1155/2001/189054&rft_dat=%3Ccrossref%3E10_1155_2001_189054%3C/crossref%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c1834-aca8b790921d25d4da69a61123990f191855e9872dca8f05827d6e55af8ad98f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true