Experience with efficient array data flow analysis for array privatization

Junjie Gu, Zhiyuan Li, Kyung Ho Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

22 Citations (Scopus)

Abstract

Array data flow analysis is known to be crucial to the success of array privatization, one of the most important techniques for program parallelization. It is clear that array data flow analysis should be performed interprocedurally and symbolically, and that it often needs to handle the predicates represented by IF conditions. Unfortunately, such a powerful program analysis can be extremely time-consuming if not carefully designed. How to enhance the efficiency of this analysis to a practical level remains an issue largely untouched to date. This paper documents our experience with building a highly efficient array data flow analyzer which is based on guarded array regions and which runs faster, by one or two orders of magnitude, than other similarly powerful tools.

Original languageEnglish
Title of host publicationProceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP
Editors Anon
Place of PublicationNew York, NY, United States
PublisherACM
Pages157-167
Number of pages11
Publication statusPublished - 1997 Jan 1
Externally publishedYes
EventProceedings of the 1997 6th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - Las Vegas, NV, USA
Duration: 1997 Jun 181997 Jun 21

Other

OtherProceedings of the 1997 6th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming
CityLas Vegas, NV, USA
Period97/6/1897/6/21

Fingerprint

Data flow analysis
Privatization

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Gu, J., Li, Z., & Lee, K. H. (1997). Experience with efficient array data flow analysis for array privatization. In Anon (Ed.), Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP (pp. 157-167). New York, NY, United States: ACM.

Experience with efficient array data flow analysis for array privatization. / Gu, Junjie; Li, Zhiyuan; Lee, Kyung Ho.

Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP. ed. / Anon. New York, NY, United States : ACM, 1997. p. 157-167.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gu, J, Li, Z & Lee, KH 1997, Experience with efficient array data flow analysis for array privatization. in Anon (ed.), Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP. ACM, New York, NY, United States, pp. 157-167, Proceedings of the 1997 6th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, Las Vegas, NV, USA, 97/6/18.
Gu J, Li Z, Lee KH. Experience with efficient array data flow analysis for array privatization. In Anon, editor, Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP. New York, NY, United States: ACM. 1997. p. 157-167
Gu, Junjie ; Li, Zhiyuan ; Lee, Kyung Ho. / Experience with efficient array data flow analysis for array privatization. Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP. editor / Anon. New York, NY, United States : ACM, 1997. pp. 157-167
@inproceedings{6aee3f4c279a499da1bcb1c6161a2983,
title = "Experience with efficient array data flow analysis for array privatization",
abstract = "Array data flow analysis is known to be crucial to the success of array privatization, one of the most important techniques for program parallelization. It is clear that array data flow analysis should be performed interprocedurally and symbolically, and that it often needs to handle the predicates represented by IF conditions. Unfortunately, such a powerful program analysis can be extremely time-consuming if not carefully designed. How to enhance the efficiency of this analysis to a practical level remains an issue largely untouched to date. This paper documents our experience with building a highly efficient array data flow analyzer which is based on guarded array regions and which runs faster, by one or two orders of magnitude, than other similarly powerful tools.",
author = "Junjie Gu and Zhiyuan Li and Lee, {Kyung Ho}",
year = "1997",
month = "1",
day = "1",
language = "English",
pages = "157--167",
editor = "Anon",
booktitle = "Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP",
publisher = "ACM",

}

TY - GEN

T1 - Experience with efficient array data flow analysis for array privatization

AU - Gu, Junjie

AU - Li, Zhiyuan

AU - Lee, Kyung Ho

PY - 1997/1/1

Y1 - 1997/1/1

N2 - Array data flow analysis is known to be crucial to the success of array privatization, one of the most important techniques for program parallelization. It is clear that array data flow analysis should be performed interprocedurally and symbolically, and that it often needs to handle the predicates represented by IF conditions. Unfortunately, such a powerful program analysis can be extremely time-consuming if not carefully designed. How to enhance the efficiency of this analysis to a practical level remains an issue largely untouched to date. This paper documents our experience with building a highly efficient array data flow analyzer which is based on guarded array regions and which runs faster, by one or two orders of magnitude, than other similarly powerful tools.

AB - Array data flow analysis is known to be crucial to the success of array privatization, one of the most important techniques for program parallelization. It is clear that array data flow analysis should be performed interprocedurally and symbolically, and that it often needs to handle the predicates represented by IF conditions. Unfortunately, such a powerful program analysis can be extremely time-consuming if not carefully designed. How to enhance the efficiency of this analysis to a practical level remains an issue largely untouched to date. This paper documents our experience with building a highly efficient array data flow analyzer which is based on guarded array regions and which runs faster, by one or two orders of magnitude, than other similarly powerful tools.

UR - http://www.scopus.com/inward/record.url?scp=0030678732&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030678732&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030678732

SP - 157

EP - 167

BT - Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP

A2 - Anon, null

PB - ACM

CY - New York, NY, United States

ER -