Interprocedural induction variable analysis

Peiyi Tang; Pen Chung Yew

doi:10.1109/ISPAN.2002.1004289

Interprocedural induction variable analysis

Peiyi Tang, Pen Chung Yew

Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

Induction variable analysis is an important part of the symbolic analysis in parallelizing compilers. Induction variables can be formed by FOR or DO loops within procedures or loops of recursive procedure calls. This paper presents an algorithm to find induction variables in formal parameters of procedures caused by recursive procedure calls. The compile-time knowledge of induction variables in formal parameters is essential to summarize array sections to be used for data dependency testing and parallelization.

Original language	English (US)
Title of host publication	Proceedings - International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002
Editors	D. Frank Hsu, Rafael P. Saldana, Oscar H. Ibarra
Publisher	IEEE Computer Society
Pages	245-250
Number of pages	6
ISBN (Electronic)	0769515797
DOIs	https://doi.org/10.1109/ISPAN.2002.1004289
State	Published - 2002
Event	International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002 - Makati, Manila, Philippines Duration: May 22 2002 → May 24 2002

Publication series

Name	Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN
Volume	2002-January

Other

Other	International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002
Country/Territory	Philippines
City	Makati, Manila
Period	5/22/02 → 5/24/02

Bibliographical note

Publisher Copyright:
© 2002 IEEE.

Keywords

Algorithm design and analysis
Computer science
Parallel architectures
Program processors
Testing

Access

10.1109/ISPAN.2002.1004289

OpenUrl availability

Full text

Cite this

Tang, P., & Yew, P. C. (2002). Interprocedural induction variable analysis. In D. F. Hsu, R. P. Saldana, & O. H. Ibarra (Eds.), Proceedings - International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002 (pp. 245-250). Article 1004289 (Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN; Vol. 2002-January). IEEE Computer Society. https://doi.org/10.1109/ISPAN.2002.1004289

Interprocedural induction variable analysis. / Tang, Peiyi; Yew, Pen Chung.
Proceedings - International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002. ed. / D. Frank Hsu; Rafael P. Saldana; Oscar H. Ibarra. IEEE Computer Society, 2002. p. 245-250 1004289 (Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN; Vol. 2002-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Tang, P & Yew, PC 2002, Interprocedural induction variable analysis. in DF Hsu, RP Saldana & OH Ibarra (eds), Proceedings - International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002., 1004289, Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN, vol. 2002-January, IEEE Computer Society, pp. 245-250, International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002, Makati, Manila, Philippines, 5/22/02. https://doi.org/10.1109/ISPAN.2002.1004289

Tang P, Yew PC. Interprocedural induction variable analysis. In Hsu DF, Saldana RP, Ibarra OH, editors, Proceedings - International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002. IEEE Computer Society. 2002. p. 245-250. 1004289. (Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN). doi: 10.1109/ISPAN.2002.1004289

Tang, Peiyi ; Yew, Pen Chung. / Interprocedural induction variable analysis. Proceedings - International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002. editor / D. Frank Hsu ; Rafael P. Saldana ; Oscar H. Ibarra. IEEE Computer Society, 2002. pp. 245-250 (Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN).

@inproceedings{e439b3c64455432a8e497cad26233866,

title = "Interprocedural induction variable analysis",

abstract = "Induction variable analysis is an important part of the symbolic analysis in parallelizing compilers. Induction variables can be formed by FOR or DO loops within procedures or loops of recursive procedure calls. This paper presents an algorithm to find induction variables in formal parameters of procedures caused by recursive procedure calls. The compile-time knowledge of induction variables in formal parameters is essential to summarize array sections to be used for data dependency testing and parallelization.",

keywords = "Algorithm design and analysis, Computer science, Parallel architectures, Program processors, Testing",

author = "Peiyi Tang and Yew, {Pen Chung}",

note = "Publisher Copyright: {\textcopyright} 2002 IEEE.; International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002 ; Conference date: 22-05-2002 Through 24-05-2002",

year = "2002",

doi = "10.1109/ISPAN.2002.1004289",

language = "English (US)",

series = "Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN",

publisher = "IEEE Computer Society",

pages = "245--250",

editor = "Hsu, {D. Frank} and Saldana, {Rafael P.} and Ibarra, {Oscar H.}",

booktitle = "Proceedings - International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002",

}

TY - GEN

T1 - Interprocedural induction variable analysis

AU - Tang, Peiyi

AU - Yew, Pen Chung

PY - 2002

Y1 - 2002

N2 - Induction variable analysis is an important part of the symbolic analysis in parallelizing compilers. Induction variables can be formed by FOR or DO loops within procedures or loops of recursive procedure calls. This paper presents an algorithm to find induction variables in formal parameters of procedures caused by recursive procedure calls. The compile-time knowledge of induction variables in formal parameters is essential to summarize array sections to be used for data dependency testing and parallelization.

AB - Induction variable analysis is an important part of the symbolic analysis in parallelizing compilers. Induction variables can be formed by FOR or DO loops within procedures or loops of recursive procedure calls. This paper presents an algorithm to find induction variables in formal parameters of procedures caused by recursive procedure calls. The compile-time knowledge of induction variables in formal parameters is essential to summarize array sections to be used for data dependency testing and parallelization.

KW - Algorithm design and analysis

KW - Computer science

KW - Parallel architectures

KW - Program processors

KW - Testing

UR - http://www.scopus.com/inward/record.url?scp=77954734579&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954734579&partnerID=8YFLogxK

U2 - 10.1109/ISPAN.2002.1004289

DO - 10.1109/ISPAN.2002.1004289

M3 - Conference contribution

AN - SCOPUS:77954734579

T3 - Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN

SP - 245

EP - 250

BT - Proceedings - International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002

A2 - Hsu, D. Frank

A2 - Saldana, Rafael P.

A2 - Ibarra, Oscar H.

PB - IEEE Computer Society

T2 - International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN 2002

Y2 - 22 May 2002 through 24 May 2002

ER -

Interprocedural induction variable analysis

Abstract

Publication series

Other

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this