Control flow optimization for supercomputer scalar processing

Pohua P. Chang, Wen-Mei W Hwu

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

Abstract

Control intensive scalar programs pose a very different challenge to highly pipelined supercomputers than vectorizable numeric applications. Function call/return and branch instructions disrupt the flow of instructions through the pipeline, degrading the utilization of the pipelined datapaths. This paper describes control flow optimization for scalar processing using an optimizing compiler. To obtain program control flow information, a system independent profiler has been integrated into the IMPACT-IC compiler. The control flow information obtained is converted into a weighted control graph. Based on the weighted control graph, function inline expansion, multi-way branch layout, and software branch prediction can be implemented. Using better compiler technology results in a very low cost hardware control unit (architecture) for high performance scalar processors.

Original languageEnglish (US)
Title of host publicationProceedings of the 3rd International Conference on Supercomputing, ICS 1989
PublisherAssociation for Computing Machinery
Pages145-153
Number of pages9
ISBN (Electronic)0897913094
DOIs
StatePublished - Jun 1 1989
Event3rd International Conference on Supercomputing, ICS 1989 - Crete, Greece
Duration: Jun 5 1989Jun 9 1989

Publication series

NameProceedings of the International Conference on Supercomputing
VolumePart F130180

Other

Other3rd International Conference on Supercomputing, ICS 1989
CountryGreece
CityCrete
Period6/5/896/9/89

Fingerprint

Supercomputers
Flow control
Processing
Pipelines
Hardware
Costs

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Chang, P. P., & Hwu, W-M. W. (1989). Control flow optimization for supercomputer scalar processing. In Proceedings of the 3rd International Conference on Supercomputing, ICS 1989 (pp. 145-153). (Proceedings of the International Conference on Supercomputing; Vol. Part F130180). Association for Computing Machinery. https://doi.org/10.1145/318789.318806

Control flow optimization for supercomputer scalar processing. / Chang, Pohua P.; Hwu, Wen-Mei W.

Proceedings of the 3rd International Conference on Supercomputing, ICS 1989. Association for Computing Machinery, 1989. p. 145-153 (Proceedings of the International Conference on Supercomputing; Vol. Part F130180).

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

Chang, PP & Hwu, W-MW 1989, Control flow optimization for supercomputer scalar processing. in Proceedings of the 3rd International Conference on Supercomputing, ICS 1989. Proceedings of the International Conference on Supercomputing, vol. Part F130180, Association for Computing Machinery, pp. 145-153, 3rd International Conference on Supercomputing, ICS 1989, Crete, Greece, 6/5/89. https://doi.org/10.1145/318789.318806
Chang PP, Hwu W-MW. Control flow optimization for supercomputer scalar processing. In Proceedings of the 3rd International Conference on Supercomputing, ICS 1989. Association for Computing Machinery. 1989. p. 145-153. (Proceedings of the International Conference on Supercomputing). https://doi.org/10.1145/318789.318806
Chang, Pohua P. ; Hwu, Wen-Mei W. / Control flow optimization for supercomputer scalar processing. Proceedings of the 3rd International Conference on Supercomputing, ICS 1989. Association for Computing Machinery, 1989. pp. 145-153 (Proceedings of the International Conference on Supercomputing).
@inproceedings{ce901718becc47ceba7fb1cbe4c9be3a,
title = "Control flow optimization for supercomputer scalar processing",
abstract = "Control intensive scalar programs pose a very different challenge to highly pipelined supercomputers than vectorizable numeric applications. Function call/return and branch instructions disrupt the flow of instructions through the pipeline, degrading the utilization of the pipelined datapaths. This paper describes control flow optimization for scalar processing using an optimizing compiler. To obtain program control flow information, a system independent profiler has been integrated into the IMPACT-IC compiler. The control flow information obtained is converted into a weighted control graph. Based on the weighted control graph, function inline expansion, multi-way branch layout, and software branch prediction can be implemented. Using better compiler technology results in a very low cost hardware control unit (architecture) for high performance scalar processors.",
author = "Chang, {Pohua P.} and Hwu, {Wen-Mei W}",
year = "1989",
month = "6",
day = "1",
doi = "10.1145/318789.318806",
language = "English (US)",
series = "Proceedings of the International Conference on Supercomputing",
publisher = "Association for Computing Machinery",
pages = "145--153",
booktitle = "Proceedings of the 3rd International Conference on Supercomputing, ICS 1989",

}

TY - GEN

T1 - Control flow optimization for supercomputer scalar processing

AU - Chang, Pohua P.

AU - Hwu, Wen-Mei W

PY - 1989/6/1

Y1 - 1989/6/1

N2 - Control intensive scalar programs pose a very different challenge to highly pipelined supercomputers than vectorizable numeric applications. Function call/return and branch instructions disrupt the flow of instructions through the pipeline, degrading the utilization of the pipelined datapaths. This paper describes control flow optimization for scalar processing using an optimizing compiler. To obtain program control flow information, a system independent profiler has been integrated into the IMPACT-IC compiler. The control flow information obtained is converted into a weighted control graph. Based on the weighted control graph, function inline expansion, multi-way branch layout, and software branch prediction can be implemented. Using better compiler technology results in a very low cost hardware control unit (architecture) for high performance scalar processors.

AB - Control intensive scalar programs pose a very different challenge to highly pipelined supercomputers than vectorizable numeric applications. Function call/return and branch instructions disrupt the flow of instructions through the pipeline, degrading the utilization of the pipelined datapaths. This paper describes control flow optimization for scalar processing using an optimizing compiler. To obtain program control flow information, a system independent profiler has been integrated into the IMPACT-IC compiler. The control flow information obtained is converted into a weighted control graph. Based on the weighted control graph, function inline expansion, multi-way branch layout, and software branch prediction can be implemented. Using better compiler technology results in a very low cost hardware control unit (architecture) for high performance scalar processors.

UR - http://www.scopus.com/inward/record.url?scp=12744274257&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=12744274257&partnerID=8YFLogxK

U2 - 10.1145/318789.318806

DO - 10.1145/318789.318806

M3 - Conference contribution

AN - SCOPUS:12744274257

T3 - Proceedings of the International Conference on Supercomputing

SP - 145

EP - 153

BT - Proceedings of the 3rd International Conference on Supercomputing, ICS 1989

PB - Association for Computing Machinery

ER -