Data access microarchitectures for superscalar processors with compiler-assisted data prefetching

William Y. Chen; Scott A. Mahlke; Pohua P. Chang; Wen Mei W. Hwu

doi:10.1145/123465.123478

Data access microarchitectures for superscalar processors with compiler-assisted data prefetching

William Y. Chen, Scott A. Mahlke, Pohua P. Chang, Wen Mei W. Hwu

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

Abstract

The performance of superscrdar processors is more sensitive to the memory system delay than their single-issue predecessors. This paper examines alternative data access microarchitectures that effectively support compilerassisted data prefetching in superscalar processors. In particular, a prefetch buffer is shown to be more effective than increasing the cache dimension in solving the cache pollution problem. All in all, we show that a small data cache with compiler-assisted data prefetching can achieve a performance level close to that of an ideal cache.

Original language	English (US)
Title of host publication	MICRO 1991 - Proceedings of the 24th Annual International Symposium on Microarchitecture
Publisher	IEEE Computer Society
Pages	69-73
Number of pages	5
ISBN (Print)	0897914600, 9780897914604
DOIs	https://doi.org/10.1145/123465.123478
State	Published - Sep 1 1991
Event	24th Annual International Symposium on Microarchitecture, MICRO 1991 - Albuquerque, United States Duration: Nov 18 1991 → Nov 20 1991

Publication series

Name	Proceedings of the Annual International Symposium on Microarchitecture, MICRO
ISSN (Print)	1072-4451

Other

Other	24th Annual International Symposium on Microarchitecture, MICRO 1991
Country	United States
City	Albuquerque
Period	11/18/91 → 11/20/91

Fingerprint

ASJC Scopus subject areas

Hardware and Architecture

Cite this

Chen, W. Y., Mahlke, S. A., Chang, P. P., & Hwu, W. M. W. (1991). Data access microarchitectures for superscalar processors with compiler-assisted data prefetching. In MICRO 1991 - Proceedings of the 24th Annual International Symposium on Microarchitecture (pp. 69-73). (Proceedings of the Annual International Symposium on Microarchitecture, MICRO). IEEE Computer Society. https://doi.org/10.1145/123465.123478

Chen, WY, Mahlke, SA, Chang, PP & Hwu, WMW 1991, Data access microarchitectures for superscalar processors with compiler-assisted data prefetching. in MICRO 1991 - Proceedings of the 24th Annual International Symposium on Microarchitecture. Proceedings of the Annual International Symposium on Microarchitecture, MICRO, IEEE Computer Society, pp. 69-73, 24th Annual International Symposium on Microarchitecture, MICRO 1991, Albuquerque, United States, 11/18/91. https://doi.org/10.1145/123465.123478

Chen WY, Mahlke SA, Chang PP, Hwu WMW. Data access microarchitectures for superscalar processors with compiler-assisted data prefetching. In MICRO 1991 - Proceedings of the 24th Annual International Symposium on Microarchitecture. IEEE Computer Society. 1991. p. 69-73. (Proceedings of the Annual International Symposium on Microarchitecture, MICRO). https://doi.org/10.1145/123465.123478

Chen, William Y. ; Mahlke, Scott A. ; Chang, Pohua P. ; Hwu, Wen Mei W. / Data access microarchitectures for superscalar processors with compiler-assisted data prefetching. MICRO 1991 - Proceedings of the 24th Annual International Symposium on Microarchitecture. IEEE Computer Society, 1991. pp. 69-73 (Proceedings of the Annual International Symposium on Microarchitecture, MICRO).

@inproceedings{fced1b6fc6e44c02b8cfd429c6145df8,

title = "Data access microarchitectures for superscalar processors with compiler-assisted data prefetching",

abstract = "The performance of superscrdar processors is more sensitive to the memory system delay than their single-issue predecessors. This paper examines alternative data access microarchitectures that effectively support compilerassisted data prefetching in superscalar processors. In particular, a prefetch buffer is shown to be more effective than increasing the cache dimension in solving the cache pollution problem. All in all, we show that a small data cache with compiler-assisted data prefetching can achieve a performance level close to that of an ideal cache.",

author = "Chen, {William Y.} and Mahlke, {Scott A.} and Chang, {Pohua P.} and Hwu, {Wen Mei W.}",

year = "1991",

month = sep

day = "1",

doi = "10.1145/123465.123478",

language = "English (US)",

isbn = "0897914600",

series = "Proceedings of the Annual International Symposium on Microarchitecture, MICRO",

publisher = "IEEE Computer Society",

pages = "69--73",

booktitle = "MICRO 1991 - Proceedings of the 24th Annual International Symposium on Microarchitecture",

note = "24th Annual International Symposium on Microarchitecture, MICRO 1991 ; Conference date: 18-11-1991 Through 20-11-1991",

}

TY - GEN

T1 - Data access microarchitectures for superscalar processors with compiler-assisted data prefetching

AU - Chen, William Y.

AU - Mahlke, Scott A.

AU - Chang, Pohua P.

AU - Hwu, Wen Mei W.

PY - 1991/9/1

Y1 - 1991/9/1

N2 - The performance of superscrdar processors is more sensitive to the memory system delay than their single-issue predecessors. This paper examines alternative data access microarchitectures that effectively support compilerassisted data prefetching in superscalar processors. In particular, a prefetch buffer is shown to be more effective than increasing the cache dimension in solving the cache pollution problem. All in all, we show that a small data cache with compiler-assisted data prefetching can achieve a performance level close to that of an ideal cache.

AB - The performance of superscrdar processors is more sensitive to the memory system delay than their single-issue predecessors. This paper examines alternative data access microarchitectures that effectively support compilerassisted data prefetching in superscalar processors. In particular, a prefetch buffer is shown to be more effective than increasing the cache dimension in solving the cache pollution problem. All in all, we show that a small data cache with compiler-assisted data prefetching can achieve a performance level close to that of an ideal cache.

UR - http://www.scopus.com/inward/record.url?scp=84944799568&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944799568&partnerID=8YFLogxK

U2 - 10.1145/123465.123478

DO - 10.1145/123465.123478

M3 - Conference contribution

AN - SCOPUS:84944799568

SN - 0897914600

SN - 9780897914604

T3 - Proceedings of the Annual International Symposium on Microarchitecture, MICRO

SP - 69

EP - 73

BT - MICRO 1991 - Proceedings of the 24th Annual International Symposium on Microarchitecture

PB - IEEE Computer Society

T2 - 24th Annual International Symposium on Microarchitecture, MICRO 1991

Y2 - 18 November 1991 through 20 November 1991

ER -

Access to Document

10.1145/123465.123478