Improved lookahead instruction prefetching

Gi Ho Park; Oh Young Kwon; Tack Don Hah; Shin Dug Kim; Sung Bong Yang

Improved lookahead instruction prefetching

Gi Ho Park, Oh Young Kwon, Tack Don Hah, Shin Dug Kim, Sung Bong Yang

College of Computing

Research output: Contribution to conference › Paper › peer-review

4 Citations (Scopus)

Abstract

A new lookahead instruction prefetching mechanism is proposed in this paper. Though significant performance improvement can be obtained by improving both the cache miss ratio and average access time for successfully prefetched blocks, most conventional prefetching mechanisms improve only one out of the two factors. To achieve balanced improvement of the two factors, a lookahead prefetching scheme that fetches multiple blocks for a prefetch request and adopts prefetch on miss mechanism is proposed. Performance evaluation is carried out through the trace-driven simulation and the proposed prefetch scheme reduces 32% to approximately 56% of the memory access delay time of the cache system that does not perform any prefetching.

Original language	English
Pages	712-715
Number of pages	4
Publication status	Published - 1997
Event	Proceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97 - Seoul, South Korea Duration: 1997 Apr 28 → 1997 May 2

Other

Other	Proceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97
City	Seoul, South Korea
Period	97/4/28 → 97/5/2

All Science Journal Classification (ASJC) codes

Computer Science(all)

Cite this

@conference{8ffa80cdcf6740458937e664eb8b645b,

title = "Improved lookahead instruction prefetching",

abstract = "A new lookahead instruction prefetching mechanism is proposed in this paper. Though significant performance improvement can be obtained by improving both the cache miss ratio and average access time for successfully prefetched blocks, most conventional prefetching mechanisms improve only one out of the two factors. To achieve balanced improvement of the two factors, a lookahead prefetching scheme that fetches multiple blocks for a prefetch request and adopts prefetch on miss mechanism is proposed. Performance evaluation is carried out through the trace-driven simulation and the proposed prefetch scheme reduces 32% to approximately 56% of the memory access delay time of the cache system that does not perform any prefetching.",

author = "Park, {Gi Ho} and Kwon, {Oh Young} and Hah, {Tack Don} and Kim, {Shin Dug} and Yang, {Sung Bong}",

year = "1997",

language = "English",

pages = "712--715",

note = "Proceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97 ; Conference date: 28-04-1997 Through 02-05-1997",

}

TY - CONF

T1 - Improved lookahead instruction prefetching

AU - Park, Gi Ho

AU - Kwon, Oh Young

AU - Hah, Tack Don

AU - Kim, Shin Dug

AU - Yang, Sung Bong

PY - 1997

Y1 - 1997

N2 - A new lookahead instruction prefetching mechanism is proposed in this paper. Though significant performance improvement can be obtained by improving both the cache miss ratio and average access time for successfully prefetched blocks, most conventional prefetching mechanisms improve only one out of the two factors. To achieve balanced improvement of the two factors, a lookahead prefetching scheme that fetches multiple blocks for a prefetch request and adopts prefetch on miss mechanism is proposed. Performance evaluation is carried out through the trace-driven simulation and the proposed prefetch scheme reduces 32% to approximately 56% of the memory access delay time of the cache system that does not perform any prefetching.

AB - A new lookahead instruction prefetching mechanism is proposed in this paper. Though significant performance improvement can be obtained by improving both the cache miss ratio and average access time for successfully prefetched blocks, most conventional prefetching mechanisms improve only one out of the two factors. To achieve balanced improvement of the two factors, a lookahead prefetching scheme that fetches multiple blocks for a prefetch request and adopts prefetch on miss mechanism is proposed. Performance evaluation is carried out through the trace-driven simulation and the proposed prefetch scheme reduces 32% to approximately 56% of the memory access delay time of the cache system that does not perform any prefetching.

UR - http://www.scopus.com/inward/record.url?scp=0030682883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030682883&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0030682883

SP - 712

EP - 715

T2 - Proceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97

Y2 - 28 April 1997 through 2 May 1997

ER -

Improved lookahead instruction prefetching

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this