Presentation 2002/4/12
Energy Efficiency of History-Based Tag-Comparison Cache for Media Applications
Koji INOUE, Vasily G. MOSHNYAGA, Kazuaki MURAKAMI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have proposed a history-based tag-comparison cache (HBL cache) architecture for low-energy consumption. Jo conventional direct-mapped caches, tag checks are performed to examine whether the current reference hits the cache. On the other hand, the HBTC cache attempts to reduce the frequency of tag checks by exploiting execution footprints. In this paper, we improve the proposed HBTC cache, and evaluate performance/energy efficiency by using media applications. Simulation results show that such an approach can eliminate up to 95% of tag checks, saving the cache energy by 17%, while affecting the processor performance by 0.2%.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) low power / cache / tag comparison / execution history / run-time optimization / reuse
Paper # DC2002-10
Date of Issue

Conference Information
Committee DC
Conference Date 2002/4/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Dependable Computing (DC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Energy Efficiency of History-Based Tag-Comparison Cache for Media Applications
Sub Title (in English)
Keyword(1) low power
Keyword(2) cache
Keyword(3) tag comparison
Keyword(4) execution history
Keyword(5) run-time optimization
Keyword(6) reuse
1st Author's Name Koji INOUE
1st Author's Affiliation Department of Electronics and computer Science, Fukuoka University()
2nd Author's Name Vasily G. MOSHNYAGA
2nd Author's Affiliation Department of Electronics and computer Science, Fukuoka University
3rd Author's Name Kazuaki MURAKAMI
3rd Author's Affiliation Department of Informatics, Kushu University
Date 2002/4/12
Paper # DC2002-10
Volume (vol) vol.102
Number (no) 28
Page pp.pp.-
#Pages 6
Date of Issue