Towards refresh-optimized EDRAM-based caches with a selective fine-grain round-robin refresh scheme

Joonho Kong, Young Ho Gong, Sung Woo Jung

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Recently, EDRAM cells have gained much attention as a promising alternative to construct on-chip memories. However, due to inherent characteristics of DRAM cells, they need to be refreshed periodically, causing a huge refresh energy burden. Particularly, employing EDRAM cells in large-scale last-level caches will make refresh burden much higher due to their large capacity. In this paper, we propose a selective fine-grain round-robin refresh scheme for both performance improvement and refresh energy reduction. To reduce bank conflicts between normal cache accesses and refresh operations, we employ a refresh scheme which refreshes cache lines in a bank-wise round-robin fashion. We also apply a selective refresh depending on the inclusive information in cache hierarchies. For the data which reside in both LLC and upper-level cache (i.e., L2 cache), the data access will be filtered by the upper-level cache. Based on this insight, we skip the refresh to the cache block in the EDRAM-based LLC which also exists in the upper-level caches. By doing so, we can reduce unnecessary refresh operations in EDRAM-based LLCs. According to our evaluation, our proposed scheme improves performance by 7.3% and reduces energy per instruction by 13.3% compared to the baseline all-bank refresh scheme.

Original languageEnglish
JournalMicroprocessors and Microsystems
DOIs
Publication statusAccepted/In press - 2016 May 15

Fingerprint

Dynamic random access storage
Data storage equipment

Keywords

  • Embedded dynamic random access Memory
  • Energy-efficiency
  • Last-level cache
  • Performance
  • Refresh

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Towards refresh-optimized EDRAM-based caches with a selective fine-grain round-robin refresh scheme. / Kong, Joonho; Gong, Young Ho; Jung, Sung Woo.

In: Microprocessors and Microsystems, 15.05.2016.

Research output: Contribution to journalArticle

@article{636a520547da4d36bfc2a419cace16c5,
title = "Towards refresh-optimized EDRAM-based caches with a selective fine-grain round-robin refresh scheme",
abstract = "Recently, EDRAM cells have gained much attention as a promising alternative to construct on-chip memories. However, due to inherent characteristics of DRAM cells, they need to be refreshed periodically, causing a huge refresh energy burden. Particularly, employing EDRAM cells in large-scale last-level caches will make refresh burden much higher due to their large capacity. In this paper, we propose a selective fine-grain round-robin refresh scheme for both performance improvement and refresh energy reduction. To reduce bank conflicts between normal cache accesses and refresh operations, we employ a refresh scheme which refreshes cache lines in a bank-wise round-robin fashion. We also apply a selective refresh depending on the inclusive information in cache hierarchies. For the data which reside in both LLC and upper-level cache (i.e., L2 cache), the data access will be filtered by the upper-level cache. Based on this insight, we skip the refresh to the cache block in the EDRAM-based LLC which also exists in the upper-level caches. By doing so, we can reduce unnecessary refresh operations in EDRAM-based LLCs. According to our evaluation, our proposed scheme improves performance by 7.3{\%} and reduces energy per instruction by 13.3{\%} compared to the baseline all-bank refresh scheme.",
keywords = "Embedded dynamic random access Memory, Energy-efficiency, Last-level cache, Performance, Refresh",
author = "Joonho Kong and Gong, {Young Ho} and Jung, {Sung Woo}",
year = "2016",
month = "5",
day = "15",
doi = "10.1016/j.micpro.2016.11.007",
language = "English",
journal = "Microprocessors and Microsystems",
issn = "0141-9331",
publisher = "Elsevier",

}

TY - JOUR

T1 - Towards refresh-optimized EDRAM-based caches with a selective fine-grain round-robin refresh scheme

AU - Kong, Joonho

AU - Gong, Young Ho

AU - Jung, Sung Woo

PY - 2016/5/15

Y1 - 2016/5/15

N2 - Recently, EDRAM cells have gained much attention as a promising alternative to construct on-chip memories. However, due to inherent characteristics of DRAM cells, they need to be refreshed periodically, causing a huge refresh energy burden. Particularly, employing EDRAM cells in large-scale last-level caches will make refresh burden much higher due to their large capacity. In this paper, we propose a selective fine-grain round-robin refresh scheme for both performance improvement and refresh energy reduction. To reduce bank conflicts between normal cache accesses and refresh operations, we employ a refresh scheme which refreshes cache lines in a bank-wise round-robin fashion. We also apply a selective refresh depending on the inclusive information in cache hierarchies. For the data which reside in both LLC and upper-level cache (i.e., L2 cache), the data access will be filtered by the upper-level cache. Based on this insight, we skip the refresh to the cache block in the EDRAM-based LLC which also exists in the upper-level caches. By doing so, we can reduce unnecessary refresh operations in EDRAM-based LLCs. According to our evaluation, our proposed scheme improves performance by 7.3% and reduces energy per instruction by 13.3% compared to the baseline all-bank refresh scheme.

AB - Recently, EDRAM cells have gained much attention as a promising alternative to construct on-chip memories. However, due to inherent characteristics of DRAM cells, they need to be refreshed periodically, causing a huge refresh energy burden. Particularly, employing EDRAM cells in large-scale last-level caches will make refresh burden much higher due to their large capacity. In this paper, we propose a selective fine-grain round-robin refresh scheme for both performance improvement and refresh energy reduction. To reduce bank conflicts between normal cache accesses and refresh operations, we employ a refresh scheme which refreshes cache lines in a bank-wise round-robin fashion. We also apply a selective refresh depending on the inclusive information in cache hierarchies. For the data which reside in both LLC and upper-level cache (i.e., L2 cache), the data access will be filtered by the upper-level cache. Based on this insight, we skip the refresh to the cache block in the EDRAM-based LLC which also exists in the upper-level caches. By doing so, we can reduce unnecessary refresh operations in EDRAM-based LLCs. According to our evaluation, our proposed scheme improves performance by 7.3% and reduces energy per instruction by 13.3% compared to the baseline all-bank refresh scheme.

KW - Embedded dynamic random access Memory

KW - Energy-efficiency

KW - Last-level cache

KW - Performance

KW - Refresh

UR - http://www.scopus.com/inward/record.url?scp=85006837042&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006837042&partnerID=8YFLogxK

U2 - 10.1016/j.micpro.2016.11.007

DO - 10.1016/j.micpro.2016.11.007

M3 - Article

AN - SCOPUS:85006837042

JO - Microprocessors and Microsystems

JF - Microprocessors and Microsystems

SN - 0141-9331

ER -