Exploiting Refresh Effect of DRAM Read Operations: A Practical Approach to Low-Power Refresh

Young Ho Gong, Sung Woo Jung

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Dynamic random access memory (DRAM) requires periodic refresh operations to retain its data. In practice, DRAM retention times are normally distributed from 64 ms to several seconds. However, the conventional refresh method uses 64 ms as the refresh interval, since it applies the same refresh interval to all DRAM rows. Thus, the conventional refresh method results in unnecessary refresh operations (eventually, energy waste) to the DRAM rows whose retention times are longer than 64 ms. In this paper, we propose a practical refresh scheme that exploits refresh effect of DRAM read operations to reduce refresh overhead. Our proposed scheme applies a refresh interval longer than the conventional refresh interval (64 ms) to the DRAM chip. In this case, weak DRAM rows (DRAM rows whose retention times are shorter than the refresh interval of the DRAM chip) cannot retain their data. In order to retain the data stored in the weak DRAM rows, the memory controller issues read operations to the weak DRAM rows every required refresh interval for the weak DRAM rows. Our evaluation results show that our proposed scheme with 192 ms refresh interval reduces average refresh energy consumption up to 66.0 percent, which in turn reduces average DRAM energy consumption up to 31.8 percent, compared to the conventional refresh method (64 ms). Our proposed scheme requires no modification to internal DRAM chip structures, but it only adds a small weak row buffer (the buffer for the weak row information) to the memory controller, which has a negligible area overhead.

Original languageEnglish
Article number7130609
Pages (from-to)1507-1517
Number of pages11
JournalIEEE Transactions on Computers
Volume65
Issue number5
DOIs
Publication statusPublished - 2016 May 1

Fingerprint

Random Access
Data storage equipment
Interval
Chip
Percent
Energy Consumption
Buffer
Energy utilization
Controller
Controllers

Keywords

  • DRAM Refresh
  • Low-power Scheme
  • Main Memory
  • Refresh Interval

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software
  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Exploiting Refresh Effect of DRAM Read Operations : A Practical Approach to Low-Power Refresh. / Gong, Young Ho; Jung, Sung Woo.

In: IEEE Transactions on Computers, Vol. 65, No. 5, 7130609, 01.05.2016, p. 1507-1517.

Research output: Contribution to journalArticle

@article{7304c1687fa0414d8bd499f2e1c2e604,
title = "Exploiting Refresh Effect of DRAM Read Operations: A Practical Approach to Low-Power Refresh",
abstract = "Dynamic random access memory (DRAM) requires periodic refresh operations to retain its data. In practice, DRAM retention times are normally distributed from 64 ms to several seconds. However, the conventional refresh method uses 64 ms as the refresh interval, since it applies the same refresh interval to all DRAM rows. Thus, the conventional refresh method results in unnecessary refresh operations (eventually, energy waste) to the DRAM rows whose retention times are longer than 64 ms. In this paper, we propose a practical refresh scheme that exploits refresh effect of DRAM read operations to reduce refresh overhead. Our proposed scheme applies a refresh interval longer than the conventional refresh interval (64 ms) to the DRAM chip. In this case, weak DRAM rows (DRAM rows whose retention times are shorter than the refresh interval of the DRAM chip) cannot retain their data. In order to retain the data stored in the weak DRAM rows, the memory controller issues read operations to the weak DRAM rows every required refresh interval for the weak DRAM rows. Our evaluation results show that our proposed scheme with 192 ms refresh interval reduces average refresh energy consumption up to 66.0 percent, which in turn reduces average DRAM energy consumption up to 31.8 percent, compared to the conventional refresh method (64 ms). Our proposed scheme requires no modification to internal DRAM chip structures, but it only adds a small weak row buffer (the buffer for the weak row information) to the memory controller, which has a negligible area overhead.",
keywords = "DRAM Refresh, Low-power Scheme, Main Memory, Refresh Interval",
author = "Gong, {Young Ho} and Jung, {Sung Woo}",
year = "2016",
month = "5",
day = "1",
doi = "10.1109/TC.2015.2448079",
language = "English",
volume = "65",
pages = "1507--1517",
journal = "IEEE Transactions on Computers",
issn = "0018-9340",
publisher = "IEEE Computer Society",
number = "5",

}

TY - JOUR

T1 - Exploiting Refresh Effect of DRAM Read Operations

T2 - A Practical Approach to Low-Power Refresh

AU - Gong, Young Ho

AU - Jung, Sung Woo

PY - 2016/5/1

Y1 - 2016/5/1

N2 - Dynamic random access memory (DRAM) requires periodic refresh operations to retain its data. In practice, DRAM retention times are normally distributed from 64 ms to several seconds. However, the conventional refresh method uses 64 ms as the refresh interval, since it applies the same refresh interval to all DRAM rows. Thus, the conventional refresh method results in unnecessary refresh operations (eventually, energy waste) to the DRAM rows whose retention times are longer than 64 ms. In this paper, we propose a practical refresh scheme that exploits refresh effect of DRAM read operations to reduce refresh overhead. Our proposed scheme applies a refresh interval longer than the conventional refresh interval (64 ms) to the DRAM chip. In this case, weak DRAM rows (DRAM rows whose retention times are shorter than the refresh interval of the DRAM chip) cannot retain their data. In order to retain the data stored in the weak DRAM rows, the memory controller issues read operations to the weak DRAM rows every required refresh interval for the weak DRAM rows. Our evaluation results show that our proposed scheme with 192 ms refresh interval reduces average refresh energy consumption up to 66.0 percent, which in turn reduces average DRAM energy consumption up to 31.8 percent, compared to the conventional refresh method (64 ms). Our proposed scheme requires no modification to internal DRAM chip structures, but it only adds a small weak row buffer (the buffer for the weak row information) to the memory controller, which has a negligible area overhead.

AB - Dynamic random access memory (DRAM) requires periodic refresh operations to retain its data. In practice, DRAM retention times are normally distributed from 64 ms to several seconds. However, the conventional refresh method uses 64 ms as the refresh interval, since it applies the same refresh interval to all DRAM rows. Thus, the conventional refresh method results in unnecessary refresh operations (eventually, energy waste) to the DRAM rows whose retention times are longer than 64 ms. In this paper, we propose a practical refresh scheme that exploits refresh effect of DRAM read operations to reduce refresh overhead. Our proposed scheme applies a refresh interval longer than the conventional refresh interval (64 ms) to the DRAM chip. In this case, weak DRAM rows (DRAM rows whose retention times are shorter than the refresh interval of the DRAM chip) cannot retain their data. In order to retain the data stored in the weak DRAM rows, the memory controller issues read operations to the weak DRAM rows every required refresh interval for the weak DRAM rows. Our evaluation results show that our proposed scheme with 192 ms refresh interval reduces average refresh energy consumption up to 66.0 percent, which in turn reduces average DRAM energy consumption up to 31.8 percent, compared to the conventional refresh method (64 ms). Our proposed scheme requires no modification to internal DRAM chip structures, but it only adds a small weak row buffer (the buffer for the weak row information) to the memory controller, which has a negligible area overhead.

KW - DRAM Refresh

KW - Low-power Scheme

KW - Main Memory

KW - Refresh Interval

UR - http://www.scopus.com/inward/record.url?scp=84963938373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963938373&partnerID=8YFLogxK

U2 - 10.1109/TC.2015.2448079

DO - 10.1109/TC.2015.2448079

M3 - Article

AN - SCOPUS:84963938373

VL - 65

SP - 1507

EP - 1517

JO - IEEE Transactions on Computers

JF - IEEE Transactions on Computers

SN - 0018-9340

IS - 5

M1 - 7130609

ER -