OCMAS: Online Page Clustering for Multibank Scratchpad Memory

Da-Wei Chang, Ing-Chao Lin, Yi Chiao Lin, Wen Zhi Huang

研究成果: Article

摘要

Scratchpad memory (SPM), a software-controlled on-chip memory, is being increasingly used in embedded systems to reduce on-chip memory energy consumption. To further reduce energy consumption, multibank SPM architecture is proposed. In multibank SPM, each bank can be accessed independently, and unused banks can enter the low power mode, thus reducing leakage energy. However, if both frequently and infrequently used data exist in the same bank, the bank will not be able to enter the low power mode, resulting in less energy reduction. To address this issue, we propose online page clustering for multibank SPM (OCMAS) to reduce the leakage energy in multibank SPM. OCMAS groups SPM pages with similar access frequencies into the same bank, allowing banks containing infrequently used data to stay in low power mode longer. We also propose a method to dynamically adjust the thresholds for determining cold pages (pages that contain infrequently used data), so banks that contain cold pages can enter the low power mode with a shorter idle timeout. Compared to conventional timeout-based, periodic drowsy, and bank-based methods, OCMAS can reduce the energy delay product by up to 37.67% (18.14% on average), 39.53% (22.38% on average), and 132.32% (23.34% on average) in 32 KB 4-bank SPM, by up to 25.33% (15.71% on average), 29.87% (15.92% on average), and 72.25% (22.64% on average) in 32 KB 8-bank SPM, by up to 28.99% (13.45% on average), 30.71% (14.74% on average), and 96.67% (19.94% on average) in 16 KB 4-bank SPM, and by up to 30.18% (10.05% on average), 32.13% (11.62% on average), and 65.56% (16.2% on average) in 16 KB 8-bank SPM. The area overhead is approximately 0.72%, which is insignificant.

原文English
文章編號8299556
頁(從 - 到)220-233
頁數14
期刊IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
38
發行號2
DOIs
出版狀態Published - 2018 一月 1

指紋

Data storage equipment
Energy utilization
Memory architecture
Embedded systems

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering

引用此文

@article{d1c00e73559340e58ae11accad232e01,
title = "OCMAS: Online Page Clustering for Multibank Scratchpad Memory",
abstract = "Scratchpad memory (SPM), a software-controlled on-chip memory, is being increasingly used in embedded systems to reduce on-chip memory energy consumption. To further reduce energy consumption, multibank SPM architecture is proposed. In multibank SPM, each bank can be accessed independently, and unused banks can enter the low power mode, thus reducing leakage energy. However, if both frequently and infrequently used data exist in the same bank, the bank will not be able to enter the low power mode, resulting in less energy reduction. To address this issue, we propose online page clustering for multibank SPM (OCMAS) to reduce the leakage energy in multibank SPM. OCMAS groups SPM pages with similar access frequencies into the same bank, allowing banks containing infrequently used data to stay in low power mode longer. We also propose a method to dynamically adjust the thresholds for determining cold pages (pages that contain infrequently used data), so banks that contain cold pages can enter the low power mode with a shorter idle timeout. Compared to conventional timeout-based, periodic drowsy, and bank-based methods, OCMAS can reduce the energy delay product by up to 37.67{\%} (18.14{\%} on average), 39.53{\%} (22.38{\%} on average), and 132.32{\%} (23.34{\%} on average) in 32 KB 4-bank SPM, by up to 25.33{\%} (15.71{\%} on average), 29.87{\%} (15.92{\%} on average), and 72.25{\%} (22.64{\%} on average) in 32 KB 8-bank SPM, by up to 28.99{\%} (13.45{\%} on average), 30.71{\%} (14.74{\%} on average), and 96.67{\%} (19.94{\%} on average) in 16 KB 4-bank SPM, and by up to 30.18{\%} (10.05{\%} on average), 32.13{\%} (11.62{\%} on average), and 65.56{\%} (16.2{\%} on average) in 16 KB 8-bank SPM. The area overhead is approximately 0.72{\%}, which is insignificant.",
author = "Da-Wei Chang and Ing-Chao Lin and Lin, {Yi Chiao} and Huang, {Wen Zhi}",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/TCAD.2018.2808228",
language = "English",
volume = "38",
pages = "220--233",
journal = "IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems",
issn = "0278-0070",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

OCMAS : Online Page Clustering for Multibank Scratchpad Memory. / Chang, Da-Wei; Lin, Ing-Chao; Lin, Yi Chiao; Huang, Wen Zhi.

於: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 卷 38, 編號 2, 8299556, 01.01.2018, p. 220-233.

研究成果: Article

TY - JOUR

T1 - OCMAS

T2 - Online Page Clustering for Multibank Scratchpad Memory

AU - Chang, Da-Wei

AU - Lin, Ing-Chao

AU - Lin, Yi Chiao

AU - Huang, Wen Zhi

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Scratchpad memory (SPM), a software-controlled on-chip memory, is being increasingly used in embedded systems to reduce on-chip memory energy consumption. To further reduce energy consumption, multibank SPM architecture is proposed. In multibank SPM, each bank can be accessed independently, and unused banks can enter the low power mode, thus reducing leakage energy. However, if both frequently and infrequently used data exist in the same bank, the bank will not be able to enter the low power mode, resulting in less energy reduction. To address this issue, we propose online page clustering for multibank SPM (OCMAS) to reduce the leakage energy in multibank SPM. OCMAS groups SPM pages with similar access frequencies into the same bank, allowing banks containing infrequently used data to stay in low power mode longer. We also propose a method to dynamically adjust the thresholds for determining cold pages (pages that contain infrequently used data), so banks that contain cold pages can enter the low power mode with a shorter idle timeout. Compared to conventional timeout-based, periodic drowsy, and bank-based methods, OCMAS can reduce the energy delay product by up to 37.67% (18.14% on average), 39.53% (22.38% on average), and 132.32% (23.34% on average) in 32 KB 4-bank SPM, by up to 25.33% (15.71% on average), 29.87% (15.92% on average), and 72.25% (22.64% on average) in 32 KB 8-bank SPM, by up to 28.99% (13.45% on average), 30.71% (14.74% on average), and 96.67% (19.94% on average) in 16 KB 4-bank SPM, and by up to 30.18% (10.05% on average), 32.13% (11.62% on average), and 65.56% (16.2% on average) in 16 KB 8-bank SPM. The area overhead is approximately 0.72%, which is insignificant.

AB - Scratchpad memory (SPM), a software-controlled on-chip memory, is being increasingly used in embedded systems to reduce on-chip memory energy consumption. To further reduce energy consumption, multibank SPM architecture is proposed. In multibank SPM, each bank can be accessed independently, and unused banks can enter the low power mode, thus reducing leakage energy. However, if both frequently and infrequently used data exist in the same bank, the bank will not be able to enter the low power mode, resulting in less energy reduction. To address this issue, we propose online page clustering for multibank SPM (OCMAS) to reduce the leakage energy in multibank SPM. OCMAS groups SPM pages with similar access frequencies into the same bank, allowing banks containing infrequently used data to stay in low power mode longer. We also propose a method to dynamically adjust the thresholds for determining cold pages (pages that contain infrequently used data), so banks that contain cold pages can enter the low power mode with a shorter idle timeout. Compared to conventional timeout-based, periodic drowsy, and bank-based methods, OCMAS can reduce the energy delay product by up to 37.67% (18.14% on average), 39.53% (22.38% on average), and 132.32% (23.34% on average) in 32 KB 4-bank SPM, by up to 25.33% (15.71% on average), 29.87% (15.92% on average), and 72.25% (22.64% on average) in 32 KB 8-bank SPM, by up to 28.99% (13.45% on average), 30.71% (14.74% on average), and 96.67% (19.94% on average) in 16 KB 4-bank SPM, and by up to 30.18% (10.05% on average), 32.13% (11.62% on average), and 65.56% (16.2% on average) in 16 KB 8-bank SPM. The area overhead is approximately 0.72%, which is insignificant.

UR - http://www.scopus.com/inward/record.url?scp=85042359642&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042359642&partnerID=8YFLogxK

U2 - 10.1109/TCAD.2018.2808228

DO - 10.1109/TCAD.2018.2808228

M3 - Article

AN - SCOPUS:85042359642

VL - 38

SP - 220

EP - 233

JO - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

JF - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

SN - 0278-0070

IS - 2

M1 - 8299556

ER -