A 3D hybrid cache design for CMP architecture for data-intensive applications

Ing-Chao Lin, Jeng Nian Chiou, Yun Kae Law

研究成果: Chapter

摘要

With the advance of CMOS technology, CPU performance has been improved by increasing frequency. However, the performance improvement for a single-core processor has reached a 60bottleneck due to chip power and heat removal limitations. To overcome these problems, chip multiprocessors (CMPs) have gradually replaced single-core processors, and the number of cores in CMPs is expected to continue to grow. A processor integrating 80 cores has been demonstrated by Intel [1]. In CMP architecture, the last level cache (LLC) is shared by multicore processors and has a significant influence on performance. Therefore, as the CMP architecture has become more widely used, LLC-related research has drawn increased attention.

原文English
主出版物標題High Performance Computing for Big Data
主出版物子標題Methodologies and Applications
發行者CRC Press
頁面59-80
頁數22
ISBN(電子)9781498784009
ISBN(列印)9781498783996
DOIs
出版狀態Published - 2017 一月 1

指紋

Program processors
Hot Temperature
Performance improvement

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Economics, Econometrics and Finance(all)
  • Business, Management and Accounting(all)

引用此文

Lin, I-C., Chiou, J. N., & Law, Y. K. (2017). A 3D hybrid cache design for CMP architecture for data-intensive applications. 於 High Performance Computing for Big Data: Methodologies and Applications (頁 59-80). CRC Press. https://doi.org/10.1201/b21235
Lin, Ing-Chao ; Chiou, Jeng Nian ; Law, Yun Kae. / A 3D hybrid cache design for CMP architecture for data-intensive applications. High Performance Computing for Big Data: Methodologies and Applications. CRC Press, 2017. 頁 59-80
@inbook{27f5490783e249718afd2ce3016adec5,
title = "A 3D hybrid cache design for CMP architecture for data-intensive applications",
abstract = "With the advance of CMOS technology, CPU performance has been improved by increasing frequency. However, the performance improvement for a single-core processor has reached a 60bottleneck due to chip power and heat removal limitations. To overcome these problems, chip multiprocessors (CMPs) have gradually replaced single-core processors, and the number of cores in CMPs is expected to continue to grow. A processor integrating 80 cores has been demonstrated by Intel [1]. In CMP architecture, the last level cache (LLC) is shared by multicore processors and has a significant influence on performance. Therefore, as the CMP architecture has become more widely used, LLC-related research has drawn increased attention.",
author = "Ing-Chao Lin and Chiou, {Jeng Nian} and Law, {Yun Kae}",
year = "2017",
month = "1",
day = "1",
doi = "10.1201/b21235",
language = "English",
isbn = "9781498783996",
pages = "59--80",
booktitle = "High Performance Computing for Big Data",
publisher = "CRC Press",

}

Lin, I-C, Chiou, JN & Law, YK 2017, A 3D hybrid cache design for CMP architecture for data-intensive applications. 於 High Performance Computing for Big Data: Methodologies and Applications. CRC Press, 頁 59-80. https://doi.org/10.1201/b21235

A 3D hybrid cache design for CMP architecture for data-intensive applications. / Lin, Ing-Chao; Chiou, Jeng Nian; Law, Yun Kae.

High Performance Computing for Big Data: Methodologies and Applications. CRC Press, 2017. p. 59-80.

研究成果: Chapter

TY - CHAP

T1 - A 3D hybrid cache design for CMP architecture for data-intensive applications

AU - Lin, Ing-Chao

AU - Chiou, Jeng Nian

AU - Law, Yun Kae

PY - 2017/1/1

Y1 - 2017/1/1

N2 - With the advance of CMOS technology, CPU performance has been improved by increasing frequency. However, the performance improvement for a single-core processor has reached a 60bottleneck due to chip power and heat removal limitations. To overcome these problems, chip multiprocessors (CMPs) have gradually replaced single-core processors, and the number of cores in CMPs is expected to continue to grow. A processor integrating 80 cores has been demonstrated by Intel [1]. In CMP architecture, the last level cache (LLC) is shared by multicore processors and has a significant influence on performance. Therefore, as the CMP architecture has become more widely used, LLC-related research has drawn increased attention.

AB - With the advance of CMOS technology, CPU performance has been improved by increasing frequency. However, the performance improvement for a single-core processor has reached a 60bottleneck due to chip power and heat removal limitations. To overcome these problems, chip multiprocessors (CMPs) have gradually replaced single-core processors, and the number of cores in CMPs is expected to continue to grow. A processor integrating 80 cores has been demonstrated by Intel [1]. In CMP architecture, the last level cache (LLC) is shared by multicore processors and has a significant influence on performance. Therefore, as the CMP architecture has become more widely used, LLC-related research has drawn increased attention.

UR - http://www.scopus.com/inward/record.url?scp=85052681135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052681135&partnerID=8YFLogxK

U2 - 10.1201/b21235

DO - 10.1201/b21235

M3 - Chapter

AN - SCOPUS:85052681135

SN - 9781498783996

SP - 59

EP - 80

BT - High Performance Computing for Big Data

PB - CRC Press

ER -

Lin I-C, Chiou JN, Law YK. A 3D hybrid cache design for CMP architecture for data-intensive applications. 於 High Performance Computing for Big Data: Methodologies and Applications. CRC Press. 2017. p. 59-80 https://doi.org/10.1201/b21235