Filter router: An enhanced router design for efficient stacked shared cache network

Huatao Zhao, Xu Jia, Takahiro Watanabe

Research output: Contribution to journalLetter

1 Citation (Scopus)

Abstract

In this paper, many shared cache accesses such as crossed accesses and repeated accesses will be filtered in proposed router network for purpose of access latency reduction. Firstly, the distribution features of all shared cache accesses are analyzed for further optimization on access latency. And then, a meshed router network integrated with enhanced routers is proposed for fast identification of target accesses and further handling them. Hence, the experimental results show that our network design can achieve an average improvement of 26.1 percent on speedup IPC and an average saving of 9.7 percent on energy consumption over base system.

Original languageEnglish
Article number20190358
Journalieice electronics express
Volume16
Issue number14
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Routers
filters
energy consumption
Energy utilization
optimization

Keywords

  • Network on a chip
  • Router architecture
  • Shared cache memory
  • Stacked integration
  • TSVs

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Electrical and Electronic Engineering

Cite this

Filter router : An enhanced router design for efficient stacked shared cache network. / Zhao, Huatao; Jia, Xu; Watanabe, Takahiro.

In: ieice electronics express, Vol. 16, No. 14, 20190358, 01.01.2019.

Research output: Contribution to journalLetter

@article{575318699ca34d2cbd5f8aa089781ea6,
title = "Filter router: An enhanced router design for efficient stacked shared cache network",
abstract = "In this paper, many shared cache accesses such as crossed accesses and repeated accesses will be filtered in proposed router network for purpose of access latency reduction. Firstly, the distribution features of all shared cache accesses are analyzed for further optimization on access latency. And then, a meshed router network integrated with enhanced routers is proposed for fast identification of target accesses and further handling them. Hence, the experimental results show that our network design can achieve an average improvement of 26.1 percent on speedup IPC and an average saving of 9.7 percent on energy consumption over base system.",
keywords = "Network on a chip, Router architecture, Shared cache memory, Stacked integration, TSVs",
author = "Huatao Zhao and Xu Jia and Takahiro Watanabe",
year = "2019",
month = "1",
day = "1",
doi = "10.1587/elex.16.20190358",
language = "English",
volume = "16",
journal = "IEICE Electronics Express",
issn = "1349-2543",
publisher = "The Institute of Electronics, Information and Communication Engineers (IEICE)",
number = "14",

}

TY - JOUR

T1 - Filter router

T2 - An enhanced router design for efficient stacked shared cache network

AU - Zhao, Huatao

AU - Jia, Xu

AU - Watanabe, Takahiro

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In this paper, many shared cache accesses such as crossed accesses and repeated accesses will be filtered in proposed router network for purpose of access latency reduction. Firstly, the distribution features of all shared cache accesses are analyzed for further optimization on access latency. And then, a meshed router network integrated with enhanced routers is proposed for fast identification of target accesses and further handling them. Hence, the experimental results show that our network design can achieve an average improvement of 26.1 percent on speedup IPC and an average saving of 9.7 percent on energy consumption over base system.

AB - In this paper, many shared cache accesses such as crossed accesses and repeated accesses will be filtered in proposed router network for purpose of access latency reduction. Firstly, the distribution features of all shared cache accesses are analyzed for further optimization on access latency. And then, a meshed router network integrated with enhanced routers is proposed for fast identification of target accesses and further handling them. Hence, the experimental results show that our network design can achieve an average improvement of 26.1 percent on speedup IPC and an average saving of 9.7 percent on energy consumption over base system.

KW - Network on a chip

KW - Router architecture

KW - Shared cache memory

KW - Stacked integration

KW - TSVs

UR - http://www.scopus.com/inward/record.url?scp=85070089002&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070089002&partnerID=8YFLogxK

U2 - 10.1587/elex.16.20190358

DO - 10.1587/elex.16.20190358

M3 - Letter

AN - SCOPUS:85070089002

VL - 16

JO - IEICE Electronics Express

JF - IEICE Electronics Express

SN - 1349-2543

IS - 14

M1 - 20190358

ER -