EZ-Pass: An Energy & Performance-Efficient Power-Gating Router Architecture for Scalable NoCs

Hao Zheng, Ahmed Louri

Research output: Contribution to journalArticlepeer-review

12 Scopus citations

Abstract

With technology scaling into nanometer regime, static power is becoming the dominant factor in the overall power consumption of Network-on-Chips (NoCs). Static power can be reduced by powering off routers during consecutive idle time through power-gating techniques. However, power-gating techniques suffer from a large wake-up latency to wake up the powered-off routers. Recent research aims to improve the wake-up latency penalty by hiding it through early wake-up techniques. However, these techniques do not exploit the full advantage of power-gating due to the early wake-up. Consequently, they do not achieve significant power savings. In this paper, we propose an architecture called Easy Pass (EZ-Pass) router that remedies the large wake-up latency overheads while providing significant static power savings. The proposed architecture takes advantage of idle resources in the network interface to transmit packets without waking up the router. Additionally, the technique hides the wake-up latency by continuing to provide packet transmission during the wake-up phase. We use full system simulation to evaluate our EZ-Pass router on a 64-core NoC with a mesh topology using PARSEC benchmark suites. Our results show that the proposed router reduces static power by up to 31 percent and overall network latency by up to 32 percent as compared to early-wakeup optimized power-gating techniques.

Original languageEnglish (US)
Pages (from-to)88-91
Number of pages4
JournalIEEE Computer Architecture Letters
Volume17
Issue number1
DOIs
StatePublished - Jan 1 2018
Externally publishedYes

Keywords

  • Power-gating
  • energy-efficient
  • nework-on-chips

ASJC Scopus subject areas

  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'EZ-Pass: An Energy & Performance-Efficient Power-Gating Router Architecture for Scalable NoCs'. Together they form a unique fingerprint.

Cite this