Automatic design space exploration of register bypasses in embedded processors

Aviral Shrivastava, Sanghyun Park, Eugene Earlie, Nikil Dutt, Alex Nicolau, Yunheung Paek

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Register Bypassing is a popular and powerful architectural feature to improve processor performance in pipelined processors by eliminating certain data hazards. However, extensive bypassing comes with a significant impact on cycle time, area and power consumption of the processor. Recent research therefore advocates the use of partial bypassing in processor. However, accurate performance evaluation of partially bypassed processors is still a challenge; primarily due to the lack of bypass-sensitive retargetable compilation techniques. No existing partial bypass exploration framework estimates the power and area overhead of partial bypassing. As a result the designers end up making sub-optimal design decisions during the exploration of partial bypass design space. This article presents FBExplore: An automatic design space exploration framework for register bypasses. PBExplore accurately evaluates the performance of a partially bypassed processor using a bypass-sensitive compilation technique. It synthesizes the bypass control logic and estimates the area and energy overhead of each bypass configuration. PBExplore is thus able to effectively perform multi-dimensional exploration of the partial bypass design space. We present experimental results of benchmarks from the MiBench suite on the Intel XScale architecture on and demonstrate the need, utility and exploration capabilities of PBExplore.

Original languageEnglish (US)
Pages (from-to)2102-2115
Number of pages14
JournalIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Volume26
Issue number12
DOIs
StatePublished - Dec 2007

Fingerprint

Hazards
Electric power utilization
Optimal design

Keywords

  • Bypasses
  • Forwarding path
  • Operation table
  • Partial bypassing
  • Partially bypassed processor
  • Pipeline hazard detection
  • Processor pipeline

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Hardware and Architecture
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Automatic design space exploration of register bypasses in embedded processors. / Shrivastava, Aviral; Park, Sanghyun; Earlie, Eugene; Dutt, Nikil; Nicolau, Alex; Paek, Yunheung.

In: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Vol. 26, No. 12, 12.2007, p. 2102-2115.

Research output: Contribution to journalArticle

Shrivastava, Aviral ; Park, Sanghyun ; Earlie, Eugene ; Dutt, Nikil ; Nicolau, Alex ; Paek, Yunheung. / Automatic design space exploration of register bypasses in embedded processors. In: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2007 ; Vol. 26, No. 12. pp. 2102-2115.
@article{4bb51932154c4be8844a70a0bf1ca79e,
title = "Automatic design space exploration of register bypasses in embedded processors",
abstract = "Register Bypassing is a popular and powerful architectural feature to improve processor performance in pipelined processors by eliminating certain data hazards. However, extensive bypassing comes with a significant impact on cycle time, area and power consumption of the processor. Recent research therefore advocates the use of partial bypassing in processor. However, accurate performance evaluation of partially bypassed processors is still a challenge; primarily due to the lack of bypass-sensitive retargetable compilation techniques. No existing partial bypass exploration framework estimates the power and area overhead of partial bypassing. As a result the designers end up making sub-optimal design decisions during the exploration of partial bypass design space. This article presents FBExplore: An automatic design space exploration framework for register bypasses. PBExplore accurately evaluates the performance of a partially bypassed processor using a bypass-sensitive compilation technique. It synthesizes the bypass control logic and estimates the area and energy overhead of each bypass configuration. PBExplore is thus able to effectively perform multi-dimensional exploration of the partial bypass design space. We present experimental results of benchmarks from the MiBench suite on the Intel XScale architecture on and demonstrate the need, utility and exploration capabilities of PBExplore.",
keywords = "Bypasses, Forwarding path, Operation table, Partial bypassing, Partially bypassed processor, Pipeline hazard detection, Processor pipeline",
author = "Aviral Shrivastava and Sanghyun Park and Eugene Earlie and Nikil Dutt and Alex Nicolau and Yunheung Paek",
year = "2007",
month = "12",
doi = "10.1109/TCAD.2007.907066",
language = "English (US)",
volume = "26",
pages = "2102--2115",
journal = "IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems",
issn = "0278-0070",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "12",

}

TY - JOUR

T1 - Automatic design space exploration of register bypasses in embedded processors

AU - Shrivastava, Aviral

AU - Park, Sanghyun

AU - Earlie, Eugene

AU - Dutt, Nikil

AU - Nicolau, Alex

AU - Paek, Yunheung

PY - 2007/12

Y1 - 2007/12

N2 - Register Bypassing is a popular and powerful architectural feature to improve processor performance in pipelined processors by eliminating certain data hazards. However, extensive bypassing comes with a significant impact on cycle time, area and power consumption of the processor. Recent research therefore advocates the use of partial bypassing in processor. However, accurate performance evaluation of partially bypassed processors is still a challenge; primarily due to the lack of bypass-sensitive retargetable compilation techniques. No existing partial bypass exploration framework estimates the power and area overhead of partial bypassing. As a result the designers end up making sub-optimal design decisions during the exploration of partial bypass design space. This article presents FBExplore: An automatic design space exploration framework for register bypasses. PBExplore accurately evaluates the performance of a partially bypassed processor using a bypass-sensitive compilation technique. It synthesizes the bypass control logic and estimates the area and energy overhead of each bypass configuration. PBExplore is thus able to effectively perform multi-dimensional exploration of the partial bypass design space. We present experimental results of benchmarks from the MiBench suite on the Intel XScale architecture on and demonstrate the need, utility and exploration capabilities of PBExplore.

AB - Register Bypassing is a popular and powerful architectural feature to improve processor performance in pipelined processors by eliminating certain data hazards. However, extensive bypassing comes with a significant impact on cycle time, area and power consumption of the processor. Recent research therefore advocates the use of partial bypassing in processor. However, accurate performance evaluation of partially bypassed processors is still a challenge; primarily due to the lack of bypass-sensitive retargetable compilation techniques. No existing partial bypass exploration framework estimates the power and area overhead of partial bypassing. As a result the designers end up making sub-optimal design decisions during the exploration of partial bypass design space. This article presents FBExplore: An automatic design space exploration framework for register bypasses. PBExplore accurately evaluates the performance of a partially bypassed processor using a bypass-sensitive compilation technique. It synthesizes the bypass control logic and estimates the area and energy overhead of each bypass configuration. PBExplore is thus able to effectively perform multi-dimensional exploration of the partial bypass design space. We present experimental results of benchmarks from the MiBench suite on the Intel XScale architecture on and demonstrate the need, utility and exploration capabilities of PBExplore.

KW - Bypasses

KW - Forwarding path

KW - Operation table

KW - Partial bypassing

KW - Partially bypassed processor

KW - Pipeline hazard detection

KW - Processor pipeline

UR - http://www.scopus.com/inward/record.url?scp=36348941906&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36348941906&partnerID=8YFLogxK

U2 - 10.1109/TCAD.2007.907066

DO - 10.1109/TCAD.2007.907066

M3 - Article

VL - 26

SP - 2102

EP - 2115

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 - 12

ER -