Low-Power High-Level Synthesis for FPGA Architectures

Deming Chen, Jason Gong, Yiping Fan

Research output: Contribution to journalConference article

Abstract

This paper addresses two aspects of low-power design for FPGA circuits. First, we present an RT-level power estimator for FPGAs with consideration of wire length. The power estimator closely reflects both dynamic and static power contributed by various FPGA components in 0.1um technology. The power estimation error is 16.2% on average. Second, we present a low power high level synthesis system, named LOPASS, for FPGA designs. It includes two algorithms for power consumption reduction: (i) a simulated annealing engine that carries out resource selection, function unit binding, scheduling, register binding, and data path generation simultaneously to effectively reduce power; (ii) an enhanced weighted bipartite matching algorithm that is able to reduce the total amount of MUX ports by 22.7%. Experimental results show that LOPASS is able to reduce power consumption by 35.8% compared to the results of Synopsys' Behavioral Compiler.

Original languageEnglish (US)
Pages (from-to)134-139
Number of pages6
JournalProceedings of the International Symposium on Low Power Electronics and Design
StatePublished - Dec 1 2003
EventProceedings of the 2003 International Symposium on Low Power Electronics and Design, (ISLPED'03) - Seoul, Korea, Republic of
Duration: Aug 25 2003Aug 27 2003

Fingerprint

Field programmable gate arrays (FPGA)
Electric power utilization
Simulated annealing
Error analysis
Scheduling
Wire
Engines
High level synthesis
Networks (circuits)

Keywords

  • Data path optimization
  • FPGA power reduction
  • RT-level power estimation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Low-Power High-Level Synthesis for FPGA Architectures. / Chen, Deming; Gong, Jason; Fan, Yiping.

In: Proceedings of the International Symposium on Low Power Electronics and Design, 01.12.2003, p. 134-139.

Research output: Contribution to journalConference article

@article{b77d8fda595f405c96a44b2d99d12220,
title = "Low-Power High-Level Synthesis for FPGA Architectures",
abstract = "This paper addresses two aspects of low-power design for FPGA circuits. First, we present an RT-level power estimator for FPGAs with consideration of wire length. The power estimator closely reflects both dynamic and static power contributed by various FPGA components in 0.1um technology. The power estimation error is 16.2{\%} on average. Second, we present a low power high level synthesis system, named LOPASS, for FPGA designs. It includes two algorithms for power consumption reduction: (i) a simulated annealing engine that carries out resource selection, function unit binding, scheduling, register binding, and data path generation simultaneously to effectively reduce power; (ii) an enhanced weighted bipartite matching algorithm that is able to reduce the total amount of MUX ports by 22.7{\%}. Experimental results show that LOPASS is able to reduce power consumption by 35.8{\%} compared to the results of Synopsys' Behavioral Compiler.",
keywords = "Data path optimization, FPGA power reduction, RT-level power estimation",
author = "Deming Chen and Jason Gong and Yiping Fan",
year = "2003",
month = "12",
day = "1",
language = "English (US)",
pages = "134--139",
journal = "Proceedings of the International Symposium on Low Power Electronics and Design",
issn = "1533-4678",

}

TY - JOUR

T1 - Low-Power High-Level Synthesis for FPGA Architectures

AU - Chen, Deming

AU - Gong, Jason

AU - Fan, Yiping

PY - 2003/12/1

Y1 - 2003/12/1

N2 - This paper addresses two aspects of low-power design for FPGA circuits. First, we present an RT-level power estimator for FPGAs with consideration of wire length. The power estimator closely reflects both dynamic and static power contributed by various FPGA components in 0.1um technology. The power estimation error is 16.2% on average. Second, we present a low power high level synthesis system, named LOPASS, for FPGA designs. It includes two algorithms for power consumption reduction: (i) a simulated annealing engine that carries out resource selection, function unit binding, scheduling, register binding, and data path generation simultaneously to effectively reduce power; (ii) an enhanced weighted bipartite matching algorithm that is able to reduce the total amount of MUX ports by 22.7%. Experimental results show that LOPASS is able to reduce power consumption by 35.8% compared to the results of Synopsys' Behavioral Compiler.

AB - This paper addresses two aspects of low-power design for FPGA circuits. First, we present an RT-level power estimator for FPGAs with consideration of wire length. The power estimator closely reflects both dynamic and static power contributed by various FPGA components in 0.1um technology. The power estimation error is 16.2% on average. Second, we present a low power high level synthesis system, named LOPASS, for FPGA designs. It includes two algorithms for power consumption reduction: (i) a simulated annealing engine that carries out resource selection, function unit binding, scheduling, register binding, and data path generation simultaneously to effectively reduce power; (ii) an enhanced weighted bipartite matching algorithm that is able to reduce the total amount of MUX ports by 22.7%. Experimental results show that LOPASS is able to reduce power consumption by 35.8% compared to the results of Synopsys' Behavioral Compiler.

KW - Data path optimization

KW - FPGA power reduction

KW - RT-level power estimation

UR - http://www.scopus.com/inward/record.url?scp=1542299296&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542299296&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:1542299296

SP - 134

EP - 139

JO - Proceedings of the International Symposium on Low Power Electronics and Design

JF - Proceedings of the International Symposium on Low Power Electronics and Design

SN - 1533-4678

ER -