Algorithms and analysis of scheduling for low-power high-performance DSP on VLIW processors

Zili Shao; Qingfeng Zhuge; Youtao Zhang; Edwin H.M. Sha

Algorithms and analysis of scheduling for low-power high-performance DSP on VLIW processors

Zili Shao, Qingfeng Zhuge, Youtao Zhang, Edwin H.M. Sha

Research output: Journal article publication › Journal article › Academic research › peer-review

Abstract

Switching activity and schedule length are the two most important factors that influence the energy consumption of an application executed on a VLIW (very long instruction word) processor. Considering these two factors together, we propose an instruction-level energy-minimisation scheduling technique to reduce the energy consumption of applications on VLIW processors. We first formally prove that this problem is NP-complete. Then three heuristic algorithms, MSAS, MLMSA, and EMSA, are proposed. While switching activity and schedule length are given higher priority in MSAS and MLMSA respectively, EMSA gives the best result considering both of them. The experimental results show that EMSA gives a 31.7% reduction in energy compared with the traditional list scheduling approach on average.

Original language	English
Pages (from-to)	4-16
Number of pages	13
Journal	International Journal of High Performance Computing and Networking
Volume	1
Issue number	1-3
Publication status	Published - 1 Jan 2004
Externally published	Yes

Keywords

DSP
low power
scheduling
VLIW

ASJC Scopus subject areas

Software
Hardware and Architecture
Computer Networks and Communications

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

@article{9e6714feae7748aeb444cc54070e1868,

title = "Algorithms and analysis of scheduling for low-power high-performance DSP on VLIW processors",

abstract = "Switching activity and schedule length are the two most important factors that influence the energy consumption of an application executed on a VLIW (very long instruction word) processor. Considering these two factors together, we propose an instruction-level energy-minimisation scheduling technique to reduce the energy consumption of applications on VLIW processors. We first formally prove that this problem is NP-complete. Then three heuristic algorithms, MSAS, MLMSA, and EMSA, are proposed. While switching activity and schedule length are given higher priority in MSAS and MLMSA respectively, EMSA gives the best result considering both of them. The experimental results show that EMSA gives a 31.7% reduction in energy compared with the traditional list scheduling approach on average.",

keywords = "DSP, low power, scheduling, VLIW",

author = "Zili Shao and Qingfeng Zhuge and Youtao Zhang and Sha, {Edwin H.M.}",

year = "2004",

month = jan,

day = "1",

language = "English",

volume = "1",

pages = "4--16",

journal = "International Journal of High Performance Computing and Networking",

issn = "1740-0562",

publisher = "Inderscience Enterprises Ltd",

number = "1-3",

}

TY - JOUR

T1 - Algorithms and analysis of scheduling for low-power high-performance DSP on VLIW processors

AU - Shao, Zili

AU - Zhuge, Qingfeng

AU - Zhang, Youtao

AU - Sha, Edwin H.M.

PY - 2004/1/1

Y1 - 2004/1/1

N2 - Switching activity and schedule length are the two most important factors that influence the energy consumption of an application executed on a VLIW (very long instruction word) processor. Considering these two factors together, we propose an instruction-level energy-minimisation scheduling technique to reduce the energy consumption of applications on VLIW processors. We first formally prove that this problem is NP-complete. Then three heuristic algorithms, MSAS, MLMSA, and EMSA, are proposed. While switching activity and schedule length are given higher priority in MSAS and MLMSA respectively, EMSA gives the best result considering both of them. The experimental results show that EMSA gives a 31.7% reduction in energy compared with the traditional list scheduling approach on average.

AB - Switching activity and schedule length are the two most important factors that influence the energy consumption of an application executed on a VLIW (very long instruction word) processor. Considering these two factors together, we propose an instruction-level energy-minimisation scheduling technique to reduce the energy consumption of applications on VLIW processors. We first formally prove that this problem is NP-complete. Then three heuristic algorithms, MSAS, MLMSA, and EMSA, are proposed. While switching activity and schedule length are given higher priority in MSAS and MLMSA respectively, EMSA gives the best result considering both of them. The experimental results show that EMSA gives a 31.7% reduction in energy compared with the traditional list scheduling approach on average.

KW - DSP

KW - low power

KW - scheduling

KW - VLIW

UR - http://www.scopus.com/inward/record.url?scp=84951713449&partnerID=8YFLogxK

M3 - Journal article

SN - 1740-0562

VL - 1

SP - 4

EP - 16

JO - International Journal of High Performance Computing and Networking

JF - International Journal of High Performance Computing and Networking

IS - 1-3

ER -

Algorithms and analysis of scheduling for low-power high-performance DSP on VLIW processors

Abstract

Keywords

ASJC Scopus subject areas

UN SDGs

Other files and links

Fingerprint

Cite this