Architecture-dependent register allocation and instruction scheduling on VLIW

Lei Wang; Gui Chen

doi:10.1109/ICCET.2010.5485441

Architecture-dependent register allocation and instruction scheduling on VLIW

Lei Wang^*
, Gui Chen

^*Corresponding author for this work

School of Computer Science and Engineering

Beihang University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Architecture-dependent optimization is very important for VLIW architecture. In this paper we have described a new architecture of VLIW - EPRC. And a new architecture-dependent optimization method based on micro-operation for exploiting the characteristics of target machine is described. The software bypassing based on static single-assignment is used to allocate pseudo registers, and the scheduling and register assignment algorithm with heuristics is adopted. Finally, the experimental results of Livermore and Whetstone are given.

Original language	English
Title of host publication	ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings
Pages	V2292-V2296
DOIs	https://doi.org/10.1109/ICCET.2010.5485441
State	Published - 2010
Event	2010 2nd International Conference on Computer Engineering and Technology, ICCET 2010 - Chengdu, China Duration: 16 Apr 2010 → 18 Apr 2010

Publication series

Name	ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings
Volume	2

Conference

Conference	2010 2nd International Conference on Computer Engineering and Technology, ICCET 2010
Country/Territory	China
City	Chengdu
Period	16/04/10 → 18/04/10

Keywords

Architecture-dependent optimization
List scheduling
Software bypassing
VLIW

Access to Document

10.1109/ICCET.2010.5485441

Cite this

Wang, L., & Chen, G. (2010). Architecture-dependent register allocation and instruction scheduling on VLIW. In ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings (pp. V2292-V2296). Article 5485441 (ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings; Vol. 2). https://doi.org/10.1109/ICCET.2010.5485441

@inproceedings{002b7be467954f0f81eec871b9756716,

title = "Architecture-dependent register allocation and instruction scheduling on VLIW",

abstract = "Architecture-dependent optimization is very important for VLIW architecture. In this paper we have described a new architecture of VLIW - EPRC. And a new architecture-dependent optimization method based on micro-operation for exploiting the characteristics of target machine is described. The software bypassing based on static single-assignment is used to allocate pseudo registers, and the scheduling and register assignment algorithm with heuristics is adopted. Finally, the experimental results of Livermore and Whetstone are given.",

keywords = "Architecture-dependent optimization, List scheduling, Software bypassing, VLIW",

author = "Lei Wang and Gui Chen",

year = "2010",

doi = "10.1109/ICCET.2010.5485441",

language = "英语",

isbn = "9781424463503",

series = "ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings",

pages = "V2292--V2296",

booktitle = "ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings",

note = "2010 2nd International Conference on Computer Engineering and Technology, ICCET 2010 ; Conference date: 16-04-2010 Through 18-04-2010",

}

Wang, L & Chen, G 2010, Architecture-dependent register allocation and instruction scheduling on VLIW. in ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings., 5485441, ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings, vol. 2, pp. V2292-V2296, 2010 2nd International Conference on Computer Engineering and Technology, ICCET 2010, Chengdu, China, 16/04/10. https://doi.org/10.1109/ICCET.2010.5485441

Architecture-dependent register allocation and instruction scheduling on VLIW. / Wang, Lei; Chen, Gui.
ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings. 2010. p. V2292-V2296 5485441 (ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Architecture-dependent register allocation and instruction scheduling on VLIW

AU - Wang, Lei

AU - Chen, Gui

PY - 2010

Y1 - 2010

N2 - Architecture-dependent optimization is very important for VLIW architecture. In this paper we have described a new architecture of VLIW - EPRC. And a new architecture-dependent optimization method based on micro-operation for exploiting the characteristics of target machine is described. The software bypassing based on static single-assignment is used to allocate pseudo registers, and the scheduling and register assignment algorithm with heuristics is adopted. Finally, the experimental results of Livermore and Whetstone are given.

AB - Architecture-dependent optimization is very important for VLIW architecture. In this paper we have described a new architecture of VLIW - EPRC. And a new architecture-dependent optimization method based on micro-operation for exploiting the characteristics of target machine is described. The software bypassing based on static single-assignment is used to allocate pseudo registers, and the scheduling and register assignment algorithm with heuristics is adopted. Finally, the experimental results of Livermore and Whetstone are given.

KW - Architecture-dependent optimization

KW - List scheduling

KW - Software bypassing

KW - VLIW

UR - https://www.scopus.com/pages/publications/77958049126

U2 - 10.1109/ICCET.2010.5485441

DO - 10.1109/ICCET.2010.5485441

M3 - 会议稿件

AN - SCOPUS:77958049126

SN - 9781424463503

T3 - ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings

SP - V2292-V2296

BT - ICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings

T2 - 2010 2nd International Conference on Computer Engineering and Technology, ICCET 2010

Y2 - 16 April 2010 through 18 April 2010

ER -

Architecture-dependent register allocation and instruction scheduling on VLIW

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this