Design space exploration of media processors: A parameterized scheduler

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autoren

  • Guillermo Payá-Vayá
  • Javier Martín-Langerwerf
  • Piriya Taptimthong
  • Peter Pirsch
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des SammelwerksProceedings - 2007 International Conference on Embedded Computer Systems
UntertitelArchitectures, Modeling and Simulation, IC-SAMOS 2007
Seiten41-49
Seitenumfang9
PublikationsstatusVeröffentlicht - 2007
Veranstaltung2007 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2007 - Samos, Griechenland
Dauer: 16 Juli 200719 Juli 2007

Abstract

This paper describes an enhanced list scheduling algorithm used on a parameterized assembler. The assembler, which is configurable in terms of architectural parameters, is used on a new environment system for exploring and optimizing VLIW architectures for multimedia applications. A generic VLIW architecture with a novel register file structure is used as a base architecture. The proposed scheduling algorithm includes sophisticated features. A backtracking technique allows to undo inappropriate scheduling decisions, while an advanced resource conflict function allows to work with different VLIW architecture configurations. Moreover, local register allocation in conjunction with the instruction scheduling process is also implemented for obtaining better code compaction. Two different multimedia tasks are implemented to check the correctness of the generated code for different architecture configurations. The code compaction efficiency, when scheduling these applications for different VLIW architecture configurations with a partitioned register file and limited number of functional units, reaches up to 94% of the compaction efficiency for the same configuration with an unconstrained register file and unlimited number of functional units.

ASJC Scopus Sachgebiete

Zitieren

Design space exploration of media processors: A parameterized scheduler. / Payá-Vayá, Guillermo; Martín-Langerwerf, Javier; Taptimthong, Piriya et al.
Proceedings - 2007 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2007. 2007. S. 41-49 4285732.

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Payá-Vayá, G, Martín-Langerwerf, J, Taptimthong, P & Pirsch, P 2007, Design space exploration of media processors: A parameterized scheduler. in Proceedings - 2007 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2007., 4285732, S. 41-49, 2007 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2007, Samos, Griechenland, 16 Juli 2007. https://doi.org/10.1109/ICSAMOS.2007.4285732
Payá-Vayá, G., Martín-Langerwerf, J., Taptimthong, P., & Pirsch, P. (2007). Design space exploration of media processors: A parameterized scheduler. In Proceedings - 2007 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2007 (S. 41-49). Artikel 4285732 https://doi.org/10.1109/ICSAMOS.2007.4285732
Payá-Vayá G, Martín-Langerwerf J, Taptimthong P, Pirsch P. Design space exploration of media processors: A parameterized scheduler. in Proceedings - 2007 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2007. 2007. S. 41-49. 4285732 doi: 10.1109/ICSAMOS.2007.4285732
Payá-Vayá, Guillermo ; Martín-Langerwerf, Javier ; Taptimthong, Piriya et al. / Design space exploration of media processors : A parameterized scheduler. Proceedings - 2007 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2007. 2007. S. 41-49
Download
@inproceedings{5e7768b3aecf4327ae05c2af2edb49b2,
title = "Design space exploration of media processors: A parameterized scheduler",
abstract = "This paper describes an enhanced list scheduling algorithm used on a parameterized assembler. The assembler, which is configurable in terms of architectural parameters, is used on a new environment system for exploring and optimizing VLIW architectures for multimedia applications. A generic VLIW architecture with a novel register file structure is used as a base architecture. The proposed scheduling algorithm includes sophisticated features. A backtracking technique allows to undo inappropriate scheduling decisions, while an advanced resource conflict function allows to work with different VLIW architecture configurations. Moreover, local register allocation in conjunction with the instruction scheduling process is also implemented for obtaining better code compaction. Two different multimedia tasks are implemented to check the correctness of the generated code for different architecture configurations. The code compaction efficiency, when scheduling these applications for different VLIW architecture configurations with a partitioned register file and limited number of functional units, reaches up to 94% of the compaction efficiency for the same configuration with an unconstrained register file and unlimited number of functional units.",
author = "Guillermo Pay{\'a}-Vay{\'a} and Javier Mart{\'i}n-Langerwerf and Piriya Taptimthong and Peter Pirsch",
year = "2007",
doi = "10.1109/ICSAMOS.2007.4285732",
language = "English",
isbn = "1424410584",
pages = "41--49",
booktitle = "Proceedings - 2007 International Conference on Embedded Computer Systems",
note = "2007 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2007 ; Conference date: 16-07-2007 Through 19-07-2007",

}

Download

TY - GEN

T1 - Design space exploration of media processors

T2 - 2007 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2007

AU - Payá-Vayá, Guillermo

AU - Martín-Langerwerf, Javier

AU - Taptimthong, Piriya

AU - Pirsch, Peter

PY - 2007

Y1 - 2007

N2 - This paper describes an enhanced list scheduling algorithm used on a parameterized assembler. The assembler, which is configurable in terms of architectural parameters, is used on a new environment system for exploring and optimizing VLIW architectures for multimedia applications. A generic VLIW architecture with a novel register file structure is used as a base architecture. The proposed scheduling algorithm includes sophisticated features. A backtracking technique allows to undo inappropriate scheduling decisions, while an advanced resource conflict function allows to work with different VLIW architecture configurations. Moreover, local register allocation in conjunction with the instruction scheduling process is also implemented for obtaining better code compaction. Two different multimedia tasks are implemented to check the correctness of the generated code for different architecture configurations. The code compaction efficiency, when scheduling these applications for different VLIW architecture configurations with a partitioned register file and limited number of functional units, reaches up to 94% of the compaction efficiency for the same configuration with an unconstrained register file and unlimited number of functional units.

AB - This paper describes an enhanced list scheduling algorithm used on a parameterized assembler. The assembler, which is configurable in terms of architectural parameters, is used on a new environment system for exploring and optimizing VLIW architectures for multimedia applications. A generic VLIW architecture with a novel register file structure is used as a base architecture. The proposed scheduling algorithm includes sophisticated features. A backtracking technique allows to undo inappropriate scheduling decisions, while an advanced resource conflict function allows to work with different VLIW architecture configurations. Moreover, local register allocation in conjunction with the instruction scheduling process is also implemented for obtaining better code compaction. Two different multimedia tasks are implemented to check the correctness of the generated code for different architecture configurations. The code compaction efficiency, when scheduling these applications for different VLIW architecture configurations with a partitioned register file and limited number of functional units, reaches up to 94% of the compaction efficiency for the same configuration with an unconstrained register file and unlimited number of functional units.

UR - http://www.scopus.com/inward/record.url?scp=47749086307&partnerID=8YFLogxK

U2 - 10.1109/ICSAMOS.2007.4285732

DO - 10.1109/ICSAMOS.2007.4285732

M3 - Conference contribution

AN - SCOPUS:47749086307

SN - 1424410584

SN - 9781424410583

SP - 41

EP - 49

BT - Proceedings - 2007 International Conference on Embedded Computer Systems

Y2 - 16 July 2007 through 19 July 2007

ER -