IEICE TRANSACTIONS on Information
Resource-Optimal Software Pipelining Using Flow Graphs
Summary :
We present a new approach to the loop scheduling problem, which excels previous solutions in two important aspects: The resource constraints are formulated using flow graphs, and the initiation interval λ is treated as a rational variable. The approach supports heterogeneous processor architectures and pipelined functional units, and the Integer Linear Programming implementation produces an optimum loop schedule, whereby a minimum λ is achieved. Our flow graph model facilitates the cyclic binding of loop operations to functional units. Compared to previous research results, the solution can provide faster loop schedules and a significant reduction of the problem complexity and solution time.
- Publication
- IEICE TRANSACTIONS on Information Vol.E86-D No.9 pp.1560-1568
- Publication Date
- 2003/09/01
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section INVITED PAPER (Special Issue on Parallel and Distributed Computing, Applications and Technologies)
- Category
- Software Systems and Technologies
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Dirk FIMMEL, Jan MULLER, Renate MERKER, "Resource-Optimal Software Pipelining Using Flow Graphs" in IEICE TRANSACTIONS on Information,
vol. E86-D, no. 9, pp. 1560-1568, September 2003, doi: .
Abstract: We present a new approach to the loop scheduling problem, which excels previous solutions in two important aspects: The resource constraints are formulated using flow graphs, and the initiation interval λ is treated as a rational variable. The approach supports heterogeneous processor architectures and pipelined functional units, and the Integer Linear Programming implementation produces an optimum loop schedule, whereby a minimum λ is achieved. Our flow graph model facilitates the cyclic binding of loop operations to functional units. Compared to previous research results, the solution can provide faster loop schedules and a significant reduction of the problem complexity and solution time.
URL: https://global.ieice.org/en_transactions/information/10.1587/e86-d_9_1560/_p
Copy
@ARTICLE{e86-d_9_1560,
author={Dirk FIMMEL, Jan MULLER, Renate MERKER, },
journal={IEICE TRANSACTIONS on Information},
title={Resource-Optimal Software Pipelining Using Flow Graphs},
year={2003},
volume={E86-D},
number={9},
pages={1560-1568},
abstract={We present a new approach to the loop scheduling problem, which excels previous solutions in two important aspects: The resource constraints are formulated using flow graphs, and the initiation interval λ is treated as a rational variable. The approach supports heterogeneous processor architectures and pipelined functional units, and the Integer Linear Programming implementation produces an optimum loop schedule, whereby a minimum λ is achieved. Our flow graph model facilitates the cyclic binding of loop operations to functional units. Compared to previous research results, the solution can provide faster loop schedules and a significant reduction of the problem complexity and solution time.},
keywords={},
doi={},
ISSN={},
month={September},}
Copy
TY - JOUR
TI - Resource-Optimal Software Pipelining Using Flow Graphs
T2 - IEICE TRANSACTIONS on Information
SP - 1560
EP - 1568
AU - Dirk FIMMEL
AU - Jan MULLER
AU - Renate MERKER
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E86-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2003
AB - We present a new approach to the loop scheduling problem, which excels previous solutions in two important aspects: The resource constraints are formulated using flow graphs, and the initiation interval λ is treated as a rational variable. The approach supports heterogeneous processor architectures and pipelined functional units, and the Integer Linear Programming implementation produces an optimum loop schedule, whereby a minimum λ is achieved. Our flow graph model facilitates the cyclic binding of loop operations to functional units. Compared to previous research results, the solution can provide faster loop schedules and a significant reduction of the problem complexity and solution time.
ER -
English
