A Method that Determines Optimal Grain Size and Inherent Parallelism Concurrently

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Yiqun Ge Articles by David Y. Y. Yun

1996 International Symposium on Parallel Architectures, Algorithms and Networks (ISPAN '96)

Beijing, CHINA

June 12-June 14

ISBN: 0-8186-7460-1

	ASCII Text	x
	Yiqun Ge, David Y. Y. Yun, "A Method that Determines Optimal Grain Size and Inherent Parallelism Concurrently," Parallel Architectures, Algorithms, and Networks, International Symposium on, pp. 200, 1996 International Symposium on Parallel Architectures, Algorithms and Networks (ISPAN '96), 1996.

	BibTex	x
	@article{ 10.1109/ISPAN.1996.508982, author = {Yiqun Ge and David Y. Y. Yun}, title = {A Method that Determines Optimal Grain Size and Inherent Parallelism Concurrently}, journal ={Parallel Architectures, Algorithms, and Networks, International Symposium on}, volume = {0}, year = {1996}, issn = {1087-4089}, pages = {200}, doi = {http://doi.ieeecomputersociety.org/10.1109/ISPAN.1996.508982}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Parallel Architectures, Algorithms, and Networks, International Symposium on TI - A Method that Determines Optimal Grain Size and Inherent Parallelism Concurrently SN - 1087-4089 SP EP A1 - Yiqun Ge, A1 - David Y. Y. Yun, PY - 1996 KW - Grain Packing KW - Scheduling KW - Inherent Parallelism KW - 2D Compression KW - Multiple Objectives VL - 0 JA - Parallel Architectures, Algorithms, and Networks, International Symposium on ER -

Yiqun Ge, Laboratories of Intelligent and Parallel Systems (LIPS)

David Y. Y. Yun, Laboratories of Intelligent and Parallel Systems (LIPS)

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ISPAN.1996.508982

Grain packing is an important problem to the development of efficient parallel programs. It is desirable that the grain packing can be performed automatically, so that the programmer can write parallel programs without being troubled by the details of parallel-programming languages and parallel architectures, and the same parallel program can be executed efficiently on different machines. This paper presents a 2D Compression (2DC) grain packing method for determining optimal grain size and inherent parallelism concurrently. This ability is mainly due to 2DC's continuing efforts for achieving conflicting objectives. Experimental results demonstrate that 2DC increases the solution effectiveness, in comparison with state-of-art approaches that aim at economizing either speedup or resource utilization. Additionally, 2DC can determine inherent parallelism, which means that users will no longer be required to specify the number of processors before the compilation stage.

Index Terms:

Grain Packing, Scheduling, Inherent Parallelism, 2D Compression, Multiple Objectives

Citation:

Yiqun Ge, David Y. Y. Yun, "A Method that Determines Optimal Grain Size and Inherent Parallelism Concurrently," ispan, pp.200, 1996 International Symposium on Parallel Architectures, Algorithms and Networks (ISPAN '96), 1996

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.