TY - GEN
T1 - Multiple quadratic forms
T2 - 1993 International Conference on Parallel Processing, ICPP 1993
AU - Wang, Mu Cheng
AU - Nation, Wayne G.
AU - Armstrong, James B.
AU - Siegel, Howard Jay
AU - Kim, Shin Dug
AU - Nichols, Mark A.
AU - Gherrity, Michael
N1 - Publisher Copyright:
© 1993 IEEE.
Copyright:
Copyright 2019 Elsevier B.V., All rights reserved.
PY - 1993
Y1 - 1993
N2 - Parallel implementations of the computationally intensive task of solving multiple quadratic forms (MQFs) have been examined. Coupled and uncoupled parallel methods are investigated, where coupling relates to the degree of interaction among the processors. Also, the impact of partitioning a large MQF problem into smaller non-interacting subtasks is studied. Trade-offs among the implementations for various data-she/machine-size ratios are categorized in terms of complex arithmetic operation counts, communication overhead, and memory storage requirements. From the complexity analyses, it is shown that none of the algorithms presented in this paper is best for alt data-size!machine-size ratios. Thus, to achieve scalability (i.e., good performance as the number of processors available in a machine increases (4), instead of using a single algorithm, the approach proposed is to have a set of algorithms from which the most appropriate algorithm or combination of algorithms is selected based on the ratio calculated from the scaled machine size. The analytical results nave been verified from experiments on the MasPar MP-1, nCUBE 2, and PASM prototype.
AB - Parallel implementations of the computationally intensive task of solving multiple quadratic forms (MQFs) have been examined. Coupled and uncoupled parallel methods are investigated, where coupling relates to the degree of interaction among the processors. Also, the impact of partitioning a large MQF problem into smaller non-interacting subtasks is studied. Trade-offs among the implementations for various data-she/machine-size ratios are categorized in terms of complex arithmetic operation counts, communication overhead, and memory storage requirements. From the complexity analyses, it is shown that none of the algorithms presented in this paper is best for alt data-size!machine-size ratios. Thus, to achieve scalability (i.e., good performance as the number of processors available in a machine increases (4), instead of using a single algorithm, the approach proposed is to have a set of algorithms from which the most appropriate algorithm or combination of algorithms is selected based on the ratio calculated from the scaled machine size. The analytical results nave been verified from experiments on the MasPar MP-1, nCUBE 2, and PASM prototype.
UR - http://www.scopus.com/inward/record.url?scp=85065707329&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85065707329&partnerID=8YFLogxK
U2 - 10.1109/ICPP.1993.120
DO - 10.1109/ICPP.1993.120
M3 - Conference contribution
AN - SCOPUS:85065707329
T3 - Proceedings of the International Conference on Parallel Processing
SP - 37
EP - 46
BT - Algorithms and Applications
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 16 August 1993 through 20 August 1993
ER -