NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Predicting performance of parallel computationsAn accurate and computationally efficient method for predicting the performance of a class of parallel computations running on concurrent systems is described. A parallel computation is modeled as a task system with precedence relationships expressed as a series-parallel directed acyclic graph. Resources in a concurrent system are modeled as service centers in a queuing network model. Using these two models as inputs, the method outputs predictions of expected execution time of the parallel computation and the concurrent system utilization. The method is validated against both detailed simulation and actual execution on a commercial multiprocessor. Using 100 test cases, the average error of the prediction when compared to simulation statistics is 1.7 percent, with a standard deviation of 1.5 percent; the maximum error is about 10 percent.
Document ID
19900058349
Acquisition Source
Legacy CDMS
Document Type
Reprint (Version printed in journal)
External Source(s)
Authors
Mak, Victor W.
(Bell Communications Research, Inc. Morristown, NJ, United States)
Lundstrom, Stephen F.
(Stanford University CA, United States)
Date Acquired
August 14, 2013
Publication Date
July 1, 1990
Publication Information
Publication: IEEE Transactions on Parallel and Distributed Systems
Volume: 1
ISSN: 1045-9219
Subject Category
Computer Systems
Accession Number
90A45404
Funding Number(s)
CONTRACT_GRANT: NAGW-419
CONTRACT_GRANT: NAG2-248
Distribution Limits
Public
Copyright
Other

Available Downloads

There are no available downloads for this record.
No Preview Available