DMCA
Benchmarking for Distributed Memory Parallel Systems: Gaining Insight from Numbers (0)
| Citations: | 3 - 0 self |
BibTeX
@MISC{Getov_benchmarkingfor,
author = {Addison Getov and C. A. Addison and V. S. Getov and A. J. G. Hey and R. W. Hockney and I. C. Wolton},
title = {Benchmarking for Distributed Memory Parallel Systems: Gaining Insight from Numbers},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
. The inherent difficulties of benchmarking parallel computers and the motivation behind the development of the GENESIS benchmark suite introduce the paper. Some of the broader issues that must be taken into account with any rigorous benchmarking effort on a distributed memory system are then discussed together with a relevant example. The initial version of the GENESIS benchmarks was used to evaluate the SUPRENUM computer. The later releases of the suite have been developed to achieve portability of codes across different distributed memory systems by means of the PARMACS macros. Strict portability is however infeasible due to the relative immaturity of current distributed memory computers and the presence of so many different architectures. Therefore some aspects of transportable software are also described, which were felt important when porting the benchmarks to different parallel platforms. 1 Introduction Benchmarking is one of those activities that everyone claims to know someth...
Keyphrases
distributed memory parallel system later release many different architecture rigorous benchmarking effort parmacs macro memory system different distributed memory system relevant example genesis benchmark transportable software introduction benchmarking inherent difficulty genesis benchmark suite parallel computer current distributed memory computer suprenum computer different parallel platform relative immaturity strict portability initial version
