Scalable scientific library subroutines
on a parallel-vector supercomputer
148. R. P. Brent, A. J. Cleary, M. Hegland, J. H. Jenkinson,
Z. Leyk, M. Nakanishi, M. R. Osborne, P. J. Price, S. Roberts
and D. B. Singleton,
Implementation and performance of scalable scientific library subroutines
on Fujitsu's VPP500 parallel-vector supercomputer,
Proceedings of the Scalable High Performance Computing Conference,
(Knoxville, Tennessee, 23-25 May, 1994),
IEEE CS Press, 1994, 526-533.
Also appeared as "Area 4 Working Note" #16, May 1994, 9 pp.
Paper:
dvi (25K),
pdf (193K),
ps (53K).
Abstract
We report progress to date on our project to implement high-impact scientific
subroutines on Fujitsu's parallel-vector VPP500. Areas covered in the project
are generally between the level of basic building blocks and complete applications,
including such things as random number generators, fast Fourier transforms,
various linear equation solvers, and eigenvalue solvers. Highlights so
far include a suite of fast Fourier transform methods with extensive functionality
and performance of approximately one third of peak; a parallel random number
generator guaranteed to not repeat sequences on different processors, yet
reproducible over separate runs, that produces randoms in 2.2 machine cycles;
and a Gaussian elimination code that has achieved over a Gflop per processor
for 32 processors of the VPP500, and 124.5 Gflops total on the Fujitsu-built
Numerical Wind Tunnel, a machine very similar architecturally to the VPP500.
Comments
For more recent developments see
[182,
187].
Go to next publication
Return to Richard Brent's index page