home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!pmafire!news.dell.com!natinst.com!cs.utexas.edu!uwm.edu!zaphod.mps.ohio-state.edu!darwin.sura.net!gatech!emory!cs.utk.edu!cs.utk.edu!eijkhout
- From: eijkhout@cupid.cs.utk.edu (Victor Eijkhout)
- Newsgroups: comp.sys.super
- Subject: Re: World's Most Powerful Computing Sites
- Date: 23 Jan 93 16:43:14
- Organization: /pearl/homes/eijkhout/.organization
- Lines: 23
- Distribution: inet
- Message-ID: <EIJKHOUT.93Jan23164314@cupid.cs.utk.edu>
- References: <1993Jan20.232809.29241@nas.nasa.gov> <1993Jan21.165159.10149@meiko.com>
- <1993Jan22.015827.26653@nas.nasa.gov>
- NNTP-Posting-Host: cupid.cs.utk.edu
- In-reply-to: fineberg@wilbur.nas.nasa.gov's message of 22 Jan 93 01:58:27 GMT
-
- In article <1993Jan22.015827.26653@nas.nasa.gov> fineberg@wilbur.nas.nasa.gov (Samuel A. Fineberg) writes:
-
- I don't know too many people that write assembly code, and that is what you
- need to do to get 35 MFLOPs. As far as I'm concerned, assembly coded
- benchnmarks are useless.
-
- Assembly coded benchmarks, maybe. But the BLAS routines (Basic Linear
- Algebra Subroutines) exist on many machines in assembler, and
- precisely because they are 1/ standardized across all platforms
- 2/ optimized for each, you can write real programs in Fortran or C,
- with a reasonable speed if you need the BLAS often enough.
-
- Just interface your program to assembler *kernels*.
-
- I know of people who write distributed memory linear system
- solvers, that get over 50% performance out of *500 i860's*
- using those assembler BLAS.
-
- --
- Victor Eijkhout ................................ `There are also a few bugs,
- Department of Computer Science .......... though not as many as I've come to
- University of Tennessee ............... expect in new [MS]Windows products.'
- Knoxville TN 37919 ................................ (from a software review)
-