PGI and HPL benchmarking
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Daniel Kidger Daniel.Kidger at quadrics.comMon Sep 17 10:18:40 PDT 2001
- Previous message: PGI and HPL benchmarking
- Next message: PVM: problem distributing on smp nodes with different number of processors
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Marc wrote: >I am trying to compile the High Performance Computing Linpack Benchmark (HPL) >software on a cluster that has Portland (PGI) 3.2 >compiler. The PGI compiler installs it's own BLAS routines so I would like to use >those. I modify one of the make files, such as, Make.Linux_PII_FBLAS but still >get errors during the compile. Has anyone successfully built and run this >benchmark with PGI >compilers. You do not say why you want to use PGI's BLAS ? Check out http://computational-battery.org/Programvare/blas-lib-comparison.html Their results show that Portland's BLAS implementation trails a long way behind ATLAS and Intel's MKL. Daniel. -------------------------------------------------------------- Dr. Dan Kidger, Quadrics Ltd. daniel.kidger at quadrics.com One Bridewell St., Bristol, BS1 2AA, UK 0117 907 5375 ----------------------- www.quadrics.com --------------------
- Previous message: PGI and HPL benchmarking
- Next message: PVM: problem distributing on smp nodes with different number of processors
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
