PORTLAND COMPILERS
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.
Doug Farley d.l.farley at larc.nasa.govFri Jun 14 11:24:32 PDT 2002
- Previous message: PORTLAND COMPILERS
- Next message: Myrinet scalability
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Ivan, I must say, the PGI compilers have provided a 20% speedup on some apps for us, and we only have one licence on the master node. However, if it was not for PGI being the only PC compiler that supports Cray Pointers and our users extremely legacy f77 code, I think we would use gcc only. But i've experienced no problems with just having the compiler on the master, and using that binary on the compute nodes. The only place I could see needing it on more than just the master is if you don't have a homogenous cluster. HTH, Doug Doug Farley Data Analysis and Imaging Branch Systems Engineering Competency NASA Langley Research Center < D.L.FARLEY at LaRC.NASA.GOV > < Phone +1 757 864-8141 >
- Previous message: PORTLAND COMPILERS
- Next message: Myrinet scalability
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
