[Beowulf] re: open64 from AMD (was newbie)
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.
Mark Hahn hahn at mcmaster.caTue May 12 22:26:42 PDT 2009
- Previous message: [Beowulf] re: open64 from AMD (was newbie)
- Next message: [Beowulf] re: open64 from AMD (was newbie)
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
>> me too, but it brings up a thorny topic: how to compare the >> performance of different compilers? the obvious "run it on >> your code and see" is not helpful in my case, since my goal >> is to have a good choice for a large shared HPC organization >> (several thousand users currently.) > > Personally I think you're on a hiding to nothing if > you try to do that, sorry, but could you decode this 'hiding' thing? spanking? > what we do is provide multiple > compilers and recommend to our users that they test > their code themselves. yeah, that's what we say as well - I'm guessing it doesn't work any better for you as for us ;) users are lazy, and rightfully so! for most of them, HPC is just a tool, and spending part of their lives bumming some cycles doesn't make sense. it might be different if we didn't provide free, all-you-can-eat cycles... I still think it's a useful question. even if the answer is that different compilers/switches only make 5% difference, that's useful to know... > Not a direct answer I'm afraid, but just wanted to > share our experiences (we've got a 600+ registered > users at present, but they're not all active at once > thankfully). we're up to 3300 users, >300 active at any time...
- Previous message: [Beowulf] re: open64 from AMD (was newbie)
- Next message: [Beowulf] re: open64 from AMD (was newbie)
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
