I met George Woltman in Orlando, Florida a week ago and as I recall, he
agreed that (as you said, Jason) "If Prime95 is ever rewritten for IA64 it
would have to be not only a total rewrite but a complete rethinking of the
FFTs it uses." George is up to the task, happily.
At 01:27 AM 6/18/00 -0400, Jason Papad wrote:
>
>
>On Sat, 17 Jun 2000 [EMAIL PROTECTED] wrote:
>
>> Will Prime95 be rewritten to run on the Itanium, when it comes out?
Seems to
>> me like 64-bit operation will speed it up significantly, as will the insane
>> amount of registers and floating point units and all the other
>> microprocessor
>> whatnot that I'm not current on.
>
>Intel has had documentation available on the Web for a while that details
>the architecture of Itanium. If Prime95 is ever rewritten for IA64 it
>would have to be not only a total rewrite but a complete rethinking of
>the FFTs it uses. For example, integer multiply-adds take only a little
>longer than floating point multiply-adds; should IA64Prime use an integer
>or floating point FFT? If integer, there are big delays in shuffling
>between integer and FPU registers (only the FPU can multiply). If floating
>point, loads and stores will all take longer, the cache behavior is
>totally different, and the arrays involved get longer because you can't
>pack bits as densely as an integer solution.
>
>Itanium can do two FPU operations per clock, but both can be multiply-adds
>instead of just multiplies or adds. Can you rearrange a real-valued FFT
>to use multiply-adds as much as possible? It could cut the operation count
>in half if you do, but to my knowledge no one has yet done so. It's been
>done for complex FFTs, but Prime95 really wants real-valued FFTs, not
>complex ones.
>
>Moving to IA64 will be a much bigger challenge than simply rewriting
>half a meg of assembly language.
>
>jasonp
>
>
>_________________________________________________________________
>Unsubscribe & list info -- http://www.scruz.net/~luke/signup.htm
>Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
>
_________________________________________________________________
Unsubscribe & list info -- http://www.scruz.net/~luke/signup.htm
Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
