Hi,
At 11:38 PM 5/14/2001 +0100, Thomas Womack wrote:
>When I run it on my K62/333 laptop, the self-test tries to test M5242881
>with a 256k FFT, gives an excess-roundoff-error message and dies; this is
>presumably a bug.
Yes, apparently I broke the old FFT code.... Another good reason for
only P4 users to download this version!
>When I run it on the P4, the self-test checks a set of thirty or so
>exponents with a 320k FFT length, and then does it again, and again, until
>it's run a total of 306 tests. This surprised me slightly; I was expecting
>it to exercise all the FFT lengths with random exponents to check for
>edge-conditions in the new P4 code.
The SSE2 instructions only support 53 bits of precision. The old Intel
FPU supports 64 bits of precision. Consequently, the old FFT code
can handle slightly higher exponents. For a 256K FFT, the old code
could handle up to 5,250,000, the new code can only handle up to 5,140,000.
>Is the self-test in fact just to check
>that there's not something in the CPU which goes glitchy when running
>flat-out SSE2 code for hours on end?
Yes. The QA suite that Ken Kriesel and Brian Beesley worked on does a
better job at testing edge conditions. Of course, they'll need to update that
suite using the new limits.
Regards,
George
_________________________________________________________________________
Unsubscribe & list info -- http://www.scruz.net/~luke/signup.htm
Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
