[Numpy-discussion] re: gcc 3.0 vs. 2.95.2

Rob europax at home.com
Sun Sep 16 10:33:01 CDT 2001


Peter Soendergaard wrote:
> 
> Hello,
> 
> I just browsed over the archives for Numpy-discussion and saw this, and
> decided to sign up.
> 
> I work on the ATLAS-project http://math-atlas.sourceforge.net/ and we have
> had similar problems with gcc3.0 Gcc 3.0 has a completely new backend
> which produces much slower floating point code on i386 machines. It is
> most visible on the Athlon, but it also also shows on on P4 and PIII
> machines. We havn't yet figured out if there are some optimizations that
> can make this go away, but if you need performance stick with the old 2.95
> release for now.
> 
> By the way, if you would like to use Atlas in NumPy (I don't know if you
> do it already) I might be of some help. There is c-interfaces to the BLAS
> bundled with ATLAS, supporting both row-major and column-major storage.
> 
> Cheers,
> 
> Peter.
> 
> FROM: Rob
> DATE: 09/04/2001 18:02:05
> SUBJECT:  [Numpy-discussion] Python and Numpy compiled on Athlon
> optimized gcc3.01
> 
> Just for kicks last night I installed gcc3.01 which claims to have Athlon
> optimization, ie. -march=athlon.  I recompiled Python and Numpy, and then
> ran a big simulation.  The new compiler ran 200 seconds slower than the
> old gcc2.95 with plain -march=pentium.  I need to go to the gcc website
> and see just what optimization they are claiming.  Maybe I should have
> also used -02.   Rob.
> 
> --
> The Numeric Python EM Project
> 
> http://www.members.home.net/europax
> 
> _______________________________________________
> Numpy-discussion mailing list
> Numpy-discussion at lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/numpy-discussion


Hi Peter,  great to know that I'm not alone.   Maybe I can build an EM
simulator using all integer math :).  I think I mentioned this on the
list before, but Win2k on my laptop (1Ghz) runs Numpy and Python faster
than my 1.2Ghz Athlon DDR machine using FreeBSD :(   Also, for
reference, I have a 3DNow optimized MP3encoding program Gogo that
encodes mp3's 10x faster on the athlon than Lame does on my FreeBSD
system on the laptop.  Go figure!

-- 
The Numeric Python EM Project

www.members.home.net/europax




More information about the Numpy-discussion mailing list