This is the mail archive of the gcc@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]

Re: Performance of Integer Multiplication on PIII (Results forgcc-2.95 & Athlon)



Hi,

> Note that with -march=i686 new gcc often perofrms worse on Athlon, but it is
> mainly because it do more Athlon specific stuff.

well, actually i compare gcc-3.0.x with gcc-2.95.x (doesn't matter much
which, since both scheduler are switched off for i686) for my floating-point
heavy stuff. And  gcc-3.0.x performs worse compared with gcc-2.95.x (with
-march=i686) regardles of -march=athlon or -march=i686. Other "oddities"
may render any improvements of this flag to nearly invisibility ...

How did you check your -march=athlon improvements? Integer blended
C-code only, or fp-blended code too &, that matters, which source?
Since i found indeed some fp code, for which gcc-3.0.x performs better
then gcc-2.95.x ... but it's more the exeception, than the regula.
{Had to peek at home for examples}

Peter





Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]