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


On Sun, 4 Nov 2001 pete@ltoi.iap.physik.tu-darmstadt.de wrote:

> Thus:
>       On i586: gcc's code generator is not bad
>       On i686: gcc's code generator could/should be smarter.
>                But, for a sort of varity: Did you crosschecked
>                with gcc-2.95.x?

No.  However I did cross check it on whatever compiler is shipped with
Mandrake 8.1 "gcc 2.96..." and got very similar results.  In fact the last
set of results was using the Mandrake compiler instead of gcc 3.0.2.  However,
Gcc 3.0.2 does do slightly worse than gcc 2.96, but the difference is not
substantial, a 1 or two clock cycles at most.  I will try to post the
results with Gcc 3.0.2 if I get a chance.

>                It may be, that this is just another example of
>                the new de-improved x86 backend of the gcc-3.0 line .(?).


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