Re: gcc 2.7.1 and other measures.

Etienne Lorrain (lorrain@fb.sony.de)
Wed, 12 Aug 1998 15:08:16 +0001

"Bernard Sébastien" <sbernard@suresnes.marben.fr> a écrit:
> The 2.7.3.2 version of the gcc could be used without
> the -fno-strength-reduce because the feature has been
> disabled internaly for the i386 architecture. The compilation
> is always done with that flag set, even if you do not put it
> in the CFLAGS. So, with or without, it is the same. If you want
> to benchmark the results, try the 2.8.x version of some of
> the pgcc equivalent version.

Hi,

Thanks for the confirmation.

My aim was not really to check compilers, but I just tried
my small benchmark on 2.1.115 and the standard 2.0.35-2 RH kernel.

First, SMP on UP 386/387IRQ13 is working again... maybe because
there is no more FPU instructions in the kernel ?

I have these general result:
115 UP : 24 min 30 s
115 SMP : 24 min 22 s
RH 35-2 UP: 24 min 45 s

Is there a problem in my benchmark or the SMP kernel is no
more slower than the UP one ?

Etienne.

--
-- The world belong to its organizer.


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html