|
From: Bart V. A. <bar...@gm...> - 2006-08-25 13:10:17
|
Hello Julian,
I tried to run "make perf", but got the following error messages:
if gcc -DHAVE_CONFIG_H -I. -I. -I../../.. -Winline -Wall -O -mregnames
-DHAS_
ALTIVEC -maltivec -m32 -Wno-long-long -Wdeclaration-after-statement -MT
jm_insns
-jm-insns.o -MD -MP -MF ".deps/jm_insns-jm-insns.Tpo" -c -o jm_insns-
jm-insns.o
`test -f 'jm-insns.c' || echo './'`jm-insns.c; \
then mv -f ".deps/jm_insns-jm-insns.Tpo" ".deps/jm_insns-jm-insns.Po"; else
rm -
f ".deps/jm_insns-jm-insns.Tpo"; exit 1; fi
In file included from jm-insns.c:192:
/usr/lib/gcc/powerpc-montavista-linux/3.4.3/include/altivec.h:36:2: #error
Use t
he "-maltivec" flag to enable PowerPC AltiVec support
jm-insns.c:377: error: parse error before "unsigned"
jm-insns.c:4119: error: syntax error before "unsigned"
jm-insns.c:4121: error: syntax error before "float"
jm-insns.c: In function `build_viargs_table':
jm-insns.c:4365: error: `__vector' undeclared (first use in this function)
On 8/25/06, Julian Seward <js...@ac...> wrote:
>
>
> Bart
>
> The ppc32-linux port is one of the most efficient, and has performance
> characteristics similar to x86-linux. Running on an MPC7447A
> (1250 MHz Freescale CPU in a Mac Mini) it consistently shows amongst
> the lowest slowdowns I have seen.
>
> Performance of V depends on many facets, and it's impossible to tell
> from your bash run what the problem might be. It would be better to
> run the performance test suite ("make perf" at the top level) and
> report the results of that for both platforms. At least for the few
> programs in that suite we have some idea of what parts of the
> system they stress.
>
|