Re: [B2-devel] Optimizations to AltiVec code now in CVS

[Gwenole B. <gb...@di...>]

Hi,

> In file included from ../kpx_cpu/src/cpu/ppc/ppc-dyngen-ops.cpp:1493:
> /usr/lib/gcc-lib/i486-slackware-linux/3.2.3/include/xmmintrin.h: In 
> function
>    `void _mm_stream_pi(vector int*, vector int)':
> /usr/lib/gcc-lib/i486-slackware-linux/3.2.3/include/xmmintrin.h:1036: 
> cannot
>    convert `vector int*' to `long long unsigned int*' for argument `1' 
> to
> `void
>    __builtin_ia32_movntq(long long unsigned int*, long long unsigned 
> int)'

AFAIK, there is no "vector" definition in any released gcc for x86. SSE 
types are generally defined as __attribute__((__mode__(__V4SI__))) & 
friends.

I tried a build with 3.2.2, 3.3.1, 3.3.2 and 3.4, they are all fine. 
Note that on AMD64, you would need to arrange <xmmintrin.h> a little if 
you were to use 3.3.1-4mdk. You will have to check your headers and 
possibly report to your distributor. Look around 
ppc-dyngen-ops.cpp:1493 and try to excercise a testcase. I simply know 
that MDK compilers are fine. ;-)

Bye,
Gwenole