[XviD-devel] [CVS commit] Linux amd64 preliminary support
Guillaume POIRIER
guillaume.poirier at etudiant.univ-rennes1.fr
Fri Jan 7 14:32:44 CET 2005
Hi,
Edouard Gomez a écrit :
> Guillaume POIRIER (guillaume.poirier at etudiant.univ-rennes1.fr) wrote:
>
>
>> That's all for today, I'll try to test the qpel fix soon.
>>
>
>
> Thanks for the comparisons.
>
You're very welcome.
>
> I'll just add that for the test:
>
>
>> On IA-32
>> Pure C | XviD SIMD yasm | XviD Edouard SIMD | lavc + SIMD
>> Pass 1: 10fps | N/A | 44fps | 42fps
>> Pass 2: 3fps | N/A | 13fps | 11fps
>>
>
>
> XviD SIMD yasm would give exactly the same speed, the only difference
> between nasm and yasm output is that some short jumps are turned into
> long jumps because nasm uses one more pass over the opcodes and can
> post-determine that a long jump can be written as short jumps. But this
> small difference is absolutly not significant.
>
I'm really sorry if I confused you. What I meant is that Andre
Werthmann's port (based on XviD-1.0.2) is slower than you port based on
XviD 1.1.x
I quess I shouldn't have called it the "yasm" version but the Andre's
version.
I'd like to add also that, in this bench, all programs and libs are
compiled with gcc-3.4 and nasm, so the 1fps of different doesn't come
from there.
> You can test that simply letting the configure script doing its job, and
> then hand editing the resulting platform.inc file, changing AS+nasm to
> AS=yasm
>
I guess I can do that if ever I find the time to do so. BTW, other than
benches, do you only expect bug reports, or do I miss something?
Regards,
Guillaume
More information about the XviD-devel
mailing list