[x264-devel] Re: OSX Intel breakage..

[Guillaume POIRIER]

Salut,


On 11/7/06, Felix Kühne <fk at aenneburghardt.de> wrote:
> Hello,
>
> sorry for the late response. Here's the backtrace (which is pretty
> short, but somehow I can't produce a longer one) plus some other dumps:

Well, it's enough to see the problem.


> #0  0x057dc695 in x264_pixel_satd_8x8_sse2 ()
> #1  0x05788bb6 in x264_slicetype_mb_cost ()
> Previous frame inner to this frame (corrupt stack?)
>
> Dump of assembler code from 0x57dc675 to 0x57dc6b5:
> 0x057dc675 <x264_pixel_satd_8x8_sse2+662>:      paddusw %mm1,%mm0
> 0x057dc678 <x264_pixel_satd_8x8_sse2+665>:      paddusw %xmm3,%xmm2
> 0x057dc67c <x264_pixel_satd_8x8_sse2+669>:      paddusw %xmm0,%xmm6
> 0x057dc680 <x264_pixel_satd_8x8_sse2+673>:      paddusw %xmm2,%xmm6
> 0x057dc684 <x264_pixel_satd_8x8_sse2+677>:      psrlw  $0x1,%xmm6
> 0x057dc689 <x264_pixel_satd_8x8_sse2+682>:      call   0x57dc68e
> <x264_pixel_satd_8x8_sse2+687>
> 0x057dc68e <x264_pixel_satd_8x8_sse2+687>:      pop    %ebx
> 0x057dc68f <x264_pixel_satd_8x8_sse2+688>:      add    $0xffffd4a1,%ebx
> 0x057dc695 <x264_pixel_satd_8x8_sse2+694>:      pmaddwd (%ebx),%xmm6


[..]

> info all-registers:
> eax            0xb0506a30       -1336907216
> ecx            0x7ecdf20        132964128
> edx            0x10     16
> ebx            0x57d9b2f        92117807

[..]

As you can see, pmaddwd is used with an unaligne address, which causes
the crash. I don't know how to fix this right now though...

Guillaume
-- 
With DADVSI (http://en.wikipedia.org/wiki/DADVSI), France finally has
a lead on USA on selling out individuals right to corporations!
Vive la France!

-- 
This is the x264-devel mailing-list
To unsubscribe, go to: http://developers.videolan.org/lists.html