[FFmpeg-devel] [PATCH] Make MMX2 put_no_rnd_pixels _x2 and _y2 bitexact

David Conrad lessen42
Fri Jun 4 06:46:26 CEST 2010


On Jun 1, 2010, at 11:30 AM, Michael Niedermayer wrote:

> On Mon, May 31, 2010 at 08:00:03PM -0400, David Conrad wrote:
>> On May 30, 2010, at 12:39 PM, Michael Niedermayer wrote:
>> 
>>> On Fri, May 28, 2010 at 06:27:41PM -0400, David Conrad wrote:
>>>> On May 28, 2010, at 6:25 PM, Stefan Gehrer wrote:
>>>> 
>>>>> On 05/28/2010 11:49 PM, David Conrad wrote:
>>>>>> Hi,
>>>>>> 
>>>>>> The mmx2/3dnow put_no_rnd functions don't always round correctly, since they compensate for the +1 in pavgb by subtracting 1 from one of the inputs. This causes our theora decoder to not be bitexact to libtheora, though I haven't found any real source where the error accumulates enough to be visible.
>>>>>> 
>>>>>> This fixes it by using the property that (a+b)>>1 is equivalent to ~(~a+~b+1)>>1. This makes these functions 5 cycles slower on my penryn, but on my atom the additional instructions appear to be free probably due to load stalls.
>>>>> 
>>>>> Wouldn't it be worth creating new bitexact functions, but still
>>>>> override them with the old/faster ones if BITEXACT is not set?
>>>> 
>>>> The problem is that theora must always be bitexact, and codecs can't set the bitexact flag themselves.
>>> 
>>> if you still want it, you could change the used functions under
>>> if(codec_id == CODEC_ID_THEORA)
>> 
>> Like so?
>> 
> 
>> commit 01049d1c24d450a9247acec6f0f52a9db9ffa55b
>> Author: David Conrad <lessen42 at gmail.com>
>> Date:   Fri May 28 02:20:58 2010 -0400
>> 
>>    Add bitexact versions of put_no_rnd_pixels8 _x2 and _y2 for vp3/theora
> 
> if you want thatm then ok

Applied.



More information about the ffmpeg-devel mailing list