[FFmpeg-cvslog] random thoughts about refactoring

Alexander Strange astrange
Mon Jan 11 00:05:36 CET 2010



On Jan 10, 2010, at 5:16 PM, compn <tempn at twmi.rr.com> wrote:

> On Sun, 10 Jan 2010 22:23:34 +0100, Michael Niedermayer wrote:
>> On Sun, Jan 10, 2010 at 02:48:00PM -0500, compn wrote:
>>> On Sun, 10 Jan 2010 17:42:24 +0100, Michael Niedermayer wrote:
>>>> On Sun, Jan 10, 2010 at 12:44:24PM +0100, Diego Biurrun wrote:
>>>>> On Fri, Jan 08, 2010 at 02:28:16AM +0100, Michael Niedermayer  
>>>>> wrote:
>>>>>> On Fri, Jan 08, 2010 at 01:20:03AM +0100, Diego Biurrun wrote:
>>>>>>> On Wed, Jan 06, 2010 at 06:38:14PM +0100, Michael Niedermayer  
>>>>>>> wrote:
>>>>>>>> On Tue, Jan 05, 2010 at 11:08:22PM +0100, Diego Biurrun wrote:
>>>>>>>>> On Tue, Jan 05, 2010 at 08:43:51PM +0100, Michael  
>>>>>>>>> Niedermayer wrote:
>>>>>>>>>> On Tue, Jan 05, 2010 at 11:29:46AM +0100, Diego Biurrun  
>>>>>>>>>> wrote:
>>>>>>>>>>> On Tue, Jan 05, 2010 at 03:20:47AM +0100, Michael  
>>>>>>>>>>> Niedermayer wrote:
>>>>>>>>>>>> On Mon, Jan 04, 2010 at 08:23:23PM +0100, Diego Biurrun  
>>>>>>>>>>>> wrote:
>>>>>>>>> There are people here who know H.264 well enough to lend
>>>>>>>>> a helping hand in theory, but in practice the implementation  
>>>>>>>>> in lavc is
>>>>>>>>> just too impenetrable.  h264.c is around 10.000 lines if you  
>>>>>>>>> count svq3.c
>>>>>>>>> which it directly includes!
>>>>>>>>
>>>>>>>>>
>>>>>>>>> Also, our H.264 decoder is not a speed demon.
>>>>>>>>
>>>>>>>> That seems to depend on CPU and situation, gcc making poor  
>>>>>>>> inlining choices
>>>>>>>> and overflowing the available caches is not exactly the codes  
>>>>>>>> fault ...
>>>>>>>
>>>>>>> Carl Eugen was the first person I have ever heard claim that our
>>>>>>> H.264 decoder was faster than anything, ever...
>>>>>>
>>>>>> Ive never tried CoreAVC, but i can assure you the reference  
>>>>>> implementation
>>>>>> is much much slower
>>>>>
>>>>> You are referring to the H.264 reference implementation?
>>>>>
>>>>> Jason mentioned two new H.264 decoders on IRC that are even  
>>>>> faster than
>>>>> CoreAVC...
>>>>
>>>> Why is this information not posted on the mailing list ?
>>>
>>> i'll paste some relevent irc chat:
>>
>> thank you!
>> while not as usefull as i thought, it is usefull.
>
> here is some more, probably more useful.
>
> [16:23] <astrange> http://github.com/astrange/ffmpeg/commits/h264
> [16:23] <astrange> i kept not testing those because i always have  
> vmware open, so it adds too much benchmark noise
> [16:23] <astrange> maybe i should get a shell somewhere else

I'll go through these tonight. But they work best when statically  
compiled for SSE2/Altivec/etc, so most binary distributions wouldn't  
benefit much.

> [16:28] <astrange> http://github.com/astrange/ffmpeg/commit/4964d8dede05662da59becaacbb2f3f0c5462cdd 
>  oh, i submitted this one with a slight speedup but didn't get a  
> practical reply
> [16:28] <astrange> though it might be cpu dependent
> [16:29] <Dark_Shikari> astrange: you should really just be able to  
> commit that imo...
> [16:29] <Dark_Shikari> doesn't that free up a register too?

One more read (maybe forwarded), slightly more ILP. I can't find the  
thread on this phone.



More information about the ffmpeg-cvslog mailing list