[FFmpeg-devel] [PATCH] Move CPU detection to libavutil and cleanup

[Måns Rullgård]

Stefano Sabatini <stefano.sabatini-lala at poste.it> writes:

> On date Sunday 2010-07-04 03:59:34 +0100, M?ns Rullg?rd encoded:
>> Eli Friedman <eli.friedman at gmail.com> writes:
>> 
>> > 2010/7/3 M?ns Rullg?rd <mans at mansr.com>:
>> >> Baptiste Coudurier <baptiste.coudurier at gmail.com> writes:
>> >>
>> >>> On 7/3/10 6:27 PM, Eli Friedman wrote:
>> >>>> On Sat, Jul 3, 2010 at 4:41 PM, Baptiste Coudurier
>> >>>> <baptiste.coudurier at gmail.com> ?wrote:
>> >>>>> On 7/3/10 8:06 AM, Carl Eugen Hoyos wrote:
>> >>>>>>
>> >>>>>> Baptiste Coudurier<baptiste.coudurier<at> ? ?gmail.com> ? ?writes:
>> >>>>>>
>> >>>>>>> Here is my first attempt to port yadif to libavfilter.
>> >>>>>>
>> >>>>>> Did you see this version which contains some SSE3 optimisations?
>> >>>>>> http://avisynth.org.ru/yadif/yadif.html
>> >>>>>>
>> >>>>>> There were also posts to mplayer-devel with optimisations:
>> >>>>>>
>> >>>>>> http://lists.mplayerhq.hu/pipermail/mplayer-dev-eng/2008-November/058981.html
>> >>>>>> http://article.gmane.org/gmane.comp.video.mplayer.devel/50353
>> >>>>>> (Thread very broken)
>> >>>>>
>> >>>>> Yes, I saw them.
>> >>>>> I think it's better to have the original version in svn.
>> >>>>> Afterwards, I'm sure optimizations gurus here will have a shot at it :)
>> >>>>>
>> >>>>> Nonetheless, I'm a bit stuck at porting mm_support to libavutil.
>> >>>>
>> >>>> Stuck? ?What's the issue?
>> >>>
>> >>> It fails linking when using shared libraries, and it needs renaming to
>> >>> av_mm_support and av_mm_flags.
>> >>
>> >> The whole thing is a mess. ?I think we should take this chance to
>> >> clean it up.
>> >>
>> >> Firstly, there is no need to store the flags in a global variable.
>> >> Every place using them calls the detection function anyway. ?If
>> >> detecting the flags is slow, the result can be cached in a static
>> >> variable within the function instead.
>> >
>> > Not quite... the one place where this is an issue is emms_c(); I
>> > strongly doubt we want to run CPU detection on every call to that.
>> 
>> How about instead making it compile-time conditional on ARCH_X86_32 &&
>> HAVE_MMX?  If there are still people around with non-mmx x86 machines,
>> they'd have to disable it when building, but what the hell.  It would
>> save a few cycles per call everywhere else.
>> 
>> This is also another absurd name we should fix.
>
> Updated with a less absurd name and with actually moving the code (not
> only the declaration of the interface) from libavcodec to libavutil.
>
> I preferred to put all the code in a single cpuid.c file rather than
> split the code in various x86/ppc/arm, also because this way it looked
> simpler.

Arch-specific code goes in the arch dirs.  No discussion.

> FF_MM_* flags also maybe should be renamed something like:
>
> AV_CPU_MM_FLAG_*
> or maybe:
> AVCPU_MM_FLAG_*
>
> Please review it, regards.

Didn't we mostly agree on dropping the global mm_flags (used only in
emms_c())?  A patch for that is underway as soon as it finishes
testing here.  Getting rid of that global should reduce the size of
this patch significantly.

-- 
M?ns Rullg?rd
mans at mansr.com