[cairo] More info about fbCompositeCopyAreammx

[Frédéric Plourde]

Vladimir Vukicevic a écrit :
>
> On Mar 27, 2008, at 11:51 AM, Frédéric Plourde wrote:
>>
>> Remember that issue you brought up about subimage_copy with 512X512 
>> which made things slower ?
>> I've got some more news about it...
>>
>> Since Soeren questionned the precision of giving perf results with 
>> only a small number of iterations, I've used a minimum of 100 
>> iterations on my perf tests.
>> Take a look at the newest results about "subimage_copy"...
>>
>> http://pastebin.mozilla.org/383418
>>
>> First group of results shows NO GAIN between  pre-mmx and post-mmx 
>> versions
>> except for the 512X512 case alone, which shows 58% speedup... that's 
>> weird
>>
>> The second group of results shows perf GAINS between :  before 
>> applying my patch and after applying my "fbCompositeCopyArea" patch
>> But these gains, as you noticed earlier, seem to fade out as the 
>> image scales up.
>>
>> I'll investigate some more about that, but for now, I think the patch 
>> "pixman_OPT_MMX_addFastPath_to_fbCompositeCopyAreammx.patch" is worth 
>> it.
>
> Sounds good to me -- Soeren, adding an x8r8g8b8 -> a8r8g8b8 SOURCE 
> path being a Copy sounds sane, right?  Fred, I notice that your patch 
> only adds that path for the MMX case, but the same path can be added 
> for non-MMX also, I think.
>
>     - Vlad

By non-mmx, you mean the regular c_fast_paths, right ?... Then,  Yep, 
the optimization benefits there also, but it's been already done in the 
past.
The fastpath function name is not named consistently with the mmx one 
though...

see the
{ PIXMAN_OP_SRC, PIXMAN_a8r8g8b8,  PIXMAN_null,     PIXMAN_x8r8g8b8, 
fbCompositeSrc_8888xx888, 0 }, and
{ PIXMAN_OP_SRC, PIXMAN_a8b8g8r8,  PIXMAN_null,     PIXMAN_x8b8g8r8, 
fbCompositeSrc_8888xx888, 0 }, in pixman-pict.c
which both call function "fbCompositeSrc_8888xx888" that simply does the 
trick using memcpy(...) ;-)

-fred-