| Thu, 16 Oct 2008 13:34:09 +0000 |
flameeyes |
Convert asm keyword into __asm__.
libavcodec
|
| Sat, 19 Jul 2008 21:53:54 +0000 |
michael |
Fix h264_loop_filter_strength_mmx2() so it works with PAFF.
libavcodec
|
| Thu, 08 May 2008 21:11:24 +0000 |
ramiro |
Do not misuse long as the size of a register in x86.
libavcodec
|
| Tue, 01 Apr 2008 04:51:28 +0000 |
lorenm |
h264 chroma mc ssse3
libavcodec
|
| Sun, 10 Feb 2008 01:45:42 +0000 |
lorenm |
asm argument that might be in memory needs a size
libavcodec
|
| Wed, 06 Feb 2008 12:32:31 +0000 |
lorenm |
sse2 h264 motion compensation. not new code, just separate out the cases that didn't need ssse3.
libavcodec
|
| Wed, 06 Feb 2008 04:44:21 +0000 |
lorenm |
put loop counter in a register if possible. makes some of the qpel functions 3% faster.
libavcodec
|
| Wed, 06 Feb 2008 04:14:07 +0000 |
lorenm |
fix aliasing warnings. simpler too.
libavcodec
|
| Tue, 05 Feb 2008 11:22:55 +0000 |
lorenm |
ssse3 h264 motion compensation.
libavcodec
|
| Tue, 05 Feb 2008 03:58:13 +0000 |
lorenm |
add qpel rounder once during hv rather than twice during hv and whatever it's averaged with
libavcodec
|
| Tue, 05 Feb 2008 01:16:48 +0000 |
lorenm |
clean up an ugliness introduced in r11826. this syntax will require fewer changes when adding future sse2 code.
libavcodec
|
| Sun, 03 Feb 2008 16:19:37 +0000 |
lorenm |
use mmx2/3dnow avg functions in avg_qpel*_mc00
libavcodec
|
| Sun, 03 Feb 2008 07:05:11 +0000 |
lorenm |
ff_h264_idct8_add_sse2.
libavcodec
|
| Sun, 03 Feb 2008 03:21:47 +0000 |
lorenm |
remove some movq in ff_h264_idct8_add_mmx. 225->217 cycles on core2.
libavcodec
|
| Fri, 11 Jan 2008 08:29:58 +0000 |
diego |
Factorize some duplicated code from CAVS and H.264 into a common file.
libavcodec
|
| Fri, 21 Dec 2007 23:11:22 +0000 |
gpoirier |
add MMX version for put_no_rnd_h264_chroma_mc8_c, used in VC-1 decoding.
libavcodec
|
| Tue, 27 Nov 2007 22:36:15 +0000 |
aurel |
use ff_ prefix for extern vars
libavcodec
|
| Tue, 27 Nov 2007 22:23:34 +0000 |
aurel |
make ff_p* vars extern so that they can be used in various *_mmx.c files
libavcodec
|
| Thu, 11 Oct 2007 22:18:38 +0000 |
cehoyos |
Fix intended order of operations for 4 assert() checks.
libavcodec
|
| Tue, 08 May 2007 17:55:56 +0000 |
lorenm |
cosmetics: remove duplicate transpose macro
libavcodec
|
| Thu, 19 Apr 2007 16:12:06 +0000 |
reimar |
Fix parts missed in clip -> av_clip rename
libavcodec
|
| Fri, 16 Feb 2007 21:22:53 +0000 |
michael |
add a few asserts to ensure alignment
libavcodec
|
| Fri, 16 Feb 2007 21:21:07 +0000 |
michael |
prevent h.264 MC related functions from being inlined (yes this is much faster the code just doesnt fit in the code cache otherwise)
libavcodec
|
| Fri, 03 Nov 2006 16:54:05 +0000 |
michael |
ensure alignment (no speed change)
libavcodec
|
| Fri, 03 Nov 2006 16:02:18 +0000 |
michael |
merging mov & and (no speedchange)
libavcodec
|
| Fri, 03 Nov 2006 15:40:57 +0000 |
michael |
2 instructions less (same speed)
libavcodec
|
| Fri, 03 Nov 2006 15:17:36 +0000 |
michael |
comment about failed optimization
libavcodec
|
| Fri, 03 Nov 2006 14:28:30 +0000 |
michael |
move luma tc0 related init into asm
libavcodec
|
| Fri, 03 Nov 2006 12:07:53 +0000 |
michael |
2 instructions less in h264_loop_filter_luma_mmx2()
libavcodec
|
| Fri, 03 Nov 2006 11:07:35 +0000 |
michael |
preempt possible overflow
libavcodec
|
