Wed, 15 Apr 2009 19:10:16 +0000 |
conrad |
avg_ pixel functions need to use (dst+pix+1)>>1 to average with existing
libavcodec
|
Wed, 15 Apr 2009 02:25:42 +0000 |
conrad |
VC1: extend MMX qpel MC to include MMX2 avg qpel
libavcodec
|
Tue, 14 Apr 2009 23:56:10 +0000 |
conrad |
VC1: add and use avg_no_rnd chroma MC functions
libavcodec
|
Tue, 14 Apr 2009 23:55:39 +0000 |
conrad |
Rename put_no_rnd_h264_chroma* to reflect its usage in VC1 only
libavcodec
|
Sat, 04 Apr 2009 13:20:53 +0000 |
stefano |
Rename FF_MM_MMXEXT to FF_MM_MMX2, for both clarity and consistency
libavcodec
|
Fri, 03 Apr 2009 14:03:49 +0000 |
reimar |
Mark line_skip3 asm argument as output-only instead of using av_uninit.
libavcodec
|
Fri, 03 Apr 2009 14:02:34 +0000 |
reimar |
Mark put_signed_pixels_clamped_mmx output operands as early-clobber because
libavcodec
|
Fri, 03 Apr 2009 14:01:24 +0000 |
reimar |
Use DECLARE_ASM_CONST for non-global ff_vector128 constant used via MANGLE
libavcodec
|
Thu, 02 Apr 2009 21:02:42 +0000 |
alexc |
Rewrite put_signed_pixels_clamped_mmx() to eliminate mmx.h from dsputil_mmx.c.
libavcodec
|
Fri, 13 Feb 2009 00:02:33 +0000 |
aurel |
add SSE2 version of vp6_filter_diag
libavcodec
|
Thu, 12 Feb 2009 23:52:52 +0000 |
aurel |
add MMX version of vp6_filter_diag
libavcodec
|
Thu, 12 Feb 2009 23:48:07 +0000 |
aurel |
convert ff_pw_64 into an xmm_reg for future use in vp6 sse code
libavcodec
|
Wed, 11 Feb 2009 11:16:00 +0000 |
diego |
Add check whether the compiler/assembler supports 10 or more operands.
libavcodec
|
Sun, 08 Feb 2009 17:45:30 +0000 |
lorenm |
ff_add_hfyu_median_prediction_mmx2
libavcodec
|
Mon, 26 Jan 2009 03:40:48 +0000 |
conrad |
Workaround for gcc 3.4 to align sh properly
libavcodec
|