| Mon, 03 Nov 2008 18:08:00 +0000 |
rathann |
Remove duplicated MM_* macros for CPU capabilities from dsputil.h.
libavcodec
|
| Mon, 27 Oct 2008 14:35:58 +0000 |
flameeyes |
Rename template included sources from .h to _template.c.
libavcodec
|
| Mon, 20 Oct 2008 16:05:29 +0000 |
reimar |
Use x86_reg type instead of long in float_to_int16 MMX/SSE functions.
libavcodec
|
| Sun, 19 Oct 2008 04:44:24 +0000 |
conrad |
Cosmetics: reindent
libavcodec
|
| Sun, 19 Oct 2008 04:43:35 +0000 |
conrad |
Combine non-bitexact sections
libavcodec
|
| Sun, 19 Oct 2008 04:40:24 +0000 |
conrad |
VP3 loop filter is mmx2 not mmx
libavcodec
|
| Fri, 17 Oct 2008 03:18:08 +0000 |
conrad |
MMX VP3 Loop Filter
libavcodec
|
| Thu, 16 Oct 2008 13:34:09 +0000 |
flameeyes |
Convert asm keyword into __asm__.
libavcodec
|
| Wed, 17 Sep 2008 19:49:31 +0000 |
conrad |
Ensure MMX/SSE2 VP3 IDCT selection isn't disabled when only Theora is enabled
libavcodec
|
| Wed, 17 Sep 2008 19:30:03 +0000 |
conrad |
MMX/SSE2 VP3 IDCT are bitexact now that the dequantization matrices are permutated correctly
libavcodec
|
| Sun, 31 Aug 2008 07:05:55 +0000 |
conrad |
Use ff_vp3_idct_data in vp3dsp_mmx.c rather than duplicating it
libavcodec
|
| Sat, 30 Aug 2008 19:40:21 +0000 |
conrad |
Let ff_pw_8 be used as an SSE constant
libavcodec
|
| Thu, 14 Aug 2008 04:40:46 +0000 |
lorenm |
gcc chokes on the 7 registers needed for float_to_int16_interleave6 (even inside HAVE_7REGS), so write it in yasm
libavcodec
|
| Thu, 14 Aug 2008 04:39:59 +0000 |
lorenm |
gcc chokes on xmm constraints, so pessimize int32_to_float_fmul_scalar_sse a little
libavcodec
|
| Wed, 13 Aug 2008 23:36:37 +0000 |
lorenm |
special case 6 channel version of float_to_int16_interleave
libavcodec
|
| Wed, 13 Aug 2008 23:35:40 +0000 |
lorenm |
simd int->float
libavcodec
|
| Wed, 13 Aug 2008 23:33:48 +0000 |
lorenm |
simd downmix
libavcodec
|
| Tue, 12 Aug 2008 00:51:45 +0000 |
lorenm |
cosmetics in dsp init
libavcodec
|
| Sat, 02 Aug 2008 17:32:55 +0000 |
diego |
Mark add_png_paeth_prediction_* functions which are only used within this file
libavcodec
|
| Wed, 16 Jul 2008 00:50:12 +0000 |
lorenm |
float_to_int16_interleave: change src to an array of pointers instead of assuming it's contiguous.
libavcodec
|
| Tue, 15 Jul 2008 04:11:30 +0000 |
lorenm |
10l, float_to_int16_interleave_sse/3dnow wrote the wrong samples
libavcodec
|
| Sun, 13 Jul 2008 15:03:58 +0000 |
lorenm |
exploit mdct symmetry
libavcodec
|
| Sun, 13 Jul 2008 14:56:01 +0000 |
lorenm |
simplify vorbis windowing
libavcodec
|
| Fri, 11 Jul 2008 04:48:38 +0000 |
kostya |
SSE2 optimizations for Monkey's Audio decoder vector functions
libavcodec
|
| Wed, 09 Jul 2008 07:21:12 +0000 |
michael |
float_to_int16_sse2()
libavcodec
|
| Mon, 07 Jul 2008 21:25:18 +0000 |
michael |
1 c-asm loop less and 1x unroll of float_to_int16_sse()
libavcodec
|
| Mon, 07 Jul 2008 21:04:29 +0000 |
michael |
Fix x86-64
libavcodec
|
| Mon, 07 Jul 2008 20:46:03 +0000 |
michael |
dont use C-asm loops and unroll once float_to_int16_3dnow()
libavcodec
|
| Sun, 22 Jun 2008 07:05:40 +0000 |
reimar |
Fix add_bytes_mmx and add_bytes_l2_mmx for w < 16
libavcodec
|
| Fri, 09 May 2008 11:56:36 +0000 |
diego |
Use full path for #includes from another directory.
libavcodec
|
