Commit Graph

167 Commits

Author SHA1 Message Date
Alex Beregszaszi
43c7c7c7cf use DECLARE_ALIGNED from mem.h (which is included through common.h)
Originally committed as revision 9015 to svn://svn.ffmpeg.org/ffmpeg/trunk
2007-05-13 14:01:15 +00:00
Loren Merritt
1edbfe1994 factor sum_abs_dctelem out of dct_sad, and simd it.
sum_abs_dctelem_* alone:
core2: c=186 mmx2=39 sse2=21 ssse3=13 (cycles)
k8: c=163 mmx2=33 sse2=31
p4: c=370 mmx2=60 sse2=60
 dct_sad including sum_abs_dctelem_*:
core2: c=405 mmx2=258 sse2=240 ssse3=232
k8: c=624 mmx2=394 sse2=392
p4: c=849 mmx2=556 sse2=556

Originally committed as revision 9001 to svn://svn.ffmpeg.org/ffmpeg/trunk
2007-05-12 02:41:25 +00:00
Diego Biurrun
2029f312e8 Remove redundant #inclusion of common.h, avcodec.h already #includes it.
Originally committed as revision 8967 to svn://svn.ffmpeg.org/ffmpeg/trunk
2007-05-10 09:00:44 +00:00
Luca Barbato
30f1505380 Typos in comments
Originally committed as revision 8561 to svn://svn.ffmpeg.org/ffmpeg/trunk
2007-03-30 20:56:32 +00:00
Loren Merritt
5900637219 mmx 16-bit ssd. 2.3x faster svq1 encoding.
Originally committed as revision 8559 to svn://svn.ffmpeg.org/ffmpeg/trunk
2007-03-30 19:15:31 +00:00
Panagiotis Issaris
9dd6c80453 Add the const specifier as needed to reduce the number of warnings.
Originally committed as revision 7764 to svn://svn.ffmpeg.org/ffmpeg/trunk
2007-01-30 10:31:34 +00:00
Guillaume Poirier
5a5c770d5a Add SSSE3 (Core2 aka Conroe/Merom/Woodcrester new instructions) detection
Originally committed as revision 7332 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-12-18 22:43:09 +00:00
Michael Niedermayer
6dc7d5da70 ff_check_alignment to warn the user about a missaligned stack
Originally committed as revision 7249 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-12-07 18:33:00 +00:00
Panagiotis Issaris
f1862127f5 Added entry for H.264 DCT to the DSP context.
Originally committed as revision 7247 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-12-07 16:09:33 +00:00
Panagiotis Issaris
ea9f5d6f76 Add comment denoting group of H.264 functions
Originally committed as revision 7227 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-12-05 21:57:31 +00:00
Reimar Döffinger
cf1e119bb2 Move BE_*/LE_*/ST*/LD* macros to a common place. Some further
optimization/cleanup would be desirable (e.g. LE_* and LD*
should be the same on x86).

Originally committed as revision 7218 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-12-03 16:35:30 +00:00
Brian Foley
49cef7443a Move copy_block* functions to dsp dsputil.h
Patch by Brian Foley % bfoley A compsoc P nuigalway P ie %
Original thread:
Date: Nov 26, 2006 6:44 PM
Subject: Re: [Ffmpeg-devel] [PATCH] put_mpeg4_qpel16_h_lowpass altivec, take 2

Originally committed as revision 7172 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-11-26 18:25:07 +00:00
Kostya Shishkov
61f5b14a8e Correct rounding values in overlap filtering
Originally committed as revision 7171 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-11-26 04:57:31 +00:00
Måns Rullgård
486497e07b revert bad checkin
Originally committed as revision 7044 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-11-14 03:18:09 +00:00
Måns Rullgård
be6ed6fff4 move some CFLAGS settings away from config.* writing section
Originally committed as revision 7043 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-11-14 03:12:29 +00:00
Måns Rullgård
1d50395746 rename squareTbl -> ff_squareTbl
Originally committed as revision 6995 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-11-12 21:48:04 +00:00
Måns Rullgård
55fde95e3b rename cropTbl -> ff_cropTbl
Originally committed as revision 6992 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-11-12 20:08:09 +00:00
Diego Biurrun
b78e7197a8 Change license headers to say 'FFmpeg' instead of 'this program/this library'
and fix GPL/LGPL version mismatches.

Originally committed as revision 6577 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-07 15:30:46 +00:00
Loren Merritt
2833fc4646 approximate qpel functions: sacrifice some quality for some decoding speed. enabled on B-frames with -lavdopts fast.
Originally committed as revision 6412 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-01 21:25:17 +00:00
Loren Merritt
ebbafcb454 sse implementation of imdct.
patch mostly by Zuxy Meng (zuxy dot meng at gmail dot com)

Originally committed as revision 6311 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-09-21 16:37:39 +00:00
Michael Benjamin
5ca030fed4 ADI Blackfin optimizations
patch by Michael Benjamin, neuroptik gmail com

Originally committed as revision 6282 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-09-16 22:26:09 +00:00
Kostya Shishkov
6243da0d50 Drop put_vc1_qpel_pixels_tab as they won't be needed anymore.
Originally committed as revision 6152 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-09-02 04:58:51 +00:00
Kostya Shishkov
e34350a376 New function for chroma MC (will be used in VC-1)
Originally committed as revision 6150 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-09-02 04:52:00 +00:00
Luca Barbato
9814587500 Align the input buffer in ffplay, introduce a public macro for aligned declarations
Update the avcodec_decode_audio and the float_to_int16 descriptions accordingly

Originally committed as revision 6147 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-31 19:14:00 +00:00
Kostya Shishkov
74691b7bcb New qpel MC functions conforming to VC-1 standard.
Existing DSPUtil functions cause chroma artifacts on some files.

Originally committed as revision 6139 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-31 04:44:54 +00:00
Loren Merritt
3e20143ee7 mmx implementation of deblocking strength decision.
2-3% faster h264.

Originally committed as revision 6113 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-28 09:33:01 +00:00
Loren Merritt
069720565c vorbis simd tweaks
Originally committed as revision 5983 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-11 18:19:37 +00:00
Loren Merritt
eb4825b5d4 sse and 3dnow implementations of float->int conversion and mdct windowing.
15% faster vorbis.

Originally committed as revision 5975 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-10 19:06:25 +00:00
Loren Merritt
bcfa3e58ee 3dnow2 implementation of imdct.
6% faster vorbis and wma.

Originally committed as revision 5954 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-08 04:01:04 +00:00
Loren Merritt
2dac4acfc0 sse & sse2 implementations of vorbis channel coupling.
9% faster vorbis (on a K8).

Originally committed as revision 5898 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-03 03:18:47 +00:00
Kostya Shishkov
64db55aedb New functions in DSPContext for VC-1 decoding
Originally committed as revision 5862 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-07-30 03:45:02 +00:00
Michael Niedermayer
b482e2d12f CAVS decoder by (Stefan Gehrer stefan.gehrer gmx.de)
Originally committed as revision 5590 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-07-03 00:16:45 +00:00
Zuxy Meng
392f6da897 Remove unused and unsupported Cyrix's "Extended MMX",
Add SSE3 support.
Patch by Zuxy Meng < zuxy POIS meng AH gmail POIS com >
Original thread:
04/26/06 13:13:
[Ffmpeg-devel] [PATCH] Bug fix,	SSE3 support in i386/cputest.c and dsputil.h

Originally committed as revision 5326 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-04-28 07:46:13 +00:00
Loren Merritt
703c8195a8 mmx implementation of 3-point GMC. (5x faster than C)
Originally committed as revision 5265 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-04-04 09:23:45 +00:00
Michael Niedermayer
54009d4295 remove mpegvideo.c img resample dependancy
Originally committed as revision 5258 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-03-31 20:43:37 +00:00
Steve L'Homme
dc2bf20e27 ST16 is undefined for non-GNU compilers.
Patch by Steve Lhomme <slhomme at divxcorp com>

Originally committed as revision 5206 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-03-24 01:33:22 +00:00
Loren Merritt
513fbd8e5a prefetch pixels for future motion compensation. 2-5% faster h264.
Originally committed as revision 5203 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-03-23 20:16:36 +00:00
Robert Edele
059715a41c First part of a series of speed-enchancing patches.
This one sets up a snow.h and makes snow use the dsputil function pointer
framework to access the three functions that will be implemented in asm
in the other parts of the patchset.
Patch by Robert Edele < yartrebo AH earthlink POIS net>
Original thread:
Subject: [Ffmpeg-devel] [PATCH] Snow mmx+sse2 asm optimizations
Date: Sun, 05 Feb 2006 12:47:14 -0500

Originally committed as revision 5172 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-03-16 19:18:18 +00:00
Zuxy Meng
82eb4b0f1b 3DNow! & Extended 3DNow! versions of FFT
Patch by Zuxy Meng, zuxy <<dot>> meng >>at<< gmail <<dot>> com
Minor non-functional diff-related fixes by me.

Originally committed as revision 5125 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-03-08 04:13:55 +00:00
Loren Merritt
ef9d1d1575 h264: special case dc-only idct. ~1% faster overall
Originally committed as revision 4971 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-02-10 06:55:25 +00:00
Steve L'Homme
68b51e58ce MSVC-compatible __align8/__align16 declaration
patch by Steve Lhomme, steve .dot. lhomme .at. free .dot. fr

Originally committed as revision 4942 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-02-05 13:35:17 +00:00
Diego Biurrun
5509bffa88 Update licensing information: The FSF changed postal address.
Originally committed as revision 4842 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-01-12 22:43:26 +00:00
Loren Merritt
e8b562087d tweak h264_biweight
Originally committed as revision 4835 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-01-09 03:38:37 +00:00
Michael Niedermayer
80e44bc3bf use h264 MC functions for 2xX Xx2 blocks in snow too
Originally committed as revision 4824 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-01-08 01:50:34 +00:00
Michael Niedermayer
27c61ac53d 8x8 integer dct from x264 as cmp function (under CONFIG_GPL)
if this gives better quality then SATD then someone should port the x86 code too or maybe we could even just call it from libx264
the 4x4 one could be tried too ...

Originally committed as revision 4811 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-01-04 16:31:23 +00:00
Diego Biurrun
bb270c0896 COSMETICS: tabs --> spaces, some prettyprinting
Originally committed as revision 4764 to svn://svn.ffmpeg.org/ffmpeg/trunk
2005-12-22 01:10:11 +00:00
Diego Biurrun
115329f160 COSMETICS: Remove all trailing whitespace.
Originally committed as revision 4749 to svn://svn.ffmpeg.org/ffmpeg/trunk
2005-12-17 18:14:38 +00:00
Diego Biurrun
7df6545556 Move lrintf implementation from libavcodec/dsputil.h to libavutil/common.h
where it makes more sense.

Originally committed as revision 4599 to svn://svn.ffmpeg.org/ffmpeg/trunk
2005-09-19 23:26:47 +00:00
Gildas Bazin
eba9ae3cfc IWMMXT configure support + runtime selection patch by (Gildas Bazin, gbazin : altern org)
Originally committed as revision 4409 to svn://svn.ffmpeg.org/ffmpeg/trunk
2005-06-28 22:46:36 +00:00
Loren Merritt
36940eca76 H.264 lossless mode
Originally committed as revision 4381 to svn://svn.ffmpeg.org/ffmpeg/trunk
2005-06-17 08:24:35 +00:00