Mercurial > libavcodec.hg
graph
-
avoid a few if(x==0) checks in the inner loops libavcodecThu, 24 Aug 2006 11:18:41 +0000, by michael
-
optimize reorder_block() though this function seems to be executed too rarely for this to make much difference libavcodecThu, 24 Aug 2006 08:40:09 +0000, by michael
-
faster handling of zero coeffs in the low freq decode libavcodecThu, 24 Aug 2006 01:12:26 +0000, by michael
-
Alignment of the LT window, segfault fix patch by Baptiste Coudurier. libavcodecTue, 22 Aug 2006 16:23:56 +0000, by banan
-
MUL* for ARM code based on a patch by Siarhei Siamashka libavcodecTue, 22 Aug 2006 13:25:09 +0000, by michael
-
replace MULL with asm too, no significnat speedup but its probably better to not take any chances, some versions of gcc will almost certainly mess it up too if they can libavcodecTue, 22 Aug 2006 12:07:02 +0000, by michael
-
make high precission synth filter 3 times faster on x86 libavcodecTue, 22 Aug 2006 11:11:04 +0000, by michael
-
replace MULL by MULH + shift in dct32() (code is very slightly faster, and the compiler should be able to optimize the shift away on 64bit archs) libavcodecTue, 22 Aug 2006 06:24:59 +0000, by michael
-
reorder butterflies to reduce memory load/store libavcodecSun, 20 Aug 2006 22:18:26 +0000, by michael
-
Allow swscale emulation header to be included by C++ programs libavcodecSat, 19 Aug 2006 15:14:44 +0000, by lucabe
-
SIMD vector optimizations. 3% faster overall decoding. libavcodecSat, 19 Aug 2006 08:46:52 +0000, by banan
-
ff_fft_calc_3dn/3dn2/sse: convert intrinsics to inline asm. libavcodecFri, 18 Aug 2006 23:53:49 +0000, by lorenm
-
Add YV12 support, patch by Steve Lhomme % steve P lhomme A free P fr % libavcodecFri, 18 Aug 2006 07:55:08 +0000, by gpoirier
-
Move all internal -I parameters to the front of CFLAGS to avoid using external libavcodecThu, 17 Aug 2006 16:32:08 +0000, by diego
-
10l, thanks to Emanuele Giaquinta <exg@gentoo.org> for testing and finding the issue libavcodecTue, 15 Aug 2006 20:36:05 +0000, by lu_zero
-
Compile fix (for GCC<3.3) when encoders are disabled libavcodecTue, 15 Aug 2006 14:59:27 +0000, by gpoirier
-
Fix building with --disable-opts but MMX enabled. libavcodecSun, 13 Aug 2006 10:10:06 +0000, by diego
-
Clean up:make dsputil subfile names consistent libavcodecSun, 13 Aug 2006 08:26:43 +0000, by lu_zero
-
Support for MacIntel, last part: balign directives libavcodecSat, 12 Aug 2006 16:37:31 +0000, by gpoirier
-
Fix CHECK_BIDIR macro so it works with Intel's Compiler libavcodecSat, 12 Aug 2006 16:31:17 +0000, by gpoirier
-
Disable B-frames decoding until I return and finish their proper decoding. libavcodecFri, 11 Aug 2006 04:41:30 +0000, by kostya
-
keep in sync with dsputil, makes --disable-decoder=vorbis build libavcodecFri, 11 Aug 2006 02:56:32 +0000, by lu_zero
-
convert vector_fmul_reverse_sse2 and vector_fmul_add_add_sse2 to sse libavcodecThu, 10 Aug 2006 20:24:58 +0000, by michael
-
sse and 3dnow implementations of float->int conversion and mdct windowing. libavcodecThu, 10 Aug 2006 19:06:25 +0000, by lorenm
-
r5954 broke fft on cpus with 3dnow but without mm3dnow.h libavcodecThu, 10 Aug 2006 18:49:47 +0000, by lorenm
-
Fix x86 SIMD asm and pic, patch from Martin von Gagern <Martin.vGagern@gmx.net> libavcodecThu, 10 Aug 2006 16:05:29 +0000, by lu_zero
-
Support for MacIntel, take xx: '/nop' illegal for old versions of GAS libavcodecThu, 10 Aug 2006 15:26:18 +0000, by gpoirier
-
Add support for Mac OS X Intel part 2: Assembler macros in fdct_mmx.c libavcodecThu, 10 Aug 2006 11:29:57 +0000, by gpoirier
-
Support for Mac OS X Intel, part 3: binary integer constants: libavcodecThu, 10 Aug 2006 09:06:06 +0000, by gpoirier
-
gcc 2.95 and 3.4.x on x86 32bit without fomit-frame-pointer can't even find 5 registers for asm input. libavcodecWed, 09 Aug 2006 06:33:49 +0000, by lorenm
-
slightly faster ff_imdct_calc_3dn2() on amd64. (gcc added a bunch of useless movsxd) libavcodecTue, 08 Aug 2006 21:47:11 +0000, by lorenm
-
change vorbis_inverse_coupling_sse2() so it works on sse1 cpus libavcodecTue, 08 Aug 2006 12:03:51 +0000, by michael
-
Fix some "'static' is not at beginning of declaration" warnings. libavcodecTue, 08 Aug 2006 10:24:26 +0000, by diego
-
Correct MC for B-frames and some improvements (not 100% complete though) libavcodecSun, 06 Aug 2006 03:44:31 +0000, by kostya
-
Bicubic interpolation requires two additional pixels for block libavcodecSun, 06 Aug 2006 03:42:39 +0000, by kostya
-
printf -> av_log, only occurs in DEBUG cases libavcodecFri, 04 Aug 2006 22:51:20 +0000, by melanson
-
Fix a stupid typo and another error, thanks to Emanuele Giaquinta <exg@gentoo.org> for pointing out the issue and the patch libavcodecFri, 04 Aug 2006 19:03:01 +0000, by lu_zero
-
100l: intensity compensation must be also done in 4-MV mode libavcodecFri, 04 Aug 2006 03:31:01 +0000, by kostya
-
Almost cosmetic changes in dsputil_init_ppc and vorbis_inverse_coupling_altivec: libavcodecThu, 03 Aug 2006 16:13:50 +0000, by lu_zero
-
avoid alignment hacks, luckly gcc does the right thing on arches different from x86 libavcodecThu, 03 Aug 2006 13:21:13 +0000, by lu_zero
-
10l, vorbis_inverse_coupling_sse() was really 3dnow libavcodecThu, 03 Aug 2006 07:09:29 +0000, by lorenm
-
another div -> fastdiv, another 2% faster vorbis. libavcodecThu, 03 Aug 2006 06:07:13 +0000, by lorenm
-
Looks like to be a good time to re-enable WMV3 decoder libavcodecThu, 03 Aug 2006 05:15:50 +0000, by kostya
-
Don't try to decode P-frames from old WMV3 variant until their format is figured libavcodecThu, 03 Aug 2006 05:09:36 +0000, by kostya
-
sse & sse2 implementations of vorbis channel coupling. libavcodecThu, 03 Aug 2006 03:18:47 +0000, by lorenm
-
int16_t is faster than int_fast16_t for division. libavcodecThu, 03 Aug 2006 02:18:07 +0000, by lorenm
-
Use bicubic MC (should also remove those ringing artifacts) when needed libavcodecSun, 30 Jul 2006 03:50:31 +0000, by kostya
-
Remove spurious references to Ogg Theora encoder, such a thing never existed. libavcodecSat, 29 Jul 2006 20:47:47 +0000, by diego
-
Set MpegEncContext->mspel flag (here it indicates that bicubic MC will be use) libavcodecSat, 29 Jul 2006 03:11:14 +0000, by kostya
-
Remove sws_global_init() from swscaler emulation libavcodecThu, 27 Jul 2006 12:31:31 +0000, by lucabe
-
Some B-frames support (parsing and decoding only, no motion compesation is done) libavcodecMon, 24 Jul 2006 04:24:53 +0000, by kostya
-
Do not crash when the first frame is not a keyframe (and thus none of the libavcodecSun, 23 Jul 2006 18:22:29 +0000, by reimar
-
Replace code for clipping MV vectors (which is wrong to use here) with clipping source coords. libavcodecSat, 22 Jul 2006 03:57:53 +0000, by kostya
-
Don't do non-uniform quantization on zero coeffs. libavcodecSat, 22 Jul 2006 03:54:00 +0000, by kostya
-
1000l: scale DC predictors instead of predicted value. libavcodecFri, 21 Jul 2006 04:06:06 +0000, by kostya
-
Set DC = 0 for skipped MB as it interferes DC prediction libavcodecFri, 21 Jul 2006 04:03:56 +0000, by kostya
-
Set correctly quantizer and transform mode when parsing frame header. libavcodecFri, 21 Jul 2006 03:58:48 +0000, by kostya
-
remove 166 useless underscores, and make this file valid c code as a result libavcodecWed, 19 Jul 2006 23:21:20 +0000, by michael
-
remove a few useless casts and avoid the useless t1/t2 variables libavcodecWed, 19 Jul 2006 23:17:18 +0000, by michael
-
disable the vp3 mmx and sse2 idcts, their output doesnt match the c idct (tested with -f crc) and the theora spec does not allow different idcts not to mention the difference is quite vissible ... libavcodecWed, 19 Jul 2006 09:49:21 +0000, by michael
-
Move av_malloc(), av_realloc(), and av_free() from libavcodec to libavutil libavcodecWed, 19 Jul 2006 07:28:58 +0000, by lucabe
-
parse all QIS values (we still ignore them though ...) libavcodecMon, 17 Jul 2006 13:09:45 +0000, by michael