2006-08-26 |
michael |
10l found by valgrind
libavcodec
|
2006-08-26 |
michael |
remove duplicated parser, people who pass random gibblets of the bitstream into the decoder will have to pass it through a AVParser like for all other codecs too
libavcodec
|
2006-08-26 |
michael |
2nd try of skip_bits_long() for the ALT reader
libavcodec
|
2006-08-26 |
michael |
make A32 reader align its ptr during init no matter what missaligned mess is given to it
libavcodec
|
2006-08-26 |
michael |
3rd try :)
libavcodec
|
2006-08-26 |
michael |
2nd try for a skip_bits_long() for the A32 reader
libavcodec
|
2006-08-26 |
michael |
move align_get_bits() to .h to avoid conflicts between different bitstream readers in different codecs
libavcodec
|
2006-08-26 |
michael |
prevent bitstream reader to be overriden
libavcodec
|
2006-08-25 |
michael |
avoid branch
libavcodec
|
2006-08-25 |
michael |
move variable declarations so that their scope is smaller
libavcodec
|
2006-08-25 |
michael |
move the +400 out of the innermost loop
libavcodec
|
2006-08-25 |
michael |
avoid reading exponent twice
libavcodec
|
2006-08-25 |
michael |
reduce size of vlc table, thats slightly faster here
libavcodec
|
2006-08-25 |
michael |
try to avoid l3_unscale() by using a table
libavcodec
|
2006-08-25 |
michael |
replace l3_unscale(1, exponents[pos]) by LUT
libavcodec
|
2006-08-25 |
michael |
maybe fixing the segfault on ARM
libavcodec
|
2006-08-24 |
aurel |
cook shouldn't try to enforce the bitstream reader type
libavcodec
|
2006-08-24 |
bcoudurier |
add codec id and tag for JPEG 2000
libavcodec
|
2006-08-24 |
michael |
10l typo
libavcodec
|
2006-08-24 |
michael |
avoid a few if(x==0) checks in the inner loops
libavcodec
|
2006-08-24 |
michael |
fix non ALT bitstream reader
libavcodec
|
2006-08-24 |
michael |
optimize reorder_block() though this function seems to be executed too rarely for this to make much difference
libavcodec
|
2006-08-24 |
michael |
simplify
libavcodec
|
2006-08-24 |
michael |
dont copy the whole GetBitContext around
libavcodec
|
2006-08-24 |
michael |
faster handling of zero coeffs in the low freq decode
libavcodec
|
2006-08-24 |
michael |
optimizing high freq decode
libavcodec
|
2006-08-24 |
michael |
use memset() instead of slow c loops
libavcodec
|
2006-08-23 |
michael |
simplify
libavcodec
|
2006-08-23 |
aurel |
fix arm asm compilation in mpegaudiodec
libavcodec
|
2006-08-22 |
banan |
Alignment of the LT window, segfault fix patch by Baptiste Coudurier.
libavcodec
|
2006-08-22 |
michael |
MUL* for ARM code based on a patch by Siarhei Siamashka
libavcodec
|
2006-08-22 |
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
libavcodec
|
2006-08-22 |
michael |
replacing MULH by asm for x86
libavcodec
|
2006-08-22 |
michael |
indent preprocessor directives
libavcodec
|
2006-08-22 |
michael |
make high precission synth filter 3 times faster on x86
libavcodec
|
2006-08-22 |
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)
libavcodec
|
2006-08-21 |
michael |
replace a few MULL by MULH
libavcodec
|
2006-08-20 |
michael |
reorder butterflies to reduce memory load/store
libavcodec
|
2006-08-20 |
banan |
Added codec id for QCELP.
libavcodec
|
2006-08-19 |
michael |
cosmetics
libavcodec
|
2006-08-19 |
michael |
SWAP
libavcodec
|
2006-08-19 |
michael |
audio format conversion
libavcodec
|
2006-08-19 |
lucabe |
Allow swscale emulation header to be included by C++ programs
libavcodec
|
2006-08-19 |
banan |
SIMD vector optimizations. 3% faster overall decoding.
libavcodec
|
2006-08-19 |
lorenm |
use ff_fft_calc_3dn2 instead of sse on a K8.
libavcodec
|
2006-08-18 |
lorenm |
ff_fft_calc_3dn/3dn2/sse: convert intrinsics to inline asm.
libavcodec
|
2006-08-18 |
diego |
Explicitly include fastmemcpy.h from libvo/.
libavcodec
|
2006-08-18 |
michael |
simplify
libavcodec
|
2006-08-18 |
gpoirier |
Add YV12 support, patch by Steve Lhomme % steve P lhomme A free P fr %
libavcodec
|
2006-08-17 |
diego |
Move all internal -I parameters to the front of CFLAGS to avoid using external
libavcodec
|
2006-08-17 |
michael |
cleanup
libavcodec
|
2006-08-17 |
michael |
insufficient alignment
libavcodec
|
2006-08-15 |
lu_zero |
10l, thanks to Emanuele Giaquinta <exg@gentoo.org> for testing and finding the issue
libavcodec
|
2006-08-15 |
gpoirier |
Compile fix (for GCC<3.3) when encoders are disabled
libavcodec
|
2006-08-14 |
lu_zero |
altivec float optimizations
libavcodec
|
2006-08-14 |
michael |
fix codec timebase and timestamps
libavcodec
|
2006-08-14 |
michael |
fix h261 parsing bug
libavcodec
|
2006-08-13 |
diego |
Fix building with --disable-opts but MMX enabled.
libavcodec
|
2006-08-13 |
lu_zero |
Clean up:make dsputil subfile names consistent
libavcodec
|
2006-08-12 |
gpoirier |
Support for MacIntel, last part: balign directives
libavcodec
|
2006-08-12 |
gpoirier |
Fix CHECK_BIDIR macro so it works with Intel's Compiler
libavcodec
|
2006-08-11 |
lorenm |
vorbis simd tweaks
libavcodec
|
2006-08-11 |
kostya |
Disable B-frames decoding until I return and finish their proper decoding.
libavcodec
|
2006-08-11 |
lu_zero |
keep in sync with dsputil, makes --disable-decoder=vorbis build
libavcodec
|
2006-08-10 |
lorenm |
vorbis cosmetics: mdct0,mdct1 => mdct[2]
libavcodec
|
2006-08-10 |
lorenm |
misc tweaks in vorbis_residue_decode().
libavcodec
|
2006-08-10 |
michael |
convert vector_fmul_reverse_sse2 and vector_fmul_add_add_sse2 to sse
libavcodec
|
2006-08-10 |
lorenm |
sse and 3dnow implementations of float->int conversion and mdct windowing.
libavcodec
|
2006-08-10 |
lorenm |
r5954 broke fft on cpus with 3dnow but without mm3dnow.h
libavcodec
|
2006-08-10 |
lu_zero |
Fix x86 SIMD asm and pic, patch from Martin von Gagern <Martin.vGagern@gmx.net>
libavcodec
|
2006-08-10 |
gpoirier |
Support for MacIntel, take xx: '/nop' illegal for old versions of GAS
libavcodec
|
2006-08-10 |
gpoirier |
Add support for Mac OS X Intel part 2: Assembler macros in fdct_mmx.c
libavcodec
|
2006-08-10 |
gpoirier |
Support for Mac OS X Intel, part 3: binary integer constants:
libavcodec
|
2006-08-09 |
diego |
Correct wrong memset invocation.
libavcodec
|
2006-08-09 |
lorenm |
emms -> femms
libavcodec
|
2006-08-09 |
lorenm |
gcc 2.95 and 3.4.x on x86 32bit without fomit-frame-pointer can't even find 5 registers for asm input.
libavcodec
|
2006-08-08 |
lorenm |
slightly faster ff_imdct_calc_3dn2() on amd64. (gcc added a bunch of useless movsxd)
libavcodec
|
2006-08-08 |
lucabe |
Enable swscale usage in ffmpeg
libavcodec
|
2006-08-08 |
michael |
change vorbis_inverse_coupling_sse2() so it works on sse1 cpus
libavcodec
|
2006-08-08 |
diego |
Fix some "'static' is not at beginning of declaration" warnings.
libavcodec
|
2006-08-08 |
lorenm |
3dnow2 implementation of imdct.
libavcodec
|
2006-08-06 |
lu_zero |
Cosmetics: 2->4 spaces and some braces
libavcodec
|
2006-08-06 |
kostya |
Correct MC for B-frames and some improvements (not 100% complete though)
libavcodec
|
2006-08-06 |
kostya |
Bicubic interpolation requires two additional pixels for block
libavcodec
|
2006-08-04 |
melanson |
printf -> av_log, only occurs in DEBUG cases
libavcodec
|
2006-08-04 |
lu_zero |
Yet another typo
libavcodec
|
2006-08-04 |
lu_zero |
Fix a stupid typo and another error, thanks to Emanuele Giaquinta <exg@gentoo.org> for pointing out the issue and the patch
libavcodec
|
2006-08-04 |
kostya |
100l: intensity compensation must be also done in 4-MV mode
libavcodec
|
2006-08-03 |
lu_zero |
standalone snow dsputil init
libavcodec
|
2006-08-03 |
lu_zero |
Almost cosmetic changes in dsputil_init_ppc and vorbis_inverse_coupling_altivec:
libavcodec
|
2006-08-03 |
lu_zero |
Minor fix
libavcodec
|
2006-08-03 |
lu_zero |
avoid alignment hacks, luckly gcc does the right thing on arches different from x86
libavcodec
|
2006-08-03 |
lu_zero |
vorbis_inverse_coupling_altivec
libavcodec
|
2006-08-03 |
lu_zero |
Cleanup
libavcodec
|
2006-08-03 |
lorenm |
10l, vorbis_inverse_coupling_sse() was really 3dnow
libavcodec
|
2006-08-03 |
lorenm |
another div -> fastdiv, another 2% faster vorbis.
libavcodec
|