Tue, 22 Aug 2006 11:11:04 +0000 |
michael |
make high precission synth filter 3 times faster on x86
libavcodec
|
Tue, 22 Aug 2006 06:24:59 +0000 |
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
|
Mon, 21 Aug 2006 12:12:43 +0000 |
michael |
replace a few MULL by MULH
libavcodec
|
Sun, 20 Aug 2006 22:18:26 +0000 |
michael |
reorder butterflies to reduce memory load/store
libavcodec
|
Sun, 20 Aug 2006 19:08:05 +0000 |
banan |
Added codec id for QCELP.
libavcodec
|
Sat, 19 Aug 2006 23:12:10 +0000 |
michael |
cosmetics
libavcodec
|
Sat, 19 Aug 2006 20:55:02 +0000 |
michael |
SWAP
libavcodec
|
Sat, 19 Aug 2006 20:22:57 +0000 |
michael |
audio format conversion
libavcodec
|
Sat, 19 Aug 2006 15:14:44 +0000 |
lucabe |
Allow swscale emulation header to be included by C++ programs
libavcodec
|
Sat, 19 Aug 2006 08:46:52 +0000 |
banan |
SIMD vector optimizations. 3% faster overall decoding.
libavcodec
|
Sat, 19 Aug 2006 02:42:20 +0000 |
lorenm |
use ff_fft_calc_3dn2 instead of sse on a K8.
libavcodec
|
Fri, 18 Aug 2006 23:53:49 +0000 |
lorenm |
ff_fft_calc_3dn/3dn2/sse: convert intrinsics to inline asm.
libavcodec
|