index
:
libav.git
avcodec_yuv_range
avconv
avoption_list
avscale
bitstream
bitstream_unmerge
bs
c11
cfhd
cuvid
cuvid2
decode_significance
dxva
ffmpeg_encoder_opts
frame_duration
frame_map
frame_map_sort
hevc
hwaccel_thread
lavfi_opt_files
live
master
metrics
mt_enc_wip
mv-hevc
playlists
recon
refcount
thread_receive
ts_flags
[no description]
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
libavcodec
/
i386
Commit message (
Expand
)
Author
Age
*
altivec support for snow
Luca Barbato
2006-03-27
*
simplified and slightly faster h264_chroma_mc8_mmx
Loren Merritt
2006-03-25
*
prefetch pixels for future motion compensation. 2-5% faster h264.
Loren Merritt
2006-03-23
*
10l
Loren Merritt
2006-03-22
*
added mmx implementation of h264_chroma_mc2
Loren Merritt
2006-03-22
*
add MMX and SSE versions of ff_snow_inner_add_yblock
Robert Edele
2006-03-22
*
snow mmx+sse2 optimizations, part 4
Robert Edele
2006-03-21
*
Add the mmx and sse2 implementations of ff_snow_vertical_compose().
Robert Edele
2006-03-20
*
First part of a series of speed-enchancing patches.
Robert Edele
2006-03-16
*
3DNow! & Extended 3DNow! versions of FFT
Zuxy Meng
2006-03-08
*
h264_idct8_add_mmx
Loren Merritt
2006-03-07
*
h264_idct_add only needs mmx1
Loren Merritt
2006-03-07
*
use xorps instead of mulps to toggle the sign of a float, as suggested by Sof...
Zuxy Meng
2006-03-05
*
gcc2.95 workaround
Loren Merritt
2006-03-05
*
remove some useless instructions
Loren Merritt
2006-03-04
*
4% faster h264_qpel_mc
Loren Merritt
2006-03-02
*
h264: special case dc-only idct. ~1% faster overall
Loren Merritt
2006-02-10
*
10l in 1.12
Loren Merritt
2006-02-09
*
10l (x86_64)
Loren Merritt
2006-02-07
*
18% faster put_h264_qpel16_mc[13]2_mmx2
Loren Merritt
2006-02-07
*
11% faster put_h264_qpel16_v_lowpass_mmx2
Loren Merritt
2006-02-07
*
15% faster put_h264_qpel16_hv_lowpass_mmx2
Loren Merritt
2006-02-07
*
MSVC-compatible __align8/__align16 declaration
Steve L'Homme
2006-02-05
*
Update licensing information: The FSF changed postal address.
Diego Biurrun
2006-01-12
*
tweak h264_biweight
Loren Merritt
2006-01-09
*
fix some potential arithmetic overflows in pred_direct_motion() and
Loren Merritt
2005-12-30
*
COSMETICS: tabs --> spaces, some prettyprinting
Diego Biurrun
2005-12-22
*
COSMETICS: Remove all trailing whitespace.
Diego Biurrun
2005-12-17
*
Add the rest of missing Reg_* macros to support both AMD-64 style regs and IA...
Guillaume Poirier
2005-12-10
*
use sse16_sse2() in nsse
Loren Merritt
2005-11-12
*
faster h264_chroma_mc8_mmx, added h264_chroma_mc4_mmx.
Loren Merritt
2005-10-27
*
h264 mmx weighted prediction. up to 3% overall speedup.
Loren Merritt
2005-10-09
*
sse2 16x16 sum squared diff (306=>268 cycles on a K8)
Loren Merritt
2005-09-30
*
replace a few mov + psrlq with pshufw, there are more cases which could benef...
Michael Niedermayer
2005-09-21
*
Fix compile without CONFIG_GPL, misplaced #endif caused a missing }.
Reimar Döffinger
2005-09-10
*
remove unused table entries
Michael Niedermayer
2005-09-10
*
xvids mmx&mmx2 idcts
Michael Niedermayer
2005-09-10
*
Kill some compiler warnings. Compiled code verified identical after changes.
Måns Rullgård
2005-09-06
*
simplify (d&a) and (d&~a) calculation, hint by skal
Michael Niedermayer
2005-09-03
*
add consts (this was in my local tree, dunno where it came from, probably for...
Michael Niedermayer
2005-09-02
*
kill a bunch of compiler warnings
Måns Rullgård
2005-08-14
*
libavutil: Utility code from libavcodec moved to a separate library.
Alexander Strasser
2005-08-01
*
sort H.264 mmx dsp functions into their own file
Loren Merritt
2005-06-02
*
adding a few const
Michael Niedermayer
2005-06-01
*
100l for myself (breaking amd64)
Michael Niedermayer
2005-06-01
*
merge a few asm blocks so gcc cant unoptimize it (658->631 dezicycles on duron)
Michael Niedermayer
2005-06-01
*
get rid of 2 movq (680 -> 658 dezicycles on duron)
Michael Niedermayer
2005-06-01
*
avoid one transpose (730->680 dezicycles on duron)
Michael Niedermayer
2005-06-01
*
10l (symbol mangling)
Loren Merritt
2005-06-01
*
add rounding bias before the horizontal idct (765->730 dezicyles on duron)
Michael Niedermayer
2005-06-01
[next]