* qatar/master:
fate: Work around non-standard wc implementations at more places
fate: work around non-standard wc implementations
x86: rv40: Mark rv40_weight functions as MMX2; they use MMX2 instructions.
ac3dsp: simplify x86 versions of ac3_max_msb_abs_int16
fate: use standard diff options
tta: Fix comment about channel number; TTA supports >2 channels.
avfilter: Move ff_get_ref_perms_string() to where it is used.
build: Add 'check' target to run all compile and test targets.
indeo3: validate new frame size before resetting decoder
indeo3: when freeing buffers, set pointers referencing them to NULL as well
indeo3: initialise pixel planes on allocation
indeo3: ensure that decoded cell data is in 7-bit range as presumed by decoder
fate: rename psx-str-v3-mdec to mdec-v3
fate: convert psx-str to a demuxer test
lavf: add mdec to is_intra_only() list
Conflicts:
doc/developer.texi
libavcodec/indeo3.c
libavfilter/video.c
libavformat/utils.c
tests/fate/demux.mak
tests/fate/video.mak
tests/lavf-regression.sh
tests/ref/vsynth1/cljr
tests/ref/vsynth1/ffvhuff
tests/ref/vsynth2/cljr
tests/ref/vsynth2/ffvhuff
Merged-by: Michael Niedermayer <michaelni@gmx.at>
* qatar/master: (25 commits)
rv40dsp x86: MMX/MMX2/3DNow/SSE2/SSSE3 implementations of MC
ape: Use unsigned integer maths
arm: dsputil: fix overreads in put/avg_pixels functions
h264: K&R formatting cosmetics for header files (part II/II)
h264: K&R formatting cosmetics for header files (part I/II)
rtmp: Implement check bandwidth notification.
rtmp: Support 'rtmp_swfurl', an option which specifies the URL of the SWF player.
rtmp: Support 'rtmp_flashver', an option which overrides the version of the Flash plugin.
rtmp: Support 'rtmp_tcurl', an option which overrides the URL of the target stream.
cmdutils: Add fallback case to switch in check_stream_specifier().
sctp: be consistent with socket option level
configure: Add _XOPEN_SOURCE=600 to Solaris preprocessor flags.
vcr1enc: drop pointless empty encode_init() wrapper function
vcr1: drop pointless write-only AVCodecContext member from VCR1Context
vcr1: group encoder code together to save #ifdefs
vcr1: cosmetics: K&R prettyprinting, typos, parentheses, dead code, comments
mov: make one comment slightly more specific
lavr: replace the SSE version of ff_conv_fltp_to_flt_6ch() with SSE4 and AVX
lavfi: move audio-related functions to a separate file.
lavfi: remove some audio-related function from public API.
...
Conflicts:
cmdutils.c
libavcodec/h264.h
libavcodec/h264_mvpred.h
libavcodec/vcr1.c
libavfilter/avfilter.c
libavfilter/avfilter.h
libavfilter/defaults.c
libavfilter/internal.h
Merged-by: Michael Niedermayer <michaelni@gmx.at>
Code mostly inspired by vp8's MC, however:
- its MMX2 horizontal filter is worse because it can't take advantage of
the coefficient redundancy
- that same coefficient redundancy allows better code for non-SSSE3 versions
Benchmark (rounded to tens of unit):
V8x8 H8x8 2D8x8 V16x16 H16x16 2D16x16
C 445 358 985 1785 1559 3280
MMX* 219 271 478 714 929 1443
SSE2 131 158 294 425 515 892
SSSE3 120 122 248 387 390 763
End result is overall around a 15% speedup for SSSE3 version (on 6 sequences);
all loop filter functions now take around 55% of decoding time, while luma MC
dsp functions are around 6%, chroma ones are 1.3% and biweight around 2.3%.
Signed-off-by: Diego Biurrun <diego@biurrun.de>
* qatar/master: (22 commits)
rv40dsp x86: use only one register, for both increment and loop counter
rv40dsp: implement prescaled versions for biweight.
avconv: use default channel layouts when they are unknown
avconv: parse channel layout string
nutdec: K&R formatting cosmetics
vda: Signal 4 byte NAL headers to the decoder regardless of what's in the extradata
mem: Consistently return NULL for av_malloc(0)
vf_overlay: implement poll_frame()
vf_scale: support named constants for sws flags.
lavc doxy: add all installed headers to doxy groups.
lavc doxy: add avfft to the main lavc group.
lavc doxy: add remaining avcodec.h functions to a misc doxygen group.
lavc doxy: add AVPicture functions to a doxy group.
lavc doxy: add resampling functions to a doxy group.
lavc doxy: replace \ with /
lavc doxy: add encoding functions to a doxy group.
lavc doxy: add decoding functions to a doxy group.
lavc doxy: fix formatting of AV_PKT_DATA_{PARAM_CHANGE,H263_MB_INFO}
lavc doxy: add AVPacket-related stuff to a separate doxy group.
lavc doxy: add core functions/definitions to a doxy group.
...
Conflicts:
ffmpeg.c
libavcodec/avcodec.h
libavcodec/vda.c
libavcodec/x86/rv40dsp.asm
libavfilter/vf_scale.c
libavformat/nutdec.c
libavutil/mem.c
tests/ref/acodec/pcm_s24daud
Merged-by: Michael Niedermayer <michaelni@gmx.at>
Quite often, the original weights are multiple of 512. By prescaling them
by 1/512 when they are computed (once per frame), no intermediate shifting
is needed, and no prescaling on each call either.
The x86 code already used that trick.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
Provide MMX, SSE2 and SSSE3 versions, with a fast-path when the weights are
multiples of 512 (which is often the case when the values round up nicely).
*_TIMER report for the 16x16 and 8x8 cases:
C:
9015 decicycles in 16, 524257 runs, 31 skips
2656 decicycles in 8, 524271 runs, 17 skips
MMX:
4156 decicycles in 16, 262090 runs, 54 skips
1206 decicycles in 8, 262131 runs, 13 skips
MMX on fast-path:
2760 decicycles in 16, 524222 runs, 66 skips
995 decicycles in 8, 524252 runs, 36 skips
SSE2:
2163 decicycles in 16, 262131 runs, 13 skips
832 decicycles in 8, 262137 runs, 7 skips
SSE2 with fast path:
1783 decicycles in 16, 524276 runs, 12 skips
711 decicycles in 8, 524283 runs, 5 skips
SSSE3:
2117 decicycles in 16, 262136 runs, 8 skips
814 decicycles in 8, 262143 runs, 1 skips
SSSE3 with fast path:
1315 decicycles in 16, 524285 runs, 3 skips
578 decicycles in 8, 524286 runs, 2 skips
This means around a 4% speedup for some sequences.
Signed-off-by: Diego Biurrun <diego@biurrun.de>
