This fixes crashes in chromium on win64 on machines with AVX
(crashes that apparently aren't triggered by fate).
Signed-off-by: Martin Storsjö <martin@martin.st>
change the treatment of the strip y coordinates which previously did
not follow the description (nor did it behave like the binary decoder
on files with absolute strip offsets).
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
The new code is also faster and more robust.
As for the performance:
old decoder + conversion to rgb: fps = 2618
old decoder, without converting to rgb: fps = 4012
new decoder, producing rgb: fps = 4502
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This gets rid of a number of warnings about casts discarding
qualifiers from the pointer target, present since 7ebfb466a.
Signed-off-by: Martin Storsjö <martin@martin.st>
Instead, only extend edges on-demand when the motion vector actually
crosses the visible decoded area using ff_emulated_edge_mc(). This
changes decoding time for cathedral from 8.722sec to 8.706sec, i.e.
0.2% faster overall. More generally (VP8 uses this also), low-motion
content gets significant speed improvements, whereas high-motion content
tends to decode in approximately the same time.
Signed-off-by: Martin Storsjö <martin@martin.st>
Instead, keep them in the bitstream buffer until we read them verbatim,
this saves a memcpy() and a subsequent clearing of the target buffer.
decode_cabac+decode_mb for a sample file (CAPM3_Sony_D.jsv) goes from
6121.4 to 6095.5 cycles, i.e. 26 cycles faster.
Signed-off-by: Martin Storsjö <martin@martin.st>
This allows more transparent mixing of get_bits and whole-byte access
without having to touch get_bits internals.
Signed-off-by: Martin Storsjö <martin@martin.st>
These functions are mostly H264-specific (the only other user I can
spot is bink), and this allows us to special-case some functionality
for H264. Also remove the 16-bit-coeff with >8bpp versions (unused)
and merge the duplicate 32-bit-coeff for >8bpp (identical).
Signed-off-by: Martin Storsjö <martin@martin.st>
The non-alpha and alpha-Y planes are cleared in the idct_put/add()
calls. For the alpha U/V planes, we only care about the DC for entropy
context prediction purposes, the rest of the data is unused.
Signed-off-by: Martin Storsjö <martin@martin.st>
The non-intra-pcm branch in hl_decode_mb (simple, 8bpp) goes from 700
to 672 cycles, and the complete loop of decode_mb_cabac and hl_decode_mb
(in the decode_slice loop) goes from 1759 to 1733 cycles on the clip
tested (cathedral), i.e. almost 30 cycles per mb faster.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
The residual block data of 16x16 blocks was ignored for b-frames, which
leads to easy-to-identify artifacts. After this patch, the artifacts are
gone. Sample video: svq3_watermark.mov. (Fate results unaffected.)
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Reference:
commit 3615e2be84
Author: Michael Niedermayer <michaelni@gmx.at>
Date: Tue Dec 2 22:02:57 2003 +0000
h263_h_loop_filter_mmx
Originally committed as revision 2553 to svn://svn.ffmpeg.org/ffmpeg/trunk
commit 359f98ded9
Author: Michael Niedermayer <michaelni@gmx.at>
Date: Tue Dec 2 20:28:10 2003 +0000
h263_v_loop_filter_mmx
Originally committed as revision 2552 to svn://svn.ffmpeg.org/ffmpeg/trunk
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Not all hwaccels implement all codecs, so using one single list for
multiple such codecs means some codecs will be represented in the list,
even though they don't actually handle that codec. Copying specific
lists in each codec fixes that.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This was caused by unconditionally referencing a conditionally compiled
table. Now the code is also compiled conditionally.
Signed-off-by: Diego Biurrun <diego@biurrun.de>
This avoids SIMD-optimized functions having to sign-extend their
line size argument manually to be able to do pointer arithmetic.
Signed-off-by: Diego Biurrun <diego@biurrun.de>
The symbol "ff_h263_loop_filter_strength" is defined in h263.c, but
the h263 loopfilter functions (in the .asm file) are not optimized
out (even though their function pointers are never assigned).
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Instead, only extend edges on-demand when the motion vector actually
crosses the visible decoded area using ff_emulated_edge_mc(). This
changes decoding time for cathedral from 8.722sec to 8.706sec, i.e.
0.2% faster overall. More generally (VP8 uses this also), low-motion
content gets significant speed improvements, whereas high-motion content
tends to decode in approximately the same time.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Instead, keep them in the bitstream buffer until we read them verbatim,
this saves a memcpy() and a subsequent clearing of the target buffer.
decode_cabac+decode_mb for a sample file (CAPM3_Sony_D.jsv) goes from
6121.4 to 6095.5 cycles, i.e. 26 cycles faster.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Some applications do not like that.
Fixes VDA
Reduces noise for VDPAU
Tested-by: Guillaume POIRIER <poirierg@gmail.com>
Tested-by: Carl Eugen Hoyos <cehoyos@ag.or.at>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Michael Niedermayer
Matt Wolenetz
Paul B Mahol
Carl Eugen Hoyos
Diego Biurrun
u-bo1b@0w.se
Martin Storsjö
Ronald S. Bultje
Daniel Kang
Matti Hamalainen
Luca Barbato
Clément Bœsch