9680 decicycles in loop_filter_v_88_16_c, 4193765 runs, 539 skips
9233 decicycles in loop_filter_h_88_16_c, 4193751 runs, 553 skips
1929 decicycles in ff_vp9_loop_filter_v_88_16_ssse3, 4194118 runs, 186 skips
2738 decicycles in ff_vp9_loop_filter_h_88_16_ssse3, 4193861 runs, 443 skips
5.978 → 5.417 overall decode time on ped1080p.webm (-threads 1)
Adding SSE2 support should be relatively trivial (just a matter of
changing the pshufb [mask_mix] with something else), patch welcome.
This was suggested by Rodeo on IRC
<Rodeo> for consistency with the rest, MODE_7_1_FRONT_CENTER would be AV_CH_LAYOUT_7POINT1_WIDE_BACK (since LS+RS is mapped to back channels in other modes)
Reviewed-by: Jean First <jeanfirst@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This was suggested by Rodeo on IRC
<Rodeo> sorry, I meant MODE_7_1_REAR_SURROUND would probably be AV_CH_LAYOUT_7POINT1
Reviewed-by: Jean First <jeanfirst@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Introduce 2 additional registers for stride3 and mstride3 to allow
direct accesses (lea drops).
3931 → 3827 decicycles in ff_vp9_loop_filter_v_16_16_ssse3
Also uses defines to clarify the code.
Fixes invalid reads and crashes in vp90-2-05-resize.webm and fuzzed6.ivf.
The output is still not identical to what libvpx does (because we don't
actually scale in MC).
Reviewed-by: ubitux
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Prevents some invalid memory accesses after resolution change in
vp90-2-05-resize.webm, and libvpx does this too.
Reviewed-by: ubitux
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
7.1(wide) and 7.1(wide-side) channel layouts are supported in fdk_aac since october 2013 (commit fa3eba1644)
Signed-off-by: Jean First <jeanfirst@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This fixes the speed regression from 20626f53e9
and still checks sufficiently to prevent out of allocated memory accesses
due to the index
Before:
1823 decicycles in mpeg2_fast_decode_block_non_intra, 8388493 runs, 115 skips
After:
1808 decicycles in mpeg2_fast_decode_block_non_intra, 8388494 runs, 114 skips
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This fixes the speed regression from 20626f53e9
and still checks sufficiently to prevent out of allocated memory accesses
due to the index
Before:
1681 decicycles in mpeg2_fast_decode_block_intra, 4194238 runs, 66 skips
After:
1658 decicycles in mpeg2_fast_decode_block_intra, 4194248 runs, 56 skips
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Before this patch, we explicitly modify rsp, which isn't necessarily
universally acceptable, since the space under the stack pointer might
be modified in things like signal handlers. Therefore, use an explicit
register to hold the stack pointer relative to the bottom of the stack
(i.e. rsp). This will also clear out valgrind errors about the use of
uninitialized data that started occurring after the idct16x16/ssse3
optimizations were first merged.
- The memcpy was completely wrong because
s->prob_ctx[s->framectxid].coef is a [4][2][2][6][6][3] array, whereas
s->prob.coef is a [4][2][2][6][6][11] array.
- The additional check was committed to ffmpeg by Ronald S. Bultje.
Signed-off-by: Anton Khirnov <anton@khirnov.net>
Michael Niedermayer
James Almer
Clément Bœsch
Carl Eugen Hoyos
Rainer Hochecker
Ronald S. Bultje
Jean First
Janne Grunau
Wim Vander Schelden
Kostya Shishkov
Guillaume Martres