paddq is an SSE2 instruction so it cannot be used for MMX.
This was probably just a typo because the sums are dwords anyway.
Reviewed-by: Pascal Massimino <pascal.massimino@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
integration by Neil Birkbeck, with help from Vitor Sessak.
core SSE2 loop by Skal (pascal.massimino@gmail.com)
Reviewed-by: Clément Bœsch <u@pkh.me>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
And use the x86util ones instead, which are optimized for mmxext/sse2.
About ~1% increase in performance on pre SSSE3 processors.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This makes C and MMX match, no change to fate as the differences where
apparently not sufficient to show up in fate
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Those macros take a byte number as shift argument, as this argument
differs between MMX and SSE2 instructions.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* commit '01c5779f56cf708e6cb88b11cfdc248cae7e2ee8':
x86: Drop some unnecessary YASM ifdefs
Conflicts:
libavfilter/x86/vf_yadif_init.c
Merged-by: Michael Niedermayer <michaelni@gmx.at>
This reverts commit 975110a85ef8e794fdc041455ff41b0ad30bc01e.
Signed-off-by: Robert Krüger <krueger@lesspain.de>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This reverts commit a87b17f3283aada762820f1b797eeb7a2dff6c61.
This reduces the amount of non LGPL code, making a relicensing to LGPL
easier
Conflicts:
libavfilter/vf_yadif.c
libavfilter/x86/yadif.c
libavfilter/x86/yadif_template.c
libavfilter/yadif.h
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This reverts commit fc5fe4804fd2ee9a29de502e9431b12d027c0c89, reversing
changes made to ffe33500983983946048def3a6047920d97d957b.
The factoring is broken; it's not calling the ssse3 code anymore, and
calling the mmx2 code with bad alignment. It also broke some FATE
instances.
Conflicts:
libavfilter/x86/vf_gradfun_init.c
* commit 'ed1a11ed52bbd1f15bb9b0416d69b7924bee3191':
gradfun: x86: Factor out common code for some gradfun_filter_line() variants
Conflicts:
libavfilter/x86/vf_gradfun_init.c
Merged-by: Michael Niedermayer <michaelni@gmx.at>
* qatar/master:
Consistently use "cpu_flags" as variable/parameter name for CPU flags
Conflicts:
libavcodec/x86/dsputil_init.c
libavcodec/x86/h264dsp_init.c
libavcodec/x86/hpeldsp_init.c
libavcodec/x86/motion_est.c
libavcodec/x86/mpegvideo.c
libavcodec/x86/proresdsp_init.c
Merged-by: Michael Niedermayer <michaelni@gmx.at>
Always use the special filter for the first and last 3 columns (only).
Changes made in 64ed397 slowed the filter to just under 3/4 of what it
was. This commit restores the speed while maintaining identical output.
For reference, on my Athlon64:
1733222 decicycles in old
2358563 decicycles in new
1727558 decicycles in this
Signed-off-by: Anton Khirnov <anton@khirnov.net>
* qatar/master:
x86: Move some conditional code around to avoid unused variable warnings
Conflicts:
libavcodec/x86/dsputil_mmx.c
libavfilter/x86/vf_yadif_init.c
Merged-by: Michael Niedermayer <michaelni@gmx.at>
Current code divides before increasing precision.
Also reduce upper bound for strength from 255 to 64. This will prevent
an overflow in the SSSE3 and MMX filter_line code: delta is expressed as
an u16 being shifted by 2 to the left. If it overflows, having a
strength not above 64 will make sure that m is set to 0 (making the
m*m*delta >> 14 expression void).
A value above 64 should not make any sense unless gradfun is used as
a blur filter.
Signed-off-by: Anton Khirnov <anton@khirnov.net>
