GCC 4.9.2 on a Core i5-4200U @ 1.60GHz, Linux x86_64
Before
715487 decicycles in sao_edge_filter_8, 262144 runs, 0 skips
After
672104 decicycles in sao_edge_filter_8, 262144 runs, 0 skips
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
pb_eo must be handled as a rip relative address for MSVC64, so an
intermediate register is needed. Should fix link failures.
Suggested by Hendrik Leppkes and Christophe Gisquet.
Tested-By: Hendrik Leppkes <h.leppkes@gmail.com>
Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
Original x86 intrinsics code by Pierre-Edouard Lepere.
Yasm port, refactoring and optimizations by James Almer.
Benchmarks of BQTerrace_1920x1080_60_qp22.bin with an Intel Core i5-4200U
Width 32
342694 decicycles in sao_edge_filter_10, 16384 runs, 0 skips
29476 decicycles in ff_hevc_sao_edge_filter_32_10_ssse3, 16384 runs, 0 skips
13996 decicycles in ff_hevc_sao_edge_filter_32_10_avx2, 16381 runs, 3 skips
Width 64
581163 decicycles in sao_edge_filter_10, 8192 runs, 0 skips
59774 decicycles in ff_hevc_sao_edge_filter_64_10_ssse3, 8192 runs, 0 skips
28383 decicycles in ff_hevc_sao_edge_filter_64_10_avx2, 8191 runs, 1 skips
Signed-off-by: James Almer <jamrial@gmail.com>
Original x86 intrinsics code and initial yasm port by Pierre-Edouard Lepere.
Refactoring and optimizations by James Almer.
Benchmarks of BQTerrace_1920x1080_60_qp22.bin with an Intel Core i5-4200U
Width 32
158583 decicycles in edge, sao_edge_filter_8 runs, 0 skips
5205 decicycles in ff_hevc_sao_edge_filter_32_8_ssse3, 32767 runs, 1 skips
2942 decicycles in ff_hevc_sao_edge_filter_32_8_avx2, 32767 runs, 1 skips
Width 64
705639 decicycles in sao_edge_filter_8, 262144 runs, 0 skips
19224 decicycles in ff_hevc_sao_edge_filter_64_8_ssse3, 262111 runs, 33 skips
10433 decicycles in ff_hevc_sao_edge_filter_64_8_avx2, 262115 runs, 29 skips
Signed-off-by: James Almer <jamrial@gmail.com>
As with sao_band_filter, pass instead the two variables from the struct needed in the function.
This simplifies writing asm optimized versions.
Reviewed-by: Mickaël Raulet <mraulet@insa-rennes.fr>
Signed-off-by: James Almer <jamrial@gmail.com>
Pass instead the two variables from the struct needed in the function.
This simplifies writing asm optimized versions of the function
Signed-off-by: James Almer <jamrial@gmail.com>
x86inc can translate r*m into a register or stack on its own
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
Regression since 745730c9c2.
The dynamic buffer was not being used or freed.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
There's no benefit from using blendps here except on CPUs with AVX, where
it's faster than shufps according to Intel's documentation.
As such, rename the sse4 functions to sse/sse2 and use shufps instead.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
__sync built-ins are considered legacy and will be deprecated.
These new memory model aware built-ins have been available since GCC 4.7.0
Use them by default when available except for __atomic_compare_exchange_n(),
which is slower, and is instead implemented as a fallback for when and if gcc
removes the legacy __sync built-ins.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
No need to keep the old symbols around until a major bump since lavd functions
with the avpriv_ prefix were never exposed.
Signed-off-by: James Almer <jamrial@gmail.com>
Reviewed-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
Reviewed-by: Stefano Sabatini <stefasab@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Handle it inside the __asm__() block.
Fixes fate-vc1_ilaced_twomv when using the gcc-usan toolchain.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
Wrap the function calls in a similar fashion to how it's being done
with the critical section API.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
This silences warnings about passing arguments from incompatible pointer type
when targeting Windows Vista or newer.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
Wrap the function calls in a similar fashion to how it's being done
with the critical section API.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
This silences warnings about passing arguments from incompatible pointer type
when targeting Windows Vista or newer.
Tested-by: Matt Oliver <protogonoi@gmail.com>
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
This makes the addition of arch optimized functions easier.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Anton Khirnov <anton@khirnov.net>
This makes the addition of arch optimized functions easier.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
~15% faster.
Also add an mmxext version that takes advantage of the new code, and
build it alongside with the mmx version only on x86_32.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
It may be used by ff_add_pixels_clamped_sse2().
Should fix fate-cavs failures on some systems.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
Also add sse2 versions for both.
put_pixels_clamped port and sse2 version originally written by Timothy Gu.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
Same behavior as in simple_idct.
This way the best optimized versions available will be used instead.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
Roughly 25% faster MC than ssse3 for blocksizes 32 and 64.
Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
Also add mmxext versions of vsad8 and vsad_intra8, and sse2 versions of
vsad16 and vsad_intra16.
Since vsad8 and vsad16 are not bitexact, they are accordingly marked as
approximate.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
No point in having the sad8 functions separate now that the loop is no
longer unrolled.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
Also add a missing c->pix_abs[0][0] initialization, and sse2 versions of
sad16_x2, sad16_y2 and sad16_xy2 (%15 to %20 faster than mmxext).
Since the _xy2 versions are not bitexact, they are accordingly marked as
approximate.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
James AlmerandMichael Niedermayer
