When compiling FFmpeg with GCC-9, some very random segfaults were
observed in code which had previously called down into the SBC encoder
NEON assembly routines. This was caused by these functions clobbering
some of the vfp callee saved registers (d8 - d15 aka q4 - q7). GCC was
using these registers to save local variables, but after these
functions returned, they would contain garbage.
Fix by reallocating the registers in the two affected functions in
the following way:
ff_sbc_analyze_4_neon: q2-q5 => q8-q11, then q1-q4 => q8-q11
ff_sbc_analyze_8_neon: q2-q9 => q8-q15
The reason for using these replacements is to keep closely related
sets of registers consecutively numbered which hopefully makes the
code more easy to follow. Since this commit only reallocates
registers, it should have no performance impact.
Signed-off-by: James Cowgill <jcowgill@debian.org>
Signed-off-by: Martin Storsjö <martin@martin.st>
Reviewed-by: Peter Ross <pross@xvid.org>
Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
This has been broken since the start, and it was only discovered
when I started testing my replacement for the FFT.
Disable it, since there's no point in fixing slower code that's about
to be removed anyway.
The vfp version is not affected.
checkasm benchmarks on 1.5 GHz Cortex-A72 are as follows.
vc1dsp.vc1_unescape_buffer_c: 918624.7
vc1dsp.vc1_unescape_buffer_neon: 142958.0
Signed-off-by: Ben Avison <bavison@riscosopen.org>
Signed-off-by: Martin Storsjö <martin@martin.st>
checkasm benchmarks on 1.5 GHz Cortex-A72 are as follows. Note that the C
version can still outperform the NEON version in specific cases. The balance
between different code paths is stream-dependent, but in practice the best
case happens about 5% of the time, the worst case happens about 40% of the
time, and the complexity of the remaining cases fall somewhere in between.
Therefore, taking the average of the best and worst case timings is
probably a conservative estimate of the degree by which the NEON code
improves performance.
vc1dsp.vc1_h_loop_filter4_bestcase_c: 19.0
vc1dsp.vc1_h_loop_filter4_bestcase_neon: 48.5
vc1dsp.vc1_h_loop_filter4_worstcase_c: 144.7
vc1dsp.vc1_h_loop_filter4_worstcase_neon: 76.2
vc1dsp.vc1_h_loop_filter8_bestcase_c: 41.0
vc1dsp.vc1_h_loop_filter8_bestcase_neon: 75.0
vc1dsp.vc1_h_loop_filter8_worstcase_c: 294.0
vc1dsp.vc1_h_loop_filter8_worstcase_neon: 102.7
vc1dsp.vc1_h_loop_filter16_bestcase_c: 54.7
vc1dsp.vc1_h_loop_filter16_bestcase_neon: 130.0
vc1dsp.vc1_h_loop_filter16_worstcase_c: 569.7
vc1dsp.vc1_h_loop_filter16_worstcase_neon: 186.7
vc1dsp.vc1_v_loop_filter4_bestcase_c: 20.2
vc1dsp.vc1_v_loop_filter4_bestcase_neon: 47.2
vc1dsp.vc1_v_loop_filter4_worstcase_c: 164.2
vc1dsp.vc1_v_loop_filter4_worstcase_neon: 68.5
vc1dsp.vc1_v_loop_filter8_bestcase_c: 43.5
vc1dsp.vc1_v_loop_filter8_bestcase_neon: 55.2
vc1dsp.vc1_v_loop_filter8_worstcase_c: 316.2
vc1dsp.vc1_v_loop_filter8_worstcase_neon: 72.7
vc1dsp.vc1_v_loop_filter16_bestcase_c: 62.2
vc1dsp.vc1_v_loop_filter16_bestcase_neon: 103.7
vc1dsp.vc1_v_loop_filter16_worstcase_c: 646.5
vc1dsp.vc1_v_loop_filter16_worstcase_neon: 110.7
Signed-off-by: Ben Avison <bavison@riscosopen.org>
Signed-off-by: Martin Storsjö <martin@martin.st>
This avoids unnecessary rebuilds of most source files if only the
list of enabled components has changed, but not the other properties
of the build, set in config.h.
Signed-off-by: Martin Storsjö <martin@martin.st>
This reverts commit 2589060b92 which was
originally to fix the FATE test. The real cause of the test breakage was
fixed in 22b7c37275.
Signed-off-by: J. Dekker <jdek@itanimul.li>
The assembly is written assuming that the width is a multiple of 8.
However the real issue is the functions were errorneously assigned to
the 2, 4, 6 & 12 widths. This behaviour never broke the decoder as
samples which trigger the functions for these widths have not been found
in the wild. This relies on the mappings in ff_hevc_pel_weight[].
Signed-off-by: J. Dekker <jdek@itanimul.li>
Don't use the loaded registers directly, avoiding stalls on in
order cores. Use vrhadd.u8 with q registers where easily possible.
Signed-off-by: Martin Storsjö <martin@martin.st>
This unbreaks the fate-checkasm-hevc_pel test on arm targets.
The assembly assumed that the width passed to the DSP functions is
a multiple of 8, while the checkasm test used other widths too.
This wasn't noticed before, because the hevc_pel checkasm tests
(that were added in 9c513edb79 in
January) weren't run as part of fate until in
b492cacffd in August.
As this hasn't been an issue in practice with actual full decoding
tests, it seems like the actual decoder doesn't call these functions
with such widths. Therefore, we could alternatively fix the test
to only test things that the real decoder does, and this modification
could be reverted.
Signed-off-by: Martin Storsjö <martin@martin.st>
Deprecated in commits 7fc329e2dd
and 31f6a4b4b8.
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
Signed-off-by: James Almer <jamrial@gmail.com>
Some files currently rely on libavutil/cpu.h to include it for them;
yet said file won't use include it any more after the currently
deprecated functions are removed, so include attributes.h directly.
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
No longer used by anything.
Unfortunately the old FFT_FLOAT/FFT_FIXED_32 is left as-is. It's
simply too much work for code meant to be all removed anyway.
Fix an occasional crash for hevc decoder in ARM 32 platform, the
root cause is the memory over read(read cross the memory boundary)
in SAO NENO functions ff_hevc_sao_band_filter_neon_8 and
ff_hevc_sao_edge_filter_neon_8.
After this fix, the crash disapper in the massive Android phone
test.
Signed-off-by: qoroliang <qoroliang@tencent.com>
* commit '0676de935b1e81bc5b5698fef3e7d48ff2ea77ff':
arm: Implement a NEON version of 422 h264_h_loop_filter_chroma
Merged-by: James Almer <jamrial@gmail.com>
This makes it similar to put_epel16_v6, and gives a 10-25%
speedup of this function.
Before: Cortex A7 A8 A9 A53 A72
vp8_put_epel16_h6v6_neon: 3058.0 2218.5 2459.8 2183.0 1572.2
After:
vp8_put_epel16_h6v6_neon: 2670.8 1934.2 2244.4 1729.4 1503.9
Signed-off-by: Martin Storsjö <martin@martin.st>
When targeting darwin, clang requires commas between arguments,
while the no-comma form is allowed for other targets.
Since Xcode 9.3, the bundled clang supports altmacro and doesn't
require using gas-preprocessor any longer.
Signed-off-by: Martin Storsjö <martin@martin.st>
Clang supports the macro expansion counter (used for making unique
labels within macro expansions), but not when targeting darwin.
Convert uses of the counter into normal local labels, as used
elsewhere.
Since Xcode 9.3, the bundled clang supports altmacro and doesn't
require using gas-preprocessor any longer.
Signed-off-by: Martin Storsjö <martin@martin.st>
When targeting darwin, clang requires commas between arguments,
while the no-comma form is allowed for other targets.
Since Xcode 9.3, the bundled clang supports altmacro and doesn't
require using gas-preprocessor any longer.
Signed-off-by: Martin Storsjö <martin@martin.st>
Compilation error "out of range" fixed for armeabi-v7a. Compilation failed
trying to build libvlc.aar for ARM7 android on ubuntu 16.04 host. Error
messages is "Offset out of range". The reason of the error is assembler LDR
directives in function "ff_hevc_transform_luma_4x4_neon_8" need local storage
in range <1k, but no such storage provided.
Based on a patch by Ihor Bobalo <bob@eleks.com>
Suggested-by: wbs
Signed-off-by: James Almer <jamrial@gmail.com>
* commit '9dde6ab06c48f9447cd16f39bee33569cddb7be4':
arm: Fix SIGBUS on ARM when compiled with binutils 2.29
Merged-by: James Almer <jamrial@gmail.com>
* commit '118dd4a321a2d67f67c21b076abd0b4d939ab642':
hevc: 16x16 NEON idct: Use the right element size for loads/stores
Merged-by: James Almer <jamrial@gmail.com>
