Should fix https://ffmpeg.org/pipermail/ffmpeg-devel/2018-February/225058.html

Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>

This reverts commit adff97be5e.

It currently fails on Windows targets.

Signed-off-by: James Almer <jamrial@gmail.com>

This fixes fate-checkasm-hevc_mc on ARMCC 5.0 after adding
NEON HEVC MC assembly.

Signed-off-by: Martin Storsjö <martin@martin.st>

Signed-off-by: James Almer <jamrial@gmail.com>

Signed-off-by: James Almer <jamrial@gmail.com>

Tested for 10000 iterations on x86-32

Fixes: Ticket6848

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>

Signed-off-by: James Almer <jamrial@gmail.com>

Signed-off-by: James Almer <jamrial@gmail.com>

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: James Almer <jamrial@gmail.com>

Signed-off-by: James Almer <jamrial@gmail.com>

Signed-off-by: James Almer <jamrial@gmail.com>

add_median_pred
add_left_pred : add two func one with acc 0, and one with random acc
add_left_pred16

Also modify the required alignment, to 32 instead of 16
for several codecs

Signed-off-by: James Almer <jamrial@gmail.com>

Signed-off-by: James Almer <jamrial@gmail.com>

Signed-off-by: Martin Storsjö <martin@martin.st>

Signed-off-by: James Almer <jamrial@gmail.com>

On ARM platforms, accessing the PMU registers requires special user
access permissions. Since there is no other way to get accurate timers,
the current implementation of timers in FFmpeg rely on these registers.
Unfortunately, enabling user access to these registers on Linux is not
trivial, and generally involve compiling a random and unreliable github
kernel module, or patching somehow your kernel.

Such module is very unlikely to reach the upstream anytime soon. Quoting
Robin Murphin from ARM:

> Say you do give userspace direct access to the PMU; now run two or more
> programs at once that believe they can use the counters for their own
> "minimal-overhead" profiling. Have fun interpreting those results...
>
> And that's not even getting into the implications of scheduling across
> different CPUs, CPUidle, etc. where the PMU state is completely beyond
> userspace's control. In general, the plan to provide userspace with
> something which might happen to just about work in a few corner cases,
> but is meaningless, misleading or downright broken in all others, is to
> never do so.

As a result, the alternative is to use the Performance Monitoring Linux
API which makes use of these registers internally (assuming the PMU of
your ARM board is supported in the kernel, which is definitely not a
given...).

While the Linux API is obviously cross platform, it does have a
significant overhead which needs to be taken into account. As a result,
that mode is only weakly enabled on ARM platforms exclusively.

Note on the non flexibility of the implementation: the timers (native
FFmpeg vs Linux API) are selected at compilation time to prevent the
need of function calls, which would result in a negative impact on the
cycle counters.

This reverts commit 547db1eaec.

This commit wasn't supposed to be pushed (yet) since it hasn't
been reviewed.

Signed-off-by: Martin Storsjö <martin@martin.st>

This was missing from f8d0689d3f.
Fixes checkasm.

Signed-off-by: James Almer <jamrial@gmail.com>

Signed-off-by: James Almer <jamrial@gmail.com>

The function returns a float.

This fixes the test in x86_32 targets.

Signed-off-by: James Almer <jamrial@gmail.com>

Missed in the last commit.

This includes various fixes and improvements from James Almer.

Signed-off-by: James Almer <jamrial@gmail.com>

Reviewed-by: Paul B Mahol <onemda@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>

Avoids overriding the v0 register (which containins the result of the
tested function) in checkasm_call_checked.

None of them are specific to the YASM assembler.

(Cherry-picked from libav commit 39e208f4d4)

Signed-off-by: James Almer <jamrial@gmail.com>

Ported from libavutil/tests/float_dsp.c

Signed-off-by: James Almer <jamrial@gmail.com>

Meant for DSP functions returning a float or double, as they'd fail if emms
is called after every run on x86_32.

Signed-off-by: James Almer <jamrial@gmail.com>

Should prevents future conflicts with the similarly named floatdsp tests

Loads from this strictly doesn't require alignment, but specify it
just for consistency with the arm version.

Signed-off-by: Martin Storsjö <martin@martin.st>

This makes it easier to group them with the rest when running e.g.
--bench=hevc.

Signed-off-by: Martin Storsjö <martin@martin.st>

Tested-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: James Almer <jamrial@gmail.com>

This is following Libav layout to ease merges.