GitLab

Clang emits aligned AVX stores for things like zeroing stack-allocated
variables when using -mavx even with -fno-tree-vectorize set which can
result in crashes if this occurs before we've realigned the stack.

Previously we only ensured that the stack was realigned before calling
assembly functions that accesses stack-allocated buffers but this is
not sufficient. Fix the issue by changing the stack realignment to
instead occur immediately in all CLI, API and thread entry points.

32-bit shifts are only defined for values in the range 0-31.

Now behaves the same as bs_align_0 and bs_align_1.

This was always required, but accidentally happened to work correctly
in a few cases.

This picks the right assembler automatically for arm and aarch64
llvm-mingw targets.

This doesn't get the right assembler for clang setups when clang
acts like MSVC and uses MSVC headers though (where it perhaps
should use armasm as before), but that's probably an even more
obscure setup.

 * Drop empty addition of GPLed filters

 * Replace backticks with $()

Improves cache efficiency.

Fixes segfaults on Windows where the stack is only 16-byte aligned.

sasshka authored May 21, 2017 and Anton Mitrofanov committed Dec 24, 2017

5x speed up vs C code.

Martin Storsjö authored Oct 26, 2017 and Anton Mitrofanov committed Dec 24, 2017

This version supports converting aarch64 assembly for MS armasm64.exe.

Henrik Gramner authored Oct 22, 2017 and Anton Mitrofanov committed Dec 24, 2017

swscale can read past the end of the input buffer, which may result in
crashes if such a read crosses a page boundary into an invalid page.

Work around this by adding some padding space at the end of the buffer when
using memory-mapped input frames. This may sometimes require copying the
last frame into a new buffer on Windows since the Microsoft memory-mapping
implementation has very limited capabilities compared to POSIX systems.

Henrik Gramner authored Oct 22, 2017 and Anton Mitrofanov committed Dec 24, 2017

Use the AVComponentDescriptor depth field instead of depth_minus1.

Martin Storsjö authored Oct 18, 2017 and Anton Mitrofanov committed Dec 24, 2017

The assembler (both gas and clang/llvm) automatically fixes this,
armasm64 doesn't. We can fix it in gas-preprocessor, but we should
also be using the right instruction form.

Martin Storsjö authored Oct 16, 2017 and Anton Mitrofanov committed Dec 24, 2017

For windows, when building with armasm, we already filtered these out
with gas-preprocessor.

By filtering them out already in the source, we can also build directly
with clang for windows (which also require wrapping the assembler in
gas-preprocessor for converting instructions to thumb form, but
gas-preprocessor doesn't and shouldn't filter out them in the clang
configuration).

Martin Storsjö authored Oct 16, 2017 and Anton Mitrofanov committed Dec 24, 2017

This confuses gas-preprocessor, which tries to replace actual
st2 instructions by the integer 1 or 2.

Henrik Gramner authored Oct 14, 2017 and Anton Mitrofanov committed Dec 24, 2017

Only 17 elements are actually used. It was originally padded to 64 bytes to
avoid cache line splits in the x86 assembly, but those haven't really been
an issue on x86 CPU:s made in the past decade or so.

Benchmarking shows no performance impact from dropping the padding, so
might as well remove it and save some cache.

Henrik Gramner authored Oct 11, 2017 and Anton Mitrofanov committed Dec 24, 2017

Some ancient Pentium-M and Core 1 CPU:s had slow SSE units, and using MMX
was preferable. Nowadays many assembly functions in x264 completely lack MMX
implementations and falling back to C code will likely make things worse.

Some misconfigured virtualized systems could sometimes also trigger this code
path and cause assertions.

Vittorio Giovara authored Oct 09, 2017 and Anton Mitrofanov committed Dec 24, 2017

 * Use the codec parameters API instead of the AVStream codec field.
 * Use av_packet_unref() instead of av_free_packet().
 * Use the AVFrame pts field instead of pkt_pts.

Henrik Gramner authored Oct 07, 2017 and Anton Mitrofanov committed Dec 24, 2017

Takes advantage of opmasks to avoid having to use scalar code for the tail.

Also make some slight improvements to the checkasm test.

Henrik Gramner authored Oct 07, 2017 and Anton Mitrofanov committed Dec 24, 2017

Use a different multiplier in order to eliminate some shifts.

About 25% faster than before.

It have caused significant quality hit without any meaningful (if any) speed up.

Fixes some thread safety doubts and makes code cleaner.
Downside: slightly higher memory usage when calling multiple encoders from the same application.

Fix thread safety of x264_threading_init() and use of X264_PTHREAD_MUTEX_INITIALIZER with win32thread

Log result of pkg-config checks to config.log.
Fix lavf support detection for pkg-config fallback case.
Fix detection of linking dependencies errors for lavf/lsmash/gpac.
Cosmetics.