Force-inlining increases object size by 8kB and causes a 2% slowdown.

Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

is_block2 was always 0, so just remove it, and change accordingly the code.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

120->100 cycles.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

Commit 356ee8d7 caused the initial inversion.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

141 cycles down to 51.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

This adds a hand-optimized assembly version for get_cabac much like the
existing one, but it works if the table offsets are RIP-relative.
Compared to the non-RIP-relative version this adds 2 lea instructions
and it needs one extra register. get_cabac() gets about 40% faster, for
an overall speedup of about 5%.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

The reason is this is easier for PIC code (in particular on darwin...).
Keep the old names as pointers (static in cabac_functions.h so gcc
knows these are just immediate offsets) so the c code can nicely stay the same
(alternatively could use offsets directly in the functions needing the
tables). This should produce the same code as before with non-pic and better
code (confirmed) with pic.

The assembly uses the new table but still won't work for PIC case.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

Signed-off-by: Diego Biurrun <diego@biurrun.de>

As pointed by Paul B Mahol <onemda@gmail.com> the previous code could
lead to null pointer dereference.

Its behaviour in line with ffurl_close(NULL).

Skip to parse fields for additional independent substreams and its
associated dependent substreams since libavcodec's E-AC-3 decoder does not
support them yet.
Signed-off-by: Justin Ruggles <justin.ruggles@gmail.com>

This fixes crashes, where the demuxer could return 0 even
if the returned AVPacket isn't initialized at all. This
could happen if running into EOF or running out of probesize
with non-seekable sources.
Signed-off-by: Martin Storsjö <martin@martin.st>

Ignoring all files that start with the name of a library matches some
files that are not generated.  So replace libfoo/libfoo* with patterns
for static and shared libraries, pkg-config and version files.

Indexing outside an array is invalid and causes errors with
gcc 4.8.
Signed-off-by: Mans Rullgard <mans@mansr.com>

Signed-off-by: Mans Rullgard <mans@mansr.com>

This disables the warning "external declaration in primary source file"
which is issued when a prototype for an extern function is found in a
.c file rather than a header file.  We have such prototypes for asm
functions where a separate header file would be pointless.
Signed-off-by: Mans Rullgard <mans@mansr.com>

This can be useful for testing.
Signed-off-by: Mans Rullgard <mans@mansr.com>

Signed-off-by: Mans Rullgard <mans@mansr.com>

This moves the cpu flag parsing code from avconv to avutil so
it can be accessed elsewhere.
Signed-off-by: Mans Rullgard <mans@mansr.com>

The assembler may fail to place literal pools close enough to
instructions referencing them.  An explicit .ltorg directive
fixes this.
Signed-off-by: Mans Rullgard <mans@mansr.com>

Based on patch by Ronald S. Bultje <rsbultje@gmail.com>,
partially ported from libvpx.
Signed-off-by: Mans Rullgard <mans@mansr.com>

This is a preparation for complete ARMv6 optimisations.
Signed-off-by: Mans Rullgard <mans@mansr.com>

This adds some macros simplifying Thumb and pre-v6T2 compatibility.
Signed-off-by: Mans Rullgard <mans@mansr.com>

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>

An invalid duration is AV_NOPTS_VALUE not 0.

This uses correct stereo to 5.1 upmixing via libavresample.

This is a new library for audio sample format, channel layout, and sample rate
conversion.

This partially reverts acb17302
which would only have needed to change the checksums if channel mixing had
been properly avoided. This changes the output file size reference and the
seek test reference back to the previous values.

DTS LBR identifier ('dtse') is not included since libavcodec doesn't support it yet.
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>

The new incremental parser doesn't always clear prev_pkt,
however the packet queue is cleared when seeking. Which leads
to a use-after-free.

Verified using Valgrind.
Signed-off-by: Dale Curtis <dalecurtis@chromium.org>
Signed-off-by: Justin Ruggles <justin.ruggles@gmail.com>

Aligning nb_samples will give both correct plane pointer alignment and enough
padding for SIMD-optimized functions.

Fixes a division by 0.

Found-by: Mateusz "j00ru" Jurczyk and Gynvael Coldwind
Signed-off-by: Martin Storsjö <martin@martin.st>

libschroedinger is the preferred way to decode Dirac video.

Reduces the amount of upfront data required for cluster parsing
thus decreasing latency on seek and startup.

The change in the seek-lavf_mkv FATE test is due to incremental
parsing no longer reading as much data as the old parser and
thus not having that additional data to generate index entries
based on keyframes.  Index entries are added correctly as the
file is parsed.

All FATE tests pass and Chrome has been using this patch for ~6
months without issue.

Currently incremental parsing is not supported for files with
SSA tracks since they require merging packets between clusters.
In this case the code falls back to non-incremental parsing.
Signed-off-by: Aaron Colwell <acolwell@chromium.org>
Signed-off-by: Dale Curtis <dalecurtis@chromium.org>
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>

nb_input_files is already an invalid index.

The mpegts demuxer reads 5 KB at startup just for discovering
the packet size. Since the default avio buffer size is 32 KB,
the seek back to the start will in most cases be within the
avio buffer, and will in most cases succeed even if the actual
protocol isn't seekable.

This makes the demuxer startup faster/with less data when
reading data from a non-seekable input, by not skipping
the first few KB.

If it fails, don't warn if the protocol isn't seekable, making
it behave as before in the failure case.
Signed-off-by: Martin Storsjö <martin@martin.st>