Still much left to optimize, but it provides a significant performance
improvement - 10% for 300Mbps (1080p30), 25% for 1.5Gbps (4k 60fps) in
comparison with the default implementation.
Signed-off-by: Rostislav Pehlivanov <rpehlivanov@obe.tv>
Now coefficients are written to a buffer and are then dequantized by the
new SIMD dequantization functions. For the lower bands without enough
coefficients to fill a register (and hence they overwrite) the C version
of the dequantization function is used.
The buffer is per-thread and will be realloc'd if anything changes.
This prevents regressions and having to limit slice size.
Signed-off-by: Rostislav Pehlivanov <rpehlivanov@obe.tv>
Prevents having to have random magic values in the decoder and a
separate macro in the encoder.
Signed-off-by: Rostislav Pehlivanov <rpehlivanov@obe.tv>
In preparation for the following commits, this commit simplifies the
coefficient parsing and dequantization function. It was needlessly
inlined without much performance gain.
Signed-off-by: Rostislav Pehlivanov <rpehlivanov@obe.tv>
This allows simpler selection of flac in ogg from the command line,
while following the RFC 5334 recommendation[1] for the oga extension.
[1] https://tools.ietf.org/html/rfc5334#section-10.3
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: James Almer <jamrial@gmail.com>
Currently, SPS.mb_height is actually what the spec calls
PicHeightInMapUnits, which is half the frame height when interlacing is
allowed. Calling this 'mb_height' is quite confusing, and there are at
least two associated bugs where this field is treated as the actual
frame height - in the h264 parser and in the code computing maximum
reordering buffer size for a given level.
Fix those issues (and avoid possible future ones) by exporting the real
frame height in this field.
support split hls segment at duration set by hls_time
Signed-off-by: LiuQi <liuqi@gosun.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
This comment isn't true, the height can be different from the width
for these functions (which is why the height is passed as a parameter
to them).
Signed-off-by: Martin Storsjö <martin@martin.st>
GNU as evaluates true as '-1' while Apple's variant and llvm's internal
assembler evaluate it as '1'. The best way to avoid this madness is to
eliminate boolean expressions instead of trying to fix it with
preprocessor directives. Use a direct formula to calculate the
required temporary space on the stack in
ff_put_vp8_{epel,bilin}{4,8,16}_h[246]v[246]_armv6().
Fixes a checkasm segfault in vp8dsp.mc when using llvm's internal
assembler for a non-Apple target.
This is an - once again - updated patch, that uses avio_write instead
of avio_puts to stream clean text output without null characters. Works
now for me as intended.
Changes metadata filter to accept general urls as file argument without
breaking former behaviour. As a byproduct, it also allows for writing to
file "-" if specified as "file:-".
Example:
ffmpeg -i test.wav -filter_complex "silencedetect=n=-40dB:d=0.1,ametadata=mode=print:file='pipe\:4'" -f null
Signed-off-by: Sami Hult <sami.hult@gmail.com>
Reviewed-by: Paul B Mahol <onemda@gmail.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
This reverts commit cb8646af24.
This change has brough more issues than benefits, between compilation
time failures depending on flags used and code miscompilation causing
runtime crashes.
See the "[PATCH 2/2] configure: Enable GCC vectorization on ≥4.9"
thread in the ffmpeg-devel mailing list for the relevant discussion.
This reverts commit c67aa7f287e791b2c02c0c6471336c8adc88020e, reversing
changes made to 46bd0e8e0d.
The merge should have been a noop as the support was added in
601c238854
* commit 'a2ddfadc2d9e91cf70aa7430a7340b418bdb5b42':
avdevice: Ignore timefilter test program
This commit is a noop, /timefilter entry was added in the original merge
(5d48e4eafa)
Merged-by: Clément Bœsch <u@pkh.me>
* commit 'd6c2c2796d8885e99fc90793cdd7937826f82fab':
LICENSE: Fix silly typo
This commit is a noop, the typo disappeared when the whole paragraph was
reworked in 484aec4da3.
Merged-by: Clément Bœsch <u@pkh.me>
* commit '05a4bacbf7ece618553d339afe1d0b57bc87aea8':
avpacket: Error out when creating 0-sized side data
This commit is a noop, see 5a633ec2dd
AV_PKT_DATA_METADATA_UPDATE can be zero sized in order to clear old
meta.
Note: maybe we could add a start or end marker.
Merged-by: Clément Bœsch <u@pkh.me>
* commit '61f168ae348f94f39e7afc6971654455a5de0e4d':
h264: factor out setting the parameter sets for a frame
Michael's changes on top of the merge undo parts of the original diff
that are not factorization:
"The call point is left where it was before. Such a change should be in
a separate commit and has multiple issues, one being null pointer
dereferences the other is that some safety checks would become
conditional.
I tried to split the PPS init between the new and old functions
similarly to the SPS code."
Merged-by: Clément Bœsch <u@pkh.me>
Merged-by: Michael Niedermayer <michael@niedermayer.cc>
When writing a fragmented file, we by default write an index pointing
to all the fragments at the end of the file. This causes constantly
increasing memory usage during the muxing. For live streams, the
index might not be useful at all.
A similar fragment index is written (but at the start of the file) if
the global_sidx flag is set. If ism_lookahead is set, we need to keep
data about the last ism_lookahead+1 fragments.
If no fragment index is to be written, we don't need to store information
about all fragments, avoiding increasing the memory consumption
linearly with the muxing runtime.
This fixes out of memory situations with long live mp4 streams.
Signed-off-by: Martin Storsjö <martin@martin.st>
Rostislav Pehlivanov
Rostislav Pehlivanov
Carl Eugen Hoyos
James Almer
Anton Khirnov
Steve Lhomme
Ronald S. Bultje
Michael Niedermayer
Steven Liu
Marton Balint
Martin Storsjö
Janne Grunau
Sami Hult
Clément Bœsch
Matthieu Bouron
Hendrik Leppkes