Makes Bulldozer prefer AVX functions rather than AVX2,
which are 64% slower:
AVX: 117653 decicycles in av_tx (fft), 1048535 runs, 41 skips
AVX2: 193385 decicycles in av_tx (fft), 1048561 runs, 15 skips
The only difference between both is that vgatherdpd is used in
the former. We don't want to mark them with the new SLOW_GATHER
flag however, since gathers are still faster on Haswell/Zen 2/3
than plain loads.
If a codelet initializes 2 subtransforms, and the second one fails,
the failure would free all subcontexts.
Instead, if there are subcontexts still left, don't free the array.
If all initializations fail, the init() function will return,
and reset_ctx() from the previous step will clean up all contained
subtransforms.
Fix CID: 1497864
The control flow should return ENOSYS if nb_cd_matches is 0 at before
and the ret equal AVERROR(ENOMEM) or goto end label, so remove the last
control flow if (ret >= 0) before end label.
Signed-off-by: Steven Liu <liuqi05@kuaishou.com>
This broke builds with --disable-mmx, which also disabled assembly
entirely, but ARCH_X86 was still true, so the init file tried to find
assembly that didn't exist.
Instead of checking for architecture, check if external x86 assembly
is enabled.
RDFTs are full of conventions that vary between implementations.
What I've gone for here is what's most common between
both fftw, avcodec's rdft and what we use, the equivalent of
which is DFT_R2C for forward and IDFT_C2R for inverse. The
other 2 conventions (IDFT_R2C and DFT_C2R) were not used at
all in our code, and their names are also not appropriate.
If there's a use for either, we can easily add a flag which
would just flip the sign on one exptab.
For some unknown reason, possibly to allow reusing FFT's exp tables,
av_rdft's C2R output is 0.5x lower than what it should be to ensure
a proper back-and-forth conversion.
This code outputs its real samples at the correct level, which
matches FFTW's level, and allows the user to change the level
and insert arbitrary multiplies for free by setting the scale option.
This commit rewrites the internal transform code into a constructor
that stitches transforms (codelets).
This allows for transforms to reuse arbitrary parts of other
transforms, and allows transforms to be stacked onto one
another (such as a full iMDCT using a half-iMDCT which in turn
uses an FFT). It also permits for each step to be individually
replaced by assembly or a custom implementation (such as an ASIC).
qHD is 960x540 (q stands for quarter) and QHD is 2560x1440 (Q is quad).
use quadhd for QHD for abbreviation.
Fix ticket#9591
Signed-off-by: Limin Wang <lance.lmwang@gmail.com>
Trying to write too much will currently overwrite previous data. Trying
to read too much will either av_assert2() in av_fifo_drain() or return
old data. Trying to peek too much will either av_assert2() in
av_fifo_generic_peek_at() or return old data.
Return an error code in all these cases, which is safer and more
consistent.
It returns a pointer inside the fifo's buffer, which cannot be safely
used without accessing AVFifoBuffer internals. It is easier and safer to
use av_fifo_generic_peek_at().
The test /libavutil/tests/hwdevice checks that when deriving a device
from a source device and then deriving back to the type of the source
device, the result is matching the original source device, i.e. the
derivation mechanism doesn't create a new device in this case.
Previously, this test was usually passed, but only due to two different
kind of flaws:
1. The test covers only a single level of derivation (and back)
It derives device Y from device X and then Y back to the type of X and
checks whether the result matches X.
What it doesn't check for, are longer chains of derivation like:
CUDA1 > OpenCL2 > CUDA3 and then back to OpenCL4
In that case, the second derivation returns the first device (CUDA3 ==
CUDA1), but when deriving OpenCL4, hwcontext.c was creating a new
OpenCL4 context instead of returning OpenCL2, because there was no link
from CUDA1 to OpenCL2 (only backwards from OpenCL2 to CUDA1)
If the test would check for two levels of derivation, it would have
failed.
This patch fixes those (yet untested) cases by introducing forward
references (derived_device) in addition to the existing back references
(source_device).
2. hwcontext_qsv didn't properly set the source_device
In case of QSV, hwcontext_qsv creates a source context internally
(vaapi, dxva2 or d3d11va) without calling av_hwdevice_ctx_create_derived
and without setting source_device.
This way, the hwcontext test ran successful, but what practically
happened, was that - for example - deriving vaapi from qsv didn't return
the original underlying vaapi device and a new one was created instead:
Exactly what the test is intended to detect and prevent. It just
couldn't do so, because the original device was hidden (= not set as the
source_device of the QSV device).
This patch properly makes these setting and fixes all derivation
scenarios.
(at a later stage, /libavutil/tests/hwdevice should be extended to check
longer derivation chains as well)
Reviewed-by: Lynne <dev@lynne.ee>
Reviewed-by: Anton Khirnov <anton@khirnov.net>
Tested-by: Wenbin Chen <wenbin.chen@intel.com>
Signed-off-by: softworkz <softworkz@hotmail.com>
Signed-off-by: Haihao Xiang <haihao.xiang@intel.com>
This is done a second time for 5.0 because master was
merged into 5.0 so that it contains the recent DOVI additions.
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
In order to be able to extend this struct later (as the Dolby Vision RPU
evolves), all of the 'container' structs are considered extensible, and
the individual constituent fields must instead be accessed via offsets.
The precedent for this style of access is set in
<libavutil/detection_bbox.h>
Signed-off-by: Niklas Haas <git@haasn.dev>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
We don't use it. Was copied from libplacebo's recommended defaults.
Creates problems with validation on Intel devices, where the driver
still advertizes it, even though it's not usable without a swapchain.
Fix#7830
When we upload a frame that is not padded as MSDK requires, we create a
new AVFrame to copy data. The frame's padding data is uninitialized so
it brings run to run problem. For example, If we run the following
command serveral times we will get different outputs.
ffmpeg -init_hw_device qsv=qsv:hw -qsv_device /dev/dri/renderD128 \
-filter_hw_device qsv -f rawvideo -s 192x200 -pix_fmt p010 \
-i 192x200_P010.yuv -vf "format=nv12,hwupload=extra_hw_frames=16" \
-c:v hevc_qsv output.265
According to https://github.com/Intel-Media-SDK/MediaSDK/blob/master/doc/mediasdk-man.md#encoding-procedures
"Note: It is the application's responsibility to fill pixels outside
of crop window when it is smaller than frame to be encoded. Especially
in cases when crops are not aligned to minimum coding block size (16
for AVC, 8 for HEVC and VP9)"
I add a function to fill padding area with border pixel to fix this
run2run problem, and also move the new AVFrame to global structure
to reduce redundant allocation operation to increase preformance.
Signed-off-by: Wenbin Chen <wenbin.chen@intel.com>
Signed-off-by: Haihao Xiang <haihao.xiang@intel.com>
The previous implementation swapped the two halves of the plaintext. The
existing tests only decrypted data with a plaintext of all zeroes, which is
not affected by swapping the halves. Tests which detect the old buggy behavior
have been added.
Signed-off-by: Sebastian Kirmayer <ffmpeg@kirmayer.eu>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
Andreas Rheinhardt
Timo Rothenpieler
nyanmisaka
Lynne
Steven Liu
Diederick Niehorster
Anton Khirnov
Limin Wang
Cameron Gutman
Wu Jianhua
Haihao Xiang
Soft Works
Niklas Haas
Michael Niedermayer
Wenbin Chen
rcombs
James Almer
Alan Kelly
Zhao Zhili
Aman Karmani
Sebastian Kirmayer