| Commit message (Collapse) | Author | Age |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Async depth will allow qsv filter cache few frames, and avoid force
switch and end filter task frame by frame. This change will improve
performance for some multi-task case, for example 1:N transcode(
decode + vpp + encode) with all QSV plugins.
Performance data test on my Coffee Lake Desktop(i7-8700K) by using
the following 1:8 transcode test case improvement:
1. Fps improved from 55 to 130.
2. Render/Video usage improved from ~61%/~38% to ~100%/~70%.(Data get
from intel_gpu_top)
test CMD:
ffmpeg -v verbose -init_hw_device qsv=hw:/dev/dri/renderD128 -filter_hw_device \
hw -hwaccel qsv -hwaccel_output_format qsv -c:v h264_qsv -i 1920x1080.264 \
-vf 'vpp_qsv=w=1280:h=720:async_depth=4' -c:v h264_qsv -r:v 30 -preset 7 -g 33 -refs 2 -bf 3 -q 24 -f null - \
-vf 'vpp_qsv=w=1280:h=720:async_depth=4' -c:v h264_qsv -r:v 30 -preset 7 -g 33 -refs 2 -bf 3 -q 24 -f null - \
-vf 'vpp_qsv=w=1280:h=720:async_depth=4' -c:v h264_qsv -r:v 30 -preset 7 -g 33 -refs 2 -bf 3 -q 24 -f null - \
-vf 'vpp_qsv=w=1280:h=720:async_depth=4' -c:v h264_qsv -r:v 30 -preset 7 -g 33 -refs 2 -bf 3 -q 24 -f null - \
-vf 'vpp_qsv=w=1280:h=720:async_depth=4' -c:v h264_qsv -r:v 30 -preset 7 -g 33 -refs 2 -bf 3 -q 24 -f null - \
-vf 'vpp_qsv=w=1280:h=720:async_depth=4' -c:v h264_qsv -r:v 30 -preset 7 -g 33 -refs 2 -bf 3 -q 24 -f null - \
-vf 'vpp_qsv=w=1280:h=720:async_depth=4' -c:v h264_qsv -r:v 30 -preset 7 -g 33 -refs 2 -bf 3 -q 24 -f null -
Signed-off-by: Fei Wang <fei.w.wang@intel.com>
Reviewed-by: Linjie Fu <linjie.justin.fu@gmail.com>
Signed-off-by: Zhong Li <zhongli_dev@126.com>
|
|
|
|
|
|
|
|
| |
Dump iopattern mode and the SDK error/warning desciptions for qsv based
filters and iopattern mode for qsvenc
Signed-off-by: Haihao Xiang <haihao.xiang@intel.com>
Signed-off-by: Linjie Fu <linjie.justin.fu@gmail.com
|
|
|
|
|
|
|
|
| |
It is a copy of the relevant part in lavc/qsv but use different function
names to avoid multiple definition when linking lavc and lavf statically.
Signed-off-by: Haihao Xiang <haihao.xiang@intel.com>
Signed-off-by: Linjie Fu <linjie.justin.fu@gmail.com
|
|
|
|
| |
Signed-off-by: Zhong Li <zhong.li@intel.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
extra_hw_frames is needed for some cases.
(eg: qsv decoding + qsv vpp + qsv look_ahead encoding, transcoding
failed if no extra_hw_frames supported:
ffmpeg -hwaccel qsv -c:v h264_qsv -i bbb_sunflower_1080p_30fps_normal_2000frames.mp4 \
-vf vpp_qsv=w=1280:h=720:extra_hw_frames=100 -v verbose -c:v h264_qsv \
-look_ahead 1 -look_ahead_depth 100 out1.mp4
)
Signed-off-by: Zhong Li <zhong.li@intel.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Currently, picref will be freed by calling av_frame_free(&picref) in
submit_frame() in qsvvpp.c when working in system memory mode,and normally it
is freed in filter_frame() in vf_vpp_qsv.c when working in other modes.
Double free happens when working in system memory mode, remove to
fix the memory issue.
Reproduce:
ffmpeg -init_hw_device qsv=foo -filter_hw_device foo -f rawvideo -pix_fmt nv12 -s:v 852x480 \
-i 852x480.nv12 -vf 'vpp_qsv=w=500:h=400' -f rawvideo -pix_fmt nv12 qsv.nv12
Signed-off-by: Linjie Fu <linjie.fu@intel.com>
Signed-off-by: Zhong Li <zhong.li@intel.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
RGB32(AV_PIX_FMT_BGRA on intel platforms) format may be used as overlay with alpha blending.
So add AV_PIX_FMT_BGRA format support.
One example of alpha blending overlay: ffmpeg -hwaccel qsv -c:v h264_qsv -i BA1_Sony_D.jsv
-filter_complex 'movie=lena-rgba.png,hwupload=extra_hw_frames=16[a];[0:v][a]overlay_qsv=x=10:y=10'
-c:v h264_qsv -y out.mp4
Rename RGB32 to be BGRA to make it clearer as Mark Thompson's suggestion.
V2: Add P010 format support else will introduce HEVC 10bit encoding regression.
Thanks for LinJie's discovery.
Signed-off-by: Zhong Li <zhong.li@intel.com>
Verified-by: Fu, Linjie <linjie.fu@intel.com>
|
|\
| |
| |
| |
| |
| |
| | |
* commit 'e05e5920a4e1f1f15cc8a7c843159d519f6ec18e':
qsv: Error out if getting session handle failed in avfilter
Merged-by: James Almer <jamrial@gmail.com>
|
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Solve some issues found by an automated code scansion.
Suppress the complain "variables 'handle' is used but maybe
uninitialized".
Signed-off-by: Zhong Li <zhong.li@intel.com>
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
For filters based on framesync, the input frame was managed
by framesync, so we should not directly keep and destroy it,
instead we make a clone of it here, or else double-free will occur.
But for other filters not based on framesync, we still need to
free the input frame inside filter_frame.
Signed-off-by: Ruiling Song <ruiling.song@intel.com>
|
|\|
| |
| |
| |
| |
| |
| | |
* commit 'cca5e4f040971db6de0bfe6968f00c021d8a9c42':
qsv: adding Multi Frame Encode support
Merged-by: James Almer <jamrial@gmail.com>
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Starting from API 1.25 helps to improve performance of the simultaneous
encode, 1:N scenario, like:
./avconv -y -hwaccel qsv -c:v h264_qsv -r 30000/1001 -i
~/bbb_sunflower_1080p_60fps_normal.mp4 -vframes 600 -an \
-filter_complex "split=2[s1][s2]; [s1]scale_qsv=1280:720[o1];
[s2]scale_qsv=960:540[o2]" \
-map [o1] -c:v h264_qsv -b:v 3200k -minrate 3200k -maxrate 3200k -f
rawvideo /tmp/3200a.264 \
-map [o2] -c:v h264_qsv -b:v 1750k -minrate 1750k -maxrate 1750k -f
rawvideo /tmp/1750a.264
Signed-off-by: Maxym Dmytrychenko <maxim.d33@gmail.com>
|
|\|
| |
| |
| |
| |
| |
| | |
* commit 'ea25ccd1b2a980df8d43cc1f86a23e3c094090a6':
qsv: Join the derived session to the parent
Merged-by: James Almer <jamrial@gmail.com>
|
| |
| |
| |
| |
| | |
Should improve the performance on multiple transcoding from a single
source.
|
|/
|
|
|
|
|
|
| |
* commit 'a5a6ac1a123a927e5bed984ed757a29b7ff87dab':
libavfilter/overlay_qsv: Add QSV overlay vpp filter
libavfilter/vf_vpp: Add common filters of the qsv vpp
Merged-by: James Almer <jamrial@gmail.com>
|
|
The filter supports two inputs and (implicitly) scaling the second input
during composition, unlike the software overlay.
The code has been separated into common interface and qsv overlay
implementation. The common part mainly creates the qsv session and
manages the surface which is nearly the same for all qsv filters.
So the qsvvpp.c/qsvvpp.h API can be used by other QSV vpp filters
to reduce code redundancy.
Usage:
-hwaccel qsv -c:v mpeg2_qsv -r 25 -i in.m2v -hwaccel qsv -c:v h264_qsv
-i in.h264 -filter_complex
"overlay_qsv=eof_action=repeat:x=(W-w)/2:y=(H-h)/2" -b 2M -maxrate 3M
-c:v h264_qsv -y out.h264
Two inputs should have different sizes otherwise one will be completely
covered or you need to scale the second input as follows:
-hwaccel qsv -c:v mpeg2_qsv -r 25 -i in.m2v -hwaccel qsv -c:v h264_qsv
-i in.h264 -filter_complex
"overlay_qsv=w=720:h=576:x=(W-w)/2:y=(H-h)/2" -b 2M -maxrate 3M -c:v
h264_qsv -y out.h264
Signed-off-by: ChaoX A Liu <chaox.a.liu@gmail.com>
Signed-off-by: Zhengxu Huang <zhengxu.maxwell@gmail.com>
Signed-off-by: Andrew Zhang <huazh407@gmail.com>
Change-Id: I5c381febb0af6e2f9622c54ba00490ab99d48297
Signed-off-by: Maxym Dmytrychenko <maxim.d33@gmail.com>
|