From: Michael Niedermayer <michael@niedermayer.cc>
To: FFmpeg development discussions and patches <ffmpeg-devel@ffmpeg.org>
Subject: Re: [FFmpeg-devel] [PATCH v3 14/14] vvcdec: add full vvc decoder
Date: Mon, 4 Sep 2023 16:34:14 +0200
Message-ID: <20230904143414.GH8640@pb2> (raw)
In-Reply-To: <20230904142857.GG8640@pb2>
[-- Attachment #1.1: Type: text/plain, Size: 5394 bytes --]
On Mon, Sep 04, 2023 at 04:28:57PM +0200, Michael Niedermayer wrote:
> On Sun, Sep 03, 2023 at 12:07:41AM +0800, Nuo Mi wrote:
> > vvc decoder plug-in to avcodec.
> > split frames into slices/tiles and send them to vvc_thread for further decoding
> > reorder and wait for the frame decoding to be done and output the frame
> >
> > Features:
> > + Support I, P, B frames
> > + Support 8/10/12 bits, chroma 400, 420, 422, and 444 and range extension
> > + Support VVC new tools like MIP, CCLM, AFFINE, GPM, DMVR, PROF, BDOF, LMCS, ALF
> > + 295 conformace clips passed
> > - Not support RPR, IBC, PALETTE, and other minor features yet
> >
> > Performance:
> > C code FPS on i7-12700 (x86):
> > BQTerrace_1920x1080_60_10_420_22_RA.vvc 77.7
> > Chimera_8bit_1080P_1000_frames.vvc 174.3
> > NovosobornayaSquare_1920x1080.bin 163.7
> > RitualDance_1920x1080_60_10_420_32_LD.266 136.7
> > RitualDance_1920x1080_60_10_420_37_RA.266 154.3
> > Tango2_3840x2160_60_10_420_27_LD.266 30.0
> > Tango2_3840x2160_60_10_420_27_RA.266 29.0
> >
> > C code FPS on M1 Mac Pro (ARM):
> > BQTerrace_1920x1080_60_10_420_22_RA.vvc 58.7
> > Chimera_8bit_1080P_1000_frames.vvc 153.3
> > NovosobornayaSquare_1920x1080.bin 150.3
> > RitualDance_1920x1080_60_10_420_32_LD.266 105.0
> > RitualDance_1920x1080_60_10_420_37_RA.266 133.0
> > Tango2_3840x2160_60_10_420_27_LD.266 21.7
> >
> > Asm optimizations still working in progress. please check
> > https://github.com/ffvvc/FFmpeg/wiki#performance-data for the latest
> >
> > Contributors(based on code merge order):
> > Nuo Mi <nuomi2021@gmail.com>
> > Xu Mu <toxumu@outlook.com>
> > frankplow <post@frankplowman.com>
> > Shaun Loo <shaunloo10@gmail.com>
> > ---
> > libavcodec/vvc/vvcdec.c | 1025 ++++++++++++++++++++++++++++++++++++++-
> > 1 file changed, 1024 insertions(+), 1 deletion(-)
>
> are the fate tests like fate-cbs-vvc-SUBPIC_A_3 supposed to take really long
> after this ?
>
> (really long meaning longer than my patience before killing the task)
Heres a backtrace when i stop it
[vvc @ 0x555558699e40] Skipping NAL unit 19
[vvc @ 0x555558699e40] Skipping NAL unit 24
[vvc @ 0x555558699e40] Skipping NAL unit 19
[vvc @ 0x555558699e40] Skipping NAL unit 24
[vvc @ 0x555558699e40] Skipping NAL unit 19
^C
Thread 1 "ffmpeg_g" received signal SIGINT, Interrupt.
__lll_lock_wait () at ../sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135
135 ../sysdeps/unix/sysv/linux/x86_64/lowlevellock.S: No such file or directory.
(gdb) bt
#0 __lll_lock_wait () at ../sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135
#1 0x00007ffff00c4025 in __GI___pthread_mutex_lock (mutex=0x5555586d3540) at ../nptl/pthread_mutex_lock.c:80
#2 0x00005555567d24d5 in strict_pthread_mutex_lock (mutex=0x5555586d3540) at libavutil/thread.h:91
#3 0x00005555567d2e6c in av_executor_execute (e=0x5555586d3500, t=0x555558dc7900) at libavutil/executor.c:187
#4 0x0000555556642195 in ff_vvc_frame_add_task (s=0x55555869b400, t=0x555558dc7900) at libavcodec/vvc/vvc_thread.c:770
#5 0x000055555627f997 in decode_slice (s=0x55555869b400, fc=0x7ffff7f3b0b0, nal=0x555558721f30, unit=0x55555873e498) at libavcodec/vvc/vvcdec.c:825
#6 0x000055555627fa48 in decode_nal_unit (s=0x55555869b400, fc=0x7ffff7f3b0b0, nal=0x555558721f30, unit=0x55555873e498) at libavcodec/vvc/vvcdec.c:851
#7 0x000055555627fc11 in decode_nal_units (s=0x55555869b400, fc=0x7ffff7f3b0b0, avpkt=0x55555869ba00) at libavcodec/vvc/vvcdec.c:897
#8 0x0000555556280007 in vvc_decode_frame (avctx=0x555558699e40, output=0x55555869b0c0, got_output=0x7fffffffd400, avpkt=0x55555869ba00) at libavcodec/vvc/vvcdec.c:989
#9 0x0000555555d9fa3c in decode_simple_internal (avctx=0x555558699e40, frame=0x55555869b0c0, discarded_samples=0x7fffffffd460) at libavcodec/decode.c:432
#10 0x0000555555d9ff93 in decode_simple_receive_frame (avctx=0x555558699e40, frame=0x55555869b0c0) at libavcodec/decode.c:606
#11 0x0000555555da0103 in decode_receive_frame_internal (avctx=0x555558699e40, frame=0x55555869b0c0) at libavcodec/decode.c:634
#12 0x0000555555da04c8 in avcodec_send_packet (avctx=0x555558699e40, avpkt=0x555559917c88) at libavcodec/decode.c:731
#13 0x0000555555a9d3d8 in try_decode_frame (s=0x555558698900, st=0x5555586999c0, pkt=0x555559917c88, options=0x55555869a3c0) at libavformat/demux.c:2075
#14 0x0000555555aa01f2 in avformat_find_stream_info (ic=0x555558698900, options=0x55555869a3c0) at libavformat/demux.c:2771
#15 0x0000555555697446 in ifile_open (o=0x7fffffffdaa0, filename=0x7fffffffe56b "fate-suite//vvc-conformance/SUBPIC_A_3.bit") at fftools/ffmpeg_demux.c:1538
#16 0x00005555556baaf6 in open_files (l=0x555558698218, inout=0x55555687dc92 "input", open_file=0x555555696649 <ifile_open>) at fftools/ffmpeg_opt.c:1284
#17 0x00005555556bac9e in ffmpeg_parse_options (argc=22, argv=0x7fffffffe1c8) at fftools/ffmpeg_opt.c:1324
#18 0x00005555556c8c06 in main (argc=22, argv=0x7fffffffe1c8) at fftools/ffmpeg.c:1314
[...]
--
Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB
Everything should be made as simple as possible, but not simpler.
-- Albert Einstein
[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 195 bytes --]
[-- Attachment #2: Type: text/plain, Size: 251 bytes --]
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
next prev parent reply other threads:[~2023-09-04 14:34 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20230902160741.19197-1-nuomi2021@gmail.com>
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 02/14] vvcdec: add vvc_data Nuo Mi
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 03/14] vvcdec: add parameter parser for sps, pps, ph, sh Nuo Mi
2023-09-05 13:07 ` [FFmpeg-devel] [PATCH v4] " Nuo Mi
2023-10-15 8:54 ` [FFmpeg-devel] [PATCH v3 03/14] " Andreas Rheinhardt
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 04/14] vvcdec: add cabac decoder Nuo Mi
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 05/14] vvcdec: add reference management Nuo Mi
2023-10-15 9:45 ` Andreas Rheinhardt
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 06/14] vvcdec: add motion vector decoder Nuo Mi
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 07/14] vvcdec: add inter prediction Nuo Mi
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 08/14] vvcdec: add inv transform 1d Nuo Mi
2023-10-15 9:49 ` Andreas Rheinhardt
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 09/14] vvcdec: add intra prediction Nuo Mi
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 10/14] vvcdec: add LMCS, Deblocking, SAO, and ALF filters Nuo Mi
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 11/14] vvcdec: add dsp init and inv transform Nuo Mi
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 12/14] vvcdec: add CTU parser Nuo Mi
2023-10-15 10:17 ` Andreas Rheinhardt
2023-10-15 10:31 ` Nuo Mi
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 13/14] vvcdec: add CTU thread logical Nuo Mi
2023-09-02 16:07 ` [FFmpeg-devel] [PATCH v3 14/14] vvcdec: add full vvc decoder Nuo Mi
2023-09-02 16:14 ` Nuo Mi
2023-09-04 14:28 ` Michael Niedermayer
2023-09-04 14:34 ` Michael Niedermayer [this message]
2023-09-05 13:16 ` Nuo Mi
2023-10-15 1:26 ` Nuo Mi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230904143414.GH8640@pb2 \
--to=michael@niedermayer.cc \
--cc=ffmpeg-devel@ffmpeg.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
This inbox may be cloned and mirrored by anyone:
git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git
# If you have public-inbox 1.1+ installed, you may
# initialize and index your mirror using the following commands:
public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
ffmpegdev@gitmailbox.com
public-inbox-index ffmpegdev
Example config snippet for mirrors.
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git