[FFmpeg-user] slow performance with lut3d filter

Tue Feb 11 23:11:43 CET 2014

I'm getting very slow performance with the lut3d filter.  Is this
normal, or is there some way to improve it?  This test encode runs at
5fps, compared to the same operation without lut3d at 40fps.  CPU
usage is less than 10% during the whole encode.  I'm using a 12 core
Mac Pro.  Source footage is ProRes 4444 from Arri Alexa camera.

$ ffmpeg -i input.mov -vf lut3d=file=/Users/dit/LogCto709.dat test4.mov
ffmpeg version N-57394-gea9632b Copyright (c) 2000-2013 the FFmpeg developers
  built on Oct 24 2013 11:58:12 with Apple LLVM version 5.0
(clang-500.2.79) (based on LLVM 3.3svn)
  configuration: --enable-gpl --enable-version3 --enable-nonfree
--enable-static --enable-libass --enable-libbluray --enable-libfdk-aac
--enable-libmp3lame --enable-libvpx --enable-libx264 --enable-opencl
--enable-libfreetype --disable-shared --enable-libopenjpeg
--enable-libvorbis --enable-libtheora
  libavutil      52. 47.101 / 52. 47.101
  libavcodec     55. 38.101 / 55. 38.101
  libavformat    55. 19.104 / 55. 19.104
  libavdevice    55.  5.100 / 55.  5.100
  libavfilter     3. 89.100 /  3. 89.100
  libswscale      2.  5.101 /  2.  5.101
  libswresample   0. 17.104 /  0. 17.104
  libpostproc    52.  3.100 / 52.  3.100
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from 'input.mov':
  Metadata:
    major_brand     : qt
    minor_version   : 537199360
    compatible_brands: qt  ARRI
    creation_time   : 2014-02-11 19:27:14
    timecode        : 03:16:55:05
  Duration: 00:00:08.38, start: 0.000000, bitrate: 398876 kb/s
    Stream #0:0(eng): Video: prores (ap4h / 0x68347061), yuv444p10le,
2048x1152, 315153 kb/s, SAR 1:1 DAR 16:9, 23.98 fps, 23.98 tbr, 23976
tbn, 23976 tbc (default)
    Metadata:
      creation_time   : 2014-02-11 19:27:14
      handler_name    : Apple Alias Data Handler
    Stream #0:1(eng): Data: none (tmcd / 0x64636D74), 0 kb/s (default)
    Metadata:
      creation_time   : 2014-02-11 19:27:14
      handler_name    : Apple Alias Data Handler
      timecode        : 03:16:55:05
[swscaler @ 0x7ff214801600] full chroma interpolation for destination
format 'rgb48le' not yet implemented
No pixel format specified, yuv444p for H.264 encoding chosen.
Use -pix_fmt yuv420p for compatibility with outdated media players.
[libx264 @ 0x7ff213804200] using SAR=1/1
[libx264 @ 0x7ff213804200] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2
[libx264 @ 0x7ff213804200] profile High 4:4:4 Predictive, level 5.0, 4:4:4 8-bit
[libx264 @ 0x7ff213804200] 264 - core 138 r2358 9e941d1 - H.264/MPEG-4
AVC codec - Copyleft 2003-2013 - http://www.videolan.org/x264.html -
options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7
psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1
8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=4
threads=36 lookahead_threads=6 sliced_threads=0 nr=0 decimate=1
interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2
b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250
keyint_min=23 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf
mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40
aq=1:1.00
Output #0, mov, to 'test4.mov':
  Metadata:
    major_brand     : qt
    minor_version   : 537199360
    compatible_brands: qt  ARRI
    timecode        : 03:16:55:05
    encoder         : Lavf55.19.104
    Stream #0:0(eng): Video: h264 (libx264) (avc1 / 0x31637661),
yuv444p, 2048x1152 [SAR 1:1 DAR 16:9], q=-1--1, 11988 tbn, 23.98 tbc
(default)
    Metadata:
      creation_time   : 2014-02-11 19:27:14
      handler_name    : Apple Alias Data Handler
Stream mapping:
  Stream #0:0 -> #0:0 (prores -> libx264)
Press [q] to stop, [?] for help
frame=  201 fps=4.8 q=-1.0 Lsize=    2404kB time=00:00:08.29
bitrate=2372.4kbits/s
video:2400kB audio:0kB subtitle:0 global headers:0kB muxing overhead 0.155687%
[libx264 @ 0x7ff213804200] frame I:1     Avg QP:22.17  size:352961
[libx264 @ 0x7ff213804200] frame P:54    Avg QP:22.96  size: 27005
[libx264 @ 0x7ff213804200] frame B:146   Avg QP:26.23  size:  4421
[libx264 @ 0x7ff213804200] consecutive B-frames:  0.5%  5.0%  9.0% 85.6%
[libx264 @ 0x7ff213804200] mb I  I16..4:  4.8% 69.3% 25.9%
[libx264 @ 0x7ff213804200] mb P  I16..4:  4.3%  3.6%  0.3%  P16..4:
43.7%  8.3%  6.7%  0.0%  0.0%    skip:33.1%
[libx264 @ 0x7ff213804200] mb B  I16..4:  0.7%  0.6%  0.0%  B16..8:
26.6%  0.6%  0.1%  direct: 0.4%  skip:70.9%  L0:40.2% L1:59.1% BI:
0.7%
[libx264 @ 0x7ff213804200] 8x8 transform intra:47.5% inter:80.8%
[libx264 @ 0x7ff213804200] coded y,u,v intra: 34.7% 15.5% 22.5% inter:
5.2% 1.5% 4.1%
[libx264 @ 0x7ff213804200] i16 v,h,dc,p: 18% 21%  6% 55%
[libx264 @ 0x7ff213804200] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 20% 21% 21%
7%  5%  5%  6%  6%  9%
[libx264 @ 0x7ff213804200] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 27% 22% 11%
5%  7%  7%  7%  6%  8%
[libx264 @ 0x7ff213804200] Weighted P-Frames: Y:0.0% UV:0.0%
[libx264 @ 0x7ff213804200] ref P L0: 39.1% 10.0% 31.7% 19.2%
[libx264 @ 0x7ff213804200] ref B L0: 74.9% 18.0%  7.2%
[libx264 @ 0x7ff213804200] ref B L1: 86.2% 13.8%
[libx264 @ 0x7ff213804200] kb/s:2344.41