Recherche avancée

Sur d’autres sites (10521)

• x86inc : speed up compilation with yasm

  16 janvier 2014, par Loren Merritt

  x86inc : speed up compilation with yasm
  Work around yasm’s inefficiency with handling large numbers of variables
  
  in the global scope.
  

  • [DH] common/x86/x86inc.asm

• Speed up start of a stream recording with ffmpeg

  15 janvier 2014, par neutron

  I try to record a video stream (from the web or a local webcam stream) and save it to a .mp4 / .flv file. I use FFmpeg with the version"N-59696-gc0a33c4".

  The problem isn't the recording of the stream, it is, how log it tooks to start the recording.

  This are the parameters i used to capture the stream (the stream is some random stream I found on the web) :

  ffmpeg.exe -i mmsh://live.camstreams.com/cscamscape?MSWMExt=.asf -r 25 -t 60 C:\temp\video.mp4

  And leads to this output :

  ffmpeg.exe -i mmsh://live.camstreams.com/cscams
  
  cape?MSWMExt=.asf -r 25 -t 60 C:\temp\video.mp4
  
  ffmpeg version N-59696-gc0a33c4 Copyright (c) 2000-2014 the FFmpeg developers
  
    built on Jan  8 2014 22:01:50 with gcc 4.8.2 (GCC)
  
    configuration: --enable-gpl --enable-version3 --disable-w32threads --enable-av
  
  isynth --enable-bzlib --enable-fontconfig --enable-frei0r --enable-gnutls --enab
  
  le-iconv --enable-libass --enable-libbluray --enable-libcaca --enable-libfreetyp
  
  e --enable-libgsm --enable-libilbc --enable-libmodplug --enable-libmp3lame --ena
  
  ble-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-l
  
  ibopus --enable-librtmp --enable-libschroedinger --enable-libsoxr --enable-libsp
  
  eex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvo-aa
  
  cenc --enable-libvo-amrwbenc --enable-libvorbis --enable-libvpx --enable-libwavp
  
  ack --enable-libx264 --enable-libxavs --enable-libxvid --enable-zlib
  
    libavutil      52. 62.100 / 52. 62.100
  
    libavcodec     55. 47.100 / 55. 47.100
  
    libavformat    55. 22.102 / 55. 22.102
  
    libavdevice    55.  5.102 / 55.  5.102
  
    libavfilter     4.  0.103 /  4.  0.103
  
    libswscale      2.  5.101 /  2.  5.101
  
    libswresample   0. 17.104 /  0. 17.104
  
    libpostproc    52.  3.100 / 52.  3.100
  
  [wmv3 @ 0275db40] Extra data: 8 bits left, value: 0
  
  Input #0, asf, from 'mmsh://live.camstreams.com/cscamscape?MSWMExt=.asf':
  
    Metadata:
  
      title           : Live Fish Cam
  
      WMFSDKNeeded    : 0.0.0.0000
  
      DeviceConformanceTemplate: SP
  
      WMFSDKVersion   : 11.0.5721.5275
  
      IsVBR           : 0
  
    Duration: N/A, start: 3887858.274000, bitrate: 512 kb/s
  
      Stream #0:0(eng): Video: wmv3 (Simple) (WMV3 / 0x33564D57), yuv420p, 640x360
  
  , 512 kb/s, 62.50 tbr, 1k tbn, 1k tbc
  
  [libx264 @ 0275e400] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX
  
  [libx264 @ 0275e400] profile High, level 3.0
  
  [libx264 @ 0275e400] 264 - core 140 r2377 1ca7bb9 - H.264/MPEG-4 AVC codec - Cop
  
  yleft 2003-2013 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deb
  
  lock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 m
  
  e_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chro
  
  ma_qp_offset=-2 threads=12 lookahead_threads=2 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=25 scene
  
  cut=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
  
  [wmv3 @ 0275db40] Extra data: 8 bits left, value: 0
  
  Output #0, mp4, to 'C:\temp\video.mp4':
  
    Metadata:
  
      title           : Live Fish Cam
  
      WMFSDKNeeded    : 0.0.0.0000
  
      DeviceConformanceTemplate: SP
  
      WMFSDKVersion   : 11.0.5721.5275
  
      IsVBR           : 0
  
      encoder         : Lavf55.22.102
  
      Stream #0:0(eng): Video: h264 (libx264) ([33][0][0][0] / 0x0021), yuv420p, 6
  
  40x360, q=-1--1, 12800 tbn, 25 tbc
  
  Stream mapping:
  
    Stream #0:0 -> #0:0 (wmv3 -> libx264)
  
  Press [q] to stop, [?] for help
  
  frame=  148 fps=0.0 q=28.0 size=     228kB time=00:00:03.60 bitrate= 518.3kbits/
  
  frame=  151 fps=117 q=28.0 size=     236kB time=00:00:03.72 bitrate= 519.2kbits/
  
  frame=  178 fps= 91 q=28.0 size=     298kB time=00:00:04.80 bitrate= 508.3kbits/
  
  frame=  204 fps= 64 q=28.0 size=     347kB time=00:00:05.84 bitrate= 487.4kbits/
  
  ... 
  
  ... And so on ...

  The problem now is, that it takes around 6-10 seconds until the recording starts after I entered the command.

  Is there a way to speed up this process ?

• x86inc : Speed up assembling with Yasm

  19 janvier 2014, par Loren Merritt

  x86inc : Speed up assembling with Yasm
  Work around Yasm’s inefficiency with handling large numbers of variables
  
  in the global scope.
  Signed-off-by : Diego Biurrun <diego@biurrun.de>
  

  • [DH] libavutil/x86/x86inc.asm