Recherche avancée

Sur d’autres sites (6033)

• arm : vp9itxfm : Skip empty slices in the first pass of idct_idct 16x16 and 32x32

  9 janvier 2017, par Martin Storsjö

  arm : vp9itxfm : Skip empty slices in the first pass of idct_idct 16x16 and 32x32
  This work is sponsored by, and copyright, Google.
  Previously all subpartitions except the eob=1 (DC) case ran with
  
  the same runtime :
                                       Cortex A7       A8       A9      A53
  
  vp9_inv_dct_dct_16x16_sub16_add_neon :   3188.1   2435.4   2499.0   1969.0
  
  vp9_inv_dct_dct_32x32_sub32_add_neon :  18531.7  16582.3  14207.6  12000.3
  By skipping individual 4x16 or 4x32 pixel slices in the first pass,
  
  we reduce the runtime of these functions like this :
  vp9_inv_dct_dct_16x16_sub1_add_neon :     274.6    189.5    211.7    235.8
  
  vp9_inv_dct_dct_16x16_sub2_add_neon :    2064.0   1534.8   1719.4   1248.7
  
  vp9_inv_dct_dct_16x16_sub4_add_neon :    2135.0   1477.2   1736.3   1249.5
  
  vp9_inv_dct_dct_16x16_sub8_add_neon :    2446.7   1828.7   1993.6   1494.7
  
  vp9_inv_dct_dct_16x16_sub12_add_neon :   2832.4   2118.3   2266.5   1735.1
  
  vp9_inv_dct_dct_16x16_sub16_add_neon :   3211.7   2475.3   2523.5   1983.1
  
  vp9_inv_dct_dct_32x32_sub1_add_neon :     756.2    456.7    862.0    553.9
  
  vp9_inv_dct_dct_32x32_sub2_add_neon :   10682.2   8190.4   8539.2   6762.5
  
  vp9_inv_dct_dct_32x32_sub4_add_neon :   10813.5   8014.9   8518.3   6762.8
  
  vp9_inv_dct_dct_32x32_sub8_add_neon :   11859.6   9313.0   9347.4   7514.5
  
  vp9_inv_dct_dct_32x32_sub12_add_neon :  12946.6  10752.4  10192.2   8280.2
  
  vp9_inv_dct_dct_32x32_sub16_add_neon :  14074.6  11946.5  11001.4   9008.6
  
  vp9_inv_dct_dct_32x32_sub20_add_neon :  15269.9  13662.7  11816.1   9762.6
  
  vp9_inv_dct_dct_32x32_sub24_add_neon :  16327.9  14940.1  12626.7  10516.0
  
  vp9_inv_dct_dct_32x32_sub28_add_neon :  17462.7  15776.1  13446.2  11264.7
  
  vp9_inv_dct_dct_32x32_sub32_add_neon :  18575.5  17157.0  14249.3  12015.1
  I.e. in general a very minor overhead for the full subpartition case due
  
  to the additional loads and cmps, but a significant speedup for the cases
  
  when we only need to process a small part of the actual input data.
  In common VP9 content in a few inspected clips, 70-90% of the non-dc-only
  
  16x16 and 32x32 IDCTs only have nonzero coefficients in the upper left
  
  8x8 or 16x16 subpartitions respectively.
  This is cherrypicked from libav commit
  
  9c8bc74c2b40537b0997f646c87c008042d788c2.
  Signed-off-by : Michael Niedermayer <michael@niedermayer.cc>
  

  • [DH] libavcodec/arm/vp9itxfm_neon.S
  • [DH] tests/checkasm/vp9dsp.c

• UPnP Video Streaming with Node.js and FFMPEG - How can I relay the live stream from FFMPEG to Device ?

  20 octobre 2016, par Hadi77
  1. I tried relaying the stream from FFMPEG to a WebSocket connection but how can this happen in HTTP ?
  2. As it is not a full-duplex connection, I have to use a buffer somehow.
     So how can I use a buffer for getting stream to the TV (my UPnP Target device) ?

  I’m encoding the stream to H.264, and it is a Live Stream.

• How to pass output of ffmpeg child process to next reader of the stream ?

  17 mai 2019, par Chrisl446

  This function receives a duplex stream that I want to manipulate then send out to the next function that reads from it (not shown for simplicity). I tried using duplexify for this but it kept throwing me an EPIPE error because stdout was closing before stdin.

  const path = ffmpeg;
  
  const args = [ '-y','-i pipe:0','-vframes 1','-ss 00:00:00','-vf scale=250:-1','-f singlejpeg pipe:1' ];
  
  
  
  //Recieves Duplex Stream that ffmpeg process uses via pipe:0
  
  
  
  function ffmpegExecute(path, args) {
  
    const ffmpeg = spawn(path, args, { shell: true })
  
  
  
    //WANT TO READ FROM FFMPEGS OUTPUT HERE 
  
    //AND CONTINUING PIPING IT ALONG TO NEXT READER OF STREAM
  
  
  
  
  
  }