Recherche avancée

Sur d’autres sites (6955)

• swscale/aarch64 : use multiply accumulate and shift-right narrow

  9 décembre 2019, par Sebastian Pop

  swscale/aarch64 : use multiply accumulate and shift-right narrow
  This patch rewrites the innermost loop of ff_yuv2planeX_8_neon to avoid zips and
  
  horizontal adds by using fused multiply adds. The patch also uses ld1r to load
  
  one element and replicate it across all lanes of the vector. The patch also
  
  improves the clipping code by removing the shift right instructions and
  
  performing the shift with the shift-right narrow instructions.
  I see 8% difference on an m6g instance with neoverse-n1 CPUs :
  
  $ ffmpeg -nostats -f lavfi -i testsrc2=4k:d=2 -vf bench=start,scale=1024x1024,bench=stop -f null -
  
  before : t:0.014015 avg:0.014096 max:0.015018 min:0.013971
  
  after :  t:0.012985 avg:0.013013 max:0.013996 min:0.012818
  Tested with `make check` on aarch64-linux.
  Signed-off-by : Sebastian Pop <spop@amazon.com>
  
  Reviewed-by : Clément Bœsch <u@pkh.me>
  
  Signed-off-by : Michael Niedermayer <michael@niedermayer.cc>
  

  • [DH] libswscale/aarch64/output.S

• swscale : aarch64 : Optimize the final summation in the hscale routine

  20 avril 2022, par Martin Storsjö

  swscale : aarch64 : Optimize the final summation in the hscale routine
  Before :                     Cortex A53      A72      A73  Graviton 2  Graviton 3
  
  hscale_8_to_15_width8_neon :     8273.0   4602.5   4289.5      2429.7      1629.1
  
  hscale_8_to_15_width16_neon :   12405.7   6803.0   6359.0      3549.0      2378.4
  
  hscale_8_to_15_width32_neon :   21258.7  11491.7  11469.2      5797.2      3919.6
  
  hscale_8_to_15_width40_neon :   25652.0  14173.7  12488.2      6893.5      4810.4
  After :
  
  hscale_8_to_15_width8_neon :     7633.0   3981.5   3350.2      1980.7      1261.1
  
  hscale_8_to_15_width16_neon :   11666.7   5951.0   5512.0      3080.7      2131.4
  
  hscale_8_to_15_width32_neon :   20900.7  10733.2   9481.7      5275.2      3862.1
  
  hscale_8_to_15_width40_neon :   24826.0  13536.2  11502.0      6397.2      4731.9
  Thus, this gives overall a 8-29% speedup for the smaller filter
  
  sizes, around 1-8% for the larger filter sizes.
  Inspired by a patch by Jonathan Swinney <jswinney@amazon.com>.
  Signed-off-by : Martin Storsjö <martin@martin.st>
  

  • [DH] libswscale/aarch64/hscale.S

• Is ffmpeg able to read ArrayBuffer input from stream

  7 juillet 2017, par jAndy

  I want to accomplish the following tasks :

  • Record Video+Audio from any HTML5 (MediaStream) capable browser
  • Send that data via WebSocket as Blob / ArrayBuffer chunks to a server
  • Broadcast that input stream-data to multiple clients

  As it turns out, this brought me into a world of pain. The first task is fairly simple using the HTML5 MediaStream objects alongside WebSockets.

  // ... for simplicity...
  
  navigator.mediaDevices.getUserMedia({ audio: true, video: true }).then(stream => {
  
      let mediaRecorder = new MediaRecorder( stream );
  
      // ...
  
      mediaRecorder.ondataavailable = e => {
  
          webSocket.send( 'newVideoData', e.data ); // configured for binary data
  
      };
  
  });

  Now, I want to receive those data fragments and stream those via nginx vod module, because I guess I want the output stream in HLS or DASH.
  I could write a little nodejs script as backend, which just receives the binary chunks and write them to a file or stream, and just reference it so nginx vod module could possibly read it and create the m3u8 manifest on the fly ?

  I am wondering now,

  • if ffmpeg is able to read that binary data directly (should be webm format), without a man-in-the-middle script, "somehow" ?
  • If not, do I have to write the data down into a file and pass that as input to ffmpeg or can I (should I) pipe the data to a self spawned ffmpeg instance ? (if so, how ?)
  • Do I actually need the nginx server (probably alongside rtmp module) to deliver the output stream as HLS or could I just use ffmpeg to also create a dynamic manifest ?
  • Is the nginx vod module capable of creating a dynamic hls/dash manifest or must the input data be complete beforehand ?
  • Ultimately, am I on the totally wrong track here ? :P

  Actually I just want to create a little video-live-chat demo, without any plugins or 3rd party encoding software, pure browser.