Recherche avancée

Sur d’autres sites (8887)

• avfilter/vf_readeia608 : if parity bit check fails, set correct value

  21 décembre 2019, par Paul B Mahol

  avfilter/vf_readeia608 : if parity bit check fails, set correct value
  As described in U.S. Federal Register, Volume 56, Number 114, June 13, 1991, pages 27204-27205.
  

  • [DH] libavfilter/vf_readeia608.c

• aarch64 : h264pred : Optimize the inner loop of existing 8 bit functions

  12 avril 2021, par Martin Storsjö

  aarch64 : h264pred : Optimize the inner loop of existing 8 bit functions
  Move the loop counter decrement further from the branch instruction,
  
  this hides the latency of the decrement.
  In loops that first load, then store (the horizontal prediction cases),
  
  do the decrement after the load (where the next instruction would
  
  stall a bit anyway, waiting for the result of the load).
  In loops that store twice using the same destination register,
  
  also do the decrement between the two stores (as the second store
  
  would need to wait for the updated destination register from the
  
  first instruction).
  In loops that store twice to two different destination registers,
  
  do the decrement before both stores, to do it as soon before the
  
  branch as possible.
  This gives minor (1-2 cycle) speedups in most cases (modulo measurement
  
  noise), but the horizontal prediction functions get a rather notable
  
  speedup on the Cortex A53.
  Before :                     Cortex A53     A72     A73
  
  pred8x8_dc_8_neon :                60.7    46.2    39.2
  
  pred8x8_dc_128_8_neon :            30.7    18.0    14.0
  
  pred8x8_horizontal_8_neon :        42.2    29.2    18.5
  
  pred8x8_left_dc_8_neon :           52.7    36.2    32.2
  
  pred8x8_mad_cow_dc_0l0_8_neon :    48.2    27.7    25.7
  
  pred8x8_mad_cow_dc_0lt_8_neon :    52.5    33.2    34.7
  
  pred8x8_mad_cow_dc_l0t_8_neon :    52.5    31.7    33.2
  
  pred8x8_mad_cow_dc_l00_8_neon :    43.2    27.0    25.5
  
  pred8x8_plane_8_neon :            112.2    86.2    88.2
  
  pred8x8_top_dc_8_neon :            40.7    23.0    21.2
  
  pred8x8_vertical_8_neon :          27.2    15.5    14.0
  
  pred16x16_dc_8_neon :              91.0    73.2    70.5
  
  pred16x16_dc_128_8_neon :          43.0    34.7    30.7
  
  pred16x16_horizontal_8_neon :      86.0    49.7    44.7
  
  pred16x16_left_dc_8_neon :         87.0    67.2    67.5
  
  pred16x16_plane_8_neon :          236.0   175.7   173.0
  
  pred16x16_top_dc_8_neon :          53.2    39.0    41.7
  
  pred16x16_vertical_8_neon :        41.7    29.7    31.0
  After :
  
  pred8x8_dc_8_neon :                59.0    46.7    42.5
  
  pred8x8_dc_128_8_neon :            28.2    18.0    14.0
  
  pred8x8_horizontal_8_neon :        34.2    29.2    18.5
  
  pred8x8_left_dc_8_neon :           51.0    38.2    32.7
  
  pred8x8_mad_cow_dc_0l0_8_neon :    46.7    28.2    26.2
  
  pred8x8_mad_cow_dc_0lt_8_neon :    55.2    33.7    37.5
  
  pred8x8_mad_cow_dc_l0t_8_neon :    51.2    31.7    37.2
  
  pred8x8_mad_cow_dc_l00_8_neon :    41.7    27.5    26.0
  
  pred8x8_plane_8_neon :            111.5    86.5    89.5
  
  pred8x8_top_dc_8_neon :            39.0    23.2    21.0
  
  pred8x8_vertical_8_neon :          27.2    16.0    14.0
  
  pred16x16_dc_8_neon :              85.0    70.2    70.5
  
  pred16x16_dc_128_8_neon :          42.0    30.0    30.7
  
  pred16x16_horizontal_8_neon :      66.5    49.5    42.5
  
  pred16x16_left_dc_8_neon :         81.0    66.5    67.5
  
  pred16x16_plane_8_neon :          235.0   175.7   173.0
  
  pred16x16_top_dc_8_neon :          52.0    39.0    41.7
  
  pred16x16_vertical_8_neon :        40.2    33.2    31.0
  Despite this, a number of these functions still are slower than
  
  what e.g. GCC 7 generates - this shows the relative speedup of the
  
  neon codepaths over the compiler generated ones :
                             Cortex A53    A72    A73
  
  pred8x8_dc_8_neon :               0.86   0.65   1.04
  
  pred8x8_dc_128_8_neon :           0.59   0.44   0.62
  
  pred8x8_horizontal_8_neon :       1.51   0.58   1.30
  
  pred8x8_left_dc_8_neon :          0.72   0.56   0.89
  
  pred8x8_mad_cow_dc_0l0_8_neon :   0.93   0.93   1.37
  
  pred8x8_mad_cow_dc_0lt_8_neon :   1.37   1.41   1.68
  
  pred8x8_mad_cow_dc_l0t_8_neon :   1.21   1.17   1.32
  
  pred8x8_mad_cow_dc_l00_8_neon :   1.24   1.19   1.60
  
  pred8x8_plane_8_neon :            3.36   3.58   3.76
  
  pred8x8_top_dc_8_neon :           0.97   0.99   1.43
  
  pred8x8_vertical_8_neon :         0.86   0.78   1.18
  
  pred16x16_dc_8_neon :             1.20   1.06   1.49
  
  pred16x16_dc_128_8_neon :         0.83   0.95   0.99
  
  pred16x16_horizontal_8_neon :     1.78   0.96   1.59
  
  pred16x16_left_dc_8_neon :        1.06   0.96   1.32
  
  pred16x16_plane_8_neon :          5.78   6.49   7.19
  
  pred16x16_top_dc_8_neon :         1.48   1.53   1.94
  
  pred16x16_vertical_8_neon :       1.39   1.34   1.98
  In particular, on Cortex A72, many of these functions are slower
  
  than the compiler generated code, while they're more beneficial on
  
  e.g. the Cortex A73.
  Signed-off-by : Martin Storsjö <martin@martin.st>
  

  • [DH] libavcodec/aarch64/h264pred_neon.S

• FFMPEG Encode webcam to webm videos

  10 août 2016, par Mohammad Abu Musa

  I am building a screen recorder that captures the screen from Chrome then encode the video to webm extension using FFMPEG.

  The code below handles each frame I get from Chrome, I convert it to unit8_t I also have buffer size and frame size. The thread is working and I am handling all the frames correctly.

  I tired this these two sample codes to encode frames into a video
  https://ffmpeg.org/doxygen/trunk/encoding-example_8c-source.html
  https://www.ffmpeg.org/doxygen/0.6/output-example_8c-source.html

  but I failed,

  I want help to achieve the following

  1- Register only VP8 codec, I do not want to register all codecs because I am not using all of them. (The compilation time takes to long to link all codecs)

  2- Write frames to a context in the function write_frame(const uint8_t * data, uint32_t size, int w, int h,float timestamp)

  3- Encoding the video and store it.

  I think I will make this code open source since many people asked for it using Google Native Client but I do not have enough experience with FFMPEG so I need some help

  void OnGetFrame(int32_t result, pp::VideoFrame frame) {
  
          if (result != PP_OK) {
  
              LogToConsole(PP_LOGLEVEL_ERROR, pp::Var("OnGetFrame error"));
  
          }
  
  
  
          //get the bufffer data
  
          const uint8_t* data = static_cast<const>(frame.GetDataBuffer());
  
  
  
          pp::Size size;
  
          frame.GetSize(&amp;size);
  
  
  
          if (!attrib_width_ || !attrib_height_) {
  
              //initialize width, height and starttime
  
              attrib_starttime_ = frame.GetTimestamp();
  
              attrib_width_ = size.width();
  
              attrib_height_ = size.height();
  
          }
  
  
  
          //DO SOMETHING WITH THE FRAME
  
          if (is_recording_) {
  
              uint32_t buffersize = frame.GetDataBufferSize();
  
              frames_counter_++;
  
              write_frame(data, buffersize, size.width(), size.height(),
  
                      frame.GetTimestamp());
  
          } else
  
              return;
  
  
  
          //THEN DISPOSE IT
  
          video_track_.RecycleFrame(frame);
  
  
  
          //make sure tracks are configured properly
  
          if (need_config_) {
  
              ConfigureTrack();
  
              return;
  
          } else {
  
              //AND REQUEST A NEW FRAME
  
              video_track_.GetFrame(
  
                      callback_factory_.NewCallbackWithOutput(
  
                              &amp;EncoderInstance::OnGetFrame));
  
  
  
          }
  
  
  
      }
  
  
  
      void write_frame(const uint8_t * data, uint32_t size, int w, int h,
  
              float timestamp) {
  
          PostMessage("LOG:: Writing Frame \n");
  
      }
  
  </const>