Recherche avancée

Sur d’autres sites (3596)

• ffmpeg process has GPU usage limit

  16 mars 2021, par R.A.M

  i'm using ffmpeg and an NVIDIA for my video transcode process.
so i have one problem.
look at below image :

  


  

  


  one process just use 263MiB of my second GPU. not completly use that !!

  


  that is not good. i think there should be a way to remove this limitation for gpu process.

  


  my ffmpeg command that i run is :

  


  ffmpeg -y -loglevel info -hwaccel cuda -hwaccel_output_format cuda -hwaccel_device 1 -i "MYVIDEO" -vf scale_npp=w=426:h=240 -c:v h264_nvenc -profile:v main -b:v 400k -sc_threshold 0 -g 25 -keyint_min 25 -bf 2   -c:a aac -b:a 64k -ar 48000   -f hls -hls_time 6 -hls_playlist_type vod   -hls_allow_cache 1   -hls_segment_filename f-0-seg-%d.ts f-0.m3u8


  


• configure : Add an explicit check and option for nvcc

  21 février 2019, par Philip Langdale

  configure : Add an explicit check and option for nvcc
  The use of nvcc to compile cuda kernels is distinct from the use of
  
  cuda sdk libraries and linking against those libraries. We have
  
  previously not bothered to distinguish these two cases because all
  
  the filters that used cuda kernels also used the sdk. In the following
  
  changes, I'm going to remove the sdk dependency from those filters,
  
  but we need a way to ensure that nvcc is present and functioning, and
  
  also a way to explicitly disable its use so that the filters are not
  
  built.
  Signed-off-by : Timo Rothenpieler <timo@rothenpieler.org>
  

  • [DH] configure

• ffmpeg Nvidia build [closed]

  30 septembre 2022, par Never

  I follow this document
https://docs.nvidia.com/video-technologies/video-codec-sdk/ffmpeg-with-nvidia-gpu/#compiling-for-linux
compile ffmpeg

  


  the documentation says "To compile FFmpeg, the CUDA toolkit must be installed on the system, though the CUDA toolkit is not needed to run the FFmpeg compiled binary."

  


  Why does running ffmpeg binary still require CUDA toolkit after I compile ffmpeg

  


  $ ./ffmpeg
./ffmpeg: error while loading shared libraries: libnppig.so.11: cannot open shared object file: No such file or directory


  


  I follow this document
https://developer.nvidia.com/cuda-downloads?target_os=Linux&target_arch=x86_64&Distribution=Debian&target_version=11&target_type=deb_local
install cuda

  


  it runs ok

  


  $ ./ffmpeg

ffmpeg version N-108433-g8089fe072e Copyright (c) 2000-2022 the FFmpeg developers
  built with gcc 10 (Debian 10.2.1-6)
  configuration: --prefix=/root/ffmpeg_build --pkg-config-flags=--static --extra-cflags=-I/root/ffmpeg_build/include --extra-ldflags=-L/root/ffmpeg_build/lib --extra-libs='-lpthread -lm' --ld=g++ --bindir=/root/bin --enable-gpl --enable-gnutls --enable-libaom --enable-libass --enable-libfdk-aac --enable-libfreetype --enable-libmp3lame --enable-libopus --enable-libsvtav1 --enable-libdav1d --enable-libvorbis --enable-libvpx --enable-libx264 --enable-libx265 --enable-libmfx --enable-nonfree --enable-cuda-nvcc --enable-cuvid --enable-nvenc --enable-libnpp --extra-cflags=-I/usr/local/cuda/include --extra-ldflags=-L/usr/local/cuda/lib64
  libavutil      57. 38.100 / 57. 38.100
  libavcodec     59. 48.100 / 59. 48.100
  libavformat    59. 33.100 / 59. 33.100
  libavdevice    59.  8.101 / 59.  8.101
  libavfilter     8. 49.100 /  8. 49.100
  libswscale      6.  8.112 /  6.  8.112
  libswresample   4.  9.100 /  4.  9.100
  libpostproc    56.  7.100 / 56.  7.100
Hyper fast Audio and Video encoder
usage: ffmpeg [options] [[infile options] -i infile]... {[outfile options] outfile}...

Use -h to get full help or, even better, run 'man ffmpeg'


  


  How to run ffmpeg without installing cuda ?