Recherche avancée

Sur d’autres sites (9433)

• vp8 : make wait/thread_mb_pos atomic.

  5 avril 2017, par Ronald S. Bultje

  vp8 : make wait/thread_mb_pos atomic.
  Fixes tsan warnings like this in fate-vp8-test-vector-007 :
  WARNING : ThreadSanitizer : data race (pid=3590)
  
    Write of size 4 at 0x7d8c0000e07c by thread T2 :
  
      #0 decode_mb_row_no_filter src/libavcodec/vp8.c:2330 (ffmpeg+0x000000ffb59e)
  
  [..]
  
    Previous write of size 4 at 0x7d8c0000e07c by thread T1 :
  
      #0 decode_mb_row_no_filter src/libavcodec/vp8.c:2330 (ffmpeg+0x000000ffb59e)
  

  • [DH] libavcodec/vp8.c
  • [DH] libavcodec/vp8.h

• jrev/xvid : hardcode use of C put/add_pixels_clamped.

  4 avril 2017, par Ronald S. Bultje

  jrev/xvid : hardcode use of C put/add_pixels_clamped.
  This removes the last use of the ff_put/add_pixels_clamped global
  
  function pointers, and as such they are removed.
  This patch has a negative effect on performance on MIPS, since there’s
  
  a SIMD-optimized put/add_pixels_clamped, but no xvid or jrev. From a
  
  code maintenance point of view, that is probably acceptable.
  Because the global function pointers are removed, this fixes the following
  
  tsan warnings when running e.g. fate-dnxhr-parse :
  WARNING : ThreadSanitizer : data race (pid=29917)
  
    Write of size 8 at 0x0000025b12d8 by thread T2 (mutexes : write M1543) :
  
      #0 ff_idctdsp_init src/libavcodec/idctdsp.c:313 (ffmpeg+0x00000044b68e)
  
  [..]
  
    Previous write of size 8 at 0x0000025b12d8 by thread T1 (mutexes : write M1541) :
  
      #0 ff_idctdsp_init src/libavcodec/idctdsp.c:313 (ffmpeg+0x00000044b68e)
  

  • [DH] libavcodec/idctdsp.c
  • [DH] libavcodec/idctdsp.h
  • [DH] libavcodec/jrevdct.c
  • [DH] libavcodec/xvididct.c

• pthread_frame : allow per-field ThreadFrame owners.

  3 avril 2017, par Ronald S. Bultje

  pthread_frame : allow per-field ThreadFrame owners.
  This tries to handle cases where separate invocations of decode_frame()
  
  (each running in separate threads) write to respective fields in the
  
  same AVFrame->data[]. Having per-field owners makes interaction between
  
  readers (the referencing thread) and writers (the decoding thread)
  
  slightly more optimal if both accesses are field-based, since they will
  
  use the respective producer’s thread objects (mutex/cond) instead of
  
  sharing the thread objects of the first field’s producer.
  In practice, this fixes the following tsan-warning in fate-h264 :
  WARNING : ThreadSanitizer : data race (pid=21615)
  
    Read of size 4 at 0x7d640000d9fc by thread T2 (mutexes : write M1006) :
  
      #0 ff_thread_report_progress pthread_frame.c:569 (ffmpeg:x86_64+0x100f7cf54)
  
  [..]
  
    Previous write of size 4 at 0x7d640000d9fc by main thread (mutexes : write M1004) :
  
      #0 update_context_from_user pthread_frame.c:335 (ffmpeg:x86_64+0x100f81abb)
  

  • [DH] libavcodec/h264_slice.c
  • [DH] libavcodec/pthread_frame.c
  • [DH] libavcodec/thread.h
  • [DH] libavcodec/utils.c