Recherche avancée

Sur d’autres sites (9927)

• Revision 26b6318de8 : Make get_coef_context() branchless. This should significantly speedup cost_coef

  1er juillet 2013, par Ronald S. Bultje

  Changed Paths :
   Modify /vp9/common/vp9_entropy.c

  
   Modify /vp9/common/vp9_entropy.h

  
   Modify /vp9/decoder/vp9_detokenize.c

  
   Modify /vp9/encoder/vp9_encodemb.c

  
   Modify /vp9/encoder/vp9_rdopt.c

  
   Modify /vp9/encoder/vp9_tokenize.c

  
  
  Make get_coef_context() branchless.

  This should significantly speedup cost_coeffs(). Basically what the
  patch does is to make the neighbour arrays padded by one item to
  prevent an eob check in get_coef_context(), then it populates each
  col/row scan and left/top edge coefficient with two times the same
  neighbour - this prevents a single/double context branch in
  get_coef_context(). Lastly, it populates neighbour arrays in pixel
  order (rather than scan order), so we don't have to dereference the
  scantable to get the correct neighbours.

  Total encoding time of first 50 frames of bus (speed 0) at 1500kbps
  goes from 2min10.1 to 2min5.3, i.e. a 2.6% overall speed increase.

  Change-Id : I42bcd2210fd7bec03767ef0e2945a665b851df56

• jpeg2000 : Validate block lengthinc

  1er juillet 2013, par Luca Barbato

  jpeg2000 : Validate block lengthinc
  Currently we are using an array with a static data size.
  Similar to a patch with the same purpose by Michael Niedermayer.
  Found-by : Mateusz "j00ru" Jurczyk and Gynvael Coldwind
  Signed-off-by : Luca Barbato <lu_zero@gentoo.org>
  

  • [DBH] libavcodec/jpeg2000dec.c

• Revision 8d3d2b76f3 : Tx size selection enhancements (1) Refines the modeling function and uses that

  22 juin 2013, par Deb Mukherjee

  Changed Paths :
   Modify /vp9/common/vp9_blockd.h

  
   Modify /vp9/encoder/vp9_encodeframe.c

  
   Modify /vp9/encoder/vp9_onyx_if.c

  
   Modify /vp9/encoder/vp9_onyx_int.h

  
   Modify /vp9/encoder/vp9_rdopt.c

  
  
  Tx size selection enhancements

  (1) Refines the modeling function and uses that to add some speed
  features. Specifically, intead of using a flag use_largest_txfm as
  a speed feature, an enum tx_size_search_method is used, of which
  two of the types are USE_FULL_RD and USE_LARGESTALL. Two other
  new types are added :
  USE_LARGESTINTRA (use largest only for intra)
  USE_LARGESTINTRA_MODELINTER (use largest for intra, and model for
  inter)

  (2) Another change is that the framework for deciding transform type
  is simplified to use a heuristic count based method rather than
  an rd based method using txfm_cache. In practice the new method
  is found to work just as well - with derf only -0.01 down.
  The new method is more compatible with the new framework where
  certain rd costs are based on full rd and certain others are
  based on modeled rd or are not computed. In this patch the existing
  rd based method is still kept for use in the USE_FULL_RD mode.
  In the other modes, the count based method is used.
  However the recommendation is to remove it eventually since the
  benefit is limited, and will remove a lot of complications in
  the code

  (3) Finally a bug is fixed with the existing use_largest_txfm speed feature
  that causes mismatches when the lossless mode and 4x4 WH transform is
  forced.

  Results on derf :
  USE_FULL_RD : +0.03% (due to change in the tables), 0% encode time reduction
  USE_LARGESTINTRA : -0.21%, 15% encode time reduction (this one is a
  pretty good compromise)
  USE_LARGESTINTRA_MODELINTER : -0.98%, 22% encode time reduction
  (currently the benefit of modeling is limited for txfm size selection,
  but keeping this enum as a placeholder) .
  USE_LARGESTALL : -1.05%, 27% encode-time reduction (same as existing
  use_largest_txfm speed feature).

  Change-Id : I4d60a5f9ce78fbc90cddf2f97ed91d8bc0d4f936