vpx/vp9
Jingning Han d66c748635 Enable skipping reference frame check in rd loop
This commit allows encoder to compare the SAD cost associated with
the best motion vector predictor, per frame. If one reference frame
has this cost more than 4 times of the best SAD cost given by other
reference frames, skip NEARESTMV, NEARMV, ZEROMV mode check of this
reference frame.

This setting is turned on in speed 2 and above. Compression quality
change in speed 2:
derf  -0.014%
yt    -0.097%
hd    -0.023%
stdhd  0.046%

It reduces the speed 2 runtime of test sequences:
pedestrian_area_1080p 4000 kbps 310763 ms -> 303595 ms
bluesky_1080p 6000 kbps         259852 ms -> 251920 ms

Change-Id: I7f59cf79503d51836d61d56d50dc5bdf0e502e22
2014-01-09 18:25:53 -08:00
..
common Optimze inv 16x16 DCT with 10 non-zero coeffs - P2 2014-01-09 12:46:09 -08:00
decoder Merge "Adding RefBuffer struct." 2014-01-06 14:19:44 -08:00
encoder Enable skipping reference frame check in rd loop 2014-01-09 18:25:53 -08:00
exports_dec support building vp8 and vp9 into a single lib 2012-11-15 10:46:17 -08:00
exports_enc Removing vpx_codec_vp9x_cx and internal experimental flag. 2013-12-27 14:01:12 -08:00
vp9_common.mk Merge "Add initial intra frame neon optimization. 1~2% gain." 2014-01-08 14:41:43 -08:00
vp9_cx_iface.c Removing vpx_codec_vp9x_cx and internal experimental flag. 2013-12-27 14:01:12 -08:00
vp9_dx_iface.c Using VP9_FRAME_MARKER instead of raw number. 2013-12-27 14:50:27 -08:00
vp9_iface_common.h yv12config: remove YUV_TYPE 2013-07-12 15:25:48 -07:00
vp9cx.mk AVX2 Variance Optimization 2014-01-08 12:05:53 -07:00
vp9dx.mk Renaming vp9_dboolhuff.{h, c} to vp9_reader.{h, c}. 2013-12-20 12:53:03 -08:00