Commit Graph

201 Commits

Author SHA1 Message Date
Yaowu Xu
014acfa2af fix integer overflow errors
Change-Id: I76f440a917832c02d7a727697b225bac66b99f56
2013-09-19 08:14:26 -07:00
Paul Wilkins
cb50dc7f33 Minor clean up.
Removed some unused code and minor cleanup
/ reordering.

Change-Id: I4083ae56aeb8edfe9b85aa2f42a16aa28d19da94
2013-09-16 13:45:20 +01:00
Jingning Han
e8a967d960 Merge "Adaptive motion search control" 2013-09-13 14:43:23 -07:00
Jingning Han
c4826c5941 Adaptive motion search control
This commit enables adaptive constraint on motion search range for
smaller partitions, given the motion vectors of collocated larger
partition as a candidate initial search point.

It makes speed 0 runtime of bus at CIF and 2000 kbps goes from
167s down to 162s (3% speed-up), at 0.01dB performance gains. In
the settings of speed 1, this makes the runtime goes from 33687 ms
to 32142 ms (4.5% speed-up), at 0.03dB performance gains.

Compression performance wise, it gains at speed 1:
derf  0.118%
yt    0.237%
hd    0.203%
stdhd 0.438%

Change-Id: Ic8b34c67810d9504a9579bef2825d3fa54b69454
2013-09-13 13:58:10 -07:00
Deb Mukherjee
0c3038234d Merge "Clean up of the search best filter speed feature" 2013-09-13 11:03:59 -07:00
Deb Mukherjee
b964646756 Clean up of the search best filter speed feature
Removes this speed feature since it is very slow and unlikely
to be used in practice. This cleanup removes a bunch of unnecessary
complications in the outer encode loop.

Change-Id: I3c66ef1ca924fbfad7dadff297c9e7f652d308a1
2013-09-11 15:16:36 -07:00
Deb Mukherjee
69fe840ec4 Changes in speed 2 settings
Propose some changes to the speed 2 settings to improve quality.
In particular, turns off the adjust_thresholds_by_speed feature
which improves results by 6%. Also removes the code for
adjust_thresholds_by_speed since it conflicts with the adaptive
rd thresh feature.

Overall, with this change speed 2 is -15.2% from speed 0 settings,
on derf, which is significantly better than -21.6% down before.

Change-Id: I6e90a563470979eb0c258ec32d6183ed7ce9a505
2013-09-11 10:54:07 -07:00
Yunqing Wang
939791a129 Modify encode breakout for static frames
Thank Paul for the suggestions. While turning on static-thresh
for static-image videos, a big jump on bitrate was seen. In this
patch, we detected static frames in the video using first-pass
stats. For different cases, disable encode breakout or reduce
encode breakout threshold to limit the skipping.

More modification need be done to break incorrect partition
picking pattern for static frames while skipping happens.

Change-Id: Ia25f47041af0f04e229c70a0185e12b0ffa6047f
2013-09-10 09:06:03 -07:00
Paul Wilkins
4f660cc018 Modified mode skip functionality.
A previous speed feature skipped modes not used in earlier
partitions but this not longer worked as intended following
changes to the partition coding order and in conjunction
with some other speed features (Especially speed 2 and above).

This modified mode skip feature sets a mask after the first X
modes have been tested in each partition depending on the
reference frame of the current best case.

This patch also makes some changes to the order modes are
tested to fit better with this skip functionality.

Initial testing suggests speed and rd hit count improvements
of up to 20% at speed 1. Quality results. (derf -1.9%, std hd  +0.23%).

Change-Id: Idd8efa656cbc0c28f06d09690984c1f18b1115e1
2013-09-10 13:30:10 +01:00
Ivan Maltz
01b35c3c16 API extensions and sample app for spacial scalable encoder
Sample app: vp9_spatial_scalable_encoder
vpx_codec_control extensions:
  VP9E_SET_SVC
  VP9E_SET_WIDTH, VP9E_SET_HEIGHT, VP9E_SET_LAYER
  VP9E_SET_MIN_Q, VP9E_SET_MAX_Q
expanded buffer size for vp9_convolve

modified setting of initial width in vp9_onyx_if.c so that layer size
can be set prior to initial encode

Default number of layers set to 3 (VPX_SS_DEFAULT_LAYERS)
Number of layers set explicitly in vpx_codec_enc_cfg.ss_number_layers

Change-Id: I2c7a6fe6d665113671337032f7ad032430ac4197
2013-09-09 15:57:56 -07:00
Paul Wilkins
1f4bf79d65 Added per pixel inter rd hit count stats
Added some code to output normalized rd hit count stats.
In effect this approximates to the average number of rd
operations/tests per pixel for the sequence.

The results are not quite accurate and I have not bothered
to account for partial SB64s at frame edges and for key frames
However they do give some idea of the number of modes /
prediction methods being tested for each pixel across the
different partition sizes. This indicates how much scope their
is for further gains either by reducing the number of partitions
examined or the modes per partition through heuristics.

Patch 3 moved place where count incremented so partial rd
tests that are aborted with INT_MAX return are also counted.

Example numbers for first 50 frames of Akiyo.
Speed 0 ~84.4 rd operations / pixel
Speed 1 ~28.8
Speed 2 ~11.9

Change-Id: Ib956e787e12f7fa8b12d3a1a2f6cda19a65a6cb8
2013-08-30 00:13:51 +01:00
Deb Mukherjee
b6dbf11ed5 Merge "Adds a speed feature for fast 1-loop forw updates" 2013-08-29 15:54:04 -07:00
Deb Mukherjee
e02dc84c1a Adds a speed feature for fast 1-loop forw updates
Incorporates a speed feature for fast forward updates of
coefficients. This feature takes 3 values:
0 - use standard 2-loop version
1 - use a 1-loop version
2 - use a 1-loop version with reduced updates

Results: derfraw300 +0.007% (on speed 0) at feature value = 1
                    -0.160% (on speed 0) at feature value = 2

There is substantial speed up at speeds 2 and above for low
resolution sequences where the entropy updates are a big part
of the overall computations.

Change-Id: Ie96fc50777088a5bd441288bca6111e43d03bcae
2013-08-28 10:56:52 -07:00
Dmitry Kovalev
7b95f9bf39 Renaming BLOCK_SIZE_TYPE to BLOCK_SIZE in the encoder.
Change-Id: I62bb07c377f947cb72fac68add7a6b199e42c6b9
2013-08-27 11:05:08 -07:00
Dmitry Kovalev
78e670fcf8 Merge "Renaming D27 to D207." 2013-08-27 10:03:57 -07:00
Paul Wilkins
aa823f8667 Merge "Changes to adaptive inter rd thresholds." 2013-08-26 12:48:11 -07:00
Paul Wilkins
642696b678 Merge "Limit Key frame Intra modes checks." 2013-08-26 12:34:56 -07:00
James Zern
c8ba8c513c cosmetics: strip 'VP9_' from defines in vp9 only code
Change-Id: I481d9bb2fa3ec72b6a83d5f04d545ad8013f295c
2013-08-23 19:16:49 -07:00
Dmitry Kovalev
50ee61db4c Renaming D27 to D207.
I've already renamed d27_predictor to d207_predictor but forgot about the
corresponding constant.

Change-Id: Id312aa80fc5b5a1ab8a709a33418a029552a6857
2013-08-23 17:33:48 -07:00
Paul Wilkins
aa5b67add0 Changes to adaptive inter rd thresholds.
Values now carried over frame to frame.
Change to algorithm for decreasing threshold after
a hit and to max threshold (now based on speed)

Removed some old commented out code relating to
VP8 adaptive thresholds.

The impact of these changes tested on Akiyo (50 frames)
and measured in terms of unit rd hits is as follows:

Speed 0 84.36 -> 84.67
Speed 1 29.48 -> 22.22
Speed 2 11.76 -> 8.21
Speed 3 12.32 -> 7.21

Encode speed impact is broadly in line with these.

Change-Id: I5b886efee3077a11553fa950d796fd6d00c8cb19
2013-08-23 16:18:45 +01:00
Paul Wilkins
f76f52df61 Limit Key frame Intra modes checks.
Most of the focus so far has been on inter frames.

At high speed settings the key frame is now taking a high %
of the cycles.

This patch puts in some masking to reduce the number
of INTRA modes searched during key frame coding (as already
happens for inter frames) at higher speed settings

TODO: Develop this further with either adaptive rd thresholds
when choosing which intra modes to consider or some other
heuristic.

Impact.
At high speed settings on some clips the key frame was starting
to dominate. In a coding of the first 50 frames of AKIYO at speed
2 limiting the key frame intra modes to DC or TM_PRED resulted in
~30% overall speedup. For Bus the number was lower at ~4-5%.

Change-Id: I7bde68aee04995f9d9beb13a1902143112e341e2
2013-08-23 16:10:30 +01:00
Deb Mukherjee
2ffe64ad5c Cleanup/enhancements of switchable filter search
Cleans up the switchable filter search logic. Also adds a
speed feature - a variance threshold - to disable filter search
if source variance is lower than this value.

Results: derfraw300
threshold = 16, psnr -0.238%, 4-5% speedup (tested on football)
threshold = 32, psnr -0.381%, 8-9% speedup (tested on football)
threshold = 64, psnr -0.611%, 12-13% speedup (tested on football)
threshold = 96, psnr -0.804%, 16-17% speedup (tested on football)

Based on these results, the threshold is chosen as 16 for speed 1,
32 for speed 2, 64 for speed 3 and 96 for speed 4.

Change-Id: Ib630d39192773b1983d3d349b97973768e170c04
2013-08-20 09:47:04 -07:00
Deb Mukherjee
24856b6abc Speed feature to skip split partition based on var
Adds a speed feature to disable split partition search based on a
given threshold on the source variance. A tighter threshold derived
from the threshold provided is used to also disable horizontal and
vertical partitions.

Results on derfraw300:
threshold = 16, psnr = -0.057%, speedup ~1% (football)
threshold = 32, psnr = -0.150%, speedup ~4-5% (football)
threshold = 64, psnr = -0.570%, speedup ~10-12% (football)

Results on stdhdraw250:
threshold = 32, psnr = -0.18%, speedup is somewhat more than derf
because of a larger number of smoother blocks at higher resolution.

Based on these results, a threshold of 32 is chosen for speed 1,
and a threshold of 64 is chosen for speeds 2 and above.

Change-Id: If08912fb6c67fd4242d12a0d094783a99f52f6c6
2013-08-15 10:01:45 -07:00
Paul Wilkins
5459f68d71 Trivial clean up.
Delete unused / commented out  variable references.

Change-Id: Iaf20c0c3744f89adb296d153b516b5ea41b4f3b4
2013-08-13 13:26:18 +01:00
Dmitry Kovalev
3c43ec206c Renaming BLOCK_SIZE_TYPES constant to BLOCK_SIZES.
There will be another change set to rename BLOCK_SIZE_TYPE enum to
BLOCK_SIZE.

Change-Id: I8d1dfc873d6186fa5e554262f5169e929978085e
2013-08-09 17:47:32 -07:00
Yaowu Xu
c7c9901845 added a speed feature on lpf level picking
Change-Id: Id578f8afdeab3702fc8386969f2d832d8f1b5420
2013-08-09 07:36:32 -07:00
Deb Mukherjee
2158909fc3 Merge "Adds a new subpel motion function" 2013-08-08 12:26:55 -07:00
Deb Mukherjee
1ba91a84ad Adds a new subpel motion function
Adds a new subpel motion estimation function that uses a 2-level
tree-structured decision tree to eliminate redundant computations.
It searches fewer points than iterative search (which can search
the same point multiple times) but has the same quality roughly.

This is made the default setting at speeds 0 and 1, while at
speed 2 and above only a 1-level search is used.

Also includes various cleanups for consistency and redundancy removal.

Results:
derf: +0.012% psnr
stdhd: +0.09% psnr
Speedup of about 2-3%

Change-Id: Iedde4866f5475586dea0f0ba4cb7428fba24eee9
2013-08-08 11:41:49 -07:00
Jingning Han
debb9c68c8 Use low precision 32x32fdct for encodemb in speed1
The low precision 32x32 fdct has all the intermediate steps within
16-bit depth, hence allowing faster SSE2 implementation, at the
expense of larger round-trip error. It was used in the rate-distortion
optimization search loop only.

Using the low precision version, in replace of the high precision one,
affects the compression performance by about 0.7% (derf, stdhd) at
speed 0. For speed 1, it makes derf set down by only 0.017%.

Change-Id: I4e7d18fac5bea5317b91c8e7dabae143bc6b5c8b
2013-08-07 15:34:12 -07:00
Deb Mukherjee
71b43b0ff0 Clean ups of the subpel search functions
Removes some unused code and speed features, and organizes the
interfaces for fractional mv step functions for use in new speed
features to come.

In the process a new speed feature - number of iterations per
step during the subpel search - is exposed.

No change when this parameter is set as the original value of 3.

Results:
subpel_iters_per_step = 3: baseline
subpel_iters_per_step = 2: psnr -0.067%, 1% speedup
subpel_iters_per_step = 1: psnr -0.331%, 3-4% speedup

Change-Id: I2eba8a21f6461be8caf56af04a5337257a5693a8
2013-08-06 17:23:50 -07:00
Deb Mukherjee
15b5a6a2c7 Flexible support for various pattern searches
Adds a few pattern searches to achieve various tradeoffs
between motion estimation complexity and performance.
The search framework is unified across these searches so that a
common pattern search function is used for all. Besides it will
be easier to experiment with various patterns or combinations
thereof at different scales in the future.

The new pattern search is multi-scale and is capable of using
different patterns at different scales.

The new hex search uses 8 points at the smallest scale
and 6 points at other scales.
Two other pattern searches - big-diamond and square are
also added. Big diamond uses 4 points at the smallest scale and
8 points in diamond shape at the larger scales.
Square is very similar conceptually to the default n-step search
but is somewhat faster since it keeps only one survivor across
all scales.

Psnr/speed-up results on derf300:

hex: -1.6% psnr%, 6-8% speed-up
big-diamond: -0.96% psnr, 4-5% speedup
square: -0.93% psnr, 4-5% speedup

Change-Id: I02a7ef5193f762601e0994e2c99399a3535a43d2
2013-08-06 11:56:39 -07:00
Deb Mukherjee
33afddadb9 Merge "Add variance based mode/skipping" 2013-08-06 10:19:15 -07:00
Deb Mukherjee
8b3faccb9e Add variance based mode/skipping
Adds a speed feature to skip all intra modes other than
DC_PRED if the source variance is small. This feature is
made part of speed 1 and up.

Results on derf300: psnr -0.07%, speedup about 1-2%

Also uses the source variance to fine-tune the early
termination criteria when FLAG_EARLY_TERMINATE is on.
This feature is made part of speed 2 and up.

Results on derf300: psnr -0.52%, speedup about 5-7%

Change-Id: I59e38aa836557cfa5405ae706fc64815cbfe4232
2013-08-05 14:14:01 -07:00
Yunqing Wang
7965a6ea34 Comment out 2 unused speed features
use_min_partition_size and use_max_partition_size are not used
currently, and could be added back if needed later.

Change-Id: Ib22a9c06b064567a7c1d6d5445567ed77e0d3acc
2013-08-01 11:03:34 -07:00
Adrian Grange
fbd73648dd Merge "Cleanup typos, remove unnecessary lines, replace switch" 2013-07-30 12:59:46 -07:00
Adrian Grange
b30a06b930 Cleanup typos, remove unnecessary lines, replace switch
Removed unnecessary code lines, replaced switch with an if,
fixed spelling errors and formatting.

Change-Id: Ie48aa4604aa0ed48362ca359d792fb21b2ec1dc6
2013-07-30 12:10:32 -07:00
Dmitry Kovalev
730a34416f Renaming NB_TXFM_MODES constant to TX_MODES.
Change-Id: I10bf06e3a3d5271221ae6a42a36074d01d493039
2013-07-29 13:38:40 -07:00
Dmitry Kovalev
23391ea835 Renaming TX_SIZE_MAX_SB to TX_SIZES.
Change-Id: I6aa4191935aa93461a07c41b59fdae1eb5f5f107
2013-07-29 12:25:34 -07:00
Paul Wilkins
fe5e2a91bb Auto min and max partition size experiment.
Speed feature experiment to set an upper and lower
partition size limit based on what has been seen
in spatial neighbors.

This seems to gives quite reasonable speed gains in local
(10-15%) and when used with speed 0 the losses are small
(0.25% derf, 0.35% stdhd). However, for now I am only
enabling it on speed 1 as there may be clashes with the existing
temporal partition selection in speed 2.

Using a tighter min / max around the range derived from the
neighbors increases speed further but at the cost of a
bigger quality loss. However,  I think this spatial method could
be combined with data from either the last frame or a variance
method (or both) to refine the range of minimum and maximum
partition size. I.e. consider the min and max from spatial and
temporal neighbors and the variance recommendation.

Change-Id: I1b96bf8b84368d6aad0c7aa600fe141b4f07435f
2013-07-26 18:30:49 +01:00
Paul Wilkins
cedd24ec61 Merge "Renaming of segment constants." 2013-07-23 08:16:12 -07:00
Paul Wilkins
7c134bc0cd Merge "Reworked the auto_mv_step_size speed feature" 2013-07-23 04:49:55 -07:00
Paul Wilkins
32042af14b Renaming of segment constants.
Renamed:
  MAX_MB_SEGMENTS to MAX_SEGMENTS
  MB_SEG_TREE_PROBS to SEG_TREE_PROBS

The minimum unit for segmentation in the segment map
is now 8x8 so it is misleading to use MB_ as macro-block
traditionally refers to a 16x16 region.

Change-Id: I0b55a6f0426bb46dd13435fcfa5bae0a30a7fa22
2013-07-23 12:09:04 +01:00
James Zern
76db4d599a Merge "VP[89]_COMMON: remove golden/altref frame counts" 2013-07-22 12:55:07 -07:00
Paul Wilkins
1d189d6464 Re-order mode search in rd.
Mode search order in rd loop changed to better reflect
observed hit counts.

Also some adjustment of the baseline mode rd thresholds
to reflect the order change and observed frequencies.

Change-Id: I47a131cc83e11551df8add6d6d8d413d78d3a63c
2013-07-22 17:21:12 +01:00
Deb Mukherjee
302698fb12 Reworked the auto_mv_step_size speed feature
This patch modifies the auto_mv_step_size speed feature to
use a combination of the maximum magnitude mv from the last
inter frame, and the maximum magnitude mv for the two reference
mvs with the same reference. For arf frames, the max mav step
for the resolution is used.
The bounds therefore are slightly tighter. The feature is made
a speed 1 feature.

Rebased.

Results (when this feature is turned on over speed 0):
derfraw300: -0.046% psnr, about 5+% speedup
(tested on football: goes from 4m30.760s to 4m17.410s).

Change-Id: If492797a61b0b4b3e58c0b8f86afb880165fc9f6
2013-07-19 15:12:56 -07:00
Paul Wilkins
f3ed9f5523 Alignment of THR_MODES to vp9_mode_order[]
Change-Id: I4032dd0442043543954dcb3724df974b7cc7e515
2013-07-19 11:33:39 +01:00
James Zern
5f30a0c687 VP[89]_COMMON: remove golden/altref frame counts
these are only used in the encoder.
frames_since_golden / frames_till_alt_ref_frame -> VP[89]_COMP

Change-Id: Ie14a6f46987bced685ddb449b85dc261caba6dfe
2013-07-18 14:09:21 -07:00
Yunqing Wang
df90d58f4f Speed up motion estimation using small partitions' result(experiment)
Current partition checking starts from small sizes, and then goes up
to large sizes. This experiment uses the small partitions' motion
estimation result, which is already available, to speed up the
large partition's motion estimation. We can decide to skip some
patition checkings if they are unlikely choices. We could use the
motion vector(MV) result as current partition's prediction MV, limit
the search range and reference frame.

Current result at speed 1:
psnr loss: 1.19% for stdhd, 0.287% for derf.
speed gain: 14% for sunflower(hd), 11% for akiyo.

Further improvement will be done later.

Change-Id: I5abfd070e9cace2e91e2a0247d1325df313887ab
2013-07-17 09:11:47 -07:00
Paul Wilkins
d66eab15dd Merge "Move uv intra mode selection in rd loop." 2013-07-17 05:19:26 -07:00
Paul Wilkins
2ee338ce3b Move uv intra mode selection in rd loop.
Use an estimate based on DC_PRED for intra uv cost
within the rd loop then only do a full uv mode analysis
if an intra mode is chosen.

Significant speed gains in some cases. Currently only
enabled for speed 2 pending speed/quality tests.

Change-Id: Ie851a12400d5483bce47ec0e3ccb8516041e91c0
2013-07-17 11:11:21 +01:00