Removing unused constants, macros, and function declarations. Using
ROUND_POWER_OF_TWO macro, vp9_zero, vp9_copy where possible. Moving
#include from *.h to *.c. Merging for loops for motion vectors.

Change-Id: Ic3bf841764a2bb177128bb3a6d7aa8f68229cd13

4x4:    163 ->  123 cycles (33% faster)
8x8:    491 ->  399 cycles (23% faster)
16x16: 1889 -> 1763 cycles (7% faster)
32x32: 8311 -> 8180 cycles (1.6% faster)

Overall encoding time of first 50 frames of bus (speed 0) @ 1500kbps
goes from 1min4.33 to 1min3.00, i.e. 2.11% faster.

Change-Id: Ib52d1dbb5649b14de769d3e7a74af67440b5284f

Removing unused and duplicated constants, moving them from *.h to *.c
if possible.

Change-Id: Ief4d6b984a3ca2e9b38504f0d855ed072cf7133f

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

Total encoding time for first 50 frames of bus (speed 0) @ 1500kbps
goes 2min34.8 to 2min14.4, i.e. a 10.4% overall speedup. The code is
x86-64 only, it needs some minor modifications to be 32bit compatible,
because it uses 15 xmm registers, whereas 32bit only has 8.

Change-Id: I2df53770c2e850813ffa713e1a91b45b0082b904

Makes cost_coeffs() a lot faster:
4x4: 236 -> 181 cycles
8x8: 888 -> 588 cycles
16x16: 3550 -> 2483 cycles
32x32: 17392 -> 12010 cycles

Total encode time of first 50 frames of bus (speed 0) @ 1500kbps goes
from 2min51.6 to 2min43.9, i.e. 4.7% overall speedup.

Change-Id: I16b8d595946393c8dc661599550b3f37f5718896

This function is not called from the decoder, so it doesn't need to be
in common/.

Change-Id: I6977dd462a25b4ff39c9c7e1b0b5b16aa58ee733

This function never referenced.

Change-Id: I1c42cd355bfa88e17d169f7335a44be682af58cc

All elements of this table are equal to 252, so replace it with a
single constant VP9_COEF_UPDATE_PROB.

Change-Id: I1e2d1d284326ce6df9899a740c2fc344b3ec81c9

This patch changes the coefficient tree to move the EOB to below
the ZERO node in order to save number of bool decodes.

The advantages of moving EOB one step down as opposed to two steps down
in the other parallel patch are: 1. The coef modeling based on
the One-node becomes independent of the tree structure above it, and
2. Fewer conext/counter increases are needed.

The drawback is that the potential savings in bool decodes will be
less, but assuming that 0s are much more predominant than 1's the
potential savings is still likely to be substantial.

Results on derf300: -0.237%

Change-Id: Ie784be13dc98291306b338e8228703a4c2ea2242

Uses reduced arrays for probabilities and branch counts in the
encoder. No change in bitstream.

Change-Id: Iec605446f44db4cd325eb45fa12a3003a6ee29db

Also some unused data structures/references removed.

Change-Id: I295809e887173543e794250cb60ddaf1475ffd24

Removal from under configure flag.
A bit  renaming

Change-Id: I2213229dfe852001dfec16b149f47c52ce88f3aa

Reverts to using 128 bit LUT for the coef models rather than 48
to ease hardware implementation.

Also incorporates some cleanups including removing various
hooks to support different lookup tables based on block_type and
ref_type.

Change-Id: I54100c120cca07a2ebd3a7776bc4630fa6a153f6

Merges the experiment.

Change-Id: I4eb19af6de6df6aa3a96a2e82f231d47ed9b3ae9

Uses more aggrerssive interpolation to reduce storage for the
model tables by almost more than half. Only 48 lists of probs are
stored (as opposed to 128 before), corresponding to ONE_NODE
probabilities of:
1,
3, 7, 11, ..., 115, 119,
127, 135, ..., 247, 255.

Besides, only 1 table is used as opposed to 2 before. So the overall
memory needed for the tables is just 48 * 8 = 384 bytes.

The table currently used is based on a new Pareto distribution with
heavier tail than a generalized Gaussian - which improves results on
derf by about 0.1% over a single table Generaized Gaussian.

Results overall on derfraw300 is -0.14%.

Change-Id: I19bd03559cbf5894a9f8594b8023dcc3e546f6bd

Cleans up the experiment. Actually uses reduced counts for backward
updates, and reduced number of probabilities in the context.

No change in bitstream when the experiment is on.

Between expt on and off:
derfraw300 is down only -0.062% (which is better than when expts
were run previously).

Change-Id: I55285a049a0c22810bdb42914212ab5a4f8521b5

Change band calculation back to simpler model based
on the order in which coefficients are coded in scan order
not the absolute coefficient positions.

With the scatter scan experiment enabled the results were
appear broadly neutral on derf (-0.028) but up a little on std-hd +0.134).

Without the scatterscan experiment on the results were up derf as well.

Change-Id: Ie9ef03ce42a6b24b849a4bebe950d4a5dffa6791

Change-Id: I81c19a8f19cfb5c7183609656ade833d72feb500

Delete code under the CONFIG_CODE_ZEROGROUP flag.

Change-Id: I5fe6c7b42a5da9b73118e33594301da4129f320a

Output changes slightly because of a minor bug in (at least) the sb32x16
block2above tx16x16 tables that previously existed in vp9_blockd.c.

Change-Id: I624af28ac200a8322d64454cf05c79e9502968cc

Turns model based reverse updates on for coefficients in an
effort to reduce the memory requirement for counters.

With this patch the counters needed will be reduced by about
75% since only 3 counts are needed instead of 12.

The impact in performance is:
derf300: -0.252%
stdhd250: -0.046%

However retraining should alleviate some of the drop in
performance.

Change-Id: I6f2b3e13f6d5520aa3400b0b228fb5e8b4a43caa

Change-Id: I087e08e7909a406b71715b8525c104208daa6889

Change-Id: Id4306ef6d65d4a3984aed50b775bdf48d4f6c438

This patch does not seem to give any benefits.

Change-Id: I9d2b4091d6af3dfc0875f24db86c01e2de57f8db

Adds an experiment that codes an end-of-orientation symbol
for every eligible zero encountered in scan order.

This cleans out various other sub-experiments that were part
of the origiinal patch, which will be later included if found
useful.

Results are slightly positive on all sets (0.1 - 0.2% range).

Change-Id: I57765c605fefc7fb9d1b57f1b356843602abefaf

Change-Id: Ie4713da125e954c1d30e1d4cbeb38666fce90ccc

This patch changes the default with the modecoefprob expt
to use mode-based forward updates with one-node pegged
modeling.

The maximum difference with fully trained tables is now
less that 0.1%.

Change-Id: I06b44322e10c6703f93f3c1d48d973b1136a0618

Change-Id: If69c3d795f87af5cc7bfdfe70ef733c41b4d55c8

Use sb-common version instead.

Change-Id: If2552b5a39fd2e5272f66a41c5667dda85fd3939

Merge sb32x32 and sb64x64 functions; allow for rectangular sizes. Code
gives identical encoder results before and after. There are a few
macros for rectangular block sizes under the sbsegment experiment; this
experiment is not yet functional and should not yet be used.

Change-Id: I71f93b5d2a1596e99a6f01f29c3f0a456694d728

These are mostly just for experimental purposes. I saw small gains (in
the 0.1% range) when playing with this on derf.

Change-Id: Ib21eed477bbb46bddcd73b21c5c708a5b46abedc

Now that the first AC coefficient in both directions use the same DC
as their context, there no longer is a purpose in letting both have
their own band. Merging these two bands allows us to split bands for
some of the very high-frequency AC bands.

In addition, I'm redoing the banding for the 1D-ADST col/row scans. I
don't think the old banding made any sense at all (it merged the last
coefficient of the first row/col in the same band as the first two of
the second row/col), which was clearly an oversight from the band being
applied in scan-order (rather than in their actual position). Now,
coefficients at the same position will be in the same band, regardless
what scan order is used. I think this makes most sense for the purpose
of banding, which is basically "predict energy for this coefficient
depending on the energy of context coefficients" (i.e. pt).

After full re-training, together with previous patch, derf gains about
1.2-1.3%, and hd/stdhd gain about 0.9-1.0%.

Change-Id: I7a0cc12ba724e88b278034113cb4adaaebf87e0c

Pearson correlation for above or left is significantly higher than for
previous-in-scan-order (absolute values depend on position in scan, but
in general, we gain about 0.1-0.2 by using either above or left; using
both basically just makes this even better). For eob branch skipping,
we continue to use the previous token in scan order.

This helps about 0.9% on derf after re-training on a limited data set.
Full re-training and results on larger-resolution clips are pending.

Note that this commit breaks trellis, so we can probably get further
gains out of it by fixing trellis at some later point.

Change-Id: Iead68e296fc3a105cca746b5e3da9555d6010cfe

Replaces the default tables for single coefficient magnitudes with
those obtained from an appropriate distribution. The EOB node
is left unchanged. The model is represeted as a 256-size codebook
where the index corresponds to the probability of the Zero or the
One node. Two variations are implemented corresponding to whether
the Zero node or the One-node is used as the peg. The main advantage
is that the default prob tables will become considerably smaller and
manageable. Besides there is substantially less risk of over-fitting
for a training set.

Various distributions are tried and the one that gives the best
results is the family of Generalized Gaussian distributions with
shape parameter 0.75. The results are within about 0.2% of fully
trained tables for the Zero peg variant, and within 0.1% of the
One peg variant.

The forward updates are optionally (controlled by a macro)
model-based, i.e. restricted to only convey probabilities from the
codebook. Backward updates can also be optionally (controlled by
another macro) model-based, but is turned off by default. Currently
model-based forward updates work about the same as unconstrained
updates, but there is a drop in performance with backward-updates
being model based.

The model based approach also allows the probabilities for the key
frames to be adjusted from the defaults based on the base_qindex of
the frame. Currently the adjustment function is a placeholder that
adjusts the prob of EOB and Zero node from the nominal one at higher
quality (lower qindex) or lower quality (higher qindex) ends of the
range. The rest of the probabilities are then derived based on the
model from the adjusted prob of zero.

Change-Id: Iae050f3cbcc6d8b3f204e8dc395ae47b3b2192c9

Change-Id: I07ddf3be8bc5d6c2eb561d4241879777c315b183

Adds probability updates for extra bits for the nzcs, code for
getting nzc stats, plus some minor cleanups and fixes.

Change-Id: If2814e7f04fb52f5025ad9f400f3e6c50a00b543

This patch revamps the entropy coding of coefficients to code first
a non-zero count per coded block and correspondingly remove the EOB
token from the token set.

STATUS:
Main encode/decode code achieving encode/decode sync - done.
Forward and backward probability updates to the nzcs - done.
Rd costing updates for nzcs - done.
Note: The dynamic progrmaming apporach used in trellis quantization
is not exactly compatible with nzcs. A suboptimal approach has been
used instead where branch costs are updated to account for changes
in the nzcs.

TODO:
Training the default probs/counts for nzcs

Change-Id: I951bc1e22f47885077a7453a09b0493daa77883d

Split macroblock and superblock tokenization and detokenization
functions and coefficient-related data structs so that the bitstream
layout and related code of superblock coefficients looks less like it's
a hack to fit macroblocks in superblocks.

In addition, unify chroma transform size selection from luma transform
size (i.e. always use the same size, as long as it fits the predictor);
in practice, this means 32x32 and 64x64 superblocks using the 16x16 luma
transform will now use the 16x16 (instead of the 8x8) chroma transform,
and 64x64 superblocks using the 32x32 luma transform will now use the
32x32 (instead of the 16x16) chroma transform.

Lastly, add a trellis optimize function for 32x32 transform blocks.

HD gains about 0.3%, STDHD about 0.15% and derf about 0.1%. There's
a few negative points here and there that I might want to analyze
a little closer.

Change-Id: Ibad7c3ddfe1acfc52771dfc27c03e9783e054430

Change-Id: I5416455f8f129ca0f450d00e48358d2012605072