Change-Id: Ic8fc16ee1734cfde0d12a2e3abb3e9299382f3b1

This function is also used with the U and V planes.

Change-Id: Ib6beae0438790bfb690b3a2bda9c5c8b0e89a9b8

Change-Id: I0fd76937e847f78378a7ab3fa0af00a7c2c52b42

Change-Id: Ie829ee58a55157e6972c63cebe69a5d0a3221349

Change-Id: Ic92f15d82ff5cfa3df655d08e460335c2ef8a325

Change-Id: I6c3d47b00acabe7ffba22ffc73741173aa9a0bff

This commit takes out vp9_extend_frame_borders from
vp9_setup_scale_factors.

The refactoring is for the preparation of the use of lazy border
extension at decoder. This makes it necessary to handle border
extension separately at encoder/decoder. The use of
vp9_extend_frame_borders will be removed, when lazy border extension
is ready.

Change-Id: Ia3baba3d179d5f11eee1634f19b3b319d2a59186

The decoder ignored the display width & height
specified in the frame header.

This patch adds a control, VP9D_GET_DISPLAY_SIZE, to
allow the application to obtain the display width and
height from the frame header.

vpxdec has been modified to scale the output frame to
this size.

Should the request for the display size fail vpxdec will
use the native width and height of the raw decoded
frame instead.

Change-Id: I25db04407426dac730263720c75a7dd6400af68a

Moves all rate control variables to a separate structure,
removes some currently unused variables,
moves some rate control functions to vp9_ratectrl.c,
and splits the encode_frame_to_data_rate function.

Change-Id: I4ed54c24764b3b6de2dd676484f01473724ab52b

Change-Id: I6a48d1f35ed5fe7a2c7499675b339994c9c3bdf2

removed unnecessary ifs and branches ..

Change-Id: Id1698a35292659388f48926791024d1400f2cea9

The change caused mismatches with some test vectors on neon.

Original CL: https://gerrit.chromium.org/gerrit/#/c/67863/

Change-Id: I913891636d53783e93cb1865ca78ded1821dc4b0

This code only updates the token_cache if the result is non0.

Change-Id: Idcabd0b993a926fea9c29dbec134b9c5c4859b40

Using for loop based on max_tx_size instead of separate checks. Combining
build_coeff_contexts() with update_coef_probs().

Change-Id: Ie335a7db29830677fbc14478a9c190d3c1068665

Modifications are done to reduce the total clock cycle.
Speedup: 1.2

Tested with: park_joy_420_720p50.y4m

Change-Id: Ia36b87e62e2f80a5fadaf5628729aedc80f38f3f

Added filter_selectively_vert_row2 to be ready for parallel
loopfiltering in vertical direction. This change did 2-row
filtering at a time. If 2 vertically adjacent 8x8 blocks do same
type of filtering, we can do 16-pixel filtering in parallel.

Next, we need to provide 16-pixel loopfiltering functions in c
and optimized versions for codec speedup.

Change-Id: Idf97bbdd70566e55bd30e1fd25cb8544e33291be

Add support to do 16 pixel horizontal filtering in Neon.
Nexus devices saw about 0.5% decode speed increase.

Change-Id: I2993f6c2d49f31fa74976879eeaa289fd3f4e15d

Change-Id: I67d1681c7b17661deb792c5e6a9e2014a73ff9b7

Change-Id: Ibe847000467fe46bf8ce87d8f1ef8f2d5ad1eaf4

Although no mismatch was indicated for 8/16 wide sub-pixel filters
in issue 661, they had similar problems that could cause mismatch
potentially. This patch fixed calculations in HORIZx8/16
and VERTx8/16.

Change-Id: I169961c9d40a20340995b7d22aafc89ccf30bfca

Change-Id: I29c0dfcf41a1253d5e2a0d2ff740c0c38ebaa5a2

Change-Id: Iadd771a33c8874f3b774923bca4da3c8fe5429ee

Change-Id: I98d750ee92ff51fb714980418ea28be3b1d0f3c6

Change-Id: Ia568f70bddc1a2b62141a0197459119ca74c22b5

Change-Id: I5556e8d1fc150be8a3e93af21900829b59a500dc

Change-Id: I00a5203c8ed76c184d936fccf93d76e7c06773d3

In commit "3d50da53", the stack
pointer was modified while aligning the stack, and it needed to
be pop out at the end.

Change-Id: I062971e195f1f2ab9d0ab5fb84dcf215a0fcaa67

Change-Id: I94cb9e3d910dff74bf90906dd96e3a4e06ebdbe6

There are many places in handle_inter_mode that need to restore the
dst buffer pointers, due to buffer pointer swap and early rd search
breakout. This commit wraps these operations into an inline function
for clean-up.

Change-Id: I0462e8c41c8bc3cd8db07395489cac03d8e5be54

Change-Id: I473947b5ca70b7a81151926284bff86f8555492a

This patch fixed issue 661: "Decoder produces mismatched outputs
with ssse3 enabled and disabled." In sub-pixel filters, a pixel
value was multiplied by a filter coefficient, and the results
were added up. The order of adding up these multiplications had to
be arranged carefully to prevent incorrect overflowing.

Change-Id: Id08af4200fea9e1b896fc40157b8651c2c7e80f2

Change-Id: Ifad4b0e6355ce49fcc6f470becc080e8069452ee

As it is used in encoder only.

Change-Id: I5f2a8abbe72bb18cbf6ce36a3dc7e132aeae8ec2

Change-Id: Ic316d3374ff9a2b43897272260947d56765a0fdd

Change-Id: I64b189dfeee1cf3e90134a1a93497072f3361e5e

Change-Id: I6f6ba91b1b8b280902b171472314d665aa0baf0b

Reversing bit order of partition_context_lookup, and modifying accordingly
update_partition_context() and partition_plane_context().

Change-Id: I64a11f1a94962a3bf217de2f50698cb781db71a5

There is no need to use that function, it is much clear to pass offset
directly to the buffer.

Change-Id: I9026cb0c5094c46f97df5d7f7daeb952f2843b24

Change-Id: I23fea0a2e85be8373600e3e2dae98d36acde389c

This rebase is a better implementation of the previous ones.

Modifications are done to reduce the total clock cycle.
Speedup: 1.341
Compiled with -O3
Tested with: park_joy_420_720p50.y4m

Change-Id: I940eaf283f60597ca0d9d2e13d518878d55ff02d