GitLab

Change-Id: If90c1bc822873156d4e38fca1938e4907f6c95f0

Change-Id: Ib719a9f74924718715592e0238bc391ae239d026

Change-Id: Ib49d8dbc67c590f22a1a70251ff607c9f38febd7

The core motion estimation fucntions all return sad now consistently.
The only exception is vp9_full_pixel_diamond(), however the core diamond
and refining search routines called from vp9_full_pixel_diamond() also
return SAD. If variance of pred error + mv cost is desired it must be
calculated explicitly outside these functions. For very fast encoding,
hopefully this will eliminate some redundant computations.

Also suggests reimplementing FAST_HEX with the vp9_pattern_search
framework. It is not exactly the same as the existing FAST_HEX, but
performance is slightly better and speed is very similar. Enables
removing a lot of duplicate code.

Change-Id: I152736393438c25bdf7e96b37cbb8ce330f4f94a

Change-Id: I4a54b12e5229705222c5a101258b9d1f81e2948d

Change-Id: I9423b543e1be414e5c9e10480b813f06e6b88f8a

This patch adds a new speed feature which doesn't do the rather
expensive entropy context lookup or save to the table,  while
doing costing.

The speed up on desktop36p.y4m is around 10% other clips much less.

On the RTC test set this was + 1% in overall datarate.

Change-Id: Ia5144bbf45270671e7be9c8e4055369909e2f738

This gets more accurate mode hit stats. It's also the first step to
handling ZEROMV not being allowed more intelligently.

Change-Id: I5de6734507b5177bf73e9ddbad923f218c39f3e4

Reset FAST_HEX search_method, which was lost because of code merging.

Change-Id: Ic2b2cb9ec2f1751e96f7db0f9226310f605fcc83

intra_y_mode_mask is already enforced for the sub8x8 case.
intra_uv_mode_mask is already enforced for all sizes.

Change-Id: Ia9dd14701cb49873c2e8f24eb5f8b255eaf76a1f

Clear warning caused by implied conversion from int32 to int64.

Change-Id: I473b37a54984cbfb22702eb3f712465881ff86e8

Change-Id: I5a01d0dccc9afc87e2adbb5ddc7d44379fe1f125

There is one parameter that is never used, therefore is removed.

Change-Id: I595722e7c5731534c72831315359e4dce9c21763

Two paramemters are not in use, therefore are removed.

Change-Id: I41eb601b7b4bf2feedb13b3f240315656d8694f9

Change-Id: Ia319bd924401677b5c30b0f46d1ab2be6a1f446e

Change-Id: I111c5bd0dd47db7b1f6952c18056bee548bb42e9

Change-Id: I6d47618e8aee6e6c2fe1cf0b8bb4da0b2a0bab66

In addition, a local variable was renamed to avoid confusion.

Change-Id: Id4c497f9cfa219e8a414aa9fee9a85af5f147249

The function has evolved over time, now only calls vp9_rtcd(), so this
commit removes the function and changes to call vp9_rtcd() directly.

Change-Id: I8cfa6190daa4b28f6f3d1e11bb3a07f9c95322bf

The parameter was never used.

Change-Id: I99fd9aad697917ddbe3d10c71cae344228fafc31

Optimizing 2 functions to process 32 elements in parallel instead of 16:
1. vp9_sub_pixel_avg_variance64x64
2. vp9_sub_pixel_avg_variance32x32
both of those function were calling vp9_sub_pixel_avg_variance16xh_ssse3
instead of calling that function, it calls vp9_sub_pixel_avg_variance32xh_avx2
that is written in avx2 and process 32 elements in parallel.
This Optimization gave 80% function level gain and 2% user level gain

Change-Id: Iea694654e1b7612dc6ed11e2626208c2179502c8

Change-Id: I7255b3bc47d760333f58ac4878becbcc8ad30967

Change-Id: I909a81991aa0cc18afe6526542c7513837445213

Change-Id: I7e2591b4b54e0eac8521e128c7d97f62d2057ed8

Adds a speed 8 to VP9 where only the nearestmv (0 mv) is searched.
This seems to be about the same speed as vp8 speed 5.

Adds a new speed feature to disable inter modes based on a mask for
each blocksize.

Adds code for having lower complexity motion search methods
in nonrd pick mode function, even though speed 7 still uses DIAMOND
search for now.

Also uses HEX search for speed 6 rather than FAST_HEX which improves
psnr by 0.56% without any noticeable speed drop (tested on gipsmotion).

Change-Id: Ic13176572dbd3aed5884a26786940a4b1bbd8a75

Change-Id: Ib68d4a2de838254a66272324b909292048cbe60d

Change-Id: I64172710654e95a90ee754d14d7104337d28010f

Change-Id: Ic32eb103d0d7f98c0a16c4e7bdec117faf05df02

Change-Id: Icc057b819d80c608a6003fd7ef58aefed7a15824

Change-Id: Iee4f8443971fe2b21762d87f0be5751329768b5a

For blocks at frame boundary, the selected block size sometimes needs
to be smaller than that was first given. This commit forces such block
size change only between square blocks, so as to avoid the potential
use case containing 32x16 + 16x8 + 16x8, for 1080p sequences.

Local test suggested no visible coding speed difference. Borg test
reveals no difference in terms of compression performance.

Change-Id: Ie8de87f3c6febc3acf11b4cbfdf2077f9f6def52

Change-Id: Id5b56c7bc5671859f54ae69693064804d3fadd98

Change-Id: I9a38af32f16f196b83dd69755eafb9543edf5691

This commit checks if the motion vector associated with the current
mode has been computed in previous mode tests. If possible, skip the
redundant reference block generation and SAD calculation in the
non-RD mode decision process.

For test sequence pedestrian_area 1080p, the runtime goes from
24261 ms to 23770 ms. This does not change compression performance.
The speed-up is mostly around places with consistent motion.

Change-Id: I97be63c6a2d07c57be26b3c600fbda3803adddda

Change-Id: I4e5ca10f7aef2d37fda835b369828d0bbff7c8a0

Change-Id: Iaaa16b4b2c581eaeb9e4ecfcfe60f98b8a0fa40b

Change-Id: I7d11c6ae259aff6560710d16fea3032c661e5b02

Change-Id: Ie9c66a93d45271e54b84bea6a38f07db6c4fd1ca

Change-Id: Id145da99259866109cfee8b47a1d8f309944b937

Change-Id: Iba128039534e16a6e0a8cfe7e58306c4655e9f0d