Commit Graph

5689 Commits

Author SHA1 Message Date
James Zern
f89335f7ca remove unused VP8 com/dec asm offsets
Change-Id: Ib3b26ee27f04b2dcbbd32b3127afb45e9f50cfcf
2013-07-09 14:33:49 -07:00
John Koleszar
f0d9f10d24 Remove all asm offset files from VP9
The files are empty and unused.

Change-Id: Ieb4242d14273efdf24149bda33f9591540bba06a
2013-07-09 14:26:53 -07:00
Scott LaVarnway
5900d13183 Merge "Removed unnecessary xd->mode_info_context assignment" 2013-07-09 12:45:32 -07:00
Frank Galligan
198fa6d0a0 Add Neon horizontal and vertical vp9_mbloop_filter
- The vp9 mbfilter C code will branch on flat and mask. This CL
  will perform both branches and combine the data. A later CL will
  perform a check to see if all patch will take one branch.
- These functions are about 1.75 times faster than the C code on
  Nexus 7.

PS #3
- Changed all functions to dub limit, blimit, and thresh from
  vld {dx[]}, freeing up r4-r6.
- Changed code to use vbif to reduce one instruction and free
  up a d register.

Change-Id: I028dae0e434dc9891c3677bdb182e201ffb04777
2013-07-09 12:40:05 -07:00
Dmitry Kovalev
ec68d25521 Merge "Adding update_tx_ct function, removing duplicated code." 2013-07-09 12:26:11 -07:00
Dmitry Kovalev
aeed28f143 Removing vp9_maskingmv.c and corresponding assembly file.
Change-Id: I9842d02d61d78d17dc3449bae8ffbe60f4b3ecb3
2013-07-09 11:22:56 -07:00
Dmitry Kovalev
92a9eaef50 Loop filter code cleanup.
Using MAX_LOOP_FILTER constant instead of number 63.

Change-Id: If91e0c198331b3041e7cd0707a5948479e9209d8
2013-07-09 11:18:09 -07:00
Scott LaVarnway
69d1d1d865 Removed unnecessary xd->mode_info_context assignment
mi is xd->mode_info_context

Change-Id: Ib101be922b695205ec57b5ce1828ba19bde5b41c
2013-07-09 13:41:34 -04:00
Ronald S. Bultje
204d1b7058 Merge "Unbreak lossless." 2013-07-09 09:54:48 -07:00
Ronald S. Bultje
d8fa5d45cc Merge "Make intra prediction pointers RTCD-based." 2013-07-09 09:54:43 -07:00
Ronald S. Bultje
059c0ba5d4 Unbreak lossless.
Change-Id: I8130ec9b5371c65e885f245a5ac73840c23cb4a1
2013-07-09 09:46:37 -07:00
Jim Bankoski
7f960223ea cleanup read_mode_info if (1)
Change-Id: I851af23c787a2d3637d84244b9f75063cbf782f1
2013-07-09 09:04:45 -07:00
Jim Bankoski
c36d502e92 decoder speedup - get-segment-id only if segmentation enabled
Change-Id: I9355f8446660aeb7dfdbc5ee56635c791ac35e95
2013-07-09 08:52:30 -07:00
Yaowu Xu
df5731273f Merge "Fix loopfilter bug" 2013-07-09 01:34:25 -07:00
Dmitry Kovalev
c6c279aff0 Merge "Using mi_cols instead of mb_cols." 2013-07-08 20:09:19 -07:00
Dmitry Kovalev
1c65c580d6 Merge "Refactoring setup_pre_planes function." 2013-07-08 20:08:05 -07:00
Dmitry Kovalev
6254c8d780 Merge "Calling set_partition_seg_context() instead of code duplication." 2013-07-08 20:07:06 -07:00
Ronald S. Bultje
8350e7fe38 Make intra prediction pointers RTCD-based.
This probably has a mildly negative impact on performance, but will
(in future commits - or possibly merged with this one) allow SIMD
implementations of individual intra prediction functions. We may
perhaps want to consider having separate functions per txfm-size
also (i.e. 4x4, 8x8, 16x16 and 32x32 intra prediction functions for
each intra prediction mode), but I haven't played much with that
yet.

Change-Id: Ie739985eee0a3fcbb7aed29ee6910fdb653ea269
2013-07-08 17:25:51 -07:00
John Koleszar
527fc5caf6 Fix loopfilter bug
In the rare case were 4x4 interior filtering was called for but no
8x8 or larger filtering takes place, the previous code was skipping
the filtering. This patch fixes the issue by including the interior
mask in the overall mask for the filter application loops.

Change-Id: I4a0b65056c64f97478827c2ff41e0914fc7779d0
2013-07-08 16:49:57 -07:00
Ronald S. Bultje
a5062cc635 Don't call encode_sb() for the final of 4-split subpartitions.
The resulting reconstruction is never used, thus it just wastes CPU
cycles. Reduces encode time of first 50 frames of bus (speed 0) @
1500kbps from 2min2.0 to 2min1.2, i.e. a 0.65% overall speedup.

Change-Id: I74755ca3aadc21e2be220f486259060bd4088c45
2013-07-08 16:22:39 -07:00
Ronald S. Bultje
bd867f1619 Inline vp9_get_mv_joint().
Encode time for first 50 frames of bus (speed 0) @ 1500kbps goes from
2min10.9 to 2min10.5, i.e. 0.3% faster overall, basically because we
prevent the call overhead.

Change-Id: I1eab1a95dd3eae282f9b866f1f0b3dcadff073d5
2013-07-08 16:22:39 -07:00
Ronald S. Bultje
8fde07a3ae Don't recalculate mv_ref costs for each block/partition.
Changes cost_mv_ref() into doing a LUT into pre-calculated cost
arrays instead. Encode time of first 50 frames of bus (speed 0)
@ 1500kbps goes from 2min11.6 to 2min10.9, i.e. 0.5% faster overall.

Change-Id: If186e92c34c201b29cbbc058785a15c9c09e433a
2013-07-08 16:22:39 -07:00
Ronald S. Bultje
5a73254918 Remove unnecessary memset(best_index, 0) from trellis/optimize.
First 50 frames of bus @ 1500kbps (speed 0) goes from 2min12.6 to
2min11.6, i.e. 0.75% overall speedup.

Change-Id: I67054f8146e82a02b6457c51a1c8627a937e5e1e
2013-07-08 16:22:39 -07:00
Ronald S. Bultje
fcf7998a47 Remove memcpy() in handle_inter_mode() filter selection.
Encode time of first 50 frames of bus (speed 0) @ 1500kbps goes from
2min4.9 to 2min3.1, i.e. a 1.4% speedup overall.

Change-Id: Ibe8b08d159797504c5d0c5122de1b6da3b6595e0
2013-07-08 16:22:39 -07:00
Ronald S. Bultje
ed995afba1 Make frame-wide filter-type decision fully RD-based.
Overall, on all test sets, this gains about +0.2% on all metrics.
City is a clip where this really hurts (-1.0% on all metrics), I'm
not quite sure why yet. Maybe interesting to look into in the future.

Change-Id: I6f0eecb20e72f0194633270d30bf00d76d9eae78
2013-07-08 16:22:37 -07:00
Dmitry Kovalev
b7559258a4 Using mi_cols instead of mb_cols.
Eliminating usage of mb-units, switching to mi-units. Adding
ALIGN_POWER_OF_TWO macro.

Change-Id: I2491c969f713207c062011878b57e4e531818607
2013-07-08 14:54:04 -07:00
Deb Mukherjee
d9b62160a0 Implements several heuristics to prune mode search
Skips mode searches for intra and compound inter modes depending
on the best mode so far and the reference frames. The various
heuristics to be used are selected by bits from a flag. The
previous direction based intra mode search pruning is also absorbed
in this framework.

Specifically the flags and their impact are:

1) FLAG_SKIP_INTRA_BESTINTER (skip intra mode search for oblique
directional modes and TM_PRED if the best so far is
an inter mode)
derfraw300: -0.15%, 10% speedup

2) FLAG_SKIP_INTRA_DIRMISMATCH (skip D27, D63, D117 and D153
mode search if the best so far is not one of the closest
hor/vert/diagonal directions.
derfraw300: -0.05%, about 9% speedup

3) FLAG_SKIP_COMP_BESTINTRA (skip compound prediction mode
search if the best so far is an intra mode)
derfraw300: -0.06%, about 7-8% speedup

4) FLAG_SKIP_COMP_REFMISMATCH (skip compound prediction search
if the best single ref inter mode does not have the same ref
as one of the two references being tested in the compound mode)
derfraw300: -0.56%, about 10% speedup

Change-Id: I1a736cd29b36325489e7af9f32698d6394b2c495
2013-07-08 12:17:12 -07:00
Jingning Han
a38cf2658a Merge "Refactor SSE2 8x8 functional units" 2013-07-05 11:18:18 -07:00
Tero Rintaluoma
18303b1263 Fix intermediate height in convolve
intermediate_height for horizontal filtering must be at least 8
pixels to be able to do vertical filtering correctly. Currently
it can be less for small block and y_step_q4 sizes.

Change-Id: I2ee28b0591b2041c2fa9844d0ae2ff8a1a59cc21
2013-07-05 14:58:25 +03:00
Paul Wilkins
ef0ca2deaa Merge "Fix to comp_inter_joint_search_thresh feature." 2013-07-04 03:27:00 -07:00
Dmitry Kovalev
bfcef95c45 Adding update_tx_ct function, removing duplicated code.
Change-Id: I8882fe3cd247a5a8304ab8ab2ee9abdb92830133
2013-07-03 18:24:13 -07:00
Dmitry Kovalev
f72e072555 Refactoring setup_pre_planes function.
Removing set_refs, adding set_ref function.

Change-Id: I5635c478b106ae4e57d317f1c83d929644307e63
2013-07-03 17:42:01 -07:00
Dmitry Kovalev
2ce6b23473 Merge "Adding write_skip_coeff function." 2013-07-03 16:33:58 -07:00
Jingning Han
68172dbede Merge "Enable early termination in rd search" 2013-07-03 14:20:41 -07:00
Dmitry Kovalev
430bd0c94a Merge "Replacing 64 / MI_SIZE with MI_BLOCK_SIZE." 2013-07-03 14:16:02 -07:00
Dmitry Kovalev
dda1835dc6 Adding write_skip_coeff function.
Change-Id: I221126f22ab9067348eb0efb8a73b15a8f49c3fd
2013-07-03 13:23:47 -07:00
Yaowu Xu
c86b18894e Merge "Inline a few intra predictors" 2013-07-03 13:21:22 -07:00
Jingning Han
2bd6fe08f8 Enable early termination in rd search
This commit allows encoder to detect the cumulative rate-distortion
cost per transformed block inside a partition. If the cumulative
rd cost is already above the best rd value, it terminates the rest
operations and continue to next prediction mode test.

It reduces the runtime of bus at target bit-rate 2000 from 308 second
to 266 second, i.e., about 13% speed-up at no performance penalty.

Change-Id: I5f15a3d8955d97031d5653006027866a00654e7a
2013-07-03 12:54:18 -07:00
Dmitry Kovalev
2ad62c9312 Calling set_partition_seg_context() instead of code duplication.
Change-Id: I65be6acc54c99688fd1f0c946cec3511514b8555
2013-07-03 11:15:58 -07:00
Dmitry Kovalev
5a21de8418 Replacing 64 / MI_SIZE with MI_BLOCK_SIZE.
Change-Id: I32276552b3ea6dc1dce8e298be114cfe1019b31c
2013-07-03 10:54:50 -07:00
Dmitry Kovalev
60198a595d Merge "Adding write_selected_txfm_size function." 2013-07-03 10:33:55 -07:00
Yaowu Xu
0f02dc2709 Inline a few intra predictors
Change-Id: Ib41f0643fdcc088500e7420708f4e72f1f64c710
2013-07-03 10:20:41 -07:00
Jingning Han
2cb75c9607 Refactor SSE2 8x8 functional units
These serve as building blocks for SSE2 8x8 and 16x16 ADST/DCT
hybrid transform coding.

Change-Id: I4089a754c66e0c986f67d9b8ec4dfb9627ad430d
2013-07-03 10:11:59 -07:00
Ronald S. Bultje
61fe678f36 Merge "Use pmovmskb to skip quantize loops over empty coefficients." 2013-07-03 09:05:48 -07:00
Ronald S. Bultje
98c493a1c0 Merge "Remove unused function vp9_build_inter4x4_predictors_mbuv()." 2013-07-03 09:05:20 -07:00
Paul Wilkins
f58b44ad62 Fix to comp_inter_joint_search_thresh feature.
When this is 0 (BLOCK_SIZE_AB4X4) we want to do
the inter joint search for all sizes.

Change-Id: Id40cd6fe7790e7e1165352b9cef5e12fa8c0bc88
2013-07-03 16:58:34 +01:00
Paul Wilkins
72c5778ec5 Added two new skip experiments.
sf->unused_mode_skip_lvl. Tests modes as normal for all
sizes at or below the given level. At larger sizes it skips
all modes that were not chosen at any smaller size.
Hence setting BLOCK_SIZE_SB64X64 is in effect off.
Setting BLOCK_SIZE_AB4X4 will only consider modes that
were chosen for one or more 4x4 blocks at larger sizes.

sf->reference_masking.
Do a test encode of the NONE partition at one size and create
a reference frame mask based on the best rd choice. In the
full search only allow this reference frame.
Currently it is testing 64x64 and repeats this in the full search.
This does not work well with Jim's Partition code just now and
is disabled by default.

Change-Id: I8f8c52d2ef4a0c08100150b0ea4155d1aaab93dd
2013-07-03 16:56:06 +01:00
Scott LaVarnway
5e6b333902 Bug fix: set frame_parallel_decoding_mode
This patch allows the frame_parallel_decoding_mode flag
to be set instead of returning a codec error.

Change-Id: I4a1631c625723ac8873290d0fd0211074a87d112
2013-07-03 10:25:29 -04:00
Paul Wilkins
b0a2871c35 Merge "Adjust Speed 0 settings." 2013-07-03 02:47:18 -07:00
Dmitry Kovalev
1f6e95e76a Merge "Removing redundant struct from union b_mode_info." 2013-07-02 18:09:31 -07:00