generic-library/vpx
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
vpx/vp9/common/vp9_blockd.c

924 lines
37 KiB
C
Raw Normal View History

Initial WebM release
2010-05-18 11:58:33 -04:00
/*
Use WebM in copyright notice for consistency Changes 'The VP8 project' to 'The WebM project', for consistency with other webmproject.org repositories. Fixes issue #97. Change-Id: I37c13ed5fbdb9d334ceef71c6350e9febed9bbba
2010-09-09 08:16:39 -04:00
* Copyright (c) 2010 The WebM project authors. All Rights Reserved.
Initial WebM release
2010-05-18 11:58:33 -04:00
*
cosmetics: trim trailing whitespace When the license headers were updated, they accidentally contained trailing whitespace, so unfortunately we have to touch all the files again. Change-Id: I236c05fade06589e417179c0444cb39b09e4200d
2010-06-18 12:39:21 -04:00
* Use of this source code is governed by a BSD-style license
LICENSE: update with latest text Change-Id: Ieebea089095d9073b3a94932791099f614ce120c
2010-06-04 16:19:40 -04:00
* that can be found in the LICENSE file in the root of the source
* tree. An additional intellectual property rights grant can be found
cosmetics: trim trailing whitespace When the license headers were updated, they accidentally contained trailing whitespace, so unfortunately we have to touch all the files again. Change-Id: I236c05fade06589e417179c0444cb39b09e4200d
2010-06-18 12:39:21 -04:00
* in the file PATENTS. All contributing project authors may
LICENSE: update with latest text Change-Id: Ieebea089095d9073b3a94932791099f614ce120c
2010-06-04 16:19:40 -04:00
* be found in the AUTHORS file in the root of the source tree.
Initial WebM release
2010-05-18 11:58:33 -04:00
*/
Fairly basic integration of rectangular blocks in encoding RD loop. Adds RD integration for 32x16, 16x32, 64x32 and 32x64 rectangular blocks. Derf almost +0.6%, HD a little over +1.0%, STDHD +1.3%. Change-Id: Id651fdb6a655fdbb5c47009757e63317acfb88a5
2013-04-17 09:25:06 -07:00
#include "./vpx_config.h"
fixed includes to be fully specified Change-Id: Ia1cce221f8511561b9cbd8edb7726fbc286ff243
2012-11-28 10:41:40 -08:00
#include "vp9/common/vp9_blockd.h"
Initial WebM release
2010-05-18 11:58:33 -04:00
#include "vpx_mem/vpx_mem.h"
Make superblocks independent of macroblock code and data. 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
2013-03-04 14:12:17 -08:00
const uint8_t vp9_block2left[TX_SIZE_MAX_MB][24] = {
{ 0, 0, 0, 0,
1, 1, 1, 1,
2, 2, 2, 2,
3, 3, 3, 3,
4, 4,
5, 5,
6, 6,
7, 7 },
{ 0, 0, 0, 0,
0, 0, 0, 0,
2, 2, 2, 2,
2, 2, 2, 2,
4, 4,
4, 4,
6, 6,
6, 6 },
{ 0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0 },
Changed above and left context data layout The main reason for the change was to reduce cycles in the token decoder. (~1.5% gain for 32 bit) This layout should be more cache friendly. As a result of this change, the encoder had to be updated. Change-Id: Id5e804169d8889da0378b3a519ac04dabd28c837 Note: dixie uses a similar layout
2010-08-31 10:49:57 -04:00
};
Make superblocks independent of macroblock code and data. 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
2013-03-04 14:12:17 -08:00
const uint8_t vp9_block2above[TX_SIZE_MAX_MB][24] = {
{ 0, 1, 2, 3,
0, 1, 2, 3,
0, 1, 2, 3,
0, 1, 2, 3,
4, 5,
4, 5,
6, 7,
6, 7 },
{ 0, 0, 0, 0,
2, 2, 2, 2,
0, 0, 0, 0,
2, 2, 2, 2,
4, 4,
4, 4,
6, 6,
6, 6 },
{ 0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0 },
WebM Experimental Codec Branch Snapshot This is a code snapshot of experimental work currently ongoing for a next-generation codec. The codebase has been cut down considerably from the libvpx baseline. For example, we are currently only supporting VBR 2-pass rate control and have removed most of the code relating to coding speed, threading, error resilience, partitions and various other features. This is in part to make the codebase easier to work on and experiment with, but also because we want to have an open discussion about how the bitstream will be structured and partitioned and not have that conversation constrained by past work. Our basic working pattern has been to initially encapsulate experiments using configure options linked to #IF CONFIG_XXX statements in the code. Once experiments have matured and we are reasonably happy that they give benefit and can be merged without breaking other experiments, we remove the conditional compile statements and merge them in. Current changes include: * Temporal coding experiment for segments (though still only 4 max, it will likely be increased). * Segment feature experiment - to allow various bits of information to be coded at the segment level. Features tested so far include mode and reference frame information, limiting end of block offset and transform size, alongside Q and loop filter parameters, but this set is very fluid. * Support for 8x8 transform - 8x8 dct with 2nd order 2x2 haar is used in MBs using 16x16 prediction modes within inter frames. * Compound prediction (combination of signals from existing predictors to create a new predictor). * 8 tap interpolation filters and 1/8th pel motion vectors. * Loop filter modifications. * Various entropy modifications and changes to how entropy contexts and updates are handled. * Extended quantizer range matched to transform precision improvements. There are also ongoing further experiments that we hope to merge in the near future: For example, coding of motion and other aspects of the prediction signal to better support larger image formats, use of larger block sizes (e.g. 32x32 and up) and lossless non-transform based coding options (especially for key frames). It is our hope that we will be able to make regular updates and we will warmly welcome community contributions. Please be warned that, at this stage, the codebase is currently slower than VP8 stable branch as most new code has not been optimized, and even the 'C' has been deliberately written to be simple and obvious, not fast. The following graphs have the initial test results, numbers in the tables measure the compression improvement in terms of percentage. The build has the following optional experiments configured: --enable-experimental --enable-enhanced_interp --enable-uvintra --enable-high_precision_mv --enable-sixteenth_subpel_uv CIF Size clips: http://getwebm.org/tmp/cif/ HD size clips: http://getwebm.org/tmp/hd/ (stable_20120309 represents encoding results of WebM master branch build as of commit#7a15907) They were encoded using the following encode parameters: --good --cpu-used=0 -t 0 --lag-in-frames=25 --min-q=0 --max-q=63 --end-usage=0 --auto-alt-ref=1 -p 2 --pass=2 --kf-max-dist=9999 --kf-min-dist=0 --drop-frame=0 --static-thresh=0 --bias-pct=50 --minsection-pct=0 --maxsection-pct=800 --sharpness=0 --arnr-maxframes=7 --arnr-strength=3(for HD,6 for CIF) --arnr-type=3 Change-Id: I5c62ed09cfff5815a2bb34e7820d6a810c23183c
2012-03-09 17:32:50 -08:00
};
Make superblocks independent of macroblock code and data. 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
2013-03-04 14:12:17 -08:00
#define S(x) x + sizeof(ENTROPY_CONTEXT_PLANES) / sizeof(ENTROPY_CONTEXT)
Fairly basic integration of rectangular blocks in encoding RD loop. Adds RD integration for 32x16, 16x32, 64x32 and 32x64 rectangular blocks. Derf almost +0.6%, HD a little over +1.0%, STDHD +1.3%. Change-Id: Id651fdb6a655fdbb5c47009757e63317acfb88a5
2013-04-17 09:25:06 -07:00
#if CONFIG_SBSEGMENT
const uint8_t vp9_block2left_sb16x32[TX_SIZE_MAX_MB][48] = {
{ 0, 0, 0, 0,
1, 1, 1, 1,
2, 2, 2, 2,
3, 3, 3, 3,
S(0), S(0), S(0), S(0),
S(1), S(1), S(1), S(1),
S(2), S(2), S(2), S(2),
S(3), S(3), S(3), S(3),
4, 4,
5, 5,
S(4), S(4),
S(5), S(5),
6, 6,
7, 7,
S(6), S(6),
S(7), S(7) },
{ 0, 0, 0, 0,
0, 0, 0, 0,
2, 2, 2, 2,
2, 2, 2, 2,
S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0),
S(2), S(2), S(2), S(2),
S(2), S(2), S(2), S(2),
4, 4,
4, 4,
S(4), S(4),
S(4), S(4),
6, 6,
6, 6,
S(6), S(6),
S(6), S(6) },
{ 0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0,
S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0) },
};
const uint8_t vp9_block2above_sb16x32[TX_SIZE_MAX_MB][48] = {
{ 0, 1, 2, 3,
0, 1, 2, 3,
0, 1, 2, 3,
0, 1, 2, 3,
0, 1, 2, 3,
0, 1, 2, 3,
0, 1, 2, 3,
0, 1, 2, 3,
4, 5,
4, 5,
4, 5,
4, 5,
6, 7,
6, 7,
6, 7,
6, 7 },
{ 0, 0, 0, 0,
2, 2, 2, 2,
0, 0, 0, 0,
2, 2, 2, 2,
0, 0, 0, 0,
2, 2, 2, 2,
0, 0, 0, 0,
2, 2, 2, 2,
4, 4,
4, 4,
4, 4,
4, 4,
6, 6,
6, 6,
6, 6,
6, 6 },
{ 0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0,
0, 0, 0, 0 },
};
const uint8_t vp9_block2left_sb32x16[TX_SIZE_MAX_MB][48] = {
{ 0, 0, 0, 0, 0, 0, 0, 0,
1, 1, 1, 1, 1, 1, 1, 1,
2, 2, 2, 2, 2, 2, 2, 2,
3, 3, 3, 3, 3, 3, 3, 3,
4, 4, 4, 4,
5, 5, 5, 5,
6, 6, 6, 6,
7, 7, 7, 7 },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2,
4, 4, 4, 4,
4, 4, 4, 4,
6, 6, 6, 6,
6, 6, 6, 6 },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0 },
};
const uint8_t vp9_block2above_sb32x16[TX_SIZE_MAX_MB][48] = {
{ 0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
4, 5, S(4), S(5),
4, 5, S(4), S(5),
6, 7, S(6), S(7),
6, 7, S(6), S(7) },
{ 0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
4, 4, 4, 4,
S(4), S(4), S(4), S(4),
6, 6, 6, 6,
S(6), S(6), S(6), S(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0 },
};
#endif
Make superblocks independent of macroblock code and data. 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
2013-03-04 14:12:17 -08:00
const uint8_t vp9_block2left_sb[TX_SIZE_MAX_SB][96] = {
{ 0, 0, 0, 0, 0, 0, 0, 0,
1, 1, 1, 1, 1, 1, 1, 1,
2, 2, 2, 2, 2, 2, 2, 2,
3, 3, 3, 3, 3, 3, 3, 3,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3),
4, 4, 4, 4,
5, 5, 5, 5,
S(4), S(4), S(4), S(4),
S(5), S(5), S(5), S(5),
6, 6, 6, 6,
7, 7, 7, 7,
S(6), S(6), S(6), S(6),
S(7), S(7), S(7), S(7) },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
4, 4, 4, 4,
4, 4, 4, 4,
S(4), S(4), S(4), S(4),
S(4), S(4), S(4), S(4),
6, 6, 6, 6,
6, 6, 6, 6,
S(6), S(6), S(6), S(6),
S(6), S(6), S(6), S(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6 },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0 },
};
const uint8_t vp9_block2above_sb[TX_SIZE_MAX_SB][96] = {
{ 0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
4, 5, S(4), S(5),
4, 5, S(4), S(5),
4, 5, S(4), S(5),
4, 5, S(4), S(5),
6, 7, S(6), S(7),
6, 7, S(6), S(7),
6, 7, S(6), S(7),
6, 7, S(6), S(7) },
{ 0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
4, 4, 4, 4,
S(4), S(4), S(4), S(4),
4, 4, 4, 4,
S(4), S(4), S(4), S(4),
6, 6, 6, 6,
S(6), S(6), S(6), S(6),
6, 6, 6, 6,
S(6), S(6), S(6), S(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6 },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0 },
};
#define T(x) x + 2 * (sizeof(ENTROPY_CONTEXT_PLANES) / sizeof(ENTROPY_CONTEXT))
#define U(x) x + 3 * (sizeof(ENTROPY_CONTEXT_PLANES) / sizeof(ENTROPY_CONTEXT))
Fairly basic integration of rectangular blocks in encoding RD loop. Adds RD integration for 32x16, 16x32, 64x32 and 32x64 rectangular blocks. Derf almost +0.6%, HD a little over +1.0%, STDHD +1.3%. Change-Id: Id651fdb6a655fdbb5c47009757e63317acfb88a5
2013-04-17 09:25:06 -07:00
#if CONFIG_SBSEGMENT
const uint8_t vp9_block2left_sb32x64[TX_SIZE_MAX_SB][192] = {
{ 0, 0, 0, 0, 0, 0, 0, 0,
1, 1, 1, 1, 1, 1, 1, 1,
2, 2, 2, 2, 2, 2, 2, 2,
3, 3, 3, 3, 3, 3, 3, 3,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(1), T(1), T(1), T(1), T(1), T(1), T(1), T(1),
T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2),
T(3), T(3), T(3), T(3), T(3), T(3), T(3), T(3),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(1), U(1), U(1), U(1), U(1), U(1), U(1), U(1),
U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2),
U(3), U(3), U(3), U(3), U(3), U(3), U(3), U(3),
4, 4, 4, 4,
5, 5, 5, 5,
S(4), S(4), S(4), S(4),
S(5), S(5), S(5), S(5),
T(4), T(4), T(4), T(4),
T(5), T(5), T(5), T(5),
U(4), U(4), U(4), U(4),
U(5), U(5), U(5), U(5),
6, 6, 6, 6,
7, 7, 7, 7,
S(6), S(6), S(6), S(6),
S(7), S(7), S(7), S(7),
T(6), T(6), T(6), T(6),
T(7), T(7), T(7), T(7) },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2),
T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2),
U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2),
4, 4, 4, 4,
4, 4, 4, 4,
S(4), S(4), S(4), S(4),
S(4), S(4), S(4), S(4),
T(4), T(4), T(4), T(4),
T(4), T(4), T(4), T(4),
U(4), U(4), U(4), U(4),
U(4), U(4), U(4), U(4),
6, 6, 6, 6,
6, 6, 6, 6,
S(6), S(6), S(6), S(6),
S(6), S(6), S(6), S(6),
T(6), T(6), T(6), T(6),
T(6), T(6), T(6), T(6),
U(6), U(6), U(6), U(6),
U(6), U(6), U(6), U(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
T(4), T(4), T(4), T(4),
T(4), T(4), T(4), T(4),
T(4), T(4), T(4), T(4),
T(4), T(4), T(4), T(4),
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6,
T(6), T(6), T(6), T(6),
T(6), T(6), T(6), T(6),
T(6), T(6), T(6), T(6),
T(6), T(6), T(6), T(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0) },
};
const uint8_t vp9_block2above_sb32x64[TX_SIZE_MAX_SB][192] = {
{ 0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3),
4, 5, S(4), S(5),
4, 5, S(4), S(5),
4, 5, S(4), S(5),
4, 5, S(4), S(5),
4, 5, S(4), S(5),
4, 5, S(4), S(5),
4, 5, S(4), S(5),
4, 5, S(4), S(5),
6, 7, S(6), S(7),
6, 7, S(6), S(7),
6, 7, S(6), S(7),
6, 7, S(6), S(7),
6, 7, S(6), S(7),
6, 7, S(6), S(7),
6, 7, S(6), S(7),
6, 7, S(6), S(7) },
{ 0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
0, 0, 0, 0, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
4, 4, 4, 4,
S(4), S(4), S(4), S(4),
4, 4, 4, 4,
S(4), S(4), S(4), S(4),
4, 4, 4, 4,
S(4), S(4), S(4), S(4),
4, 4, 4, 4,
S(4), S(4), S(4), S(4),
6, 6, 6, 6,
S(6), S(6), S(6), S(6),
6, 6, 6, 6,
S(6), S(6), S(6), S(6),
6, 6, 6, 6,
S(6), S(6), S(6), S(6),
6, 6, 6, 6,
S(6), S(6), S(6), S(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
4, 4, 4, 4,
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6,
6, 6, 6, 6 },
{ 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0 },
};
const uint8_t vp9_block2left_sb64x32[TX_SIZE_MAX_SB][192] = {
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3),
4, 4, 4, 4, 4, 4, 4, 4,
5, 5, 5, 5, 5, 5, 5, 5,
S(4), S(4), S(4), S(4), S(4), S(4), S(4), S(4),
S(5), S(5), S(5), S(5), S(5), S(5), S(5), S(5),
6, 6, 6, 6, 6, 6, 6, 6,
7, 7, 7, 7, 7, 7, 7, 7,
S(6), S(6), S(6), S(6), S(6), S(6), S(6), S(6),
S(7), S(7), S(7), S(7), S(7), S(7), S(7), S(7) },
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
S(4), S(4), S(4), S(4), S(4), S(4), S(4), S(4),
S(4), S(4), S(4), S(4), S(4), S(4), S(4), S(4),
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
S(6), S(6), S(6), S(6), S(6), S(6), S(6), S(6),
S(6), S(6), S(6), S(6), S(6), S(6), S(6), S(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6 },
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 },
};
const uint8_t vp9_block2above_sb64x32[TX_SIZE_MAX_SB][192] = {
{ 0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7) },
{ 0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
4, 4, 4, 4, S(4), S(4), S(4), S(4),
T(4), T(4), T(4), T(4), U(4), U(4), U(4), U(4),
4, 4, 4, 4, S(4), S(4), S(4), S(4),
T(4), T(4), T(4), T(4), U(4), U(4), U(4), U(4),
6, 6, 6, 6, S(6), S(6), S(6), S(6),
T(6), T(6), T(6), T(6), U(6), U(6), U(6), U(6),
6, 6, 6, 6, S(6), S(6), S(6), S(6),
T(6), T(6), T(6), T(6), U(6), U(6), U(6), U(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6),
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0) },
};
#endif
Make superblocks independent of macroblock code and data. 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
2013-03-04 14:12:17 -08:00
const uint8_t vp9_block2left_sb64[TX_SIZE_MAX_SB][384] = {
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1), S(1),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3), S(3),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(1), T(1), T(1), T(1), T(1), T(1), T(1), T(1), T(1), T(1), T(1), T(1), T(1), T(1), T(1), T(1),
T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2),
T(3), T(3), T(3), T(3), T(3), T(3), T(3), T(3), T(3), T(3), T(3), T(3), T(3), T(3), T(3), T(3),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(1), U(1), U(1), U(1), U(1), U(1), U(1), U(1), U(1), U(1), U(1), U(1), U(1), U(1), U(1), U(1),
U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2),
U(3), U(3), U(3), U(3), U(3), U(3), U(3), U(3), U(3), U(3), U(3), U(3), U(3), U(3), U(3), U(3),
4, 4, 4, 4, 4, 4, 4, 4,
5, 5, 5, 5, 5, 5, 5, 5,
S(4), S(4), S(4), S(4), S(4), S(4), S(4), S(4),
S(5), S(5), S(5), S(5), S(5), S(5), S(5), S(5),
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
T(5), T(5), T(5), T(5), T(5), T(5), T(5), T(5),
U(4), U(4), U(4), U(4), U(4), U(4), U(4), U(4),
U(5), U(5), U(5), U(5), U(5), U(5), U(5), U(5),
6, 6, 6, 6, 6, 6, 6, 6,
7, 7, 7, 7, 7, 7, 7, 7,
S(6), S(6), S(6), S(6), S(6), S(6), S(6), S(6),
S(7), S(7), S(7), S(7), S(7), S(7), S(7), S(7),
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6),
T(7), T(7), T(7), T(7), T(7), T(7), T(7), T(7),
U(6), U(6), U(6), U(6), U(6), U(6), U(6), U(6),
U(7), U(7), U(7), U(7), U(7), U(7), U(7), U(7) },
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2),
T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2), T(2),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2),
U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2), U(2),
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
S(4), S(4), S(4), S(4), S(4), S(4), S(4), S(4),
S(4), S(4), S(4), S(4), S(4), S(4), S(4), S(4),
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
U(4), U(4), U(4), U(4), U(4), U(4), U(4), U(4),
U(4), U(4), U(4), U(4), U(4), U(4), U(4), U(4),
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
S(6), S(6), S(6), S(6), S(6), S(6), S(6), S(6),
S(6), S(6), S(6), S(6), S(6), S(6), S(6), S(6),
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6),
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6),
U(6), U(6), U(6), U(6), U(6), U(6), U(6), U(6),
U(6), U(6), U(6), U(6), U(6), U(6), U(6), U(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6),
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6),
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6),
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
Fairly basic integration of rectangular blocks in encoding RD loop. Adds RD integration for 32x16, 16x32, 64x32 and 32x64 rectangular blocks. Derf almost +0.6%, HD a little over +1.0%, STDHD +1.3%. Change-Id: Id651fdb6a655fdbb5c47009757e63317acfb88a5
2013-04-17 09:25:06 -07:00
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
Make superblocks independent of macroblock code and data. 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
2013-03-04 14:12:17 -08:00
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6 },
};
const uint8_t vp9_block2above_sb64[TX_SIZE_MAX_SB][384] = {
{ 0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
0, 1, 2, 3, S(0), S(1), S(2), S(3), T(0), T(1), T(2), T(3), U(0), U(1), U(2), U(3),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
4, 5, S(4), S(5), T(4), T(5), U(4), U(5),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7),
6, 7, S(6), S(7), T(6), T(7), U(6), U(7) },
{ 0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
0, 0, 0, 0, 2, 2, 2, 2, S(0), S(0), S(0), S(0), S(2), S(2), S(2), S(2),
T(0), T(0), T(0), T(0), T(2), T(2), T(2), T(2), U(0), U(0), U(0), U(0), U(2), U(2), U(2), U(2),
4, 4, 4, 4, S(4), S(4), S(4), S(4),
T(4), T(4), T(4), T(4), U(4), U(4), U(4), U(4),
4, 4, 4, 4, S(4), S(4), S(4), S(4),
T(4), T(4), T(4), T(4), U(4), U(4), U(4), U(4),
4, 4, 4, 4, S(4), S(4), S(4), S(4),
T(4), T(4), T(4), T(4), U(4), U(4), U(4), U(4),
4, 4, 4, 4, S(4), S(4), S(4), S(4),
T(4), T(4), T(4), T(4), U(4), U(4), U(4), U(4),
6, 6, 6, 6, S(6), S(6), S(6), S(6),
T(6), T(6), T(6), T(6), U(6), U(6), U(6), U(6),
6, 6, 6, 6, S(6), S(6), S(6), S(6),
T(6), T(6), T(6), T(6), U(6), U(6), U(6), U(6),
6, 6, 6, 6, S(6), S(6), S(6), S(6),
T(6), T(6), T(6), T(6), U(6), U(6), U(6), U(6),
6, 6, 6, 6, S(6), S(6), S(6), S(6),
T(6), T(6), T(6), T(6), U(6), U(6), U(6), U(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0), S(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0), U(0),
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
T(4), T(4), T(4), T(4), T(4), T(4), T(4), T(4),
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6),
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6),
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6),
T(6), T(6), T(6), T(6), T(6), T(6), T(6), T(6) },
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
Fairly basic integration of rectangular blocks in encoding RD loop. Adds RD integration for 32x16, 16x32, 64x32 and 32x64 rectangular blocks. Derf almost +0.6%, HD a little over +1.0%, STDHD +1.3%. Change-Id: Id651fdb6a655fdbb5c47009757e63317acfb88a5
2013-04-17 09:25:06 -07:00
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
Make superblocks independent of macroblock code and data. 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
2013-03-04 14:12:17 -08:00
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
Fairly basic integration of rectangular blocks in encoding RD loop. Adds RD integration for 32x16, 16x32, 64x32 and 32x64 rectangular blocks. Derf almost +0.6%, HD a little over +1.0%, STDHD +1.3%. Change-Id: Id651fdb6a655fdbb5c47009757e63317acfb88a5
2013-04-17 09:25:06 -07:00
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0), T(0),
Make superblocks independent of macroblock code and data. 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
2013-03-04 14:12:17 -08:00
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6 },
};
#undef U
#undef T
#undef S
Reference in New Issue Copy Permalink