generic-library/vpx
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
b5ce9456db
vpx/vp8/encoder/rdopt.c

2425 lines
78 KiB
C
Raw Normal View History

Initial WebM release
2010-05-18 17:58:33 +02:00
/*
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 14:16:39 +02:00
* Copyright (c) 2010 The WebM project authors. All Rights Reserved.
Initial WebM release
2010-05-18 17:58:33 +02:00
*
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 18:39:21 +02:00
* Use of this source code is governed by a BSD-style license
LICENSE: update with latest text Change-Id: Ieebea089095d9073b3a94932791099f614ce120c
2010-06-04 22:19:40 +02:00
* 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 18:39:21 +02:00
* in the file PATENTS. All contributing project authors may
LICENSE: update with latest text Change-Id: Ieebea089095d9073b3a94932791099f614ce120c
2010-06-04 22:19:40 +02:00
* be found in the AUTHORS file in the root of the source tree.
Initial WebM release
2010-05-18 17:58:33 +02:00
*/
#include <stdio.h>
#include <math.h>
#include <limits.h>
#include <assert.h>
RTCD: add remaining IDCT functions This commit continues the process of converting to the new RTCD system. Change-Id: I03c4dbf30dfd3558b0e256ff9d3ff4c012aadc80
2012-01-13 01:55:44 +01:00
#include "vpx_config.h"
#include "vpx_rtcd.h"
Fix relative include paths Allow compiling without adding vp8/{common,encoder,decoder} to the include paths. Change-Id: Ifeb5dac351cdfadcd659736f5158b315a0030b6c
2011-02-10 20:41:38 +01:00
#include "vp8/common/pragmas.h"
Initial WebM release
2010-05-18 17:58:33 +02:00
#include "tokenize.h"
#include "treewriter.h"
#include "onyx_int.h"
#include "modecosts.h"
#include "encodeintra.h"
Fix relative include paths Allow compiling without adding vp8/{common,encoder,decoder} to the include paths. Change-Id: Ifeb5dac351cdfadcd659736f5158b315a0030b6c
2011-02-10 20:41:38 +01:00
#include "vp8/common/entropymode.h"
#include "vp8/common/reconinter.h"
#include "vp8/common/reconintra4x4.h"
#include "vp8/common/findnearmv.h"
Initial WebM release
2010-05-18 17:58:33 +02:00
#include "encodemb.h"
#include "quantize.h"
#include "variance.h"
#include "mcomp.h"
Define RDCOST only once Clean up the code. Change-Id: I7db048efa4d972b528d553a7921bc45979621129
2011-04-07 22:57:25 +02:00
#include "rdopt.h"
Initial WebM release
2010-05-18 17:58:33 +02:00
#include "vpx_mem/vpx_mem.h"
Fix relative include paths Allow compiling without adding vp8/{common,encoder,decoder} to the include paths. Change-Id: Ifeb5dac351cdfadcd659736f5158b315a0030b6c
2011-02-10 20:41:38 +01:00
#include "vp8/common/systemdependent.h"
Initial WebM release
2010-05-18 17:58:33 +02:00
Added vp8_update_zbin_extra vp8cx_mb_init_quantizer was being called for every mode checked in vp8_rd_pick_inter_mode. zbin_extra is the only value that really needs to be recalculated. This calculation is disabled when using the fast quantizer for mode selection. This gave a small performance boost (~.5% to 1%). Note: This needs to be verified with segmentation_enabled. Change-Id: I62716a870b3c82b4a998bdf95130ff0b02106f1e
2010-12-29 20:30:57 +01:00
extern void vp8_update_zbin_extra(VP8_COMP *cpi, MACROBLOCK *x);
Initial WebM release
2010-05-18 17:58:33 +02:00
#define MAXF(a,b) (((a) > (b)) ? (a) : (b))
Increase static linkage, remove unused functions A large number of functions were defined with external linkage, even though they were only used from within one file. This patch changes their linkage to static and removes the vp8_ prefix from their names, which should make it more obvious to the reader that the function is contained within the current translation unit. Functions that were not referenced were removed. These symbols were identified by: $ nm -A libvpx.a | sort -k3 | uniq -c -f2 | grep ' [A-Z] ' \ | sort | grep '^ *1 ' Change-Id: I59609f58ab65312012c047036ae1e0634f795779
2011-03-17 22:07:59 +01:00
static const int auto_speed_thresh[17] =
Initial WebM release
2010-05-18 17:58:33 +02:00
{
1000,
200,
150,
130,
150,
125,
120,
115,
115,
115,
115,
115,
115,
115,
115,
115,
105
};
const MB_PREDICTION_MODE vp8_mode_order[MAX_MODES] =
{
ZEROMV,
DC_PRED,
NEARESTMV,
NEARMV,
ZEROMV,
NEARESTMV,
ZEROMV,
NEARESTMV,
NEARMV,
NEARMV,
V_PRED,
H_PRED,
TM_PRED,
NEWMV,
NEWMV,
NEWMV,
SPLITMV,
SPLITMV,
SPLITMV,
B_PRED,
};
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
/* This table determines the search order in reference frame priority order,
* which may not necessarily match INTRA,LAST,GOLDEN,ARF
*/
const int vp8_ref_frame_order[MAX_MODES] =
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
1,
0,
Initial WebM release
2010-05-18 17:58:33 +02:00
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
1,
1,
Initial WebM release
2010-05-18 17:58:33 +02:00
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
2,
2,
Initial WebM release
2010-05-18 17:58:33 +02:00
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
3,
3,
Initial WebM release
2010-05-18 17:58:33 +02:00
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
2,
3,
Initial WebM release
2010-05-18 17:58:33 +02:00
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
0,
0,
0,
Initial WebM release
2010-05-18 17:58:33 +02:00
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
1,
2,
3,
Initial WebM release
2010-05-18 17:58:33 +02:00
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
1,
2,
3,
Initial WebM release
2010-05-18 17:58:33 +02:00
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
0,
Initial WebM release
2010-05-18 17:58:33 +02:00
};
static void fill_token_costs(
Use MAX_ENTROPY_TOKENS and ENTROPY_NODES more consistently There were many instances in the code of vp8_coef_tokens and vp8_coef_tokens-1, which was a preprocessor macro despite the naming convention. Replace these with MAX_ENTROPY_TOKENS and ENTROPY_NODES, respectively. Change-Id: I72c4f6c7634c94e1fa066cd511471e5592c748da
2011-06-28 23:03:47 +02:00
unsigned int c [BLOCK_TYPES] [COEF_BANDS] [PREV_COEF_CONTEXTS] [MAX_ENTROPY_TOKENS],
const vp8_prob p [BLOCK_TYPES] [COEF_BANDS] [PREV_COEF_CONTEXTS] [ENTROPY_NODES]
Initial WebM release
2010-05-18 17:58:33 +02:00
)
{
int i, j, k;
for (i = 0; i < BLOCK_TYPES; i++)
for (j = 0; j < COEF_BANDS; j++)
for (k = 0; k < PREV_COEF_CONTEXTS; k++)
vp8_cost_tokens((int *)(c [i][j][k]), p [i][j][k], vp8_coef_tree);
}
Fix RD bug.
2010-06-07 18:34:46 +02:00
static int rd_iifactor [ 32 ] = { 4, 4, 3, 2, 1, 0, 0, 0,
Initial WebM release
2010-05-18 17:58:33 +02:00
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
};
adjusted sad_per_bit to correlate with quantizer Re-calibrated sad_per_bit16 and sad_per_bit4 tables to linearly correlated to quantizer values, these two variables are used in motion search for costing motion vectors. This change has an small positive effect on compression. Change-Id: Ic9b5ea6fb8d5078ef663ba4899db019cc51f4166
2010-12-24 04:59:12 +01:00
/* values are now correlated to quantizer */
static int sad_per_bit16lut[QINDEX_RANGE] =
Initial WebM release
2010-05-18 17:58:33 +02:00
{
adjust sad per bit constants While investigating the effect of DC values on SAD and SSE in motion estimation, a side finding indicates the two table of constants need be adjusted. The adjustment was done by multiplying old constants by 90% with rounding. Also absorb the 1/2 scaling constant into the two tables. Refer to change Ifa285c3e for background of the 1/2 factor. Cif set test showed a very small gain on all metric. Change-Id: I04333527a823371175dd46cb04a817e5b9a8b752
2011-05-20 08:12:40 +02:00
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, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 5, 5, 5, 5, 5, 5,
adjusted sad_per_bit to correlate with quantizer Re-calibrated sad_per_bit16 and sad_per_bit4 tables to linearly correlated to quantizer values, these two variables are used in motion search for costing motion vectors. This change has an small positive effect on compression. Change-Id: Ic9b5ea6fb8d5078ef663ba4899db019cc51f4166
2010-12-24 04:59:12 +01:00
5, 5, 5, 5, 5, 5, 6, 6,
adjust sad per bit constants While investigating the effect of DC values on SAD and SSE in motion estimation, a side finding indicates the two table of constants need be adjusted. The adjustment was done by multiplying old constants by 90% with rounding. Also absorb the 1/2 scaling constant into the two tables. Refer to change Ifa285c3e for background of the 1/2 factor. Cif set test showed a very small gain on all metric. Change-Id: I04333527a823371175dd46cb04a817e5b9a8b752
2011-05-20 08:12:40 +02:00
6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 8, 8,
8, 8, 8, 8, 8, 8, 8, 8,
8, 8, 9, 9, 9, 9, 9, 9,
9, 9, 9, 9, 9, 9, 10, 10,
10, 10, 10, 10, 10, 10, 11, 11,
11, 11, 11, 11, 12, 12, 12, 12,
12, 12, 13, 13, 13, 13, 14, 14
Initial WebM release
2010-05-18 17:58:33 +02:00
};
adjusted sad_per_bit to correlate with quantizer Re-calibrated sad_per_bit16 and sad_per_bit4 tables to linearly correlated to quantizer values, these two variables are used in motion search for costing motion vectors. This change has an small positive effect on compression. Change-Id: Ic9b5ea6fb8d5078ef663ba4899db019cc51f4166
2010-12-24 04:59:12 +01:00
static int sad_per_bit4lut[QINDEX_RANGE] =
Initial WebM release
2010-05-18 17:58:33 +02:00
{
adjust sad per bit constants While investigating the effect of DC values on SAD and SSE in motion estimation, a side finding indicates the two table of constants need be adjusted. The adjustment was done by multiplying old constants by 90% with rounding. Also absorb the 1/2 scaling constant into the two tables. Refer to change Ifa285c3e for background of the 1/2 factor. Cif set test showed a very small gain on all metric. Change-Id: I04333527a823371175dd46cb04a817e5b9a8b752
2011-05-20 08:12:40 +02:00
2, 2, 2, 2, 2, 2, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 5, 5,
5, 5, 5, 5, 6, 6, 6, 6,
6, 6, 6, 6, 6, 6, 6, 6,
7, 7, 7, 7, 7, 7, 7, 7,
adjusted sad_per_bit to correlate with quantizer Re-calibrated sad_per_bit16 and sad_per_bit4 tables to linearly correlated to quantizer values, these two variables are used in motion search for costing motion vectors. This change has an small positive effect on compression. Change-Id: Ic9b5ea6fb8d5078ef663ba4899db019cc51f4166
2010-12-24 04:59:12 +01:00
7, 7, 7, 7, 7, 8, 8, 8,
adjust sad per bit constants While investigating the effect of DC values on SAD and SSE in motion estimation, a side finding indicates the two table of constants need be adjusted. The adjustment was done by multiplying old constants by 90% with rounding. Also absorb the 1/2 scaling constant into the two tables. Refer to change Ifa285c3e for background of the 1/2 factor. Cif set test showed a very small gain on all metric. Change-Id: I04333527a823371175dd46cb04a817e5b9a8b752
2011-05-20 08:12:40 +02:00
8, 8, 9, 9, 9, 9, 9, 9,
10, 10, 10, 10, 10, 10, 10, 10,
11, 11, 11, 11, 11, 11, 11, 11,
12, 12, 12, 12, 12, 12, 12, 12,
13, 13, 13, 13, 13, 13, 13, 14,
14, 14, 14, 14, 15, 15, 15, 15,
16, 16, 16, 16, 17, 17, 17, 18,
18, 18, 19, 19, 19, 20, 20, 20,
Initial WebM release
2010-05-18 17:58:33 +02:00
};
void vp8cx_initialize_me_consts(VP8_COMP *cpi, int QIndex)
{
adjust sad per bit constants While investigating the effect of DC values on SAD and SSE in motion estimation, a side finding indicates the two table of constants need be adjusted. The adjustment was done by multiplying old constants by 90% with rounding. Also absorb the 1/2 scaling constant into the two tables. Refer to change Ifa285c3e for background of the 1/2 factor. Cif set test showed a very small gain on all metric. Change-Id: I04333527a823371175dd46cb04a817e5b9a8b752
2011-05-20 08:12:40 +02:00
cpi->mb.sadperbit16 = sad_per_bit16lut[QIndex];
cpi->mb.sadperbit4 = sad_per_bit4lut[QIndex];
Initial WebM release
2010-05-18 17:58:33 +02:00
}
void vp8_initialize_rd_consts(VP8_COMP *cpi, int Qvalue)
{
int q;
int i;
Further adjustment of RD behaviour with Q and Zbin. Following conversations with Tim T (Derf) I ran a large number of tests comparing the existing polynomial expression with a simpler ^2 variant. Though the polynomial was sometimes a little better at the extremes of Q it was possible to get close for most clips and even a little better on some. This code also changes the way the RD multiplier is calculated when the ZBIN is extended to use a variant of the same ^2 expression. I hope that this simpler expression will be easier to tune further as we expand our test set and consider adjustments based on content. Change-Id: I73b2564346e74d1332c33e2c1964ae093437456c
2010-06-29 13:15:54 +02:00
double capped_q = (Qvalue < 160) ? (double)Qvalue : 160.0;
adjusting rd constant slightly by ~10% This is to reflect the RD improvement in the encoder. The change has a small positive impact on quality (0.25% by VPXSSIM and 0.05% by PSNR) Change-Id: Ic66ffc19b10870645088c0624c85556f009fd210
2011-05-12 08:32:06 +02:00
double rdconst = 2.70;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_clear_system_state(); //__asm emms;
Further adjustment of RD behaviour with Q and Zbin. Following conversations with Tim T (Derf) I ran a large number of tests comparing the existing polynomial expression with a simpler ^2 variant. Though the polynomial was sometimes a little better at the extremes of Q it was possible to get close for most clips and even a little better on some. This code also changes the way the RD multiplier is calculated when the ZBIN is extended to use a variant of the same ^2 expression. I hope that this simpler expression will be easier to tune further as we expand our test set and consider adjustments based on content. Change-Id: I73b2564346e74d1332c33e2c1964ae093437456c
2010-06-29 13:15:54 +02:00
// Further tests required to see if optimum is different
// for key frames, golden frames and arf frames.
// if (cpi->common.refresh_golden_frame ||
// cpi->common.refresh_alt_ref_frame)
cpi->RDMULT = (int)(rdconst * (capped_q * capped_q));
Initial WebM release
2010-05-18 17:58:33 +02:00
Further adjustment of RD behaviour with Q and Zbin. Following conversations with Tim T (Derf) I ran a large number of tests comparing the existing polynomial expression with a simpler ^2 variant. Though the polynomial was sometimes a little better at the extremes of Q it was possible to get close for most clips and even a little better on some. This code also changes the way the RD multiplier is calculated when the ZBIN is extended to use a variant of the same ^2 expression. I hope that this simpler expression will be easier to tune further as we expand our test set and consider adjustments based on content. Change-Id: I73b2564346e74d1332c33e2c1964ae093437456c
2010-06-29 13:15:54 +02:00
// Extend rate multiplier along side quantizer zbin increases
if (cpi->zbin_over_quant > 0)
{
double oq_factor;
double modq;
// Experimental code using the same basic equation as used for Q above
// The units of cpi->zbin_over_quant are 1/128 of Q bin size
oq_factor = 1.0 + ((double)0.0015625 * cpi->zbin_over_quant);
modq = (int)((double)capped_q * oq_factor);
cpi->RDMULT = (int)(rdconst * (modq * modq));
}
Initial WebM release
2010-05-18 17:58:33 +02:00
Fix RD bug.
2010-06-07 18:34:46 +02:00
if (cpi->pass == 2 && (cpi->common.frame_type != KEY_FRAME))
Initial WebM release
2010-05-18 17:58:33 +02:00
{
cleanup: collect twopass variables This patch collects the twopass specific memebers of VP8_COMP into a dedicated struct. This is a first step towards isolating the two pass rate control and aids readability by decorating these variables with the 'twopass.' namespace. This makes it clear to the reader in what contexts the variable will be valid, and is a hint that a section of code might be a good candidate to move to firstpass.c in later refactoring. There likely will be other rate control modes that need their own specific data as well. This notation is probably overly verbose in firstpass.c, so an alternative would be to access this struct through a pointer like 'rc->' instead of 'cpi->firstpass.' in that file. Feel free to make a review comment to that effect if you prefer. Change-Id: I0ab8254647cb4b493a77c16b5d236d0d4a94ca4d
2011-05-19 23:16:39 +02:00
if (cpi->twopass.next_iiratio > 31)
Fix RD bug.
2010-06-07 18:34:46 +02:00
cpi->RDMULT += (cpi->RDMULT * rd_iifactor[31]) >> 4;
Initial WebM release
2010-05-18 17:58:33 +02:00
else
cleanup: collect twopass variables This patch collects the twopass specific memebers of VP8_COMP into a dedicated struct. This is a first step towards isolating the two pass rate control and aids readability by decorating these variables with the 'twopass.' namespace. This makes it clear to the reader in what contexts the variable will be valid, and is a hint that a section of code might be a good candidate to move to firstpass.c in later refactoring. There likely will be other rate control modes that need their own specific data as well. This notation is probably overly verbose in firstpass.c, so an alternative would be to access this struct through a pointer like 'rc->' instead of 'cpi->firstpass.' in that file. Feel free to make a review comment to that effect if you prefer. Change-Id: I0ab8254647cb4b493a77c16b5d236d0d4a94ca4d
2011-05-19 23:16:39 +02:00
cpi->RDMULT +=
(cpi->RDMULT * rd_iifactor[cpi->twopass.next_iiratio]) >> 4;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
adjusting the calculation of errorperbit RDMULT/RDDIV defines a bit worth of distortion in term of sum squared difference. This has also been used as errorperbit in subpixel motion search, where the distortions computed as variance of the difference. The variance of differences is different from sum squared differences by amount of DC squared. Typically, for inter predicted MBs, this difference averages around 10% between the two distortion, so this patch introduces a 110% constant in deriving errorperbit from RDMULT/RDDIV. Test on CIF set shows small but positive gain on overall PSNR (.03%) and SSIM (.07%), overall impact on average PSNR is 0. Change-Id: I95425f922d037b4d96083064a10c7cdd4948ee62
2011-06-21 01:30:26 +02:00
cpi->mb.errorperbit = (cpi->RDMULT / 110);
cap the best quantizer for 2nd order DC This commit also removes artificial RDMULT cap for low quantizers. The intention is to address some abnormal behavior of mode selections at the low quantizer end, where many macroblocks were coded with SPLITMV with all partitions using same motion vector including (0,0). This change improves the compression quality substantially for high quality encodings in both PSNR and SSIM terms. Overall effect on mid/low rate range is also positive for all metrics, but smaller in magnitude. Change-Id: I864b29c4bd9ff610d2545fa94a19cc7e80c02667
2011-01-26 07:24:22 +01:00
cpi->mb.errorperbit += (cpi->mb.errorperbit==0);
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_set_speed_features(cpi);
q = (int)pow(Qvalue, 1.25);
if (q < 8)
q = 8;
if (cpi->RDMULT > 1000)
{
cpi->RDDIV = 1;
cpi->RDMULT /= 100;
for (i = 0; i < MAX_MODES; i++)
{
if (cpi->sf.thresh_mult[i] < INT_MAX)
{
cpi->rd_threshes[i] = cpi->sf.thresh_mult[i] * q / 100;
}
else
{
cpi->rd_threshes[i] = INT_MAX;
}
cpi->rd_baseline_thresh[i] = cpi->rd_threshes[i];
}
}
else
{
cpi->RDDIV = 100;
for (i = 0; i < MAX_MODES; i++)
{
if (cpi->sf.thresh_mult[i] < (INT_MAX / q))
{
cpi->rd_threshes[i] = cpi->sf.thresh_mult[i] * q;
}
else
{
cpi->rd_threshes[i] = INT_MAX;
}
cpi->rd_baseline_thresh[i] = cpi->rd_threshes[i];
}
}
vp8e - entropy stats per frame type Change-Id: I4168eb6ea22ae541471738a7a3453e7d52059275
2011-12-10 01:56:18 +01:00
{
// build token cost array for the type of frame we have now
FRAME_CONTEXT *l = &cpi->lfc_n;
if(cpi->common.refresh_alt_ref_frame)
l = &cpi->lfc_a;
else if(cpi->common.refresh_golden_frame)
l = &cpi->lfc_g;
fill_token_costs(
cpi->mb.token_costs,
(const vp8_prob( *)[8][3][11]) l->coef_probs
);
/*
fill_token_costs(
cpi->mb.token_costs,
(const vp8_prob( *)[8][3][11]) cpi->common.fc.coef_probs);
*/
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8e - entropy stats per frame type Change-Id: I4168eb6ea22ae541471738a7a3453e7d52059275
2011-12-10 01:56:18 +01:00
// TODO make these mode costs depend on last,alt or gold too. (jbb)
vp8_init_mode_costs(cpi);
// TODO figure onnnnuut why making mv cost frame type dependent didn't help (jbb)
//vp8_build_component_cost_table(cpi->mb.mvcost, (const MV_CONTEXT *) l->mvc, flags);
}
Initial WebM release
2010-05-18 17:58:33 +02:00
}
void vp8_auto_select_speed(VP8_COMP *cpi)
{
avoid resetting framerate during vpx_codec_enc_config_set() The calculated frame_rate is a state variable in the codec, and shouldn't be maintained in the configuration struct. Move it to the main part of cpi so that it isn't clobbered when the configuration struct is updated. The initial framerate estimate is moved from the vp8_cx_iface.c wrapper into the body of init_config() in onyx_if.c, so that it is only called once and not reset on every call to vp8_change_config(). Change-Id: I8d9a3d1283330d1ee297d07e9d78d1f2875f2465
2011-11-11 19:47:20 +01:00
int milliseconds_for_compress = (int)(1000000 / cpi->frame_rate);
Initial WebM release
2010-05-18 17:58:33 +02:00
milliseconds_for_compress = milliseconds_for_compress * (16 - cpi->oxcf.cpu_used) / 16;
#if 0
if (0)
{
FILE *f;
f = fopen("speed.stt", "a");
fprintf(f, " %8ld %10ld %10ld %10ld\n",
cpi->common.current_video_frame, cpi->Speed, milliseconds_for_compress, cpi->avg_pick_mode_time);
fclose(f);
}
#endif
/*
// this is done during parameter valid check
clean up unused variable warnings Change-Id: I9467d7a50eac32d8e8f3a2f26db818e47c93c94b
2011-05-09 17:16:31 +02:00
if( cpi->oxcf.cpu_used > 16)
cpi->oxcf.cpu_used = 16;
if( cpi->oxcf.cpu_used < -16)
cpi->oxcf.cpu_used = -16;
Initial WebM release
2010-05-18 17:58:33 +02:00
*/
if (cpi->avg_pick_mode_time < milliseconds_for_compress && (cpi->avg_encode_time - cpi->avg_pick_mode_time) < milliseconds_for_compress)
{
if (cpi->avg_pick_mode_time == 0)
{
cpi->Speed = 4;
}
else
{
if (milliseconds_for_compress * 100 < cpi->avg_encode_time * 95)
{
cpi->Speed += 2;
cpi->avg_pick_mode_time = 0;
cpi->avg_encode_time = 0;
if (cpi->Speed > 16)
{
cpi->Speed = 16;
}
}
Increase static linkage, remove unused functions A large number of functions were defined with external linkage, even though they were only used from within one file. This patch changes their linkage to static and removes the vp8_ prefix from their names, which should make it more obvious to the reader that the function is contained within the current translation unit. Functions that were not referenced were removed. These symbols were identified by: $ nm -A libvpx.a | sort -k3 | uniq -c -f2 | grep ' [A-Z] ' \ | sort | grep '^ *1 ' Change-Id: I59609f58ab65312012c047036ae1e0634f795779
2011-03-17 22:07:59 +01:00
if (milliseconds_for_compress * 100 > cpi->avg_encode_time * auto_speed_thresh[cpi->Speed])
Initial WebM release
2010-05-18 17:58:33 +02:00
{
cpi->Speed -= 1;
cpi->avg_pick_mode_time = 0;
cpi->avg_encode_time = 0;
// In real-time mode, cpi->speed is in [4, 16].
if (cpi->Speed < 4) //if ( cpi->Speed < 0 )
{
cpi->Speed = 4; //cpi->Speed = 0;
}
}
}
}
else
{
cpi->Speed += 4;
if (cpi->Speed > 16)
cpi->Speed = 16;
cpi->avg_pick_mode_time = 0;
cpi->avg_encode_time = 0;
}
}
int vp8_block_error_c(short *coeff, short *dqcoeff)
{
int i;
int error = 0;
for (i = 0; i < 16; i++)
{
int this_diff = coeff[i] - dqcoeff[i];
error += this_diff * this_diff;
}
return error;
}
int vp8_mbblock_error_c(MACROBLOCK *mb, int dc)
{
BLOCK *be;
BLOCKD *bd;
int i, j;
int berror, error = 0;
for (i = 0; i < 16; i++)
{
be = &mb->block[i];
bd = &mb->e_mbd.block[i];
berror = 0;
for (j = dc; j < 16; j++)
{
int this_diff = be->coeff[j] - bd->dqcoeff[j];
berror += this_diff * this_diff;
}
error += berror;
}
return error;
}
int vp8_mbuverror_c(MACROBLOCK *mb)
{
BLOCK *be;
BLOCKD *bd;
int i;
int error = 0;
for (i = 16; i < 24; i++)
{
be = &mb->block[i];
bd = &mb->e_mbd.block[i];
error += vp8_block_error_c(be->coeff, bd->dqcoeff);
}
return error;
}
RTCD: add variance functions This commit continues the process of converting to the new RTCD system. Change-Id: Ie5c1aa480637e98dc3918fb562ff45c37a66c538
2012-01-13 01:55:44 +01:00
int VP8_UVSSE(MACROBLOCK *x)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
unsigned char *uptr, *vptr;
unsigned char *upred_ptr = (*(x->block[16].base_src) + x->block[16].src);
unsigned char *vpred_ptr = (*(x->block[20].base_src) + x->block[20].src);
int uv_stride = x->block[16].src_stride;
unsigned int sse1 = 0;
unsigned int sse2 = 0;
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
int mv_row = x->e_mbd.mode_info_context->mbmi.mv.as_mv.row;
int mv_col = x->e_mbd.mode_info_context->mbmi.mv.as_mv.col;
Initial WebM release
2010-05-18 17:58:33 +02:00
int offset;
BLOCKD structure cleanup Removed redundancies. All of the information can be found in the MACROBLOCKD structure. Change-Id: I7556392c6f67b43bef2a5e9932180a737466ef93
2012-01-20 19:52:16 +01:00
int pre_stride = x->e_mbd.pre.uv_stride;
Initial WebM release
2010-05-18 17:58:33 +02:00
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
if (mv_row < 0)
mv_row -= 1;
else
mv_row += 1;
if (mv_col < 0)
mv_col -= 1;
else
mv_col += 1;
mv_row /= 2;
mv_col /= 2;
Initial WebM release
2010-05-18 17:58:33 +02:00
offset = (mv_row >> 3) * pre_stride + (mv_col >> 3);
uptr = x->e_mbd.pre.u_buffer + offset;
vptr = x->e_mbd.pre.v_buffer + offset;
if ((mv_row | mv_col) & 7)
{
RTCD: add variance functions This commit continues the process of converting to the new RTCD system. Change-Id: Ie5c1aa480637e98dc3918fb562ff45c37a66c538
2012-01-13 01:55:44 +01:00
vp8_sub_pixel_variance8x8(uptr, pre_stride,
use get8x8var directly for non-subpixel motion case in VP8_UVSSE VP8_UVSSE mistakenly used subpixvar8x8 to calculate SSE for non-subpixl motion cases. Change-Id: I4a5398bb9ef39c211039f6af4540546d4972e6a9
2011-05-22 06:51:21 +02:00
mv_col & 7, mv_row & 7, upred_ptr, uv_stride, &sse2);
RTCD: add variance functions This commit continues the process of converting to the new RTCD system. Change-Id: Ie5c1aa480637e98dc3918fb562ff45c37a66c538
2012-01-13 01:55:44 +01:00
vp8_sub_pixel_variance8x8(vptr, pre_stride,
use get8x8var directly for non-subpixel motion case in VP8_UVSSE VP8_UVSSE mistakenly used subpixvar8x8 to calculate SSE for non-subpixl motion cases. Change-Id: I4a5398bb9ef39c211039f6af4540546d4972e6a9
2011-05-22 06:51:21 +02:00
mv_col & 7, mv_row & 7, vpred_ptr, uv_stride, &sse1);
Initial WebM release
2010-05-18 17:58:33 +02:00
sse2 += sse1;
}
else
{
RTCD: add variance functions This commit continues the process of converting to the new RTCD system. Change-Id: Ie5c1aa480637e98dc3918fb562ff45c37a66c538
2012-01-13 01:55:44 +01:00
vp8_variance8x8(uptr, pre_stride,
Use var8x8 instead of get8x8var in VP8_UVSSE 'sum' returned by get8x8var is not used and var8x8 has optimizations for more platforms. Change-Id: I4a907fb1a05f285669fb0b95dc71d42182c980f6
2011-05-25 11:54:34 +02:00
upred_ptr, uv_stride, &sse2);
RTCD: add variance functions This commit continues the process of converting to the new RTCD system. Change-Id: Ie5c1aa480637e98dc3918fb562ff45c37a66c538
2012-01-13 01:55:44 +01:00
vp8_variance8x8(vptr, pre_stride,
Use var8x8 instead of get8x8var in VP8_UVSSE 'sum' returned by get8x8var is not used and var8x8 has optimizations for more platforms. Change-Id: I4a907fb1a05f285669fb0b95dc71d42182c980f6
2011-05-25 11:54:34 +02:00
vpred_ptr, uv_stride, &sse1);
Initial WebM release
2010-05-18 17:58:33 +02:00
sse2 += sse1;
}
return sse2;
}
static int cost_coeffs(MACROBLOCK *mb, BLOCKD *b, int type, ENTROPY_CONTEXT *a, ENTROPY_CONTEXT *l)
{
int c = !type; /* start at coef 0, unless Y with Y2 */
Change use of eob in the encoder Changed 'int eob' to 'char *eob' in BLOCKD so that both encoder and decoder will use eobs[25] array from MACROBLOCKD structure. In future, this will enable use of the decoder side IDCT in the encoder. Change-Id: I6e1c011628cb8864fd4a0b80f0279ce16a5ca978
2011-10-25 13:25:11 +02:00
int eob = (int)(*b->eob);
Initial WebM release
2010-05-18 17:58:33 +02:00
int pt ; /* surrounding block/prev coef predictor */
int cost = 0;
short *qcoeff_ptr = b->qcoeff;
VP8_COMBINEENTROPYCONTEXTS(pt, *a, *l);
# define QC( I) ( qcoeff_ptr [vp8_default_zig_zag1d[I]] )
for (; c < eob; c++)
{
int v = QC(c);
int t = vp8_dct_value_tokens_ptr[v].Token;
cost += mb->token_costs [type] [vp8_coef_bands[c]] [pt] [t];
cost += vp8_dct_value_cost_ptr[v];
pt = vp8_prev_token_class[t];
}
# undef QC
if (c < 16)
cost += mb->token_costs [type] [vp8_coef_bands[c]] [pt] [DCT_EOB_TOKEN];
pt = (c != !type); // is eob first coefficient;
*a = *l = pt;
return cost;
}
Removed unnecessary checks. macro_block_yrd and vp8_rdcost_mby are not called for SPLITMV. Change-Id: I2224d3c8725df526d48426447482768d543752f1
2010-11-17 19:15:13 +01:00
static int vp8_rdcost_mby(MACROBLOCK *mb)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
int cost = 0;
int b;
MACROBLOCKD *x = &mb->e_mbd;
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 16:49:57 +02:00
ENTROPY_CONTEXT_PLANES t_above, t_left;
ENTROPY_CONTEXT *ta;
ENTROPY_CONTEXT *tl;
vpx_memcpy(&t_above, mb->e_mbd.above_context, sizeof(ENTROPY_CONTEXT_PLANES));
vpx_memcpy(&t_left, mb->e_mbd.left_context, sizeof(ENTROPY_CONTEXT_PLANES));
Initial WebM release
2010-05-18 17:58:33 +02:00
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 16:49:57 +02:00
ta = (ENTROPY_CONTEXT *)&t_above;
tl = (ENTROPY_CONTEXT *)&t_left;
Initial WebM release
2010-05-18 17:58:33 +02:00
for (b = 0; b < 16; b++)
Removed vp8_block2type and used defines instead. Change-Id: Idb56e0295d004793f406dfd2d8d8c546aad62e03
2011-02-23 22:37:08 +01:00
cost += cost_coeffs(mb, x->block + b, PLANE_TYPE_Y_NO_DC,
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 16:49:57 +02:00
ta + vp8_block2above[b], tl + vp8_block2left[b]);
Initial WebM release
2010-05-18 17:58:33 +02:00
Removed vp8_block2type and used defines instead. Change-Id: Idb56e0295d004793f406dfd2d8d8c546aad62e03
2011-02-23 22:37:08 +01:00
cost += cost_coeffs(mb, x->block + 24, PLANE_TYPE_Y2,
Removed unnecessary checks. macro_block_yrd and vp8_rdcost_mby are not called for SPLITMV. Change-Id: I2224d3c8725df526d48426447482768d543752f1
2010-11-17 19:15:13 +01:00
ta + vp8_block2above[24], tl + vp8_block2left[24]);
Initial WebM release
2010-05-18 17:58:33 +02:00
return cost;
}
Rationalize vp8_rd_pick_intra16x16mby_mode() Use the function macro_block_yrd() to calculate error and distortion in keeping with what is done for inter frames. The old code was using a variance metric for once case and an SSE function for measuring distortion in the other case. The function vp8_encode_intra16x16mbyrd() is no longer used. Change-Id: Ic228cb00a78ff637f4365b43f58fbe5a9273d36f
2011-01-26 19:46:34 +01:00
static void macro_block_yrd( MACROBLOCK *mb,
int *Rate,
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
int *Distortion)
Rationalize vp8_rd_pick_intra16x16mby_mode() Use the function macro_block_yrd() to calculate error and distortion in keeping with what is done for inter frames. The old code was using a variance metric for once case and an SSE function for measuring distortion in the other case. The function vp8_encode_intra16x16mbyrd() is no longer used. Change-Id: Ic228cb00a78ff637f4365b43f58fbe5a9273d36f
2011-01-26 19:46:34 +01:00
{
int b;
MACROBLOCKD *const x = &mb->e_mbd;
BLOCK *const mb_y2 = mb->block + 24;
BLOCKD *const x_y2 = x->block + 24;
short *Y2DCPtr = mb_y2->src_diff;
BLOCK *beptr;
int d;
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
vp8_subtract_mby( mb->src_diff, *(mb->block[0].base_src),
Added predictor stride argument(s) to subtract functions Patch set 2: 64 bit build fix Patch set 3: 64 bit crash fix [Tero] Patch set 4: Updated ARMv6 and NEON assembly. Added also minor NEON optimizations to subtract functions. Patch set 5: x86 stride bug fix Change-Id: I1fcca93e90c89b89ddc204e1c18f208682675c15
2011-11-15 18:53:01 +01:00
mb->block[0].src_stride, mb->e_mbd.predictor, 16);
Rationalize vp8_rd_pick_intra16x16mby_mode() Use the function macro_block_yrd() to calculate error and distortion in keeping with what is done for inter frames. The old code was using a variance metric for once case and an SSE function for measuring distortion in the other case. The function vp8_encode_intra16x16mbyrd() is no longer used. Change-Id: Ic228cb00a78ff637f4365b43f58fbe5a9273d36f
2011-01-26 19:46:34 +01:00
// Fdct and building the 2nd order block
for (beptr = mb->block; beptr < mb->block + 16; beptr += 2)
{
RTCD: add FDCT functions This commit continues the process of converting to the new RTCD system. Change-Id: I3f9c07db65eb206f6363d21bdb80e871570da767
2012-01-13 01:55:44 +01:00
mb->short_fdct8x4(beptr->src_diff, beptr->coeff, 32);
Rationalize vp8_rd_pick_intra16x16mby_mode() Use the function macro_block_yrd() to calculate error and distortion in keeping with what is done for inter frames. The old code was using a variance metric for once case and an SSE function for measuring distortion in the other case. The function vp8_encode_intra16x16mbyrd() is no longer used. Change-Id: Ic228cb00a78ff637f4365b43f58fbe5a9273d36f
2011-01-26 19:46:34 +01:00
*Y2DCPtr++ = beptr->coeff[0];
*Y2DCPtr++ = beptr->coeff[16];
}
// 2nd order fdct
mb->short_walsh4x4(mb_y2->src_diff, mb_y2->coeff, 8);
// Quantization
for (b = 0; b < 16; b++)
{
mb->quantize_b(&mb->block[b], &mb->e_mbd.block[b]);
}
// DC predication and Quantization of 2nd Order block
mb->quantize_b(mb_y2, x_y2);
// Distortion
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
d = vp8_mbblock_error(mb, 1) << 2;
d += vp8_block_error(mb_y2->coeff, x_y2->dqcoeff);
Rationalize vp8_rd_pick_intra16x16mby_mode() Use the function macro_block_yrd() to calculate error and distortion in keeping with what is done for inter frames. The old code was using a variance metric for once case and an SSE function for measuring distortion in the other case. The function vp8_encode_intra16x16mbyrd() is no longer used. Change-Id: Ic228cb00a78ff637f4365b43f58fbe5a9273d36f
2011-01-26 19:46:34 +01:00
*Distortion = (d >> 4);
// rate
*Rate = vp8_rdcost_mby(mb);
}
Initial WebM release
2010-05-18 17:58:33 +02:00
Revisited rd_pick_intra4x4block Removed unnecessary copies. No noticeable speed gains. Change-Id: I996c50c23fedd06d54ee7a3e762cbf559cc4a9d1
2011-02-24 19:31:47 +01:00
static void copy_predictor(unsigned char *dst, const unsigned char *predictor)
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
{
Revisited rd_pick_intra4x4block Removed unnecessary copies. No noticeable speed gains. Change-Id: I996c50c23fedd06d54ee7a3e762cbf559cc4a9d1
2011-02-24 19:31:47 +01:00
const unsigned int *p = (const unsigned int *)predictor;
unsigned int *d = (unsigned int *)dst;
d[0] = p[0];
d[4] = p[4];
d[8] = p[8];
d[12] = p[12];
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
}
Added early breakout for vp8_rd_pick_intra4x4mby_modes Improved performance of good quality, speed 0 (3% average) with no average quality loss. Change-Id: Ica34473f99bd74260eaebde6b132185e09e3c09d
2011-02-08 22:50:43 +01:00
static int rd_pick_intra4x4block(
Initial WebM release
2010-05-18 17:58:33 +02:00
VP8_COMP *cpi,
MACROBLOCK *x,
BLOCK *be,
BLOCKD *b,
B_PREDICTION_MODE *best_mode,
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
unsigned int *bmode_costs,
Initial WebM release
2010-05-18 17:58:33 +02:00
ENTROPY_CONTEXT *a,
ENTROPY_CONTEXT *l,
int *bestrate,
int *bestratey,
int *bestdistortion)
{
B_PREDICTION_MODE mode;
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
int best_rd = INT_MAX;
Initial WebM release
2010-05-18 17:58:33 +02:00
int rate = 0;
int distortion;
ENTROPY_CONTEXT ta = *a, tempa = *a;
ENTROPY_CONTEXT tl = *l, templ = *l;
Revisited rd_pick_intra4x4block Removed unnecessary copies. No noticeable speed gains. Change-Id: I996c50c23fedd06d54ee7a3e762cbf559cc4a9d1
2011-02-24 19:31:47 +01:00
/*
* The predictor buffer is a 2d buffer with a stride of 16. Create
* a temp buffer that meets the stride requirements, but we are only
* interested in the left 4x4 block
* */
DECLARE_ALIGNED_ARRAY(16, unsigned char, best_predictor, 16*4);
DECLARE_ALIGNED_ARRAY(16, short, best_dqcoeff, 16);
BLOCKD structure cleanup Removed redundancies. All of the information can be found in the MACROBLOCKD structure. Change-Id: I7556392c6f67b43bef2a5e9932180a737466ef93
2012-01-20 19:52:16 +01:00
int dst_stride = x->e_mbd.dst.y_stride;
unsigned char *base_dst = x->e_mbd.dst.y_buffer;
Initial WebM release
2010-05-18 17:58:33 +02:00
for (mode = B_DC_PRED; mode <= B_HU_PRED; mode++)
{
int this_rd;
int ratey;
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
rate = bmode_costs[mode];
BLOCKD structure cleanup Removed redundancies. All of the information can be found in the MACROBLOCKD structure. Change-Id: I7556392c6f67b43bef2a5e9932180a737466ef93
2012-01-20 19:52:16 +01:00
vp8_intra4x4_predict(base_dst + b->offset, dst_stride, mode,
b->predictor, 16);
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
vp8_subtract_b(be, b, 16);
RTCD: add FDCT functions This commit continues the process of converting to the new RTCD system. Change-Id: I3f9c07db65eb206f6363d21bdb80e871570da767
2012-01-13 01:55:44 +01:00
x->short_fdct4x4(be->src_diff, be->coeff, 32);
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
x->quantize_b(be, b);
Initial WebM release
2010-05-18 17:58:33 +02:00
tempa = ta;
templ = tl;
Removed vp8_block2type and used defines instead. Change-Id: Idb56e0295d004793f406dfd2d8d8c546aad62e03
2011-02-23 22:37:08 +01:00
ratey = cost_coeffs(x, b, PLANE_TYPE_Y_WITH_DC, &tempa, &templ);
Initial WebM release
2010-05-18 17:58:33 +02:00
rate += ratey;
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
distortion = vp8_block_error(be->coeff, b->dqcoeff) >> 2;
Initial WebM release
2010-05-18 17:58:33 +02:00
this_rd = RDCOST(x->rdmult, x->rddiv, rate, distortion);
if (this_rd < best_rd)
{
*bestrate = rate;
*bestratey = ratey;
*bestdistortion = distortion;
best_rd = this_rd;
*best_mode = mode;
*a = tempa;
*l = templ;
Revisited rd_pick_intra4x4block Removed unnecessary copies. No noticeable speed gains. Change-Id: I996c50c23fedd06d54ee7a3e762cbf559cc4a9d1
2011-02-24 19:31:47 +01:00
copy_predictor(best_predictor, b->predictor);
vpx_memcpy(best_dqcoeff, b->dqcoeff, 32);
Initial WebM release
2010-05-18 17:58:33 +02:00
}
}
Removed B_MODE_INFO Declared the bmi in BLOCKD as a union instead of B_MODE_INFO. Then removed B_MODE_INFO completely. Change-Id: Ieb7469899e265892c66f7aeac87b7f2bf38e7a67
2011-06-02 19:46:41 +02:00
b->bmi.as_mode = (B_PREDICTION_MODE)(*best_mode);
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
BLOCKD structure cleanup Removed redundancies. All of the information can be found in the MACROBLOCKD structure. Change-Id: I7556392c6f67b43bef2a5e9932180a737466ef93
2012-01-20 19:52:16 +01:00
vp8_short_idct4x4llm(best_dqcoeff, best_predictor, 16, base_dst + b->offset,
dst_stride);
Initial WebM release
2010-05-18 17:58:33 +02:00
Added early breakout for vp8_rd_pick_intra4x4mby_modes Improved performance of good quality, speed 0 (3% average) with no average quality loss. Change-Id: Ica34473f99bd74260eaebde6b132185e09e3c09d
2011-02-08 22:50:43 +01:00
return best_rd;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
Move RD intra block mode selection to rdopt.c This change is analogous to I0b67dae1f8a74902378da7bdf565e39ab832dda7, which made the move for the non-RD path. Change-Id: If63fc1b0cd1eb7f932e710f83ff24d91454f8ed1
2011-06-08 18:05:05 +02:00
static int rd_pick_intra4x4mby_modes(VP8_COMP *cpi, MACROBLOCK *mb, int *Rate,
int *rate_y, int *Distortion, int best_rd)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
MACROBLOCKD *const xd = &mb->e_mbd;
int i;
int cost = mb->mbmode_cost [xd->frame_type] [B_PRED];
int distortion = 0;
int tot_rate_y = 0;
cosmetics: consistently use [u]int64_t Removes mixed usage of (unsigned) long long and INT64. Fixes Issue #208. Change-Id: I220d3ed5ce4bb1280cd38bb3715f208ce23cf83a
2011-07-26 03:44:59 +02:00
int64_t total_rd = 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 16:49:57 +02:00
ENTROPY_CONTEXT_PLANES t_above, t_left;
ENTROPY_CONTEXT *ta;
ENTROPY_CONTEXT *tl;
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
unsigned int *bmode_costs;
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 16:49:57 +02:00
vpx_memcpy(&t_above, mb->e_mbd.above_context, sizeof(ENTROPY_CONTEXT_PLANES));
vpx_memcpy(&t_left, mb->e_mbd.left_context, sizeof(ENTROPY_CONTEXT_PLANES));
ta = (ENTROPY_CONTEXT *)&t_above;
tl = (ENTROPY_CONTEXT *)&t_left;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_intra_prediction_down_copy(xd);
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
bmode_costs = mb->inter_bmode_costs;
Initial WebM release
2010-05-18 17:58:33 +02:00
for (i = 0; i < 16; i++)
{
MODE_INFO *const mic = xd->mode_info_context;
const int mis = xd->mode_info_stride;
B_PREDICTION_MODE UNINITIALIZED_IS_SAFE(best_mode);
int UNINITIALIZED_IS_SAFE(r), UNINITIALIZED_IS_SAFE(ry), UNINITIALIZED_IS_SAFE(d);
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
if (mb->e_mbd.frame_type == KEY_FRAME)
{
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
const B_PREDICTION_MODE A = above_block_mode(mic, i, mis);
const B_PREDICTION_MODE L = left_block_mode(mic, i);
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
bmode_costs = mb->bmode_costs[A][L];
}
Added early breakout for vp8_rd_pick_intra4x4mby_modes Improved performance of good quality, speed 0 (3% average) with no average quality loss. Change-Id: Ica34473f99bd74260eaebde6b132185e09e3c09d
2011-02-08 22:50:43 +01:00
total_rd += rd_pick_intra4x4block(
Improved rd_pick_intra4x4block Eliminated unnecessary calculations. Improved performance by 10% on keyframes and 1.6% overall for the test clip used. Change-Id: I87671b26af5e2cc439e81d0fee3b15c7cd2a3309
2011-02-14 19:32:58 +01:00
cpi, mb, mb->block + i, xd->block + i, &best_mode, bmode_costs,
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 16:49:57 +02:00
ta + vp8_block2above[i],
tl + vp8_block2left[i], &r, &ry, &d);
Initial WebM release
2010-05-18 17:58:33 +02:00
cost += r;
distortion += d;
tot_rate_y += ry;
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
mic->bmi[i].as_mode = best_mode;
Added early breakout for vp8_rd_pick_intra4x4mby_modes Improved performance of good quality, speed 0 (3% average) with no average quality loss. Change-Id: Ica34473f99bd74260eaebde6b132185e09e3c09d
2011-02-08 22:50:43 +01:00
cosmetics: consistently use [u]int64_t Removes mixed usage of (unsigned) long long and INT64. Fixes Issue #208. Change-Id: I220d3ed5ce4bb1280cd38bb3715f208ce23cf83a
2011-07-26 03:44:59 +02:00
if(total_rd >= (int64_t)best_rd)
Revisited rd_pick_intra4x4block Removed unnecessary copies. No noticeable speed gains. Change-Id: I996c50c23fedd06d54ee7a3e762cbf559cc4a9d1
2011-02-24 19:31:47 +01:00
break;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
cosmetics: consistently use [u]int64_t Removes mixed usage of (unsigned) long long and INT64. Fixes Issue #208. Change-Id: I220d3ed5ce4bb1280cd38bb3715f208ce23cf83a
2011-07-26 03:44:59 +02:00
if(total_rd >= (int64_t)best_rd)
Revisited rd_pick_intra4x4block Removed unnecessary copies. No noticeable speed gains. Change-Id: I996c50c23fedd06d54ee7a3e762cbf559cc4a9d1
2011-02-24 19:31:47 +01:00
return INT_MAX;
Added early breakout for vp8_rd_pick_intra4x4mby_modes Improved performance of good quality, speed 0 (3% average) with no average quality loss. Change-Id: Ica34473f99bd74260eaebde6b132185e09e3c09d
2011-02-08 22:50:43 +01:00
Initial WebM release
2010-05-18 17:58:33 +02:00
*Rate = cost;
*rate_y += tot_rate_y;
*Distortion = distortion;
return RDCOST(mb->rdmult, mb->rddiv, cost, distortion);
}
Move RD intra block mode selection to rdopt.c This change is analogous to I0b67dae1f8a74902378da7bdf565e39ab832dda7, which made the move for the non-RD path. Change-Id: If63fc1b0cd1eb7f932e710f83ff24d91454f8ed1
2011-06-08 18:05:05 +02:00
static int rd_pick_intra16x16mby_mode(VP8_COMP *cpi,
MACROBLOCK *x,
int *Rate,
int *rate_y,
int *Distortion)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
MB_PREDICTION_MODE mode;
MB_PREDICTION_MODE UNINITIALIZED_IS_SAFE(mode_selected);
int rate, ratey;
warning: pointer targets differ in signedness vp8/encoder/rdopt.c:728: warning: pointer targets in passing argument 3 of 'macro_block_yrd' differ in signedness vp8/encoder/rdopt.c:541: note: expected 'int *' but argument is of type 'unsigned int *' distortion is signed when calling macro_block_yrd is both other cases, as well as for RDCOST Change-Id: I5e22358b7da76a116f498793253aac8099cb3461
2011-01-27 17:50:29 +01:00
int distortion;
Initial WebM release
2010-05-18 17:58:33 +02:00
int best_rd = INT_MAX;
Rationalize vp8_rd_pick_intra16x16mby_mode() Use the function macro_block_yrd() to calculate error and distortion in keeping with what is done for inter frames. The old code was using a variance metric for once case and an SSE function for measuring distortion in the other case. The function vp8_encode_intra16x16mbyrd() is no longer used. Change-Id: Ic228cb00a78ff637f4365b43f58fbe5a9273d36f
2011-01-26 19:46:34 +01:00
int this_rd;
Initial WebM release
2010-05-18 17:58:33 +02:00
//Y Search for 16x16 intra prediction mode
for (mode = DC_PRED; mode <= TM_PRED; mode++)
{
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
x->e_mbd.mode_info_context->mbmi.mode = mode;
Initial WebM release
2010-05-18 17:58:33 +02:00
RTCD: add recon functions This commit continues the process of converting to the new RTCD system. Change-Id: I9bfcf9bef65c3d4ba0fb9a3e1532bad1463a10d6
2012-01-13 01:55:44 +01:00
vp8_build_intra_predictors_mby
Move build_intra_predictors_mby to RTCD framework The vp8_build_intra_predictors_mby and vp8_build_intra_predictors_mby_s functions had global function pointers rather than using the RTCD framework. This can show up as a potential data race with tools such as helgrind. See https://bugzilla.mozilla.org/show_bug.cgi?id=640935 for an example. Change-Id: I29c407f828ac2bddfc039f852f138de5de888534
2011-03-11 17:35:38 +01:00
(&x->e_mbd);
Initial WebM release
2010-05-18 17:58:33 +02:00
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
macro_block_yrd(x, &ratey, &distortion);
Rationalize vp8_rd_pick_intra16x16mby_mode() Use the function macro_block_yrd() to calculate error and distortion in keeping with what is done for inter frames. The old code was using a variance metric for once case and an SSE function for measuring distortion in the other case. The function vp8_encode_intra16x16mbyrd() is no longer used. Change-Id: Ic228cb00a78ff637f4365b43f58fbe5a9273d36f
2011-01-26 19:46:34 +01:00
rate = ratey + x->mbmode_cost[x->e_mbd.frame_type]
[x->e_mbd.mode_info_context->mbmi.mode];
Initial WebM release
2010-05-18 17:58:33 +02:00
this_rd = RDCOST(x->rdmult, x->rddiv, rate, distortion);
if (this_rd < best_rd)
{
mode_selected = mode;
best_rd = this_rd;
*Rate = rate;
*rate_y = ratey;
warning: pointer targets differ in signedness vp8/encoder/rdopt.c:728: warning: pointer targets in passing argument 3 of 'macro_block_yrd' differ in signedness vp8/encoder/rdopt.c:541: note: expected 'int *' but argument is of type 'unsigned int *' distortion is signed when calling macro_block_yrd is both other cases, as well as for RDCOST Change-Id: I5e22358b7da76a116f498793253aac8099cb3461
2011-01-27 17:50:29 +01:00
*Distortion = distortion;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
}
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
x->e_mbd.mode_info_context->mbmi.mode = mode_selected;
Initial WebM release
2010-05-18 17:58:33 +02:00
return best_rd;
}
static int rd_cost_mbuv(MACROBLOCK *mb)
{
int b;
int cost = 0;
MACROBLOCKD *x = &mb->e_mbd;
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 16:49:57 +02:00
ENTROPY_CONTEXT_PLANES t_above, t_left;
ENTROPY_CONTEXT *ta;
ENTROPY_CONTEXT *tl;
vpx_memcpy(&t_above, mb->e_mbd.above_context, sizeof(ENTROPY_CONTEXT_PLANES));
vpx_memcpy(&t_left, mb->e_mbd.left_context, sizeof(ENTROPY_CONTEXT_PLANES));
Initial WebM release
2010-05-18 17:58:33 +02:00
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 16:49:57 +02:00
ta = (ENTROPY_CONTEXT *)&t_above;
tl = (ENTROPY_CONTEXT *)&t_left;
Initial WebM release
2010-05-18 17:58:33 +02:00
Removed vp8_block2type and used defines instead. Change-Id: Idb56e0295d004793f406dfd2d8d8c546aad62e03
2011-02-23 22:37:08 +01:00
for (b = 16; b < 24; b++)
cost += cost_coeffs(mb, x->block + b, PLANE_TYPE_UV,
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 16:49:57 +02:00
ta + vp8_block2above[b], tl + vp8_block2left[b]);
Initial WebM release
2010-05-18 17:58:33 +02:00
return cost;
}
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
static int rd_inter16x16_uv(VP8_COMP *cpi, MACROBLOCK *x, int *rate,
int *distortion, int fullpixel)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
vp8_build_inter16x16_predictors_mbuv(&x->e_mbd);
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
vp8_subtract_mbuv(x->src_diff,
Added predictor stride argument(s) to subtract functions Patch set 2: 64 bit build fix Patch set 3: 64 bit crash fix [Tero] Patch set 4: Updated ARMv6 and NEON assembly. Added also minor NEON optimizations to subtract functions. Patch set 5: x86 stride bug fix Change-Id: I1fcca93e90c89b89ddc204e1c18f208682675c15
2011-11-15 18:53:01 +01:00
x->src.u_buffer, x->src.v_buffer, x->src.uv_stride,
&x->e_mbd.predictor[256], &x->e_mbd.predictor[320], 8);
Initial WebM release
2010-05-18 17:58:33 +02:00
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
vp8_transform_mbuv(x);
vp8_quantize_mbuv(x);
*rate = rd_cost_mbuv(x);
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
*distortion = vp8_mbuverror(x) / 4;
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
return RDCOST(x->rdmult, x->rddiv, *rate, *distortion);
}
static int rd_inter4x4_uv(VP8_COMP *cpi, MACROBLOCK *x, int *rate,
int *distortion, int fullpixel)
{
vp8_build_inter4x4_predictors_mbuv(&x->e_mbd);
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
vp8_subtract_mbuv(x->src_diff,
Added predictor stride argument(s) to subtract functions Patch set 2: 64 bit build fix Patch set 3: 64 bit crash fix [Tero] Patch set 4: Updated ARMv6 and NEON assembly. Added also minor NEON optimizations to subtract functions. Patch set 5: x86 stride bug fix Change-Id: I1fcca93e90c89b89ddc204e1c18f208682675c15
2011-11-15 18:53:01 +01:00
x->src.u_buffer, x->src.v_buffer, x->src.uv_stride,
&x->e_mbd.predictor[256], &x->e_mbd.predictor[320], 8);
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
vp8_transform_mbuv(x);
vp8_quantize_mbuv(x);
Initial WebM release
2010-05-18 17:58:33 +02:00
*rate = rd_cost_mbuv(x);
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
*distortion = vp8_mbuverror(x) / 4;
Initial WebM release
2010-05-18 17:58:33 +02:00
Removed cpi->target_bits_per_mb cpi->target_bits_per_mb is currently not being used, so delete it. Also removed other unused code in rdopt.c. Change-Id: I98449f9030bcd2f15451d9b7a3b9b93dd1409923
2011-01-07 15:41:13 +01:00
return RDCOST(x->rdmult, x->rddiv, *rate, *distortion);
Initial WebM release
2010-05-18 17:58:33 +02:00
}
Move RD intra block mode selection to rdopt.c This change is analogous to I0b67dae1f8a74902378da7bdf565e39ab832dda7, which made the move for the non-RD path. Change-Id: If63fc1b0cd1eb7f932e710f83ff24d91454f8ed1
2011-06-08 18:05:05 +02:00
static void rd_pick_intra_mbuv_mode(VP8_COMP *cpi, MACROBLOCK *x, int *rate, int *rate_tokenonly, int *distortion)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
MB_PREDICTION_MODE mode;
MB_PREDICTION_MODE UNINITIALIZED_IS_SAFE(mode_selected);
int best_rd = INT_MAX;
int UNINITIALIZED_IS_SAFE(d), UNINITIALIZED_IS_SAFE(r);
int rate_to;
for (mode = DC_PRED; mode <= TM_PRED; mode++)
{
int rate;
int distortion;
int this_rd;
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
x->e_mbd.mode_info_context->mbmi.uv_mode = mode;
RTCD: add recon functions This commit continues the process of converting to the new RTCD system. Change-Id: I9bfcf9bef65c3d4ba0fb9a3e1532bad1463a10d6
2012-01-13 01:55:44 +01:00
vp8_build_intra_predictors_mbuv
SSE2/SSSE3 optimizations for build_predictors_mbuv{,_s}(). decoding before 10.425 10.432 10.423 =10.426 after: 10.405 10.416 10.398 =10.406, 0.2% faster encoding before 14.252 14.331 14.250 14.223 14.241 14.220 14.221 =14.248 after 14.095 14.090 14.085 14.095 14.064 14.081 14.089 =14.086, 1.1% faster Change-Id: I483d3d8f0deda8ad434cea76e16028380722aee2
2011-04-27 19:05:10 +02:00
(&x->e_mbd);
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
vp8_subtract_mbuv(x->src_diff,
Added predictor stride argument(s) to subtract functions Patch set 2: 64 bit build fix Patch set 3: 64 bit crash fix [Tero] Patch set 4: Updated ARMv6 and NEON assembly. Added also minor NEON optimizations to subtract functions. Patch set 5: x86 stride bug fix Change-Id: I1fcca93e90c89b89ddc204e1c18f208682675c15
2011-11-15 18:53:01 +01:00
x->src.u_buffer, x->src.v_buffer, x->src.uv_stride,
&x->e_mbd.predictor[256], &x->e_mbd.predictor[320], 8);
Improved vp8_rd_pick_intra_mbuv_mode Eliminated unnecessary calculations. Very small change to performance. Change-Id: Ib7213d43c64e36955177c4d47950ff472266f822
2011-02-14 22:34:33 +01:00
vp8_transform_mbuv(x);
vp8_quantize_mbuv(x);
Initial WebM release
2010-05-18 17:58:33 +02:00
rate_to = rd_cost_mbuv(x);
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
rate = rate_to + x->intra_uv_mode_cost[x->e_mbd.frame_type][x->e_mbd.mode_info_context->mbmi.uv_mode];
Initial WebM release
2010-05-18 17:58:33 +02:00
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
distortion = vp8_mbuverror(x) / 4;
Initial WebM release
2010-05-18 17:58:33 +02:00
Removed cpi->target_bits_per_mb cpi->target_bits_per_mb is currently not being used, so delete it. Also removed other unused code in rdopt.c. Change-Id: I98449f9030bcd2f15451d9b7a3b9b93dd1409923
2011-01-07 15:41:13 +01:00
this_rd = RDCOST(x->rdmult, x->rddiv, rate, distortion);
Initial WebM release
2010-05-18 17:58:33 +02:00
if (this_rd < best_rd)
{
best_rd = this_rd;
d = distortion;
r = rate;
*rate_tokenonly = rate_to;
mode_selected = mode;
}
}
*rate = r;
*distortion = d;
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
x->e_mbd.mode_info_context->mbmi.uv_mode = mode_selected;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
int vp8_cost_mv_ref(MB_PREDICTION_MODE m, const int near_mv_ref_ct[4])
{
vp8_prob p [VP8_MVREFS-1];
assert(NEARESTMV <= m && m <= SPLITMV);
vp8_mv_ref_probs(p, near_mv_ref_ct);
avoid negative array subscript warnings The mv_ref and sub_mv_ref token encodings are indexed from NEARESTMV and LEFT4X4, respectively, rather than being zero-based like the other token encodings. Change-Id: I3699c3f84111209ecfb91097c4b900773e9a3ad5
2010-08-09 19:27:26 +02:00
return vp8_cost_token(vp8_mv_ref_tree, p,
vp8_mv_ref_encoding_array - NEARESTMV + m);
Initial WebM release
2010-05-18 17:58:33 +02:00
}
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
void vp8_set_mbmode_and_mvs(MACROBLOCK *x, MB_PREDICTION_MODE mb, int_mv *mv)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
x->e_mbd.mode_info_context->mbmi.mode = mb;
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
x->e_mbd.mode_info_context->mbmi.mv.as_int = mv->as_int;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
static int labels2mode(
MACROBLOCK *x,
int const *labelings, int which_label,
B_PREDICTION_MODE this_mode,
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
int_mv *this_mv, int_mv *best_ref_mv,
Initial WebM release
2010-05-18 17:58:33 +02:00
int *mvcost[2]
)
{
MACROBLOCKD *const xd = & x->e_mbd;
MODE_INFO *const mic = xd->mode_info_context;
const int mis = xd->mode_info_stride;
int cost = 0;
int thismvcost = 0;
/* We have to be careful retrieving previously-encoded motion vectors.
Ones from this macroblock have to be pulled from the BLOCKD array
as they have not yet made it to the bmi array in our MB_MODE_INFO. */
int i = 0;
do
{
BLOCKD *const d = xd->block + i;
const int row = i >> 2, col = i & 3;
B_PREDICTION_MODE m;
if (labelings[i] != which_label)
continue;
if (col && labelings[i] == labelings[i-1])
m = LEFT4X4;
else if (row && labelings[i] == labelings[i-4])
m = ABOVE4X4;
else
{
// the only time we should do costing for new motion vector or mode
// is when we are on a new label (jbb May 08, 2007)
switch (m = this_mode)
{
case NEW4X4 :
thismvcost = vp8_mv_bit_cost(this_mv, best_ref_mv, mvcost, 102);
break;
case LEFT4X4:
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
this_mv->as_int = col ? d[-1].bmi.mv.as_int : left_block_mv(mic, i);
Initial WebM release
2010-05-18 17:58:33 +02:00
break;
case ABOVE4X4:
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
this_mv->as_int = row ? d[-4].bmi.mv.as_int : above_block_mv(mic, i, mis);
Initial WebM release
2010-05-18 17:58:33 +02:00
break;
case ZERO4X4:
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
this_mv->as_int = 0;
Initial WebM release
2010-05-18 17:58:33 +02:00
break;
default:
break;
}
if (m == ABOVE4X4) // replace above with left if same
{
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
int_mv left_mv;
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
left_mv.as_int = col ? d[-1].bmi.mv.as_int :
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
left_block_mv(mic, i);
Initial WebM release
2010-05-18 17:58:33 +02:00
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
if (left_mv.as_int == this_mv->as_int)
Initial WebM release
2010-05-18 17:58:33 +02:00
m = LEFT4X4;
}
cost = x->inter_bmode_costs[ m];
}
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
d->bmi.mv.as_int = this_mv->as_int;
Initial WebM release
2010-05-18 17:58:33 +02:00
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
x->partition_info->bmi[i].mode = m;
x->partition_info->bmi[i].mv.as_int = this_mv->as_int;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
while (++i < 16);
cost += thismvcost ;
return cost;
}
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 16:49:57 +02:00
static int rdcost_mbsegment_y(MACROBLOCK *mb, const int *labels,
int which_label, ENTROPY_CONTEXT *ta,
ENTROPY_CONTEXT *tl)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
int cost = 0;
int b;
MACROBLOCKD *x = &mb->e_mbd;
for (b = 0; b < 16; b++)
if (labels[ b] == which_label)
Removed vp8_block2type and used defines instead. Change-Id: Idb56e0295d004793f406dfd2d8d8c546aad62e03
2011-02-23 22:37:08 +01:00
cost += cost_coeffs(mb, x->block + b, PLANE_TYPE_Y_WITH_DC,
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 16:49:57 +02:00
ta + vp8_block2above[b],
tl + vp8_block2left[b]);
Initial WebM release
2010-05-18 17:58:33 +02:00
return cost;
}
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
static unsigned int vp8_encode_inter_mb_segment(MACROBLOCK *x, int const *labels, int which_label)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
int i;
unsigned int distortion = 0;
BLOCKD structure cleanup Removed redundancies. All of the information can be found in the MACROBLOCKD structure. Change-Id: I7556392c6f67b43bef2a5e9932180a737466ef93
2012-01-20 19:52:16 +01:00
int pre_stride = x->e_mbd.pre.y_stride;
unsigned char *base_pre = x->e_mbd.pre.y_buffer;
Initial WebM release
2010-05-18 17:58:33 +02:00
for (i = 0; i < 16; i++)
{
if (labels[i] == which_label)
{
BLOCKD *bd = &x->e_mbd.block[i];
BLOCK *be = &x->block[i];
BLOCKD structure cleanup Removed redundancies. All of the information can be found in the MACROBLOCKD structure. Change-Id: I7556392c6f67b43bef2a5e9932180a737466ef93
2012-01-20 19:52:16 +01:00
vp8_build_inter_predictors_b(bd, 16, base_pre, pre_stride, x->e_mbd.subpixel_predict);
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
vp8_subtract_b(be, bd, 16);
RTCD: add FDCT functions This commit continues the process of converting to the new RTCD system. Change-Id: I3f9c07db65eb206f6363d21bdb80e871570da767
2012-01-13 01:55:44 +01:00
x->short_fdct4x4(be->src_diff, be->coeff, 32);
Initial WebM release
2010-05-18 17:58:33 +02:00
// set to 0 no way to account for 2nd order DC so discount
//be->coeff[0] = 0;
Remove duplicate and unused functions Change-Id: I944035e720ef834561a9da0d723879a4f787312c
2010-06-04 00:08:44 +02:00
x->quantize_b(be, bd);
Initial WebM release
2010-05-18 17:58:33 +02:00
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
distortion += vp8_block_error(be->coeff, bd->dqcoeff);
Initial WebM release
2010-05-18 17:58:33 +02:00
}
}
return distortion;
}
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
static const unsigned int segmentation_to_sseshift[4] = {3, 3, 2, 0};
typedef struct
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
int_mv *ref_mv;
int_mv mvp;
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
int segment_rd;
int segment_num;
int r;
int d;
int segment_yrate;
B_PREDICTION_MODE modes[16];
Changed segmentation check order In SPLITMV, the 8x8 segment will be checked first. If the 8x8 rd is better than the best, we check the other segments. Otherwise bail. Adjustments to the thresh_mult were necessary to make up for the initial quality loss. The performance improved by 20% (average) for good quality, speed 0 and speed 1, while the overall quality remained the same. Change-Id: I717aef401323c8a254fba3e9777d2a316c774cc3
2010-12-16 23:01:27 +01:00
int_mv mvs[16];
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
unsigned char eobs[16];
int mvthresh;
int *mdcounts;
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
int_mv sv_mvp[4]; // save 4 mvp from 8x8
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
int sv_istep[2]; // save 2 initial step_param for 16x8/8x16
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
} BEST_SEG_INFO;
Increase static linkage, remove unused functions A large number of functions were defined with external linkage, even though they were only used from within one file. This patch changes their linkage to static and removes the vp8_ prefix from their names, which should make it more obvious to the reader that the function is contained within the current translation unit. Functions that were not referenced were removed. These symbols were identified by: $ nm -A libvpx.a | sort -k3 | uniq -c -f2 | grep ' [A-Z] ' \ | sort | grep '^ *1 ' Change-Id: I59609f58ab65312012c047036ae1e0634f795779
2011-03-17 22:07:59 +01:00
static void rd_check_segment(VP8_COMP *cpi, MACROBLOCK *x,
BEST_SEG_INFO *bsi, unsigned int segmentation)
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
{
int i;
Initial WebM release
2010-05-18 17:58:33 +02:00
int const *labels;
int br = 0;
int bd = 0;
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
B_PREDICTION_MODE this_mode;
Initial WebM release
2010-05-18 17:58:33 +02:00
Add half-pixel variance RTCD functions NEON has optimized 16x16 half-pixel variance functions, but they were not part of the RTCD framework. Add these functions to RTCD, so that other platforms can make use of this optimization in the future and special-case ARM code can be removed. A number of functions were taking two variance functions as parameters. These functions were changed to take a single parameter, a pointer to a struct containing all the variance functions for that block size. This provides additional flexibility for calling additional variance functions (the half-pixel special case, for example) and by initializing the table for all block sizes, we don't have to construct this function pointer table for each macroblock. Change-Id: I78289ff36b2715f9a7aa04d5f6fbe3d23acdc29c
2010-10-26 21:34:16 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
int label_count;
int this_segment_rd = 0;
int label_mv_thresh;
int rate = 0;
int sbr = 0;
int sbd = 0;
int segmentyrate = 0;
vp8_variance_fn_ptr_t *v_fn_ptr;
ENTROPY_CONTEXT_PLANES t_above, t_left;
ENTROPY_CONTEXT *ta;
ENTROPY_CONTEXT *tl;
ENTROPY_CONTEXT_PLANES t_above_b, t_left_b;
ENTROPY_CONTEXT *ta_b;
ENTROPY_CONTEXT *tl_b;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
vpx_memcpy(&t_above, x->e_mbd.above_context, sizeof(ENTROPY_CONTEXT_PLANES));
vpx_memcpy(&t_left, x->e_mbd.left_context, sizeof(ENTROPY_CONTEXT_PLANES));
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
ta = (ENTROPY_CONTEXT *)&t_above;
tl = (ENTROPY_CONTEXT *)&t_left;
ta_b = (ENTROPY_CONTEXT *)&t_above_b;
tl_b = (ENTROPY_CONTEXT *)&t_left_b;
br = 0;
bd = 0;
Fix compiler warnings Change-Id: I2a97f08cc3c7808ce5be39e910cc5147ecf03a1d
2010-06-11 20:33:49 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
v_fn_ptr = &cpi->fn_ptr[segmentation];
labels = vp8_mbsplits[segmentation];
label_count = vp8_mbsplit_count[segmentation];
Fix compiler warnings Change-Id: I2a97f08cc3c7808ce5be39e910cc5147ecf03a1d
2010-06-11 20:33:49 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
// 64 makes this threshold really big effectively
// making it so that we very rarely check mvs on
// segments. setting this to 1 would make mv thresh
// roughly equal to what it is for macroblocks
label_mv_thresh = 1 * bsi->mvthresh / label_count ;
// Segmentation method overheads
rate = vp8_cost_token(vp8_mbsplit_tree, vp8_mbsplit_probs, vp8_mbsplit_encodings + segmentation);
rate += vp8_cost_mv_ref(SPLITMV, bsi->mdcounts);
Removed cpi->target_bits_per_mb cpi->target_bits_per_mb is currently not being used, so delete it. Also removed other unused code in rdopt.c. Change-Id: I98449f9030bcd2f15451d9b7a3b9b93dd1409923
2011-01-07 15:41:13 +01:00
this_segment_rd += RDCOST(x->rdmult, x->rddiv, rate, 0);
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
br += rate;
for (i = 0; i < label_count; i++)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
int_mv mode_mv[B_MODE_COUNT];
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
int best_label_rd = INT_MAX;
B_PREDICTION_MODE mode_selected = ZERO4X4;
int bestlabelyrate = 0;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
// search for the best motion vector on this segment
for (this_mode = LEFT4X4; this_mode <= NEW4X4 ; this_mode ++)
{
int this_rd;
int distortion;
int labelyrate;
ENTROPY_CONTEXT_PLANES t_above_s, t_left_s;
ENTROPY_CONTEXT *ta_s;
ENTROPY_CONTEXT *tl_s;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
vpx_memcpy(&t_above_s, &t_above, sizeof(ENTROPY_CONTEXT_PLANES));
vpx_memcpy(&t_left_s, &t_left, sizeof(ENTROPY_CONTEXT_PLANES));
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
ta_s = (ENTROPY_CONTEXT *)&t_above_s;
tl_s = (ENTROPY_CONTEXT *)&t_left_s;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
if (this_mode == NEW4X4)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
int sseshift;
Initial WebM release
2010-05-18 17:58:33 +02:00
int num00;
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
int step_param = 0;
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
int further_steps;
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
int n;
int thissme;
int bestsme = INT_MAX;
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
int_mv temp_mv;
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
BLOCK *c;
BLOCKD *e;
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 16:49:57 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
// Is the best so far sufficiently good that we cant justify doing and new motion search.
if (best_label_rd < label_mv_thresh)
break;
Initial WebM release
2010-05-18 17:58:33 +02:00
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
if(cpi->compressor_speed)
{
if (segmentation == BLOCK_8X16 || segmentation == BLOCK_16X8)
{
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
bsi->mvp.as_int = bsi->sv_mvp[i].as_int;
if (i==1 && segmentation == BLOCK_16X8)
bsi->mvp.as_int = bsi->sv_mvp[2].as_int;
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
step_param = bsi->sv_istep[i];
}
// use previous block's result as next block's MV predictor.
if (segmentation == BLOCK_4X4 && i>0)
{
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
bsi->mvp.as_int = x->e_mbd.block[i-1].bmi.mv.as_int;
if (i==4 || i==8 || i==12)
bsi->mvp.as_int = x->e_mbd.block[i-4].bmi.mv.as_int;
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
step_param = 2;
}
}
further_steps = (MAX_MVSEARCH_STEPS - 1) - step_param;
Initial WebM release
2010-05-18 17:58:33 +02:00
{
further clean up of errorperbit and sadperbit this commit makes the usage errorperbit and sadperbit consistent for encoding modes and passes. Removed all different magic weight factors associated with errorperbit. Now 1/2 is used for both sadperbit16 and sadperbit4, the /2 operation is merged into initializations of the 2 variables. Tests on cif set show .23%, 0.18% and 0.19% gain by avg psnr, overall psnr and ssim respectively. Change-Id: Ifa285c3e065ce0a5a77addfc9f95aabf54ee270d
2011-06-01 20:41:05 +02:00
int sadpb = x->sadperbit4;
Adjust full-pixel clamping and motion vector limit calculation Do mvp clamping in full-pixel precision instead of 1/8-pixel precision to avoid error caused by right shifting operation. Also, further fixed the motion vector limit calculation in change: b7480454706a6b15bf091e659cd6227ab373c1a6 Change-Id: Ied88a4f7ddfb0476eb9f7afc6ceeddbf209fffd7
2011-07-07 17:21:41 +02:00
int_mv mvp_full;
mvp_full.as_mv.row = bsi->mvp.as_mv.row >>3;
mvp_full.as_mv.col = bsi->mvp.as_mv.col >>3;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
// find first label
Increase static linkage, remove unused functions A large number of functions were defined with external linkage, even though they were only used from within one file. This patch changes their linkage to static and removes the vp8_ prefix from their names, which should make it more obvious to the reader that the function is contained within the current translation unit. Functions that were not referenced were removed. These symbols were identified by: $ nm -A libvpx.a | sort -k3 | uniq -c -f2 | grep ' [A-Z] ' \ | sort | grep '^ *1 ' Change-Id: I59609f58ab65312012c047036ae1e0634f795779
2011-03-17 22:07:59 +01:00
n = vp8_mbsplit_offset[segmentation][i];
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
c = &x->block[n];
e = &x->e_mbd.block[n];
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
{
Adjust full-pixel clamping and motion vector limit calculation Do mvp clamping in full-pixel precision instead of 1/8-pixel precision to avoid error caused by right shifting operation. Also, further fixed the motion vector limit calculation in change: b7480454706a6b15bf091e659cd6227ab373c1a6 Change-Id: Ied88a4f7ddfb0476eb9f7afc6ceeddbf209fffd7
2011-07-07 17:21:41 +02:00
bestsme = cpi->diamond_search_sad(x, c, e, &mvp_full,
remove some magic weights associated with sad_per_bit sad_per_bit has been used for a number of motion vector search routines with different magic weights: 1, 1/2 and 1/4. This commit remove these magic numbers and use 1/2 for all motion search routines, also reformat a number of source code lines to within 80 column limit. Test on cif set shows overall effect is neutral on all metrics. <=0.01% Change-Id: I8a382821fa4cffc9c0acf8e8431435a03df74885
2010-07-01 03:58:54 +02:00
&mode_mv[NEW4X4], step_param,
sadpb, &num00, v_fn_ptr,
x->mvcost, bsi->ref_mv);
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
n = num00;
num00 = 0;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
while (n < further_steps)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
n++;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
if (num00)
num00--;
Initial WebM release
2010-05-18 17:58:33 +02:00
else
{
remove some magic weights associated with sad_per_bit sad_per_bit has been used for a number of motion vector search routines with different magic weights: 1, 1/2 and 1/4. This commit remove these magic numbers and use 1/2 for all motion search routines, also reformat a number of source code lines to within 80 column limit. Test on cif set shows overall effect is neutral on all metrics. <=0.01% Change-Id: I8a382821fa4cffc9c0acf8e8431435a03df74885
2010-07-01 03:58:54 +02:00
thissme = cpi->diamond_search_sad(x, c, e,
Adjust full-pixel clamping and motion vector limit calculation Do mvp clamping in full-pixel precision instead of 1/8-pixel precision to avoid error caused by right shifting operation. Also, further fixed the motion vector limit calculation in change: b7480454706a6b15bf091e659cd6227ab373c1a6 Change-Id: Ied88a4f7ddfb0476eb9f7afc6ceeddbf209fffd7
2011-07-07 17:21:41 +02:00
&mvp_full, &temp_mv,
remove some magic weights associated with sad_per_bit sad_per_bit has been used for a number of motion vector search routines with different magic weights: 1, 1/2 and 1/4. This commit remove these magic numbers and use 1/2 for all motion search routines, also reformat a number of source code lines to within 80 column limit. Test on cif set shows overall effect is neutral on all metrics. <=0.01% Change-Id: I8a382821fa4cffc9c0acf8e8431435a03df74885
2010-07-01 03:58:54 +02:00
step_param + n, sadpb,
&num00, v_fn_ptr,
x->mvcost, bsi->ref_mv);
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
if (thissme < bestsme)
{
bestsme = thissme;
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
mode_mv[NEW4X4].as_int = temp_mv.as_int;
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
}
Initial WebM release
2010-05-18 17:58:33 +02:00
}
}
}
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
sseshift = segmentation_to_sseshift[segmentation];
// Should we do a full search (best quality only)
if ((cpi->compressor_speed == 0) && (bestsme >> sseshift) > 4000)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Preload reference area in sub-pixel motion search (real-time mode) This change implemented same idea in change "Preload reference area to an intermediate buffer in sub-pixel motion search." The changes were made to vp8_find_best_sub_pixel_step() and vp8_find_best_half _pixel_step() functions which are called when speed >= 5. Test result (using tulip clip): 1. On Core2 Quad machine(Linux) rt mode, speed (-5 ~ -8), encoding speed gain: 2% ~ 3% rt mode, speed (-9 ~ -11), encoding speed gain: 1% ~ 2% rt mode, speed (-12 ~ -14), no noticeable encoding speed gain 2. On Xeon machine(Linux) Test on speed (-5 ~ -14) didn't show noticeable speed change. Change-Id: I21bec2d6e7fbe541fcc0f4c0366bbdf3e2076aa2
2011-07-22 22:01:11 +02:00
/* Check if mvp_full is within the range. */
vp8_clamp_mv(&mvp_full, x->mv_col_min, x->mv_col_max, x->mv_row_min, x->mv_row_max);
Adjust full-pixel clamping and motion vector limit calculation Do mvp clamping in full-pixel precision instead of 1/8-pixel precision to avoid error caused by right shifting operation. Also, further fixed the motion vector limit calculation in change: b7480454706a6b15bf091e659cd6227ab373c1a6 Change-Id: Ied88a4f7ddfb0476eb9f7afc6ceeddbf209fffd7
2011-07-07 17:21:41 +02:00
thissme = cpi->full_search_sad(x, c, e, &mvp_full,
remove some magic weights associated with sad_per_bit sad_per_bit has been used for a number of motion vector search routines with different magic weights: 1, 1/2 and 1/4. This commit remove these magic numbers and use 1/2 for all motion search routines, also reformat a number of source code lines to within 80 column limit. Test on cif set shows overall effect is neutral on all metrics. <=0.01% Change-Id: I8a382821fa4cffc9c0acf8e8431435a03df74885
2010-07-01 03:58:54 +02:00
sadpb, 16, v_fn_ptr,
x->mvcost, bsi->ref_mv);
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
if (thissme < bestsme)
{
bestsme = thissme;
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
mode_mv[NEW4X4].as_int = e->bmi.mv.as_int;
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
}
Initial WebM release
2010-05-18 17:58:33 +02:00
else
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
{
// The full search result is actually worse so re-instate the previous best vector
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
e->bmi.mv.as_int = mode_mv[NEW4X4].as_int;
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
}
Initial WebM release
2010-05-18 17:58:33 +02:00
}
}
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
if (bestsme < INT_MAX)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Reduce unnecessary distortion computation In vp8_pick_inter_mode(), for NEWMV mode, use the error result got from motion search as distortion. This helps performance in real- time mode. Change-Id: I398c4e46cc5381f7d874e748cf78827ef0e0860c
2011-04-14 21:53:33 +02:00
int distortion;
Use sub-pixel search's SSE in mode selection Passed SSE from sub-pixel search back to pick_inter_mode function, which is compared with the encode_breakout to see if we could skip evaluating the remaining modes. Change-Id: I4a86442834f0d1b880a19e21ea52d17d505f941d
2011-04-18 21:48:34 +02:00
unsigned int sse;
further clean up of errorperbit and sadperbit this commit makes the usage errorperbit and sadperbit consistent for encoding modes and passes. Removed all different magic weight factors associated with errorperbit. Now 1/2 is used for both sadperbit16 and sadperbit4, the /2 operation is merged into initializations of the 2 variables. Tests on cif set show .23%, 0.18% and 0.19% gain by avg psnr, overall psnr and ssim respectively. Change-Id: Ifa285c3e065ce0a5a77addfc9f95aabf54ee270d
2011-06-01 20:41:05 +02:00
cpi->find_fractional_mv_step(x, c, e, &mode_mv[NEW4X4],
bsi->ref_mv, x->errorperbit, v_fn_ptr, x->mvcost,
&distortion, &sse);
Reduce unnecessary distortion computation In vp8_pick_inter_mode(), for NEWMV mode, use the error result got from motion search as distortion. This helps performance in real- time mode. Change-Id: I398c4e46cc5381f7d874e748cf78827ef0e0860c
2011-04-14 21:53:33 +02:00
Initial WebM release
2010-05-18 17:58:33 +02:00
}
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
} /* NEW4X4 */
rate = labels2mode(x, labels, i, this_mode, &mode_mv[this_mode],
bsi->ref_mv, x->mvcost);
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
// Trap vectors that reach beyond the UMV borders
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
if (((mode_mv[this_mode].as_mv.row >> 3) < x->mv_row_min) || ((mode_mv[this_mode].as_mv.row >> 3) > x->mv_row_max) ||
((mode_mv[this_mode].as_mv.col >> 3) < x->mv_col_min) || ((mode_mv[this_mode].as_mv.col >> 3) > x->mv_col_max))
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
{
continue;
}
Initial WebM release
2010-05-18 17:58:33 +02:00
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
distortion = vp8_encode_inter_mb_segment(x, labels, i) / 4;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
labelyrate = rdcost_mbsegment_y(x, labels, i, ta_s, tl_s);
rate += labelyrate;
Initial WebM release
2010-05-18 17:58:33 +02:00
Removed cpi->target_bits_per_mb cpi->target_bits_per_mb is currently not being used, so delete it. Also removed other unused code in rdopt.c. Change-Id: I98449f9030bcd2f15451d9b7a3b9b93dd1409923
2011-01-07 15:41:13 +01:00
this_rd = RDCOST(x->rdmult, x->rddiv, rate, distortion);
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 16:49:57 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
if (this_rd < best_label_rd)
{
sbr = rate;
sbd = distortion;
bestlabelyrate = labelyrate;
mode_selected = this_mode;
best_label_rd = this_rd;
vpx_memcpy(ta_b, ta_s, sizeof(ENTROPY_CONTEXT_PLANES));
vpx_memcpy(tl_b, tl_s, sizeof(ENTROPY_CONTEXT_PLANES));
Initial WebM release
2010-05-18 17:58:33 +02:00
}
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
} /*for each 4x4 mode*/
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
vpx_memcpy(ta, ta_b, sizeof(ENTROPY_CONTEXT_PLANES));
vpx_memcpy(tl, tl_b, sizeof(ENTROPY_CONTEXT_PLANES));
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
labels2mode(x, labels, i, mode_selected, &mode_mv[mode_selected],
bsi->ref_mv, x->mvcost);
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
br += sbr;
bd += sbd;
segmentyrate += bestlabelyrate;
this_segment_rd += best_label_rd;
Initial WebM release
2010-05-18 17:58:33 +02:00
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
if (this_segment_rd >= bsi->segment_rd)
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
break;
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
} /* for each label */
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
if (this_segment_rd < bsi->segment_rd)
{
bsi->r = br;
bsi->d = bd;
bsi->segment_yrate = segmentyrate;
bsi->segment_rd = this_segment_rd;
bsi->segment_num = segmentation;
// store everything needed to come back to this!!
for (i = 0; i < 16; i++)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
bsi->mvs[i].as_mv = x->partition_info->bmi[i].mv.as_mv;
bsi->modes[i] = x->partition_info->bmi[i].mode;
Change use of eob in the encoder Changed 'int eob' to 'char *eob' in BLOCKD so that both encoder and decoder will use eobs[25] array from MACROBLOCKD structure. In future, this will enable use of the decoder side IDCT in the encoder. Change-Id: I6e1c011628cb8864fd4a0b80f0279ce16a5ca978
2011-10-25 13:25:11 +02:00
bsi->eobs[i] = x->e_mbd.eobs[i];
Initial WebM release
2010-05-18 17:58:33 +02:00
}
}
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
}
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
static __inline
void vp8_cal_step_param(int sr, int *sp)
{
int step = 0;
if (sr > MAX_FIRST_STEP) sr = MAX_FIRST_STEP;
else if (sr < 1) sr = 1;
while (sr>>=1)
step++;
*sp = MAX_MVSEARCH_STEPS - 1 - step;
}
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
static int vp8_rd_pick_best_mbsegmentation(VP8_COMP *cpi, MACROBLOCK *x,
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
int_mv *best_ref_mv, int best_rd,
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
int *mdcounts, int *returntotrate,
int *returnyrate, int *returndistortion,
int mvthresh)
{
int i;
BEST_SEG_INFO bsi;
vpx_memset(&bsi, 0, sizeof(bsi));
bsi.segment_rd = best_rd;
bsi.ref_mv = best_ref_mv;
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
bsi.mvp.as_int = best_ref_mv->as_int;
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
bsi.mvthresh = mvthresh;
bsi.mdcounts = mdcounts;
for(i = 0; i < 16; i++)
{
bsi.modes[i] = ZERO4X4;
}
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
Changed segmentation check order In SPLITMV, the 8x8 segment will be checked first. If the 8x8 rd is better than the best, we check the other segments. Otherwise bail. Adjustments to the thresh_mult were necessary to make up for the initial quality loss. The performance improved by 20% (average) for good quality, speed 0 and speed 1, while the overall quality remained the same. Change-Id: I717aef401323c8a254fba3e9777d2a316c774cc3
2010-12-16 23:01:27 +01:00
if(cpi->compressor_speed == 0)
{
/* for now, we will keep the original segmentation order
when in best quality mode */
Increase static linkage, remove unused functions A large number of functions were defined with external linkage, even though they were only used from within one file. This patch changes their linkage to static and removes the vp8_ prefix from their names, which should make it more obvious to the reader that the function is contained within the current translation unit. Functions that were not referenced were removed. These symbols were identified by: $ nm -A libvpx.a | sort -k3 | uniq -c -f2 | grep ' [A-Z] ' \ | sort | grep '^ *1 ' Change-Id: I59609f58ab65312012c047036ae1e0634f795779
2011-03-17 22:07:59 +01:00
rd_check_segment(cpi, x, &bsi, BLOCK_16X8);
rd_check_segment(cpi, x, &bsi, BLOCK_8X16);
rd_check_segment(cpi, x, &bsi, BLOCK_8X8);
rd_check_segment(cpi, x, &bsi, BLOCK_4X4);
Changed segmentation check order In SPLITMV, the 8x8 segment will be checked first. If the 8x8 rd is better than the best, we check the other segments. Otherwise bail. Adjustments to the thresh_mult were necessary to make up for the initial quality loss. The performance improved by 20% (average) for good quality, speed 0 and speed 1, while the overall quality remained the same. Change-Id: I717aef401323c8a254fba3e9777d2a316c774cc3
2010-12-16 23:01:27 +01:00
}
else
{
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
int sr;
Increase static linkage, remove unused functions A large number of functions were defined with external linkage, even though they were only used from within one file. This patch changes their linkage to static and removes the vp8_ prefix from their names, which should make it more obvious to the reader that the function is contained within the current translation unit. Functions that were not referenced were removed. These symbols were identified by: $ nm -A libvpx.a | sort -k3 | uniq -c -f2 | grep ' [A-Z] ' \ | sort | grep '^ *1 ' Change-Id: I59609f58ab65312012c047036ae1e0634f795779
2011-03-17 22:07:59 +01:00
rd_check_segment(cpi, x, &bsi, BLOCK_8X8);
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
Changed segmentation check order In SPLITMV, the 8x8 segment will be checked first. If the 8x8 rd is better than the best, we check the other segments. Otherwise bail. Adjustments to the thresh_mult were necessary to make up for the initial quality loss. The performance improved by 20% (average) for good quality, speed 0 and speed 1, while the overall quality remained the same. Change-Id: I717aef401323c8a254fba3e9777d2a316c774cc3
2010-12-16 23:01:27 +01:00
if (bsi.segment_rd < best_rd)
{
Remove unnecessary ternary constructs The code had a number of constructs like (condition)?1:0, which is redundant with C's semantics. In the cases where a boolean operator was used in the condition, simply remove the ternary part. Otherwise adjust the surrounding expression to remove the condition (eg, for rounding up. See pickinter.c and rdopt.c) Change-Id: Icb2372defa3783cf31857d90b2630d06b2c7e1be
2011-12-22 01:11:31 +01:00
int col_min = ((best_ref_mv->as_mv.col+7)>>3) - MAX_FULL_PEL_VAL;
int row_min = ((best_ref_mv->as_mv.row+7)>>3) - MAX_FULL_PEL_VAL;
Adjust full-pixel clamping and motion vector limit calculation Do mvp clamping in full-pixel precision instead of 1/8-pixel precision to avoid error caused by right shifting operation. Also, further fixed the motion vector limit calculation in change: b7480454706a6b15bf091e659cd6227ab373c1a6 Change-Id: Ied88a4f7ddfb0476eb9f7afc6ceeddbf209fffd7
2011-07-07 17:21:41 +02:00
int col_max = (best_ref_mv->as_mv.col>>3) + MAX_FULL_PEL_VAL;
int row_max = (best_ref_mv->as_mv.row>>3) + MAX_FULL_PEL_VAL;
Adjust MV borders for SPLITMV mode Add limits to avoid MV going out of range. Change-Id: I8a5deb40bf393488d29f694b5a56804d578e68b5
2010-12-28 19:23:07 +01:00
int tmp_col_min = x->mv_col_min;
int tmp_col_max = x->mv_col_max;
int tmp_row_min = x->mv_row_min;
int tmp_row_max = x->mv_row_max;
/* Get intersection of UMV window and valid MV window to reduce # of checks in diamond search. */
if (x->mv_col_min < col_min )
x->mv_col_min = col_min;
if (x->mv_col_max > col_max )
x->mv_col_max = col_max;
if (x->mv_row_min < row_min )
x->mv_row_min = row_min;
if (x->mv_row_max > row_max )
x->mv_row_max = row_max;
/* Get 8x8 result */
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
bsi.sv_mvp[0].as_int = bsi.mvs[0].as_int;
bsi.sv_mvp[1].as_int = bsi.mvs[2].as_int;
bsi.sv_mvp[2].as_int = bsi.mvs[8].as_int;
bsi.sv_mvp[3].as_int = bsi.mvs[10].as_int;
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
Adjust MV borders for SPLITMV mode Add limits to avoid MV going out of range. Change-Id: I8a5deb40bf393488d29f694b5a56804d578e68b5
2010-12-28 19:23:07 +01:00
/* Use 8x8 result as 16x8/8x16's predictor MV. Adjust search range according to the closeness of 2 MV. */
/* block 8X16 */
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
{
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
sr = MAXF((abs(bsi.sv_mvp[0].as_mv.row - bsi.sv_mvp[2].as_mv.row))>>3, (abs(bsi.sv_mvp[0].as_mv.col - bsi.sv_mvp[2].as_mv.col))>>3);
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
vp8_cal_step_param(sr, &bsi.sv_istep[0]);
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
sr = MAXF((abs(bsi.sv_mvp[1].as_mv.row - bsi.sv_mvp[3].as_mv.row))>>3, (abs(bsi.sv_mvp[1].as_mv.col - bsi.sv_mvp[3].as_mv.col))>>3);
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
vp8_cal_step_param(sr, &bsi.sv_istep[1]);
Increase static linkage, remove unused functions A large number of functions were defined with external linkage, even though they were only used from within one file. This patch changes their linkage to static and removes the vp8_ prefix from their names, which should make it more obvious to the reader that the function is contained within the current translation unit. Functions that were not referenced were removed. These symbols were identified by: $ nm -A libvpx.a | sort -k3 | uniq -c -f2 | grep ' [A-Z] ' \ | sort | grep '^ *1 ' Change-Id: I59609f58ab65312012c047036ae1e0634f795779
2011-03-17 22:07:59 +01:00
rd_check_segment(cpi, x, &bsi, BLOCK_8X16);
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
}
Adjust MV borders for SPLITMV mode Add limits to avoid MV going out of range. Change-Id: I8a5deb40bf393488d29f694b5a56804d578e68b5
2010-12-28 19:23:07 +01:00
/* block 16X8 */
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
{
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
sr = MAXF((abs(bsi.sv_mvp[0].as_mv.row - bsi.sv_mvp[1].as_mv.row))>>3, (abs(bsi.sv_mvp[0].as_mv.col - bsi.sv_mvp[1].as_mv.col))>>3);
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
vp8_cal_step_param(sr, &bsi.sv_istep[0]);
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
sr = MAXF((abs(bsi.sv_mvp[2].as_mv.row - bsi.sv_mvp[3].as_mv.row))>>3, (abs(bsi.sv_mvp[2].as_mv.col - bsi.sv_mvp[3].as_mv.col))>>3);
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
vp8_cal_step_param(sr, &bsi.sv_istep[1]);
Increase static linkage, remove unused functions A large number of functions were defined with external linkage, even though they were only used from within one file. This patch changes their linkage to static and removes the vp8_ prefix from their names, which should make it more obvious to the reader that the function is contained within the current translation unit. Functions that were not referenced were removed. These symbols were identified by: $ nm -A libvpx.a | sort -k3 | uniq -c -f2 | grep ' [A-Z] ' \ | sort | grep '^ *1 ' Change-Id: I59609f58ab65312012c047036ae1e0634f795779
2011-03-17 22:07:59 +01:00
rd_check_segment(cpi, x, &bsi, BLOCK_16X8);
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
}
Adjust MV borders for SPLITMV mode Add limits to avoid MV going out of range. Change-Id: I8a5deb40bf393488d29f694b5a56804d578e68b5
2010-12-28 19:23:07 +01:00
/* If 8x8 is better than 16x8/8x16, then do 4x4 search */
Add no_skip_block4x4_search flag in SPLITMV mode Add a flag to always enable block4x4 search for speed=0 (good quality) to guarantee no quality loss for speed0. Change-Id: Ie04bbc25f7e6a33a7bfa30e05775d33148731c81
2011-01-10 23:21:55 +01:00
/* Not skip 4x4 if speed=0 (good quality) */
if (cpi->sf.no_skip_block4x4_search || bsi.segment_num == BLOCK_8X8) /* || (sv_segment_rd8x8-bsi.segment_rd) < sv_segment_rd8x8>>5) */
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
{
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
bsi.mvp.as_int = bsi.sv_mvp[0].as_int;
Increase static linkage, remove unused functions A large number of functions were defined with external linkage, even though they were only used from within one file. This patch changes their linkage to static and removes the vp8_ prefix from their names, which should make it more obvious to the reader that the function is contained within the current translation unit. Functions that were not referenced were removed. These symbols were identified by: $ nm -A libvpx.a | sort -k3 | uniq -c -f2 | grep ' [A-Z] ' \ | sort | grep '^ *1 ' Change-Id: I59609f58ab65312012c047036ae1e0634f795779
2011-03-17 22:07:59 +01:00
rd_check_segment(cpi, x, &bsi, BLOCK_4X4);
Modify motion estimation for SPLITMV mode 1. Search for block8x16/block16x8 uses block8x8's search results. 2. Check block4x4 only if block8x8 is chosen. (This hurts quality, which will be improved in another check-in.) 3. In block4x4 search, the previous block's result is used as MV predictor for next block. This change improves performance. Change-Id: I9dc089007ca08129fb6c11fe7692777ebb8647b0
2010-12-23 17:23:03 +01:00
}
Adjust MV borders for SPLITMV mode Add limits to avoid MV going out of range. Change-Id: I8a5deb40bf393488d29f694b5a56804d578e68b5
2010-12-28 19:23:07 +01:00
/* restore UMV window */
x->mv_col_min = tmp_col_min;
x->mv_col_max = tmp_col_max;
x->mv_row_min = tmp_row_min;
x->mv_row_max = tmp_row_max;
Changed segmentation check order In SPLITMV, the 8x8 segment will be checked first. If the 8x8 rd is better than the best, we check the other segments. Otherwise bail. Adjustments to the thresh_mult were necessary to make up for the initial quality loss. The performance improved by 20% (average) for good quality, speed 0 and speed 1, while the overall quality remained the same. Change-Id: I717aef401323c8a254fba3e9777d2a316c774cc3
2010-12-16 23:01:27 +01:00
}
}
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
/* set it to the best */
Initial WebM release
2010-05-18 17:58:33 +02:00
for (i = 0; i < 16; i++)
{
BLOCKD *bd = &x->e_mbd.block[i];
Removed B_MODE_INFO Declared the bmi in BLOCKD as a union instead of B_MODE_INFO. Then removed B_MODE_INFO completely. Change-Id: Ieb7469899e265892c66f7aeac87b7f2bf38e7a67
2011-06-02 19:46:41 +02:00
bd->bmi.mv.as_int = bsi.mvs[i].as_int;
Change use of eob in the encoder Changed 'int eob' to 'char *eob' in BLOCKD so that both encoder and decoder will use eobs[25] array from MACROBLOCKD structure. In future, this will enable use of the decoder side IDCT in the encoder. Change-Id: I6e1c011628cb8864fd4a0b80f0279ce16a5ca978
2011-10-25 13:25:11 +02:00
*bd->eob = bsi.eobs[i];
Initial WebM release
2010-05-18 17:58:33 +02:00
}
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
*returntotrate = bsi.r;
*returndistortion = bsi.d;
*returnyrate = bsi.segment_yrate;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
/* save partitions */
x->e_mbd.mode_info_context->mbmi.partitioning = bsi.segment_num;
x->partition_info->count = vp8_mbsplit_count[bsi.segment_num];
Initial WebM release
2010-05-18 17:58:33 +02:00
Reduced the size of MB_MODE_INFO Moved partition_bmi and partition_count out of MB_MODE_INFO and placed into MACROBLOCK. Also reduced the size of other members of the MB_MODE_INFO struct. For 1080p, the memory was reduced by 1,209,516 bytes. The decoder performance appeared to improve by 3% for the clip used. Note: The main goal for this change is to improve the decoder performance. The encoder will be revisited at a later date for further structure cleanup. Change-Id: I4733621292ee9cc3fffa4046cb3fd4d99bd14613
2010-09-02 22:17:52 +02:00
for (i = 0; i < x->partition_info->count; i++)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
int j;
Increase static linkage, remove unused functions A large number of functions were defined with external linkage, even though they were only used from within one file. This patch changes their linkage to static and removes the vp8_ prefix from their names, which should make it more obvious to the reader that the function is contained within the current translation unit. Functions that were not referenced were removed. These symbols were identified by: $ nm -A libvpx.a | sort -k3 | uniq -c -f2 | grep ' [A-Z] ' \ | sort | grep '^ *1 ' Change-Id: I59609f58ab65312012c047036ae1e0634f795779
2011-03-17 22:07:59 +01:00
j = vp8_mbsplit_offset[bsi.segment_num][i];
Initial WebM release
2010-05-18 17:58:33 +02:00
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
x->partition_info->bmi[i].mode = bsi.modes[j];
x->partition_info->bmi[i].mv.as_mv = bsi.mvs[j].as_mv;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
/*
* used to set x->e_mbd.mode_info_context->mbmi.mv.as_int
*/
x->partition_info->bmi[15].mv.as_int = bsi.mvs[15].as_int;
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
return bsi.segment_rd;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
//The improved MV prediction
Remove copies of same functions Reduce the code size. Change-Id: I2e1998557a3c8776e262c442fd758c25e17aff7a
2011-01-26 18:03:13 +01:00
void vp8_mv_pred
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
(
VP8_COMP *cpi,
MACROBLOCKD *xd,
const MODE_INFO *here,
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
int_mv *mvp,
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
int refframe,
int *ref_frame_sign_bias,
int *sr,
int near_sadidx[]
)
{
const MODE_INFO *above = here - xd->mode_info_stride;
const MODE_INFO *left = here - 1;
const MODE_INFO *aboveleft = above - 1;
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
int_mv near_mvs[8];
int near_ref[8];
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
int_mv mv;
int vcnt=0;
int find=0;
int mb_offset;
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
int mvx[8];
int mvy[8];
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
int i;
mv.as_int = 0;
if(here->mbmi.ref_frame != INTRA_FRAME)
{
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
near_mvs[0].as_int = near_mvs[1].as_int = near_mvs[2].as_int = near_mvs[3].as_int = near_mvs[4].as_int = near_mvs[5].as_int = near_mvs[6].as_int = near_mvs[7].as_int = 0;
near_ref[0] = near_ref[1] = near_ref[2] = near_ref[3] = near_ref[4] = near_ref[5] = near_ref[6] = near_ref[7] = 0;
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
// read in 3 nearby block's MVs from current frame as prediction candidates.
if (above->mbmi.ref_frame != INTRA_FRAME)
{
near_mvs[vcnt].as_int = above->mbmi.mv.as_int;
Remove copies of same functions Reduce the code size. Change-Id: I2e1998557a3c8776e262c442fd758c25e17aff7a
2011-01-26 18:03:13 +01:00
mv_bias(ref_frame_sign_bias[above->mbmi.ref_frame], refframe, &near_mvs[vcnt], ref_frame_sign_bias);
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
near_ref[vcnt] = above->mbmi.ref_frame;
}
vcnt++;
if (left->mbmi.ref_frame != INTRA_FRAME)
{
near_mvs[vcnt].as_int = left->mbmi.mv.as_int;
Remove copies of same functions Reduce the code size. Change-Id: I2e1998557a3c8776e262c442fd758c25e17aff7a
2011-01-26 18:03:13 +01:00
mv_bias(ref_frame_sign_bias[left->mbmi.ref_frame], refframe, &near_mvs[vcnt], ref_frame_sign_bias);
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
near_ref[vcnt] = left->mbmi.ref_frame;
}
vcnt++;
if (aboveleft->mbmi.ref_frame != INTRA_FRAME)
{
near_mvs[vcnt].as_int = aboveleft->mbmi.mv.as_int;
Remove copies of same functions Reduce the code size. Change-Id: I2e1998557a3c8776e262c442fd758c25e17aff7a
2011-01-26 18:03:13 +01:00
mv_bias(ref_frame_sign_bias[aboveleft->mbmi.ref_frame], refframe, &near_mvs[vcnt], ref_frame_sign_bias);
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
near_ref[vcnt] = aboveleft->mbmi.ref_frame;
}
vcnt++;
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
// read in 5 nearby block's MVs from last frame.
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
if(cpi->common.last_frame_type != KEY_FRAME)
{
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
mb_offset = (-xd->mb_to_top_edge/128 + 1) * (xd->mode_info_stride +1) + (-xd->mb_to_left_edge/128 +1) ;
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
// current in last frame
if (cpi->lf_ref_frame[mb_offset] != INTRA_FRAME)
{
near_mvs[vcnt].as_int = cpi->lfmv[mb_offset].as_int;
Remove copies of same functions Reduce the code size. Change-Id: I2e1998557a3c8776e262c442fd758c25e17aff7a
2011-01-26 18:03:13 +01:00
mv_bias(cpi->lf_ref_frame_sign_bias[mb_offset], refframe, &near_mvs[vcnt], ref_frame_sign_bias);
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
near_ref[vcnt] = cpi->lf_ref_frame[mb_offset];
}
vcnt++;
// above in last frame
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
if (cpi->lf_ref_frame[mb_offset - xd->mode_info_stride-1] != INTRA_FRAME)
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
{
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
near_mvs[vcnt].as_int = cpi->lfmv[mb_offset - xd->mode_info_stride-1].as_int;
Remove copies of same functions Reduce the code size. Change-Id: I2e1998557a3c8776e262c442fd758c25e17aff7a
2011-01-26 18:03:13 +01:00
mv_bias(cpi->lf_ref_frame_sign_bias[mb_offset - xd->mode_info_stride-1], refframe, &near_mvs[vcnt], ref_frame_sign_bias);
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
near_ref[vcnt] = cpi->lf_ref_frame[mb_offset - xd->mode_info_stride-1];
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
}
vcnt++;
// left in last frame
if (cpi->lf_ref_frame[mb_offset-1] != INTRA_FRAME)
{
near_mvs[vcnt].as_int = cpi->lfmv[mb_offset -1].as_int;
Remove copies of same functions Reduce the code size. Change-Id: I2e1998557a3c8776e262c442fd758c25e17aff7a
2011-01-26 18:03:13 +01:00
mv_bias(cpi->lf_ref_frame_sign_bias[mb_offset -1], refframe, &near_mvs[vcnt], ref_frame_sign_bias);
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
near_ref[vcnt] = cpi->lf_ref_frame[mb_offset - 1];
}
vcnt++;
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
// right in last frame
if (cpi->lf_ref_frame[mb_offset +1] != INTRA_FRAME)
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
{
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
near_mvs[vcnt].as_int = cpi->lfmv[mb_offset +1].as_int;
Remove copies of same functions Reduce the code size. Change-Id: I2e1998557a3c8776e262c442fd758c25e17aff7a
2011-01-26 18:03:13 +01:00
mv_bias(cpi->lf_ref_frame_sign_bias[mb_offset +1], refframe, &near_mvs[vcnt], ref_frame_sign_bias);
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
near_ref[vcnt] = cpi->lf_ref_frame[mb_offset +1];
}
vcnt++;
// below in last frame
if (cpi->lf_ref_frame[mb_offset + xd->mode_info_stride +1] != INTRA_FRAME)
{
near_mvs[vcnt].as_int = cpi->lfmv[mb_offset + xd->mode_info_stride +1].as_int;
Remove copies of same functions Reduce the code size. Change-Id: I2e1998557a3c8776e262c442fd758c25e17aff7a
2011-01-26 18:03:13 +01:00
mv_bias(cpi->lf_ref_frame_sign_bias[mb_offset + xd->mode_info_stride +1], refframe, &near_mvs[vcnt], ref_frame_sign_bias);
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
near_ref[vcnt] = cpi->lf_ref_frame[mb_offset + xd->mode_info_stride +1];
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
}
vcnt++;
}
for(i=0; i< vcnt; i++)
{
if(near_ref[near_sadidx[i]] != INTRA_FRAME)
{
if(here->mbmi.ref_frame == near_ref[near_sadidx[i]])
{
mv.as_int = near_mvs[near_sadidx[i]].as_int;
find = 1;
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
if (i < 3)
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
*sr = 3;
else
*sr = 2;
break;
}
}
}
if(!find)
{
for(i=0; i<vcnt; i++)
{
mvx[i] = near_mvs[i].as_mv.row;
mvy[i] = near_mvs[i].as_mv.col;
}
Use insertion sort instead of quick sort Insertion sort performs better for sorting small arrays. In real- time encoding (speed=-5), test on test set showed 1.7% performance gain with 0% PSNR change in average. Change-Id: Ie02eaa6fed662866a937299194c590d41b25bc3d
2011-04-27 19:40:39 +02:00
insertsortmv(mvx, vcnt);
insertsortmv(mvy, vcnt);
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
mv.as_mv.row = mvx[vcnt/2];
mv.as_mv.col = mvy[vcnt/2];
find = 1;
//sr is set to 0 to allow calling function to decide the search range.
*sr = 0;
}
}
/* Set up return values */
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
mvp->as_int = mv.as_int;
vp8_clamp_mv2(mvp, xd);
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
}
Improve MV prediction in vp8_pick_inter_mode() for speed>3 Applied same method used in vp8_rd_pick_inter_mode() to improve the accuracy of MV prediction. Change-Id: Ia50ae26208b18482695601f32febd99fe89fbc17
2011-01-28 16:00:20 +01:00
void vp8_cal_sad(VP8_COMP *cpi, MACROBLOCKD *xd, MACROBLOCK *x, int recon_yoffset, int near_sadidx[])
{
int near_sad[8] = {0}; // 0-cf above, 1-cf left, 2-cf aboveleft, 3-lf current, 4-lf above, 5-lf left, 6-lf right, 7-lf below
Copy macroblock data to a buffer before encoding it I got this idea from Pascal (Thanks). Before encoding a macroblock, copy it to a 16x16 buffer, and then read source data from there instead. This will help keep the source data in cache, and help with the performance. Change-Id: Id05f4cb601299150511d59dcba0ae62c49b5b757
2011-06-23 19:54:02 +02:00
BLOCK *b = &x->block[0];
unsigned char *src_y_ptr = *(b->base_src);
Improve MV prediction in vp8_pick_inter_mode() for speed>3 Applied same method used in vp8_rd_pick_inter_mode() to improve the accuracy of MV prediction. Change-Id: Ia50ae26208b18482695601f32febd99fe89fbc17
2011-01-28 16:00:20 +01:00
//calculate sad for current frame 3 nearby MBs.
if( xd->mb_to_top_edge==0 && xd->mb_to_left_edge ==0)
{
near_sad[0] = near_sad[1] = near_sad[2] = INT_MAX;
}else if(xd->mb_to_top_edge==0)
{ //only has left MB for sad calculation.
near_sad[0] = near_sad[2] = INT_MAX;
Copy macroblock data to a buffer before encoding it I got this idea from Pascal (Thanks). Before encoding a macroblock, copy it to a 16x16 buffer, and then read source data from there instead. This will help keep the source data in cache, and help with the performance. Change-Id: Id05f4cb601299150511d59dcba0ae62c49b5b757
2011-06-23 19:54:02 +02:00
near_sad[1] = cpi->fn_ptr[BLOCK_16X16].sdf(src_y_ptr, b->src_stride, xd->dst.y_buffer - 16,xd->dst.y_stride, 0x7fffffff);
Improve MV prediction in vp8_pick_inter_mode() for speed>3 Applied same method used in vp8_rd_pick_inter_mode() to improve the accuracy of MV prediction. Change-Id: Ia50ae26208b18482695601f32febd99fe89fbc17
2011-01-28 16:00:20 +01:00
}else if(xd->mb_to_left_edge ==0)
{ //only has left MB for sad calculation.
near_sad[1] = near_sad[2] = INT_MAX;
Copy macroblock data to a buffer before encoding it I got this idea from Pascal (Thanks). Before encoding a macroblock, copy it to a 16x16 buffer, and then read source data from there instead. This will help keep the source data in cache, and help with the performance. Change-Id: Id05f4cb601299150511d59dcba0ae62c49b5b757
2011-06-23 19:54:02 +02:00
near_sad[0] = cpi->fn_ptr[BLOCK_16X16].sdf(src_y_ptr, b->src_stride, xd->dst.y_buffer - xd->dst.y_stride *16,xd->dst.y_stride, 0x7fffffff);
Improve MV prediction in vp8_pick_inter_mode() for speed>3 Applied same method used in vp8_rd_pick_inter_mode() to improve the accuracy of MV prediction. Change-Id: Ia50ae26208b18482695601f32febd99fe89fbc17
2011-01-28 16:00:20 +01:00
}else
{
Copy macroblock data to a buffer before encoding it I got this idea from Pascal (Thanks). Before encoding a macroblock, copy it to a 16x16 buffer, and then read source data from there instead. This will help keep the source data in cache, and help with the performance. Change-Id: Id05f4cb601299150511d59dcba0ae62c49b5b757
2011-06-23 19:54:02 +02:00
near_sad[0] = cpi->fn_ptr[BLOCK_16X16].sdf(src_y_ptr, b->src_stride, xd->dst.y_buffer - xd->dst.y_stride *16,xd->dst.y_stride, 0x7fffffff);
near_sad[1] = cpi->fn_ptr[BLOCK_16X16].sdf(src_y_ptr, b->src_stride, xd->dst.y_buffer - 16,xd->dst.y_stride, 0x7fffffff);
near_sad[2] = cpi->fn_ptr[BLOCK_16X16].sdf(src_y_ptr, b->src_stride, xd->dst.y_buffer - xd->dst.y_stride *16 -16,xd->dst.y_stride, 0x7fffffff);
Improve MV prediction in vp8_pick_inter_mode() for speed>3 Applied same method used in vp8_rd_pick_inter_mode() to improve the accuracy of MV prediction. Change-Id: Ia50ae26208b18482695601f32febd99fe89fbc17
2011-01-28 16:00:20 +01:00
}
if(cpi->common.last_frame_type != KEY_FRAME)
{
//calculate sad for last frame 5 nearby MBs.
unsigned char *pre_y_buffer = cpi->common.yv12_fb[cpi->common.lst_fb_idx].y_buffer + recon_yoffset;
int pre_y_stride = cpi->common.yv12_fb[cpi->common.lst_fb_idx].y_stride;
if(xd->mb_to_top_edge==0) near_sad[4] = INT_MAX;
if(xd->mb_to_left_edge ==0) near_sad[5] = INT_MAX;
if(xd->mb_to_right_edge ==0) near_sad[6] = INT_MAX;
if(xd->mb_to_bottom_edge==0) near_sad[7] = INT_MAX;
if(near_sad[4] != INT_MAX)
Copy macroblock data to a buffer before encoding it I got this idea from Pascal (Thanks). Before encoding a macroblock, copy it to a 16x16 buffer, and then read source data from there instead. This will help keep the source data in cache, and help with the performance. Change-Id: Id05f4cb601299150511d59dcba0ae62c49b5b757
2011-06-23 19:54:02 +02:00
near_sad[4] = cpi->fn_ptr[BLOCK_16X16].sdf(src_y_ptr, b->src_stride, pre_y_buffer - pre_y_stride *16, pre_y_stride, 0x7fffffff);
Improve MV prediction in vp8_pick_inter_mode() for speed>3 Applied same method used in vp8_rd_pick_inter_mode() to improve the accuracy of MV prediction. Change-Id: Ia50ae26208b18482695601f32febd99fe89fbc17
2011-01-28 16:00:20 +01:00
if(near_sad[5] != INT_MAX)
Copy macroblock data to a buffer before encoding it I got this idea from Pascal (Thanks). Before encoding a macroblock, copy it to a 16x16 buffer, and then read source data from there instead. This will help keep the source data in cache, and help with the performance. Change-Id: Id05f4cb601299150511d59dcba0ae62c49b5b757
2011-06-23 19:54:02 +02:00
near_sad[5] = cpi->fn_ptr[BLOCK_16X16].sdf(src_y_ptr, b->src_stride, pre_y_buffer - 16, pre_y_stride, 0x7fffffff);
near_sad[3] = cpi->fn_ptr[BLOCK_16X16].sdf(src_y_ptr, b->src_stride, pre_y_buffer, pre_y_stride, 0x7fffffff);
Improve MV prediction in vp8_pick_inter_mode() for speed>3 Applied same method used in vp8_rd_pick_inter_mode() to improve the accuracy of MV prediction. Change-Id: Ia50ae26208b18482695601f32febd99fe89fbc17
2011-01-28 16:00:20 +01:00
if(near_sad[6] != INT_MAX)
Copy macroblock data to a buffer before encoding it I got this idea from Pascal (Thanks). Before encoding a macroblock, copy it to a 16x16 buffer, and then read source data from there instead. This will help keep the source data in cache, and help with the performance. Change-Id: Id05f4cb601299150511d59dcba0ae62c49b5b757
2011-06-23 19:54:02 +02:00
near_sad[6] = cpi->fn_ptr[BLOCK_16X16].sdf(src_y_ptr, b->src_stride, pre_y_buffer + 16, pre_y_stride, 0x7fffffff);
Improve MV prediction in vp8_pick_inter_mode() for speed>3 Applied same method used in vp8_rd_pick_inter_mode() to improve the accuracy of MV prediction. Change-Id: Ia50ae26208b18482695601f32febd99fe89fbc17
2011-01-28 16:00:20 +01:00
if(near_sad[7] != INT_MAX)
Copy macroblock data to a buffer before encoding it I got this idea from Pascal (Thanks). Before encoding a macroblock, copy it to a 16x16 buffer, and then read source data from there instead. This will help keep the source data in cache, and help with the performance. Change-Id: Id05f4cb601299150511d59dcba0ae62c49b5b757
2011-06-23 19:54:02 +02:00
near_sad[7] = cpi->fn_ptr[BLOCK_16X16].sdf(src_y_ptr, b->src_stride, pre_y_buffer + pre_y_stride *16, pre_y_stride, 0x7fffffff);
Improve MV prediction in vp8_pick_inter_mode() for speed>3 Applied same method used in vp8_rd_pick_inter_mode() to improve the accuracy of MV prediction. Change-Id: Ia50ae26208b18482695601f32febd99fe89fbc17
2011-01-28 16:00:20 +01:00
}
if(cpi->common.last_frame_type != KEY_FRAME)
{
Use insertion sort instead of quick sort Insertion sort performs better for sorting small arrays. In real- time encoding (speed=-5), test on test set showed 1.7% performance gain with 0% PSNR change in average. Change-Id: Ie02eaa6fed662866a937299194c590d41b25bc3d
2011-04-27 19:40:39 +02:00
insertsortsad(near_sad, near_sadidx, 8);
Improve MV prediction in vp8_pick_inter_mode() for speed>3 Applied same method used in vp8_rd_pick_inter_mode() to improve the accuracy of MV prediction. Change-Id: Ia50ae26208b18482695601f32febd99fe89fbc17
2011-01-28 16:00:20 +01:00
}else
{
Use insertion sort instead of quick sort Insertion sort performs better for sorting small arrays. In real- time encoding (speed=-5), test on test set showed 1.7% performance gain with 0% PSNR change in average. Change-Id: Ie02eaa6fed662866a937299194c590d41b25bc3d
2011-04-27 19:40:39 +02:00
insertsortsad(near_sad, near_sadidx, 3);
Improve MV prediction in vp8_pick_inter_mode() for speed>3 Applied same method used in vp8_rd_pick_inter_mode() to improve the accuracy of MV prediction. Change-Id: Ia50ae26208b18482695601f32febd99fe89fbc17
2011-01-28 16:00:20 +01:00
}
}
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
static void rd_update_mvcount(VP8_COMP *cpi, MACROBLOCK *x, int_mv *best_ref_mv)
Modify MVcount in pick_inter_mode to eliminate calling of vp8_find_near_mvs Moved MVcount modification in pick_inter_mode, and eliminated calling of vp8_find_near_mvs. Change-Id: Icd47448a1dfc8fdf526f86757d0e5a7f218cb5e8
2011-05-13 16:56:45 +02:00
{
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
if (x->e_mbd.mode_info_context->mbmi.mode == SPLITMV)
Modify MVcount in pick_inter_mode to eliminate calling of vp8_find_near_mvs Moved MVcount modification in pick_inter_mode, and eliminated calling of vp8_find_near_mvs. Change-Id: Icd47448a1dfc8fdf526f86757d0e5a7f218cb5e8
2011-05-13 16:56:45 +02:00
{
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
int i;
for (i = 0; i < x->partition_info->count; i++)
Modify MVcount in pick_inter_mode to eliminate calling of vp8_find_near_mvs Moved MVcount modification in pick_inter_mode, and eliminated calling of vp8_find_near_mvs. Change-Id: Icd47448a1dfc8fdf526f86757d0e5a7f218cb5e8
2011-05-13 16:56:45 +02:00
{
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
if (x->partition_info->bmi[i].mode == NEW4X4)
Modify MVcount in pick_inter_mode to eliminate calling of vp8_find_near_mvs Moved MVcount modification in pick_inter_mode, and eliminated calling of vp8_find_near_mvs. Change-Id: Icd47448a1dfc8fdf526f86757d0e5a7f218cb5e8
2011-05-13 16:56:45 +02:00
{
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
cpi->MVcount[0][mv_max+((x->partition_info->bmi[i].mv.as_mv.row
- best_ref_mv->as_mv.row) >> 1)]++;
cpi->MVcount[1][mv_max+((x->partition_info->bmi[i].mv.as_mv.col
- best_ref_mv->as_mv.col) >> 1)]++;
Modify MVcount in pick_inter_mode to eliminate calling of vp8_find_near_mvs Moved MVcount modification in pick_inter_mode, and eliminated calling of vp8_find_near_mvs. Change-Id: Icd47448a1dfc8fdf526f86757d0e5a7f218cb5e8
2011-05-13 16:56:45 +02:00
}
}
}
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
else if (x->e_mbd.mode_info_context->mbmi.mode == NEWMV)
Modify MVcount in pick_inter_mode to eliminate calling of vp8_find_near_mvs Moved MVcount modification in pick_inter_mode, and eliminated calling of vp8_find_near_mvs. Change-Id: Icd47448a1dfc8fdf526f86757d0e5a7f218cb5e8
2011-05-13 16:56:45 +02:00
{
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
cpi->MVcount[0][mv_max+((x->e_mbd.mode_info_context->mbmi.mv.as_mv.row
- best_ref_mv->as_mv.row) >> 1)]++;
cpi->MVcount[1][mv_max+((x->e_mbd.mode_info_context->mbmi.mv.as_mv.col
- best_ref_mv->as_mv.col) >> 1)]++;
Modify MVcount in pick_inter_mode to eliminate calling of vp8_find_near_mvs Moved MVcount modification in pick_inter_mode, and eliminated calling of vp8_find_near_mvs. Change-Id: Icd47448a1dfc8fdf526f86757d0e5a7f218cb5e8
2011-05-13 16:56:45 +02:00
}
}
rdopt/pickinter: factor out some common setup Add new get_predictor_pointers() and get_reference_search_order() functions for code shared between the two implementations. Change-Id: I1ebe76aa8f168b1f5cfabc00d05d8f19a0d4d207
2012-01-11 23:38:58 +01:00
Only call vp8_find_near_mvs() once for each macroblock While doing motion search on a macroblock, we usually call vp8_find_near_mvs once per reference frame. Actually, for different reference frames, the only difference in calculating these near_mvs is they may have different sign_bias, which causes a sign change in resulting near_mvs. In this change, we only do find_near_mvs for the first reference frame. For other reference frames, only need to adjust the near_mvs according to that reference frame's sign_bias value. Change-Id: I661394b49c6ad79fed7d0f2eb2be239b9c56f149
2011-12-14 21:35:04 +01:00
void vp8_rd_pick_inter_mode(VP8_COMP *cpi, MACROBLOCK *x, int recon_yoffset,
int recon_uvoffset, int *returnrate,
int *returndistortion, int *returnintra)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
BLOCK *b = &x->block[0];
BLOCKD *d = &x->e_mbd.block[0];
MACROBLOCKD *xd = &x->e_mbd;
Removed B_MODE_INFO Declared the bmi in BLOCKD as a union instead of B_MODE_INFO. Then removed B_MODE_INFO completely. Change-Id: Ieb7469899e265892c66f7aeac87b7f2bf38e7a67
2011-06-02 19:46:41 +02:00
union b_mode_info best_bmodes[16];
Initial WebM release
2010-05-18 17:58:33 +02:00
MB_MODE_INFO best_mbmode;
Reduced the size of MB_MODE_INFO Moved partition_bmi and partition_count out of MB_MODE_INFO and placed into MACROBLOCK. Also reduced the size of other members of the MB_MODE_INFO struct. For 1080p, the memory was reduced by 1,209,516 bytes. The decoder performance appeared to improve by 3% for the clip used. Note: The main goal for this change is to improve the decoder performance. The encoder will be revisited at a later date for further structure cleanup. Change-Id: I4733621292ee9cc3fffa4046cb3fd4d99bd14613
2010-09-02 22:17:52 +02:00
PARTITION_INFO best_partition;
Correct clamping in use of vp8_find_near_mvs() Commit e06c242ba introduced a change to call vp8_find_near_mvs() only once instead of once per reference frame by observing that the only effect that the frame had was on the bias applied to the motion vector. By keeping track of the sign_bias value, the mv to use could be flip-flopped by multiplying its components by -1. This behavior was subtley wrong in the case when clamping was applied to the motion vectors found by vp8_find_near_mvs(). A motion vector could be in-bounds with one sign bias, but out of bounds after inverting the sign, or vice versa. The clamping must match that done by the decoder. This change modifies vp8_find_near_mvs() to remove the clamping from that function. The vp8_pick_inter_mode() and vp8_rd_pick_inter_mode() functions instead track the correctly clamped values for both bias values, switching between them by simple assignment. The common clamping and inversion code is in vp8_find_near_mvs_bias() Change-Id: I17e1a348d1643497eca0be232e2fbe2acf8478e1
2012-01-25 23:55:49 +01:00
int_mv best_ref_mv_sb[2];
int_mv mode_mv_sb[2][MB_MODE_COUNT];
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
int_mv best_ref_mv;
Correct clamping in use of vp8_find_near_mvs() Commit e06c242ba introduced a change to call vp8_find_near_mvs() only once instead of once per reference frame by observing that the only effect that the frame had was on the bias applied to the motion vector. By keeping track of the sign_bias value, the mv to use could be flip-flopped by multiplying its components by -1. This behavior was subtley wrong in the case when clamping was applied to the motion vectors found by vp8_find_near_mvs(). A motion vector could be in-bounds with one sign bias, but out of bounds after inverting the sign, or vice versa. The clamping must match that done by the decoder. This change modifies vp8_find_near_mvs() to remove the clamping from that function. The vp8_pick_inter_mode() and vp8_rd_pick_inter_mode() functions instead track the correctly clamped values for both bias values, switching between them by simple assignment. The common clamping and inversion code is in vp8_find_near_mvs_bias() Change-Id: I17e1a348d1643497eca0be232e2fbe2acf8478e1
2012-01-25 23:55:49 +01:00
int_mv *mode_mv;
Initial WebM release
2010-05-18 17:58:33 +02:00
MB_PREDICTION_MODE this_mode;
int num00;
int best_mode_index = 0;
int i;
int mode_index;
int mdcounts[4];
int rate;
int distortion;
Error accumulator stats bug. The error accumulator stats values cpi->prediction_error and cpi->intra_error were being populated with rd values not distortion values. These are only "currently" used in a limited way for RT compress key frame detection. Change-Id: I2702ba1cab6e49ab8dc096ba75b6b34ab3573021
2011-04-08 15:21:36 +02:00
int best_rd = INT_MAX;
int best_intra_rd = INT_MAX;
Initial WebM release
2010-05-18 17:58:33 +02:00
int rate2, distortion2;
int uv_intra_rate, uv_intra_distortion, uv_intra_rate_tokenonly;
Fix incorrect use of uv eobs in intra modes In vp8_rd_pick_inter_mode(), if total of eobs is zero, rate needs to be adjusted since there are no non-zero coefficients for transmission. The uv intra eobs calculated in rd_pick_intra_mbuv_mode() need to be saved before they are overwritten by inter-mode eobs. Change-Id: I41dd04fba912e8122ef95793d4d98a251bc60e58
2012-02-17 15:15:08 +01:00
int uv_intra_tteob = 0;
Initial WebM release
2010-05-18 17:58:33 +02:00
int rate_y, UNINITIALIZED_IS_SAFE(rate_uv);
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
int distortion_uv;
int best_yrd = INT_MAX;
Initial WebM release
2010-05-18 17:58:33 +02:00
MB_PREDICTION_MODE uv_intra_mode;
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
int_mv mvp;
Refine motion vector prediction for NEWMV mode Adjust checking points in motion vector prediction to better cover possible movements, and get a better prediction. Tests on test clips showed a 0.1% improvement in SSIM, and no change in PSNR and performance. Change-Id: Ifdab05d35e10faea1445c61bb73debf888c9d2f8
2011-01-25 21:54:34 +01:00
int near_sadidx[8] = {0, 1, 2, 3, 4, 5, 6, 7};
Improve MV prediction accuracy to achieve performance gain Add vp8_mv_pred() to better predict starting MV for NEWMV mode in vp8_rd_pick_inter_mode(). Set different search ranges according to MV prediction accuracy, which improves encoder performance without hurting the quality. Also, as Yaowu suggested, using diamond search result as full search starting point and therefore adjusting(reducing) full search range helps the performance. Change-Id: Ie4a3c8df87e697c1f4f6e2ddb693766bba1b77b6
2010-12-03 17:26:21 +01:00
int saddone=0;
int sr=0; //search range got from mv_pred(). It uses step_param levels. (0-7)
rdopt/pickinter: factor out some common setup Add new get_predictor_pointers() and get_reference_search_order() functions for code shared between the two implementations. Change-Id: I1ebe76aa8f168b1f5cfabc00d05d8f19a0d4d207
2012-01-11 23:38:58 +01:00
unsigned char *plane[4][3];
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
int ref_frame_map[4];
Only call vp8_find_near_mvs() once for each macroblock While doing motion search on a macroblock, we usually call vp8_find_near_mvs once per reference frame. Actually, for different reference frames, the only difference in calculating these near_mvs is they may have different sign_bias, which causes a sign change in resulting near_mvs. In this change, we only do find_near_mvs for the first reference frame. For other reference frames, only need to adjust the near_mvs according to that reference frame's sign_bias value. Change-Id: I661394b49c6ad79fed7d0f2eb2be239b9c56f149
2011-12-14 21:35:04 +01:00
int sign_bias = 0;
Moved ref frame calculations Moved ref frame calculations to outside of the mode_index loop. Change-Id: I06103fc7e8af88b54b84443acf6691d29b1272ac
2011-01-11 21:00:00 +01:00
Correct clamping in use of vp8_find_near_mvs() Commit e06c242ba introduced a change to call vp8_find_near_mvs() only once instead of once per reference frame by observing that the only effect that the frame had was on the bias applied to the motion vector. By keeping track of the sign_bias value, the mv to use could be flip-flopped by multiplying its components by -1. This behavior was subtley wrong in the case when clamping was applied to the motion vectors found by vp8_find_near_mvs(). A motion vector could be in-bounds with one sign bias, but out of bounds after inverting the sign, or vice versa. The clamping must match that done by the decoder. This change modifies vp8_find_near_mvs() to remove the clamping from that function. The vp8_pick_inter_mode() and vp8_rd_pick_inter_mode() functions instead track the correctly clamped values for both bias values, switching between them by simple assignment. The common clamping and inversion code is in vp8_find_near_mvs_bias() Change-Id: I17e1a348d1643497eca0be232e2fbe2acf8478e1
2012-01-25 23:55:49 +01:00
mode_mv = mode_mv_sb[sign_bias];
best_ref_mv.as_int = 0;
vpx_memset(mode_mv_sb, 0, sizeof(mode_mv_sb));
Moved ref frame calculations Moved ref frame calculations to outside of the mode_index loop. Change-Id: I06103fc7e8af88b54b84443acf6691d29b1272ac
2011-01-11 21:00:00 +01:00
vpx_memset(&best_mbmode, 0, sizeof(best_mbmode));
Removed B_MODE_INFO Declared the bmi in BLOCKD as a union instead of B_MODE_INFO. Then removed B_MODE_INFO completely. Change-Id: Ieb7469899e265892c66f7aeac87b7f2bf38e7a67
2011-06-02 19:46:41 +02:00
vpx_memset(&best_bmodes, 0, sizeof(best_bmodes));
Moved ref frame calculations Moved ref frame calculations to outside of the mode_index loop. Change-Id: I06103fc7e8af88b54b84443acf6691d29b1272ac
2011-01-11 21:00:00 +01:00
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
/* Setup search priorities */
rdopt/pickinter: factor out some common setup Add new get_predictor_pointers() and get_reference_search_order() functions for code shared between the two implementations. Change-Id: I1ebe76aa8f168b1f5cfabc00d05d8f19a0d4d207
2012-01-11 23:38:58 +01:00
get_reference_search_order(cpi, ref_frame_map);
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
Only call vp8_find_near_mvs() once for each macroblock While doing motion search on a macroblock, we usually call vp8_find_near_mvs once per reference frame. Actually, for different reference frames, the only difference in calculating these near_mvs is they may have different sign_bias, which causes a sign change in resulting near_mvs. In this change, we only do find_near_mvs for the first reference frame. For other reference frames, only need to adjust the near_mvs according to that reference frame's sign_bias value. Change-Id: I661394b49c6ad79fed7d0f2eb2be239b9c56f149
2011-12-14 21:35:04 +01:00
/* Check to see if there is at least 1 valid reference frame that we need
* to calculate near_mvs.
*/
if (ref_frame_map[1] > 0)
{
Correct clamping in use of vp8_find_near_mvs() Commit e06c242ba introduced a change to call vp8_find_near_mvs() only once instead of once per reference frame by observing that the only effect that the frame had was on the bias applied to the motion vector. By keeping track of the sign_bias value, the mv to use could be flip-flopped by multiplying its components by -1. This behavior was subtley wrong in the case when clamping was applied to the motion vectors found by vp8_find_near_mvs(). A motion vector could be in-bounds with one sign bias, but out of bounds after inverting the sign, or vice versa. The clamping must match that done by the decoder. This change modifies vp8_find_near_mvs() to remove the clamping from that function. The vp8_pick_inter_mode() and vp8_rd_pick_inter_mode() functions instead track the correctly clamped values for both bias values, switching between them by simple assignment. The common clamping and inversion code is in vp8_find_near_mvs_bias() Change-Id: I17e1a348d1643497eca0be232e2fbe2acf8478e1
2012-01-25 23:55:49 +01:00
sign_bias = vp8_find_near_mvs_bias(&x->e_mbd,
x->e_mbd.mode_info_context,
mode_mv_sb,
best_ref_mv_sb,
mdcounts,
ref_frame_map[1],
cpi->common.ref_frame_sign_bias);
mode_mv = mode_mv_sb[sign_bias];
best_ref_mv.as_int = best_ref_mv_sb[sign_bias].as_int;
Only call vp8_find_near_mvs() once for each macroblock While doing motion search on a macroblock, we usually call vp8_find_near_mvs once per reference frame. Actually, for different reference frames, the only difference in calculating these near_mvs is they may have different sign_bias, which causes a sign change in resulting near_mvs. In this change, we only do find_near_mvs for the first reference frame. For other reference frames, only need to adjust the near_mvs according to that reference frame's sign_bias value. Change-Id: I661394b49c6ad79fed7d0f2eb2be239b9c56f149
2011-12-14 21:35:04 +01:00
}
rdopt/pickinter: factor out some common setup Add new get_predictor_pointers() and get_reference_search_order() functions for code shared between the two implementations. Change-Id: I1ebe76aa8f168b1f5cfabc00d05d8f19a0d4d207
2012-01-11 23:38:58 +01:00
get_predictor_pointers(cpi, plane, recon_yoffset, recon_uvoffset);
Moved ref frame calculations Moved ref frame calculations to outside of the mode_index loop. Change-Id: I06103fc7e8af88b54b84443acf6691d29b1272ac
2011-01-11 21:00:00 +01:00
*returnintra = INT_MAX;
Initial WebM release
2010-05-18 17:58:33 +02:00
cpi->mbs_tested_so_far++; // Count of the number of MBs tested so far this frame
x->skip = 0;
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
x->e_mbd.mode_info_context->mbmi.ref_frame = INTRA_FRAME;
Move RD intra block mode selection to rdopt.c This change is analogous to I0b67dae1f8a74902378da7bdf565e39ab832dda7, which made the move for the non-RD path. Change-Id: If63fc1b0cd1eb7f932e710f83ff24d91454f8ed1
2011-06-08 18:05:05 +02:00
rd_pick_intra_mbuv_mode(cpi, x, &uv_intra_rate, &uv_intra_rate_tokenonly, &uv_intra_distortion);
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
uv_intra_mode = x->e_mbd.mode_info_context->mbmi.uv_mode;
Fix incorrect use of uv eobs in intra modes In vp8_rd_pick_inter_mode(), if total of eobs is zero, rate needs to be adjusted since there are no non-zero coefficients for transmission. The uv intra eobs calculated in rd_pick_intra_mbuv_mode() need to be saved before they are overwritten by inter-mode eobs. Change-Id: I41dd04fba912e8122ef95793d4d98a251bc60e58
2012-02-17 15:15:08 +01:00
/*
* Total of the eobs is used later to further adjust rate2. Since uv block's
* intra eobs will be overwritten when we check inter modes in following
* for-loop, we need to save uv_intra_tteob here.
*/
for (i = 16; i < 24; i++)
uv_intra_tteob += x->e_mbd.eobs[i];
Initial WebM release
2010-05-18 17:58:33 +02:00
for (mode_index = 0; mode_index < MAX_MODES; mode_index++)
{
int this_rd = INT_MAX;
int disable_skip = 0;
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
int other_cost = 0;
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
int this_ref_frame = ref_frame_map[vp8_ref_frame_order[mode_index]];
Initial WebM release
2010-05-18 17:58:33 +02:00
// Test best rd so far against threshold for trying this mode.
if (best_rd <= cpi->rd_threshes[mode_index])
continue;
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
if (this_ref_frame < 0)
continue;
Initial WebM release
2010-05-18 17:58:33 +02:00
// These variables hold are rolling total cost and distortion for this mode
rate2 = 0;
distortion2 = 0;
this_mode = vp8_mode_order[mode_index];
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
x->e_mbd.mode_info_context->mbmi.mode = this_mode;
x->e_mbd.mode_info_context->mbmi.uv_mode = DC_PRED;
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
x->e_mbd.mode_info_context->mbmi.ref_frame = this_ref_frame;
Initial WebM release
2010-05-18 17:58:33 +02:00
Experimental change to help with ARNR problem. Allow use of other reference frames for the ARF overlay frame when ARNR filtering is enabled Change-Id: Icd6a9fb38977a88fbe7cc9b9c18198eb454c0273
2011-01-14 13:07:12 +01:00
// Only consider ZEROMV/ALTREF_FRAME for alt ref frame,
// unless ARNR filtering is enabled in which case we want
// an unfiltered alternative
Testing of modes with Alt Ref frame Previously when a frame was being overlaid on a previously coded alt ref frame we only checked the alt ref 0,0 mode. Where there is a possibility that the alt ref buffer is a filtered frame we should allow the other prediction modes as normal or at the least allow use of the last frame buffer. Change-Id: I4d6227223d125c96b4f3066ec6ec9484fee7768c
2011-01-14 15:52:15 +01:00
if (cpi->is_src_frame_alt_ref && (cpi->oxcf.arnr_max_frames == 0))
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
if (this_mode != ZEROMV || x->e_mbd.mode_info_context->mbmi.ref_frame != ALTREF_FRAME)
Initial WebM release
2010-05-18 17:58:33 +02:00
continue;
}
Moved ref frame calculations Moved ref frame calculations to outside of the mode_index loop. Change-Id: I06103fc7e8af88b54b84443acf6691d29b1272ac
2011-01-11 21:00:00 +01:00
/* everything but intra */
if (x->e_mbd.mode_info_context->mbmi.ref_frame)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
rdopt/pickinter: factor out some common setup Add new get_predictor_pointers() and get_reference_search_order() functions for code shared between the two implementations. Change-Id: I1ebe76aa8f168b1f5cfabc00d05d8f19a0d4d207
2012-01-11 23:38:58 +01:00
x->e_mbd.pre.y_buffer = plane[this_ref_frame][0];
x->e_mbd.pre.u_buffer = plane[this_ref_frame][1];
x->e_mbd.pre.v_buffer = plane[this_ref_frame][2];
Only call vp8_find_near_mvs() once for each macroblock While doing motion search on a macroblock, we usually call vp8_find_near_mvs once per reference frame. Actually, for different reference frames, the only difference in calculating these near_mvs is they may have different sign_bias, which causes a sign change in resulting near_mvs. In this change, we only do find_near_mvs for the first reference frame. For other reference frames, only need to adjust the near_mvs according to that reference frame's sign_bias value. Change-Id: I661394b49c6ad79fed7d0f2eb2be239b9c56f149
2011-12-14 21:35:04 +01:00
Correct clamping in use of vp8_find_near_mvs() Commit e06c242ba introduced a change to call vp8_find_near_mvs() only once instead of once per reference frame by observing that the only effect that the frame had was on the bias applied to the motion vector. By keeping track of the sign_bias value, the mv to use could be flip-flopped by multiplying its components by -1. This behavior was subtley wrong in the case when clamping was applied to the motion vectors found by vp8_find_near_mvs(). A motion vector could be in-bounds with one sign bias, but out of bounds after inverting the sign, or vice versa. The clamping must match that done by the decoder. This change modifies vp8_find_near_mvs() to remove the clamping from that function. The vp8_pick_inter_mode() and vp8_rd_pick_inter_mode() functions instead track the correctly clamped values for both bias values, switching between them by simple assignment. The common clamping and inversion code is in vp8_find_near_mvs_bias() Change-Id: I17e1a348d1643497eca0be232e2fbe2acf8478e1
2012-01-25 23:55:49 +01:00
if (sign_bias != cpi->common.ref_frame_sign_bias[this_ref_frame])
Only call vp8_find_near_mvs() once for each macroblock While doing motion search on a macroblock, we usually call vp8_find_near_mvs once per reference frame. Actually, for different reference frames, the only difference in calculating these near_mvs is they may have different sign_bias, which causes a sign change in resulting near_mvs. In this change, we only do find_near_mvs for the first reference frame. For other reference frames, only need to adjust the near_mvs according to that reference frame's sign_bias value. Change-Id: I661394b49c6ad79fed7d0f2eb2be239b9c56f149
2011-12-14 21:35:04 +01:00
{
Correct clamping in use of vp8_find_near_mvs() Commit e06c242ba introduced a change to call vp8_find_near_mvs() only once instead of once per reference frame by observing that the only effect that the frame had was on the bias applied to the motion vector. By keeping track of the sign_bias value, the mv to use could be flip-flopped by multiplying its components by -1. This behavior was subtley wrong in the case when clamping was applied to the motion vectors found by vp8_find_near_mvs(). A motion vector could be in-bounds with one sign bias, but out of bounds after inverting the sign, or vice versa. The clamping must match that done by the decoder. This change modifies vp8_find_near_mvs() to remove the clamping from that function. The vp8_pick_inter_mode() and vp8_rd_pick_inter_mode() functions instead track the correctly clamped values for both bias values, switching between them by simple assignment. The common clamping and inversion code is in vp8_find_near_mvs_bias() Change-Id: I17e1a348d1643497eca0be232e2fbe2acf8478e1
2012-01-25 23:55:49 +01:00
sign_bias = cpi->common.ref_frame_sign_bias[this_ref_frame];
mode_mv = mode_mv_sb[sign_bias];
best_ref_mv.as_int = best_ref_mv_sb[sign_bias].as_int;
Only call vp8_find_near_mvs() once for each macroblock While doing motion search on a macroblock, we usually call vp8_find_near_mvs once per reference frame. Actually, for different reference frames, the only difference in calculating these near_mvs is they may have different sign_bias, which causes a sign change in resulting near_mvs. In this change, we only do find_near_mvs for the first reference frame. For other reference frames, only need to adjust the near_mvs according to that reference frame's sign_bias value. Change-Id: I661394b49c6ad79fed7d0f2eb2be239b9c56f149
2011-12-14 21:35:04 +01:00
}
Initial WebM release
2010-05-18 17:58:33 +02:00
}
// Check to see if the testing frequency for this mode is at its max
// If so then prevent it from being tested and increase the threshold for its testing
if (cpi->mode_test_hit_counts[mode_index] && (cpi->mode_check_freq[mode_index] > 1))
{
if (cpi->mbs_tested_so_far <= cpi->mode_check_freq[mode_index] * cpi->mode_test_hit_counts[mode_index])
{
// Increase the threshold for coding this mode to make it less likely to be chosen
cpi->rd_thresh_mult[mode_index] += 4;
if (cpi->rd_thresh_mult[mode_index] > MAX_THRESHMULT)
cpi->rd_thresh_mult[mode_index] = MAX_THRESHMULT;
cpi->rd_threshes[mode_index] = (cpi->rd_baseline_thresh[mode_index] >> 7) * cpi->rd_thresh_mult[mode_index];
continue;
}
}
// We have now reached the point where we are going to test the current mode so increment the counter for the number of times it has been tested
cpi->mode_test_hit_counts[mode_index] ++;
// Experimental code. Special case for gf and arf zeromv modes. Increase zbin size to supress noise
if (cpi->zbin_mode_boost_enabled)
{
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
if ( this_ref_frame == INTRA_FRAME )
Initial WebM release
2010-05-18 17:58:33 +02:00
cpi->zbin_mode_boost = 0;
Tuning for the more exact quantizer. Small changes to the default zero bin and rounding tables. Though the tables are currently the same for the Y1 and Y2 cases I have left them as separate tables in case we want to tune this later. There is now some adjustment of the zbin based on the prediction mode. Previously this was restricted to an adjustment for gf/arf 0,0 MV. The exact quantizer now marginal outperforms and is the default. The overall average gain is about 0.5% Change-Id: I5e4353f3d5326dde4e86823684b236a1e9ea7f47
2010-11-08 16:28:54 +01:00
else
{
if (vp8_mode_order[mode_index] == ZEROMV)
{
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
if (this_ref_frame != LAST_FRAME)
Tuning for the more exact quantizer. Small changes to the default zero bin and rounding tables. Though the tables are currently the same for the Y1 and Y2 cases I have left them as separate tables in case we want to tune this later. There is now some adjustment of the zbin based on the prediction mode. Previously this was restricted to an adjustment for gf/arf 0,0 MV. The exact quantizer now marginal outperforms and is the default. The overall average gain is about 0.5% Change-Id: I5e4353f3d5326dde4e86823684b236a1e9ea7f47
2010-11-08 16:28:54 +01:00
cpi->zbin_mode_boost = GF_ZEROMV_ZBIN_BOOST;
else
cpi->zbin_mode_boost = LF_ZEROMV_ZBIN_BOOST;
}
correct zbin boost for splitmv mode Disable zbin boost in SPLITMV mode as intended. Was incorrectly looking at vp8_ref_frame_order instead of vp8_mode_order when comparing against SPLITMV. This condition should have always been false, as SPLITMV is not in the range of valid reference frames. Change-Id: I0408cc7595eff68f00efef6d008e79f5b60d14bf
2011-03-08 02:58:37 +01:00
else if (vp8_mode_order[mode_index] == SPLITMV)
Tuning for the more exact quantizer. Small changes to the default zero bin and rounding tables. Though the tables are currently the same for the Y1 and Y2 cases I have left them as separate tables in case we want to tune this later. There is now some adjustment of the zbin based on the prediction mode. Previously this was restricted to an adjustment for gf/arf 0,0 MV. The exact quantizer now marginal outperforms and is the default. The overall average gain is about 0.5% Change-Id: I5e4353f3d5326dde4e86823684b236a1e9ea7f47
2010-11-08 16:28:54 +01:00
cpi->zbin_mode_boost = 0;
else
cpi->zbin_mode_boost = MV_ZBIN_BOOST;
}
Initial WebM release
2010-05-18 17:58:33 +02:00
Added vp8_update_zbin_extra vp8cx_mb_init_quantizer was being called for every mode checked in vp8_rd_pick_inter_mode. zbin_extra is the only value that really needs to be recalculated. This calculation is disabled when using the fast quantizer for mode selection. This gave a small performance boost (~.5% to 1%). Note: This needs to be verified with segmentation_enabled. Change-Id: I62716a870b3c82b4a998bdf95130ff0b02106f1e
2010-12-29 20:30:57 +01:00
vp8_update_zbin_extra(cpi, x);
Initial WebM release
2010-05-18 17:58:33 +02:00
}
switch (this_mode)
{
case B_PRED:
Added early breakout for vp8_rd_pick_intra4x4mby_modes Improved performance of good quality, speed 0 (3% average) with no average quality loss. Change-Id: Ica34473f99bd74260eaebde6b132185e09e3c09d
2011-02-08 22:50:43 +01:00
{
int tmp_rd;
Initial WebM release
2010-05-18 17:58:33 +02:00
// Note the rate value returned here includes the cost of coding the BPRED mode : x->mbmode_cost[x->e_mbd.frame_type][BPRED];
Move RD intra block mode selection to rdopt.c This change is analogous to I0b67dae1f8a74902378da7bdf565e39ab832dda7, which made the move for the non-RD path. Change-Id: If63fc1b0cd1eb7f932e710f83ff24d91454f8ed1
2011-06-08 18:05:05 +02:00
tmp_rd = rd_pick_intra4x4mby_modes(cpi, x, &rate, &rate_y, &distortion, best_yrd);
Initial WebM release
2010-05-18 17:58:33 +02:00
rate2 += rate;
distortion2 += distortion;
Added early breakout for vp8_rd_pick_intra4x4mby_modes Improved performance of good quality, speed 0 (3% average) with no average quality loss. Change-Id: Ica34473f99bd74260eaebde6b132185e09e3c09d
2011-02-08 22:50:43 +01:00
if(tmp_rd < best_yrd)
{
rate2 += uv_intra_rate;
rate_uv = uv_intra_rate_tokenonly;
distortion2 += uv_intra_distortion;
distortion_uv = uv_intra_distortion;
}
else
{
this_rd = INT_MAX;
disable_skip = 1;
}
}
break;
Initial WebM release
2010-05-18 17:58:33 +02:00
case SPLITMV:
{
int tmp_rd;
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
int this_rd_thresh;
Initial WebM release
2010-05-18 17:58:33 +02:00
Speed selection support for disabled reference frames There was an implicit reference frame test order (typically LAST, GOLD, ARF) in the mode selection logic, but this doesn't provide the expected results when some reference frames are disabled. For instance, in real-time mode, the speed selection logic often disables the ARF modes. So if the user disables the LAST and GOLD frames, the encoder was always choosing INTRA, when in reality searching the ARF in this case has the same speed penalty as searching LAST would have had. Instead, introduce the notion of a reference frame search order. This patch preserves the former priorities, so if a frame is disabled, the other frames bump up a slot to take its place. This patch lays the groundwork for doing something smarter in the frame test order, for example considering temporal distance or looking at the frames used by nearby blocks. Change-Id: I1199149f8662a408537c653d2c021c7f1d29a700
2011-11-18 21:47:16 +01:00
this_rd_thresh = (vp8_ref_frame_order[mode_index] == 1) ? cpi->rd_threshes[THR_NEW1] : cpi->rd_threshes[THR_NEW3];
this_rd_thresh = (vp8_ref_frame_order[mode_index] == 2) ? cpi->rd_threshes[THR_NEW2] : this_rd_thresh;
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
tmp_rd = vp8_rd_pick_best_mbsegmentation(cpi, x, &best_ref_mv,
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
best_yrd, mdcounts,
vp8_rd_pick_best_mbsegmentation code restructure Moved the code from the segmentation loop into a function which is now called for each segment. This will allow us to change the segment order checking more easily. Change-Id: I9510d26f0acae5a73043fcca8f1984b121d3e052
2010-12-06 22:42:52 +01:00
&rate, &rate_y, &distortion, this_rd_thresh) ;
Initial WebM release
2010-05-18 17:58:33 +02:00
rate2 += rate;
distortion2 += distortion;
// If even the 'Y' rd value of split is higher than best so far then dont bother looking at UV
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
if (tmp_rd < best_yrd)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
// Now work out UV cost and add it in
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
rd_inter4x4_uv(cpi, x, &rate_uv, &distortion_uv, cpi->common.full_pixel);
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
rate2 += rate_uv;
distortion2 += distortion_uv;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
else
{
this_rd = INT_MAX;
disable_skip = 1;
}
}
break;
case DC_PRED:
case V_PRED:
case H_PRED:
case TM_PRED:
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
x->e_mbd.mode_info_context->mbmi.ref_frame = INTRA_FRAME;
RTCD: add recon functions This commit continues the process of converting to the new RTCD system. Change-Id: I9bfcf9bef65c3d4ba0fb9a3e1532bad1463a10d6
2012-01-13 01:55:44 +01:00
vp8_build_intra_predictors_mby
Move build_intra_predictors_mby to RTCD framework The vp8_build_intra_predictors_mby and vp8_build_intra_predictors_mby_s functions had global function pointers rather than using the RTCD framework. This can show up as a potential data race with tools such as helgrind. See https://bugzilla.mozilla.org/show_bug.cgi?id=640935 for an example. Change-Id: I29c407f828ac2bddfc039f852f138de5de888534
2011-03-11 17:35:38 +01:00
(&x->e_mbd);
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
macro_block_yrd(x, &rate_y, &distortion) ;
Zero out block mv when an intra mode is selected instead of each time mode is tested. Change-Id: Ief0f5586dafde54cc14d348dcecdacb182e7c1d5
2011-02-01 18:55:51 +01:00
rate2 += rate_y;
distortion2 += distortion;
rate2 += x->mbmode_cost[x->e_mbd.frame_type][x->e_mbd.mode_info_context->mbmi.mode];
rate2 += uv_intra_rate;
rate_uv = uv_intra_rate_tokenonly;
distortion2 += uv_intra_distortion;
distortion_uv = uv_intra_distortion;
Initial WebM release
2010-05-18 17:58:33 +02:00
break;
case NEWMV:
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
{
int thissme;
int bestsme = INT_MAX;
int step_param = cpi->sf.first_step;
int further_steps;
int n;
int do_refine=1; /* If last step (1-away) of n-step search doesn't pick the center point as the best match,
we will do a final 1-away diamond refining search */
Initial WebM release
2010-05-18 17:58:33 +02:00
further clean up of errorperbit and sadperbit this commit makes the usage errorperbit and sadperbit consistent for encoding modes and passes. Removed all different magic weight factors associated with errorperbit. Now 1/2 is used for both sadperbit16 and sadperbit4, the /2 operation is merged into initializations of the 2 variables. Tests on cif set show .23%, 0.18% and 0.19% gain by avg psnr, overall psnr and ssim respectively. Change-Id: Ifa285c3e065ce0a5a77addfc9f95aabf54ee270d
2011-06-01 20:41:05 +02:00
int sadpb = x->sadperbit16;
Adjust full-pixel clamping and motion vector limit calculation Do mvp clamping in full-pixel precision instead of 1/8-pixel precision to avoid error caused by right shifting operation. Also, further fixed the motion vector limit calculation in change: b7480454706a6b15bf091e659cd6227ab373c1a6 Change-Id: Ied88a4f7ddfb0476eb9f7afc6ceeddbf209fffd7
2011-07-07 17:21:41 +02:00
int_mv mvp_full;
Initial WebM release
2010-05-18 17:58:33 +02:00
Remove unnecessary ternary constructs The code had a number of constructs like (condition)?1:0, which is redundant with C's semantics. In the cases where a boolean operator was used in the condition, simply remove the ternary part. Otherwise adjust the surrounding expression to remove the condition (eg, for rounding up. See pickinter.c and rdopt.c) Change-Id: Icb2372defa3783cf31857d90b2630d06b2c7e1be
2011-12-22 01:11:31 +01:00
int col_min = ((best_ref_mv.as_mv.col+7)>>3) - MAX_FULL_PEL_VAL;
int row_min = ((best_ref_mv.as_mv.row+7)>>3) - MAX_FULL_PEL_VAL;
Adjust full-pixel clamping and motion vector limit calculation Do mvp clamping in full-pixel precision instead of 1/8-pixel precision to avoid error caused by right shifting operation. Also, further fixed the motion vector limit calculation in change: b7480454706a6b15bf091e659cd6227ab373c1a6 Change-Id: Ied88a4f7ddfb0476eb9f7afc6ceeddbf209fffd7
2011-07-07 17:21:41 +02:00
int col_max = (best_ref_mv.as_mv.col>>3) + MAX_FULL_PEL_VAL;
int row_max = (best_ref_mv.as_mv.row>>3) + MAX_FULL_PEL_VAL;
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
int tmp_col_min = x->mv_col_min;
int tmp_col_max = x->mv_col_max;
int tmp_row_min = x->mv_row_min;
int tmp_row_max = x->mv_row_max;
Initial WebM release
2010-05-18 17:58:33 +02:00
Minor change in pick_inter_mode() Scott suggested to move vp8_mv_pred() under "case NEWMV" to save extra checks. Change-Id: I09e69892f34a08dd425a4d81cfcc83674e344a20
2011-07-08 20:08:45 +02:00
if(!saddone)
{
vp8_cal_sad(cpi,xd,x, recon_yoffset ,&near_sadidx[0] );
saddone = 1;
}
vp8_mv_pred(cpi, &x->e_mbd, x->e_mbd.mode_info_context, &mvp,
x->e_mbd.mode_info_context->mbmi.ref_frame, cpi->common.ref_frame_sign_bias, &sr, &near_sadidx[0]);
Adjust full-pixel clamping and motion vector limit calculation Do mvp clamping in full-pixel precision instead of 1/8-pixel precision to avoid error caused by right shifting operation. Also, further fixed the motion vector limit calculation in change: b7480454706a6b15bf091e659cd6227ab373c1a6 Change-Id: Ied88a4f7ddfb0476eb9f7afc6ceeddbf209fffd7
2011-07-07 17:21:41 +02:00
mvp_full.as_mv.col = mvp.as_mv.col>>3;
mvp_full.as_mv.row = mvp.as_mv.row>>3;
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
// Get intersection of UMV window and valid MV window to reduce # of checks in diamond search.
if (x->mv_col_min < col_min )
x->mv_col_min = col_min;
if (x->mv_col_max > col_max )
x->mv_col_max = col_max;
if (x->mv_row_min < row_min )
x->mv_row_min = row_min;
if (x->mv_row_max > row_max )
x->mv_row_max = row_max;
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
//adjust search range according to sr from mv prediction
if(sr > step_param)
step_param = sr;
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
// Initial step/diamond search
{
Adjust full-pixel clamping and motion vector limit calculation Do mvp clamping in full-pixel precision instead of 1/8-pixel precision to avoid error caused by right shifting operation. Also, further fixed the motion vector limit calculation in change: b7480454706a6b15bf091e659cd6227ab373c1a6 Change-Id: Ied88a4f7ddfb0476eb9f7afc6ceeddbf209fffd7
2011-07-07 17:21:41 +02:00
bestsme = cpi->diamond_search_sad(x, b, d, &mvp_full, &d->bmi.mv,
remove some magic weights associated with sad_per_bit sad_per_bit has been used for a number of motion vector search routines with different magic weights: 1, 1/2 and 1/4. This commit remove these magic numbers and use 1/2 for all motion search routines, also reformat a number of source code lines to within 80 column limit. Test on cif set shows overall effect is neutral on all metrics. <=0.01% Change-Id: I8a382821fa4cffc9c0acf8e8431435a03df74885
2010-07-01 03:58:54 +02:00
step_param, sadpb, &num00,
&cpi->fn_ptr[BLOCK_16X16],
x->mvcost, &best_ref_mv);
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
mode_mv[NEWMV].as_int = d->bmi.mv.as_int;
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
// Further step/diamond searches as necessary
n = 0;
further_steps = (cpi->sf.max_step_search_steps - 1) - step_param;
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
n = num00;
num00 = 0;
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
/* If there won't be more n-step search, check to see if refining search is needed. */
if (n > further_steps)
do_refine = 0;
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
while (n < further_steps)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
n++;
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
if (num00)
num00--;
Initial WebM release
2010-05-18 17:58:33 +02:00
else
{
Adjust full-pixel clamping and motion vector limit calculation Do mvp clamping in full-pixel precision instead of 1/8-pixel precision to avoid error caused by right shifting operation. Also, further fixed the motion vector limit calculation in change: b7480454706a6b15bf091e659cd6227ab373c1a6 Change-Id: Ied88a4f7ddfb0476eb9f7afc6ceeddbf209fffd7
2011-07-07 17:21:41 +02:00
thissme = cpi->diamond_search_sad(x, b, d, &mvp_full,
remove some magic weights associated with sad_per_bit sad_per_bit has been used for a number of motion vector search routines with different magic weights: 1, 1/2 and 1/4. This commit remove these magic numbers and use 1/2 for all motion search routines, also reformat a number of source code lines to within 80 column limit. Test on cif set shows overall effect is neutral on all metrics. <=0.01% Change-Id: I8a382821fa4cffc9c0acf8e8431435a03df74885
2010-07-01 03:58:54 +02:00
&d->bmi.mv, step_param + n, sadpb, &num00,
&cpi->fn_ptr[BLOCK_16X16], x->mvcost,
&best_ref_mv);
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
/* check to see if refining search is needed. */
if (num00 > (further_steps-n))
do_refine = 0;
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
if (thissme < bestsme)
{
bestsme = thissme;
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
mode_mv[NEWMV].as_int = d->bmi.mv.as_int;
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
}
else
{
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
d->bmi.mv.as_int = mode_mv[NEWMV].as_int;
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
}
Initial WebM release
2010-05-18 17:58:33 +02:00
}
}
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
}
/* final 1-away diamond refining search */
if (do_refine == 1)
{
int search_range;
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
//It seems not a good way to set search_range. Need further investigation.
//search_range = MAXF(abs((mvp.row>>3) - d->bmi.mv.as_mv.row), abs((mvp.col>>3) - d->bmi.mv.as_mv.col));
search_range = 8;
Fix a bug in motion search code(2) This fix added MV range checks for NEWMV mode as suggested by Jim. To reduce unnecessary MV range checks, I tried Yaowu's suggestion. Update UMV borders in NEWMV mode to also cover MV range check. Also, in this way, every MV that is valid gets checked in diamond search function. Change-Id: I95a89ce0daf6f178c454448f13d4249f19b30f3a
2010-12-14 23:39:25 +01:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
//thissme = cpi->full_search_sad(x, b, d, &d->bmi.mv.as_mv, sadpb, search_range, &cpi->fn_ptr[BLOCK_16X16], x->mvcost, &best_ref_mv);
remove some magic weights associated with sad_per_bit sad_per_bit has been used for a number of motion vector search routines with different magic weights: 1, 1/2 and 1/4. This commit remove these magic numbers and use 1/2 for all motion search routines, also reformat a number of source code lines to within 80 column limit. Test on cif set shows overall effect is neutral on all metrics. <=0.01% Change-Id: I8a382821fa4cffc9c0acf8e8431435a03df74885
2010-07-01 03:58:54 +02:00
thissme = cpi->refining_search_sad(x, b, d, &d->bmi.mv, sadpb,
search_range, &cpi->fn_ptr[BLOCK_16X16],
x->mvcost, &best_ref_mv);
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
if (thissme < bestsme)
Use sub-pixel search's SSE in mode selection Passed SSE from sub-pixel search back to pick_inter_mode function, which is compared with the encode_breakout to see if we could skip evaluating the remaining modes. Change-Id: I4a86442834f0d1b880a19e21ea52d17d505f941d
2011-04-18 21:48:34 +02:00
{
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
bestsme = thissme;
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
mode_mv[NEWMV].as_int = d->bmi.mv.as_int;
Reduce unnecessary distortion computation In vp8_pick_inter_mode(), for NEWMV mode, use the error result got from motion search as distortion. This helps performance in real- time mode. Change-Id: I398c4e46cc5381f7d874e748cf78827ef0e0860c
2011-04-14 21:53:33 +02:00
}
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
else
{
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
d->bmi.mv.as_int = mode_mv[NEWMV].as_int;
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
}
}
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
x->mv_col_min = tmp_col_min;
x->mv_col_max = tmp_col_max;
x->mv_row_min = tmp_row_min;
x->mv_row_max = tmp_row_max;
Initial WebM release
2010-05-18 17:58:33 +02:00
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
if (bestsme < INT_MAX)
{
int dis; /* TODO: use dis in distortion calculation later. */
unsigned int sse;
further clean up of errorperbit and sadperbit this commit makes the usage errorperbit and sadperbit consistent for encoding modes and passes. Removed all different magic weight factors associated with errorperbit. Now 1/2 is used for both sadperbit16 and sadperbit4, the /2 operation is merged into initializations of the 2 variables. Tests on cif set show .23%, 0.18% and 0.19% gain by avg psnr, overall psnr and ssim respectively. Change-Id: Ifa285c3e065ce0a5a77addfc9f95aabf54ee270d
2011-06-01 20:41:05 +02:00
cpi->find_fractional_mv_step(x, b, d, &d->bmi.mv, &best_ref_mv,
x->errorperbit,
&cpi->fn_ptr[BLOCK_16X16],
x->mvcost, &dis, &sse);
Initial WebM release
2010-05-18 17:58:33 +02:00
}
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
mode_mv[NEWMV].as_int = d->bmi.mv.as_int;
Use diamond search to replace full search in full-pixel refining search In NEWMV mode, currently, full search is used as the refining search after n-step search. By replacing it with an iterative diamond search of radius 1 largely reduced the computation complexity, but still maintained the same encoding quality since the refining search is done for every macroblock instead of only a small precentage of macroblocks while using full search. Tests on the test set showed a 3.4% encoding speed increase with none psnr & ssim loss. Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
2011-05-06 18:51:31 +02:00
// Add the new motion vector cost to our rolling cost variable
rate2 += vp8_mv_bit_cost(&mode_mv[NEWMV], &best_ref_mv, x->mvcost, 96);
}
Initial WebM release
2010-05-18 17:58:33 +02:00
case NEARESTMV:
case NEARMV:
// Clip "next_nearest" so that it does not extend to far out of image
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
vp8_clamp_mv2(&mode_mv[this_mode], xd);
Initial WebM release
2010-05-18 17:58:33 +02:00
// Do not bother proceeding if the vector (from newmv,nearest or near) is 0,0 as this should then be coded using the zeromv mode.
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
if (((this_mode == NEARMV) || (this_mode == NEARESTMV)) && (mode_mv[this_mode].as_int == 0))
Initial WebM release
2010-05-18 17:58:33 +02:00
continue;
case ZEROMV:
// Trap vectors that reach beyond the UMV borders
// Note that ALL New MV, Nearest MV Near MV and Zero MV code drops through to this point
// because of the lack of break statements in the previous two cases.
Using int_mv instead of MV The compiler produces better assembly when using int_mv for assignments. The compiler shifts and ors the two 16bit values when assigning MV. Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
2011-05-12 16:50:16 +02:00
if (((mode_mv[this_mode].as_mv.row >> 3) < x->mv_row_min) || ((mode_mv[this_mode].as_mv.row >> 3) > x->mv_row_max) ||
((mode_mv[this_mode].as_mv.col >> 3) < x->mv_col_min) || ((mode_mv[this_mode].as_mv.col >> 3) > x->mv_col_max))
Initial WebM release
2010-05-18 17:58:33 +02:00
continue;
vp8_set_mbmode_and_mvs(x, this_mode, &mode_mv[this_mode]);
Moved dequant idct into common These functions are now used by the encoder. This is WIP with the goal of creating a common idct/add for the encoder and decoder. A boost of 1.8% was seen for the HD rt test clip used. [Tero] Added needed changes to ARM side. Change-Id: Ibbb8000be09034203d7adffc457d3c3f8b06a5bf
2011-12-15 20:23:36 +01:00
vp8_build_inter16x16_predictors_mby(&x->e_mbd, x->e_mbd.predictor, 16);
Initial WebM release
2010-05-18 17:58:33 +02:00
vp8e - static threshold play Realized no need for new assembly code sum is already calculated. Change-Id: Ie2d94feb4b7c1f77c5359bca29b66228e41638c9
2010-12-07 22:07:23 +01:00
if (cpi->active_map_enabled && x->active_ptr[0] == 0) {
Initial WebM release
2010-05-18 17:58:33 +02:00
x->skip = 1;
}
fix uninitialized read in encode breakout Change I3430820 performed an uninitialized read when encode_breakout == 0, since the sum and sse wouldn't be set: if(x->encode_breakout) VARIANCE_INVOKE(..., get16x16var)(..., &sum, &sse); if (cpi->active_map_enabled && x->active_ptr[0] == 0) { ... } else if (sse < x->encode_breakout) Change-Id: I915eb76d1227b4b6d1137a0dedf2c143860098a2
2010-12-09 21:59:22 +01:00
else if (x->encode_breakout)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Use sub-pixel search's SSE in mode selection Passed SSE from sub-pixel search back to pick_inter_mode function, which is compared with the encode_breakout to see if we could skip evaluating the remaining modes. Change-Id: I4a86442834f0d1b880a19e21ea52d17d505f941d
2011-04-18 21:48:34 +02:00
unsigned int sse;
remove redundant functions The encoder defined about 4 set of similar functions to calculate sum, variance or sse or a combination of them. This commit removed one set of these functions, get8x8var and get16x16var, where calls to the later function are replaced with var16x16 by using the fact on a 16x16 MB: variance == sse - sum*sum/256 Change-Id: I803eabd1fb3ab177780a40338cbd596dffaed267
2011-06-07 01:42:58 +02:00
unsigned int var;
change the threshold of DC check for encode breakout Previously, the DC check is to make sure there is no code-able DC shift for quantizer Q0, which has been verified rather conservative. This commit changes the criteria to have two components, DC and AC, to address the conservativeness. First, it checks if all AC energy is enough to contribute a single non-zero quantized AC coefficient. Second, for DC, the decision to skip further considers two possible scenarios: 1. There is no code-able 2nd order DC coefficient at all; 2 The residue is relatively flat, but the uniform DC change is very small, i.e. less than 1/2 gray level per pixel. Comparing to previous criteria, the new criteria is about 10% to 15% faster in encoding time with a very small quality loss. (threshold ~1000 and quality range 33db-45db) It should be noted that this commit enables "automatic" static threshold for encodebreakout if a non-zero small value is passed in to encoder. Change-Id: I0f77719a1ac2c2dfddbd950d84920df374515ce3
2011-01-20 01:21:01 +01:00
int threshold = (xd->block[0].dequant[1]
* xd->block[0].dequant[1] >>4);
if(threshold < x->encode_breakout)
threshold = x->encode_breakout;
Initial WebM release
2010-05-18 17:58:33 +02:00
RTCD: add variance functions This commit continues the process of converting to the new RTCD system. Change-Id: Ie5c1aa480637e98dc3918fb562ff45c37a66c538
2012-01-13 01:55:44 +01:00
var = vp8_variance16x16
Copy macroblock data to a buffer before encoding it I got this idea from Pascal (Thanks). Before encoding a macroblock, copy it to a 16x16 buffer, and then read source data from there instead. This will help keep the source data in cache, and help with the performance. Change-Id: Id05f4cb601299150511d59dcba0ae62c49b5b757
2011-06-23 19:54:02 +02:00
(*(b->base_src), b->src_stride,
remove redundant functions The encoder defined about 4 set of similar functions to calculate sum, variance or sse or a combination of them. This commit removed one set of these functions, get8x8var and get16x16var, where calls to the later function are replaced with var16x16 by using the fact on a 16x16 MB: variance == sse - sum*sum/256 Change-Id: I803eabd1fb3ab177780a40338cbd596dffaed267
2011-06-07 01:42:58 +02:00
x->e_mbd.predictor, 16, &sse);
fix uninitialized read in encode breakout Change I3430820 performed an uninitialized read when encode_breakout == 0, since the sum and sse wouldn't be set: if(x->encode_breakout) VARIANCE_INVOKE(..., get16x16var)(..., &sum, &sse); if (cpi->active_map_enabled && x->active_ptr[0] == 0) { ... } else if (sse < x->encode_breakout) Change-Id: I915eb76d1227b4b6d1137a0dedf2c143860098a2
2010-12-09 21:59:22 +01:00
change the threshold of DC check for encode breakout Previously, the DC check is to make sure there is no code-able DC shift for quantizer Q0, which has been verified rather conservative. This commit changes the criteria to have two components, DC and AC, to address the conservativeness. First, it checks if all AC energy is enough to contribute a single non-zero quantized AC coefficient. Second, for DC, the decision to skip further considers two possible scenarios: 1. There is no code-able 2nd order DC coefficient at all; 2 The residue is relatively flat, but the uniform DC change is very small, i.e. less than 1/2 gray level per pixel. Comparing to previous criteria, the new criteria is about 10% to 15% faster in encoding time with a very small quality loss. (threshold ~1000 and quality range 33db-45db) It should be noted that this commit enables "automatic" static threshold for encodebreakout if a non-zero small value is passed in to encoder. Change-Id: I0f77719a1ac2c2dfddbd950d84920df374515ce3
2011-01-20 01:21:01 +01:00
if (sse < threshold)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
remove redundant functions The encoder defined about 4 set of similar functions to calculate sum, variance or sse or a combination of them. This commit removed one set of these functions, get8x8var and get16x16var, where calls to the later function are replaced with var16x16 by using the fact on a 16x16 MB: variance == sse - sum*sum/256 Change-Id: I803eabd1fb3ab177780a40338cbd596dffaed267
2011-06-07 01:42:58 +02:00
unsigned int q2dc = xd->block[24].dequant[0];
change the threshold of DC check for encode breakout Previously, the DC check is to make sure there is no code-able DC shift for quantizer Q0, which has been verified rather conservative. This commit changes the criteria to have two components, DC and AC, to address the conservativeness. First, it checks if all AC energy is enough to contribute a single non-zero quantized AC coefficient. Second, for DC, the decision to skip further considers two possible scenarios: 1. There is no code-able 2nd order DC coefficient at all; 2 The residue is relatively flat, but the uniform DC change is very small, i.e. less than 1/2 gray level per pixel. Comparing to previous criteria, the new criteria is about 10% to 15% faster in encoding time with a very small quality loss. (threshold ~1000 and quality range 33db-45db) It should be noted that this commit enables "automatic" static threshold for encodebreakout if a non-zero small value is passed in to encoder. Change-Id: I0f77719a1ac2c2dfddbd950d84920df374515ce3
2011-01-20 01:21:01 +01:00
/* If theres is no codeable 2nd order dc
or a very small uniform pixel change change */
remove redundant functions The encoder defined about 4 set of similar functions to calculate sum, variance or sse or a combination of them. This commit removed one set of these functions, get8x8var and get16x16var, where calls to the later function are replaced with var16x16 by using the fact on a 16x16 MB: variance == sse - sum*sum/256 Change-Id: I803eabd1fb3ab177780a40338cbd596dffaed267
2011-06-07 01:42:58 +02:00
if ((sse - var < q2dc * q2dc >>4) ||
(sse /2 > var && sse-var < 64))
vp8e - static threshold play Realized no need for new assembly code sum is already calculated. Change-Id: Ie2d94feb4b7c1f77c5359bca29b66228e41638c9
2010-12-07 22:07:23 +01:00
{
remove redundant functions The encoder defined about 4 set of similar functions to calculate sum, variance or sse or a combination of them. This commit removed one set of these functions, get8x8var and get16x16var, where calls to the later function are replaced with var16x16 by using the fact on a 16x16 MB: variance == sse - sum*sum/256 Change-Id: I803eabd1fb3ab177780a40338cbd596dffaed267
2011-06-07 01:42:58 +02:00
// Check u and v to make sure skip is ok
RTCD: add variance functions This commit continues the process of converting to the new RTCD system. Change-Id: Ie5c1aa480637e98dc3918fb562ff45c37a66c538
2012-01-13 01:55:44 +01:00
int sse2= VP8_UVSSE(x);
change the threshold of DC check for encode breakout Previously, the DC check is to make sure there is no code-able DC shift for quantizer Q0, which has been verified rather conservative. This commit changes the criteria to have two components, DC and AC, to address the conservativeness. First, it checks if all AC energy is enough to contribute a single non-zero quantized AC coefficient. Second, for DC, the decision to skip further considers two possible scenarios: 1. There is no code-able 2nd order DC coefficient at all; 2 The residue is relatively flat, but the uniform DC change is very small, i.e. less than 1/2 gray level per pixel. Comparing to previous criteria, the new criteria is about 10% to 15% faster in encoding time with a very small quality loss. (threshold ~1000 and quality range 33db-45db) It should be noted that this commit enables "automatic" static threshold for encodebreakout if a non-zero small value is passed in to encoder. Change-Id: I0f77719a1ac2c2dfddbd950d84920df374515ce3
2011-01-20 01:21:01 +01:00
if (sse2 * 2 < threshold)
fix uninitialized read in encode breakout Change I3430820 performed an uninitialized read when encode_breakout == 0, since the sum and sse wouldn't be set: if(x->encode_breakout) VARIANCE_INVOKE(..., get16x16var)(..., &sum, &sse); if (cpi->active_map_enabled && x->active_ptr[0] == 0) { ... } else if (sse < x->encode_breakout) Change-Id: I915eb76d1227b4b6d1137a0dedf2c143860098a2
2010-12-09 21:59:22 +01:00
{
x->skip = 1;
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
distortion2 = sse + sse2;
fix uninitialized read in encode breakout Change I3430820 performed an uninitialized read when encode_breakout == 0, since the sum and sse wouldn't be set: if(x->encode_breakout) VARIANCE_INVOKE(..., get16x16var)(..., &sum, &sse); if (cpi->active_map_enabled && x->active_ptr[0] == 0) { ... } else if (sse < x->encode_breakout) Change-Id: I915eb76d1227b4b6d1137a0dedf2c143860098a2
2010-12-09 21:59:22 +01:00
rate2 = 500;
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
/* for best_yrd calculation */
rate_uv = 0;
distortion_uv = sse2;
fix uninitialized read in encode breakout Change I3430820 performed an uninitialized read when encode_breakout == 0, since the sum and sse wouldn't be set: if(x->encode_breakout) VARIANCE_INVOKE(..., get16x16var)(..., &sum, &sse); if (cpi->active_map_enabled && x->active_ptr[0] == 0) { ... } else if (sse < x->encode_breakout) Change-Id: I915eb76d1227b4b6d1137a0dedf2c143860098a2
2010-12-09 21:59:22 +01:00
disable_skip = 1;
Use sub-pixel search's SSE in mode selection Passed SSE from sub-pixel search back to pick_inter_mode function, which is compared with the encode_breakout to see if we could skip evaluating the remaining modes. Change-Id: I4a86442834f0d1b880a19e21ea52d17d505f941d
2011-04-18 21:48:34 +02:00
this_rd = RDCOST(x->rdmult, x->rddiv, rate2, distortion2);
fix uninitialized read in encode breakout Change I3430820 performed an uninitialized read when encode_breakout == 0, since the sum and sse wouldn't be set: if(x->encode_breakout) VARIANCE_INVOKE(..., get16x16var)(..., &sum, &sse); if (cpi->active_map_enabled && x->active_ptr[0] == 0) { ... } else if (sse < x->encode_breakout) Change-Id: I915eb76d1227b4b6d1137a0dedf2c143860098a2
2010-12-09 21:59:22 +01:00
break;
}
vp8e - static threshold play Realized no need for new assembly code sum is already calculated. Change-Id: Ie2d94feb4b7c1f77c5359bca29b66228e41638c9
2010-12-07 22:07:23 +01:00
}
Initial WebM release
2010-05-18 17:58:33 +02:00
}
}
fix uninitialized read in encode breakout Change I3430820 performed an uninitialized read when encode_breakout == 0, since the sum and sse wouldn't be set: if(x->encode_breakout) VARIANCE_INVOKE(..., get16x16var)(..., &sum, &sse); if (cpi->active_map_enabled && x->active_ptr[0] == 0) { ... } else if (sse < x->encode_breakout) Change-Id: I915eb76d1227b4b6d1137a0dedf2c143860098a2
2010-12-09 21:59:22 +01:00
Initial WebM release
2010-05-18 17:58:33 +02:00
//intermodecost[mode_index] = vp8_cost_mv_ref(this_mode, mdcounts); // Experimental debug code
// Add in the Mv/mode cost
rate2 += vp8_cost_mv_ref(this_mode, mdcounts);
// Y cost and distortion
RTCD: add block subtraction functions This commit continues the process of converting to the new RTCD system. Change-Id: Id8a287fdd4bd050ea4452e1582ad85520f3081be
2012-01-13 01:55:44 +01:00
macro_block_yrd(x, &rate_y, &distortion);
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
rate2 += rate_y;
Initial WebM release
2010-05-18 17:58:33 +02:00
distortion2 += distortion;
// UV cost and distortion
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
rd_inter16x16_uv(cpi, x, &rate_uv, &distortion_uv, cpi->common.full_pixel);
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
rate2 += rate_uv;
distortion2 += distortion_uv;
Initial WebM release
2010-05-18 17:58:33 +02:00
break;
default:
break;
}
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
// Where skip is allowable add in the default per mb cost for the no skip case.
// where we then decide to skip we have to delete this and replace it with the
// cost of signallying a skip
if (cpi->common.mb_no_coeff_skip)
{
other_cost += vp8_cost_bit(cpi->prob_skip_false, 0);
rate2 += other_cost;
}
Calc ref_frame_cost once per frame instead of every macro block. Change-Id: I2604e94c6b89e3a8457777e21c8c38406d55b165
2011-06-13 15:50:54 +02:00
/* Estimate the reference frame signaling cost and add it
* to the rolling cost variable.
*/
rate2 +=
Moved ref_frame_cost from MACROBLOCKD to MACROBLOCK Change-Id: I05788522e9cde4322cfb12032483bdbf184bdf0b
2012-02-02 19:40:08 +01:00
x->ref_frame_cost[x->e_mbd.mode_info_context->mbmi.ref_frame];
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
Initial WebM release
2010-05-18 17:58:33 +02:00
if (!disable_skip)
{
// Test for the condition where skip block will be activated because there are no non zero coefficients and make any necessary adjustment for rate
if (cpi->common.mb_no_coeff_skip)
{
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
int tteob;
Initial WebM release
2010-05-18 17:58:33 +02:00
tteob = 0;
Fix incorrect use of uv eobs in intra modes In vp8_rd_pick_inter_mode(), if total of eobs is zero, rate needs to be adjusted since there are no non-zero coefficients for transmission. The uv intra eobs calculated in rd_pick_intra_mbuv_mode() need to be saved before they are overwritten by inter-mode eobs. Change-Id: I41dd04fba912e8122ef95793d4d98a251bc60e58
2012-02-17 15:15:08 +01:00
if (x->e_mbd.mode_info_context->mbmi.ref_frame)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Fix incorrect use of uv eobs in intra modes In vp8_rd_pick_inter_mode(), if total of eobs is zero, rate needs to be adjusted since there are no non-zero coefficients for transmission. The uv intra eobs calculated in rd_pick_intra_mbuv_mode() need to be saved before they are overwritten by inter-mode eobs. Change-Id: I41dd04fba912e8122ef95793d4d98a251bc60e58
2012-02-17 15:15:08 +01:00
for (i = 0; i <= 24; i++)
tteob += x->e_mbd.eobs[i];
}
else
{
for (i = 0; i < 16; i++)
tteob += x->e_mbd.eobs[i];
tteob += uv_intra_tteob;
tteob += x->e_mbd.eobs[24];
Initial WebM release
2010-05-18 17:58:33 +02:00
}
if (tteob == 0)
{
rate2 -= (rate_y + rate_uv);
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
//for best_yrd calculation
rate_uv = 0;
Initial WebM release
2010-05-18 17:58:33 +02:00
// Back out no skip flag costing and add in skip flag costing
if (cpi->prob_skip_false)
{
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
int prob_skip_cost;
Initial WebM release
2010-05-18 17:58:33 +02:00
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
prob_skip_cost = vp8_cost_bit(cpi->prob_skip_false, 1);
prob_skip_cost -= vp8_cost_bit(cpi->prob_skip_false, 0);
rate2 += prob_skip_cost;
other_cost += prob_skip_cost;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
}
}
// Calculate the final RD estimate for this mode
Removed cpi->target_bits_per_mb cpi->target_bits_per_mb is currently not being used, so delete it. Also removed other unused code in rdopt.c. Change-Id: I98449f9030bcd2f15451d9b7a3b9b93dd1409923
2011-01-07 15:41:13 +01:00
this_rd = RDCOST(x->rdmult, x->rddiv, rate2, distortion2);
Initial WebM release
2010-05-18 17:58:33 +02:00
}
Error accumulator stats bug. The error accumulator stats values cpi->prediction_error and cpi->intra_error were being populated with rd values not distortion values. These are only "currently" used in a limited way for RT compress key frame detection. Change-Id: I2702ba1cab6e49ab8dc096ba75b6b34ab3573021
2011-04-08 15:21:36 +02:00
// Keep record of best intra distortion
if ((x->e_mbd.mode_info_context->mbmi.ref_frame == INTRA_FRAME) &&
(this_rd < best_intra_rd) )
Initial WebM release
2010-05-18 17:58:33 +02:00
{
Error accumulator stats bug. The error accumulator stats values cpi->prediction_error and cpi->intra_error were being populated with rd values not distortion values. These are only "currently" used in a limited way for RT compress key frame detection. Change-Id: I2702ba1cab6e49ab8dc096ba75b6b34ab3573021
2011-04-08 15:21:36 +02:00
best_intra_rd = this_rd;
*returnintra = distortion2 ;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
// Did this mode help.. i.i is it the new best mode
if (this_rd < best_rd || x->skip)
{
// Note index of best mode so far
best_mode_index = mode_index;
if (this_mode <= B_PRED)
{
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
x->e_mbd.mode_info_context->mbmi.uv_mode = uv_intra_mode;
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
/* required for left and above block mv */
x->e_mbd.mode_info_context->mbmi.mv.as_int = 0;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
Calc ref_frame_cost once per frame instead of every macro block. Change-Id: I2604e94c6b89e3a8457777e21c8c38406d55b165
2011-06-13 15:50:54 +02:00
other_cost +=
Moved ref_frame_cost from MACROBLOCKD to MACROBLOCK Change-Id: I05788522e9cde4322cfb12032483bdbf184bdf0b
2012-02-02 19:40:08 +01:00
x->ref_frame_cost[x->e_mbd.mode_info_context->mbmi.ref_frame];
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
/* Calculate the final y RD estimate for this mode */
Removed cpi->target_bits_per_mb cpi->target_bits_per_mb is currently not being used, so delete it. Also removed other unused code in rdopt.c. Change-Id: I98449f9030bcd2f15451d9b7a3b9b93dd1409923
2011-01-07 15:41:13 +01:00
best_yrd = RDCOST(x->rdmult, x->rddiv, (rate2-rate_uv-other_cost),
(distortion2-distortion_uv));
Adjusted breakout RD for SPLITMV vp8_rd_pick_best_mbsegmentation looks at y only. The new breakout does not include the frame cost, the prob_skip_false cost, or the uv rate. Performance improved by a few percent and the quality remained the same. Change-Id: I94ff013998ac51e8ecce7130870f7b6600758e15
2010-12-16 15:38:02 +01:00
Initial WebM release
2010-05-18 17:58:33 +02:00
*returnrate = rate2;
*returndistortion = distortion2;
best_rd = this_rd;
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
vpx_memcpy(&best_mbmode, &x->e_mbd.mode_info_context->mbmi, sizeof(MB_MODE_INFO));
Reduced the size of MB_MODE_INFO Moved partition_bmi and partition_count out of MB_MODE_INFO and placed into MACROBLOCK. Also reduced the size of other members of the MB_MODE_INFO struct. For 1080p, the memory was reduced by 1,209,516 bytes. The decoder performance appeared to improve by 3% for the clip used. Note: The main goal for this change is to improve the decoder performance. The encoder will be revisited at a later date for further structure cleanup. Change-Id: I4733621292ee9cc3fffa4046cb3fd4d99bd14613
2010-09-02 22:17:52 +02:00
vpx_memcpy(&best_partition, x->partition_info, sizeof(PARTITION_INFO));
Initial WebM release
2010-05-18 17:58:33 +02:00
Removed B_MODE_INFO Declared the bmi in BLOCKD as a union instead of B_MODE_INFO. Then removed B_MODE_INFO completely. Change-Id: Ieb7469899e265892c66f7aeac87b7f2bf38e7a67
2011-06-02 19:46:41 +02:00
if ((this_mode == B_PRED) || (this_mode == SPLITMV))
for (i = 0; i < 16; i++)
{
best_bmodes[i] = x->e_mbd.block[i].bmi;
}
Initial WebM release
2010-05-18 17:58:33 +02:00
// Testing this mode gave rise to an improvement in best error score. Lower threshold a bit for next time
cpi->rd_thresh_mult[mode_index] = (cpi->rd_thresh_mult[mode_index] >= (MIN_THRESHMULT + 2)) ? cpi->rd_thresh_mult[mode_index] - 2 : MIN_THRESHMULT;
cpi->rd_threshes[mode_index] = (cpi->rd_baseline_thresh[mode_index] >> 7) * cpi->rd_thresh_mult[mode_index];
}
// If the mode did not help improve the best error case then raise the threshold for testing that mode next time around.
else
{
cpi->rd_thresh_mult[mode_index] += 4;
if (cpi->rd_thresh_mult[mode_index] > MAX_THRESHMULT)
cpi->rd_thresh_mult[mode_index] = MAX_THRESHMULT;
cpi->rd_threshes[mode_index] = (cpi->rd_baseline_thresh[mode_index] >> 7) * cpi->rd_thresh_mult[mode_index];
}
if (x->skip)
break;
change the threshold of DC check for encode breakout Previously, the DC check is to make sure there is no code-able DC shift for quantizer Q0, which has been verified rather conservative. This commit changes the criteria to have two components, DC and AC, to address the conservativeness. First, it checks if all AC energy is enough to contribute a single non-zero quantized AC coefficient. Second, for DC, the decision to skip further considers two possible scenarios: 1. There is no code-able 2nd order DC coefficient at all; 2 The residue is relatively flat, but the uniform DC change is very small, i.e. less than 1/2 gray level per pixel. Comparing to previous criteria, the new criteria is about 10% to 15% faster in encoding time with a very small quality loss. (threshold ~1000 and quality range 33db-45db) It should be noted that this commit enables "automatic" static threshold for encodebreakout if a non-zero small value is passed in to encoder. Change-Id: I0f77719a1ac2c2dfddbd950d84920df374515ce3
2011-01-20 01:21:01 +01:00
Initial WebM release
2010-05-18 17:58:33 +02:00
}
// Reduce the activation RD thresholds for the best choice mode
if ((cpi->rd_baseline_thresh[best_mode_index] > 0) && (cpi->rd_baseline_thresh[best_mode_index] < (INT_MAX >> 2)))
{
int best_adjustment = (cpi->rd_thresh_mult[best_mode_index] >> 2);
cpi->rd_thresh_mult[best_mode_index] = (cpi->rd_thresh_mult[best_mode_index] >= (MIN_THRESHMULT + best_adjustment)) ? cpi->rd_thresh_mult[best_mode_index] - best_adjustment : MIN_THRESHMULT;
cpi->rd_threshes[best_mode_index] = (cpi->rd_baseline_thresh[best_mode_index] >> 7) * cpi->rd_thresh_mult[best_mode_index];
// If we chose a split mode then reset the new MV thresholds as well
/*if ( vp8_mode_order[best_mode_index] == SPLITMV )
{
best_adjustment = 4; //(cpi->rd_thresh_mult[THR_NEWMV] >> 4);
cpi->rd_thresh_mult[THR_NEWMV] = (cpi->rd_thresh_mult[THR_NEWMV] >= (MIN_THRESHMULT+best_adjustment)) ? cpi->rd_thresh_mult[THR_NEWMV]-best_adjustment: MIN_THRESHMULT;
cpi->rd_threshes[THR_NEWMV] = (cpi->rd_baseline_thresh[THR_NEWMV] >> 7) * cpi->rd_thresh_mult[THR_NEWMV];
best_adjustment = 4; //(cpi->rd_thresh_mult[THR_NEWG] >> 4);
cpi->rd_thresh_mult[THR_NEWG] = (cpi->rd_thresh_mult[THR_NEWG] >= (MIN_THRESHMULT+best_adjustment)) ? cpi->rd_thresh_mult[THR_NEWG]-best_adjustment: MIN_THRESHMULT;
cpi->rd_threshes[THR_NEWG] = (cpi->rd_baseline_thresh[THR_NEWG] >> 7) * cpi->rd_thresh_mult[THR_NEWG];
best_adjustment = 4; //(cpi->rd_thresh_mult[THR_NEWA] >> 4);
cpi->rd_thresh_mult[THR_NEWA] = (cpi->rd_thresh_mult[THR_NEWA] >= (MIN_THRESHMULT+best_adjustment)) ? cpi->rd_thresh_mult[THR_NEWA]-best_adjustment: MIN_THRESHMULT;
cpi->rd_threshes[THR_NEWA] = (cpi->rd_baseline_thresh[THR_NEWA] >> 7) * cpi->rd_thresh_mult[THR_NEWA];
}*/
}
// Note how often each mode chosen as best
cpi->mode_chosen_counts[best_mode_index] ++;
vp8_pick_inter_mode code cleanup Small code cleanups before attempting to reduce the size of bmi found in BLOCKD. Change-Id: Ie9c14adb53afd847716a75bcce067d0e6c04f225
2011-05-31 20:24:42 +02:00
if (cpi->is_src_frame_alt_ref &&
(best_mbmode.mode != ZEROMV || best_mbmode.ref_frame != ALTREF_FRAME))
Initial WebM release
2010-05-18 17:58:33 +02:00
{
vp8_pick_inter_mode code cleanup Small code cleanups before attempting to reduce the size of bmi found in BLOCKD. Change-Id: Ie9c14adb53afd847716a75bcce067d0e6c04f225
2011-05-31 20:24:42 +02:00
x->e_mbd.mode_info_context->mbmi.mode = ZEROMV;
x->e_mbd.mode_info_context->mbmi.ref_frame = ALTREF_FRAME;
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
x->e_mbd.mode_info_context->mbmi.mv.as_int = 0;
vp8_pick_inter_mode code cleanup Small code cleanups before attempting to reduce the size of bmi found in BLOCKD. Change-Id: Ie9c14adb53afd847716a75bcce067d0e6c04f225
2011-05-31 20:24:42 +02:00
x->e_mbd.mode_info_context->mbmi.uv_mode = DC_PRED;
x->e_mbd.mode_info_context->mbmi.mb_skip_coeff =
Remove unnecessary ternary constructs The code had a number of constructs like (condition)?1:0, which is redundant with C's semantics. In the cases where a boolean operator was used in the condition, simply remove the ternary part. Otherwise adjust the surrounding expression to remove the condition (eg, for rounding up. See pickinter.c and rdopt.c) Change-Id: Icb2372defa3783cf31857d90b2630d06b2c7e1be
2011-12-22 01:11:31 +01:00
(cpi->common.mb_no_coeff_skip);
vp8_pick_inter_mode code cleanup Small code cleanups before attempting to reduce the size of bmi found in BLOCKD. Change-Id: Ie9c14adb53afd847716a75bcce067d0e6c04f225
2011-05-31 20:24:42 +02:00
x->e_mbd.mode_info_context->mbmi.partitioning = 0;
Bugfix for error accumulator stats Previous to commit de4e9e3, there was an early return in the alt-ref case that was inadvertantly removed when the function was refactored to return void. This patch restores the prior behavior. Change-Id: I783ffd594a4690297e2742f99526fd7ad67698b2
2011-04-11 19:05:08 +02:00
return;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
vp8_pick_inter_mode code cleanup Small code cleanups before attempting to reduce the size of bmi found in BLOCKD. Change-Id: Ie9c14adb53afd847716a75bcce067d0e6c04f225
2011-05-31 20:24:42 +02:00
Initial WebM release
2010-05-18 17:58:33 +02:00
// macroblock modes
Removed unnecessary MB_MODE_INFO copies These copies occurred for each macroblock in the encoder and decoder. Thetemp MB_MODE_INFO mbmi was removed from MACROBLOCKD. As a result, a large number compile errors had to be fixed. Change-Id: I4cf0ffae3ce244f6db04a4c217d52dd256382cf3
2010-08-12 22:25:43 +02:00
vpx_memcpy(&x->e_mbd.mode_info_context->mbmi, &best_mbmode, sizeof(MB_MODE_INFO));
Initial WebM release
2010-05-18 17:58:33 +02:00
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
if (best_mbmode.mode == B_PRED)
Initial WebM release
2010-05-18 17:58:33 +02:00
{
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
for (i = 0; i < 16; i++)
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
xd->mode_info_context->bmi[i].as_mode = best_bmodes[i].as_mode;
Initial WebM release
2010-05-18 17:58:33 +02:00
}
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
if (best_mbmode.mode == SPLITMV)
{
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
for (i = 0; i < 16; i++)
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
xd->mode_info_context->bmi[i].mv.as_int = best_bmodes[i].mv.as_int;
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
vpx_memcpy(x->partition_info, &best_partition, sizeof(PARTITION_INFO));
MODE_INFO size reduction Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO. This reduced the memory footprint by 518,400 bytes for 1080 resolutions. The decoder performance improved by ~4% for the clip used and the encoder showed very small improvements. (0.5%) This reduction was first mentioned to me by John K. and in a later discussion by Yaowu. This is WIP. Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
2011-05-24 19:24:52 +02:00
Using partition_info instead of blockd info for splitmv The partition_info struct contains info just for SPLITMV, so it should be used instead of BLOCKD. Eventually, I want to reduce the size of B_MODE_INFO struct found in BLOCKD, so this is the first step toward that goal. Also, since SPLITMV is not supported in vp8_pick_inter_mode(), the unnecessary mem copies and checks were removed. For rt encodes, this gave a slight performance improvement. Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
2011-05-19 21:03:36 +02:00
x->e_mbd.mode_info_context->mbmi.mv.as_int =
x->partition_info->bmi[15].mv.as_int;
}
Only call vp8_find_near_mvs() once for each macroblock While doing motion search on a macroblock, we usually call vp8_find_near_mvs once per reference frame. Actually, for different reference frames, the only difference in calculating these near_mvs is they may have different sign_bias, which causes a sign change in resulting near_mvs. In this change, we only do find_near_mvs for the first reference frame. For other reference frames, only need to adjust the near_mvs according to that reference frame's sign_bias value. Change-Id: I661394b49c6ad79fed7d0f2eb2be239b9c56f149
2011-12-14 21:35:04 +01:00
if (sign_bias
!= cpi->common.ref_frame_sign_bias[xd->mode_info_context->mbmi.ref_frame])
Correct clamping in use of vp8_find_near_mvs() Commit e06c242ba introduced a change to call vp8_find_near_mvs() only once instead of once per reference frame by observing that the only effect that the frame had was on the bias applied to the motion vector. By keeping track of the sign_bias value, the mv to use could be flip-flopped by multiplying its components by -1. This behavior was subtley wrong in the case when clamping was applied to the motion vectors found by vp8_find_near_mvs(). A motion vector could be in-bounds with one sign bias, but out of bounds after inverting the sign, or vice versa. The clamping must match that done by the decoder. This change modifies vp8_find_near_mvs() to remove the clamping from that function. The vp8_pick_inter_mode() and vp8_rd_pick_inter_mode() functions instead track the correctly clamped values for both bias values, switching between them by simple assignment. The common clamping and inversion code is in vp8_find_near_mvs_bias() Change-Id: I17e1a348d1643497eca0be232e2fbe2acf8478e1
2012-01-25 23:55:49 +01:00
best_ref_mv.as_int = best_ref_mv_sb[!sign_bias].as_int;
Removed bmi copy to/from BLOCKD for SPLITMV and B_PRED modes. Modified code to use the bmi found in mode_info_context instead of BLOCKD. On the decode side, the uvmvs are calculated only when required, instead of every macroblock. This is WIP. (bmi should eventually be removed from BLOCKD) Small performance gains noticed for RT encodes and decodes.(VGA) Change-Id: I2ed7f0fd5ca733655df684aa82da575c77a973e7
2011-08-24 20:42:26 +02:00
Only call vp8_find_near_mvs() once for each macroblock While doing motion search on a macroblock, we usually call vp8_find_near_mvs once per reference frame. Actually, for different reference frames, the only difference in calculating these near_mvs is they may have different sign_bias, which causes a sign change in resulting near_mvs. In this change, we only do find_near_mvs for the first reference frame. For other reference frames, only need to adjust the near_mvs according to that reference frame's sign_bias value. Change-Id: I661394b49c6ad79fed7d0f2eb2be239b9c56f149
2011-12-14 21:35:04 +01:00
rd_update_mvcount(cpi, x, &best_ref_mv);
Initial WebM release
2010-05-18 17:58:33 +02:00
}
Move RD intra block mode selection to rdopt.c This change is analogous to I0b67dae1f8a74902378da7bdf565e39ab832dda7, which made the move for the non-RD path. Change-Id: If63fc1b0cd1eb7f932e710f83ff24d91454f8ed1
2011-06-08 18:05:05 +02:00
void vp8_rd_pick_intra_mode(VP8_COMP *cpi, MACROBLOCK *x, int *rate_)
{
int error4x4, error16x16;
int rate4x4, rate16x16 = 0, rateuv;
int dist4x4, dist16x16, distuv;
int rate;
int rate4x4_tokenonly = 0;
int rate16x16_tokenonly = 0;
int rateuv_tokenonly = 0;
x->e_mbd.mode_info_context->mbmi.ref_frame = INTRA_FRAME;
rd_pick_intra_mbuv_mode(cpi, x, &rateuv, &rateuv_tokenonly, &distuv);
rate = rateuv;
error16x16 = rd_pick_intra16x16mby_mode(cpi, x,
&rate16x16, &rate16x16_tokenonly,
&dist16x16);
error4x4 = rd_pick_intra4x4mby_modes(cpi, x,
&rate4x4, &rate4x4_tokenonly,
&dist4x4, error16x16);
if (error4x4 < error16x16)
{
x->e_mbd.mode_info_context->mbmi.mode = B_PRED;
rate += rate4x4;
}
else
{
rate += rate16x16;
}
*rate_ = rate;
}
Reference in New Issue Copy Permalink