Commit Graph

6181 Commits

Author SHA1 Message Date
hkuang
62a2cd9ed2 Merge "Add neon optimize vp9_short_idct10_8x8_add." 2013-08-20 14:06:57 -07:00
Dmitry Kovalev
381d3b8b7d Merge "vp9_filter.{h, c} cleanup + adding SUBPEL_TAPS constant." 2013-08-20 13:46:53 -07:00
Dmitry Kovalev
d19ac4b66d vp9_filter.{h, c} cleanup + adding SUBPEL_TAPS constant.
Change-Id: Ib394ea23f464591dad50b5c65c316701378d06d7
2013-08-20 12:29:57 -07:00
hkuang
37cda6dc4c Add neon optimize vp9_short_idct10_8x8_add.
vp9_short_idct10_8x8_add is used to handle the block that only have valid data
at top left 4x4 block. All the other datas are 0. So we could cut several
unnecessary calculations in order to save instructions.

Change-Id: I34fda95e29082b789aded97c2df193991c2d9195
2013-08-20 11:51:07 -07:00
Jingning Han
1bf1428654 Enable zero coeff check in sub8x8 UV rd loop
Check the minimum rate-distortion cost of regular quantization and
all zero coeffs cases in the sub8x8 inter prediction rd loop for
luma components. Use this as the cumulative rdcost sent to UV rd
estimation.

Change-Id: Ia4bc7700437d5e13d7cdad4cf9ae57ab036d3e97
2013-08-20 10:33:42 -07:00
Deb Mukherjee
246381faf2 Merge "Cleanup/enhancements of switchable filter search" 2013-08-20 10:16:51 -07:00
Dmitry Kovalev
5826407f2a Merge "Moving plane_block_idx from vp9_blockd.h to vp9_quantize.c." 2013-08-20 10:06:22 -07:00
Dmitry Kovalev
5baf510f74 Merge "Adding has_second_ref function." 2013-08-20 10:06:14 -07:00
Dmitry Kovalev
039b0c4c9e Merge "Adding VP9_FILTER_BITS constant." 2013-08-20 10:05:09 -07:00
Deb Mukherjee
2ffe64ad5c Cleanup/enhancements of switchable filter search
Cleans up the switchable filter search logic. Also adds a
speed feature - a variance threshold - to disable filter search
if source variance is lower than this value.

Results: derfraw300
threshold = 16, psnr -0.238%, 4-5% speedup (tested on football)
threshold = 32, psnr -0.381%, 8-9% speedup (tested on football)
threshold = 64, psnr -0.611%, 12-13% speedup (tested on football)
threshold = 96, psnr -0.804%, 16-17% speedup (tested on football)

Based on these results, the threshold is chosen as 16 for speed 1,
32 for speed 2, 64 for speed 3 and 96 for speed 4.

Change-Id: Ib630d39192773b1983d3d349b97973768e170c04
2013-08-20 09:47:04 -07:00
Jingning Han
bb64c9a355 Merge "Enable early termination in uv rd loop" 2013-08-20 09:07:26 -07:00
Jim Bankoski
be5dc2321b Merge "fix the mv_ref_idx issue" 2013-08-20 09:00:57 -07:00
Jim Bankoski
f167433d9c fix the mv_ref_idx issue
The following issue was reported :
https://code.google.com/p/webm/issues/detail?id=601&q=jimbankoski&sort=-id&colspec=ID%20Pri%20mstone%20ReleaseBlock%20Type%20Component%20Status%20Owner%20Summary

This code makes the choice and code cleaner and removes any question
about whether the border needs to be checked.

Change-Id: Ia7aecfb3168e340618805bd318499176c2989597
2013-08-20 08:14:52 -07:00
Paul Wilkins
e8923fe492 Changes to auto partition size selection.
Changes to code to auto select a partition size range
based on data from spatial neighbors.

Now looks at the sb_type in each 8x8 block of above
and left SB64.

The effect on speed 1 is now weaker giving better
quality but less speed gain. Now also used in speed 2.

Change-Id: Iace33a97d5c3498dd2a9a8a4067351941abcbabc
2013-08-20 14:05:39 +01:00
Dmitry Kovalev
2612b99cc7 Adding VP9_FILTER_BITS constant.
Removing VP9_FILTER_WEIGHT, VP9_FILTER_SHIFT, BLOCK_WIDTH_HEIGHT
constants. Using ROUND_POWER_OF_TWO for rounding.

Change-Id: I2e8d6858dcd600a87096138209731137d7decc24
2013-08-20 00:42:25 -07:00
Dmitry Kovalev
d8286dd56d Adding has_second_ref function.
Updating implementation of vp9_get_pred_context_single_ref_p1 using
has_second_ref function to make code easier to read.

Change-Id: Ie8f60403a7195117ceb2c6c43176ca9a9e70b909
2013-08-19 18:39:34 -07:00
Yaowu Xu
c4048dbdd3 Change to limit the mv search range
As the pixel values beyond image border are duplicates of pixels
on edge, the change limits the mv search range, any mv beyond
the limits no longer produce new/different prediction values
as entire block with pixels used for subpel interpolation are
outside image border.

Change-Id: I4c6fdf06e33c1cef1489f5470ce0fb4e5e01fb79
2013-08-19 17:19:36 -07:00
Yaowu Xu
f70330a906 fix a bug when null function pointer is used.
For certain partition size, the function poniter may not be intialized
at all. The patch prevent the call if the pointer is not set.

Change-Id: I78b8c3992b639e8799a16b3c74f0973d07b8b9ac
2013-08-19 17:16:12 -07:00
Dmitry Kovalev
569ca37d09 Moving plane_block_idx from vp9_blockd.h to vp9_quantize.c.
Change-Id: Ib8af21f2e7f603c2fb407e5d15a3bba64b545b49
2013-08-19 16:44:10 -07:00
Jingning Han
3275ad701a Enable early termination in uv rd loop
This commit enables early termination in the rate-distortion
optimization search loop for chroma components. When the cumulative
rd cost is above the current best value, skip the rest per-block
transform/quantization/coeff_cost and continue to the next
prediction mode.

For bus_cif at 2000 kbps, the average run-time goes down from
168546ms -> 164678ms, (2% speed-up) at speed 0
 36197ms ->  34465ms, (4% speed-up) at speed 1

Change-Id: I9d3043864126e62bd0166250d66b3170d520b3c0
2013-08-19 16:31:19 -07:00
Dmitry Kovalev
82d4d9a008 Passing plane_bsize to foreach_transformed_block_visitor.
Updating all foreach_transformed_block_visitor functions to work with
plane block size instead of general block. Removing a lot of duplicated
code.

Change-Id: I6a9069e27528c611f5a648e1da0c5a5fd17f1bb4
2013-08-19 15:47:24 -07:00
Jingning Han
31c97c2bdf Merge "Fix potential use of uninitialized value" 2013-08-19 15:15:58 -07:00
Jingning Han
5dc0b309ab Merge "Fix the returned distortion value in rd_pick_intra" 2013-08-19 14:34:19 -07:00
Dmitry Kovalev
2e3478a593 Using plane_bsize instead of bsize.
This change set is intermediate. The next one will remove all repetitive
plane_bsize calculations, because it will be passed as argument to
foreach_transformed_block_visitor.

Change-Id: Ifc12e0b330e017c6851a28746b3a5460b9bf7f0b
2013-08-19 13:20:21 -07:00
Adrian Grange
5a1a269f67 Further correct bug in loopfilter initialization
The intent was to initialize the deltas for the
segment to the computed value, irrespective of mode
and reference frame if (mode_ref_delta_enabled == 0).

(In response to bug posted by Manjit Hota to codec-devel
and webm-discuss lists)

Change-Id: I10435cb63d0f88359bb4c14f22181878a1988e72
2013-08-19 11:58:52 -07:00
Jingning Han
b34ce04378 Fix potential use of uninitialized value
Initialize the best mode and tx_size values in the rate-distortion
optimization search loop.

Change-Id: Ibfb5c0895691f172abcd4265c23aef4cb99fa8af
2013-08-19 11:15:53 -07:00
Jingning Han
f67919ae86 Fix the returned distortion value in rd_pick_intra
Return the distortion value in vp9_rd_pick_intra_mode_sb as sum of
dist_y and dist_uv. Remove the right shift operation on dist_uv,
and make it consistent with that of vp9_rd_pick_inter_mode_sb.

Change-Id: I9d564e242d9add38e32595d33b0e0dddb1d55e5b
2013-08-16 21:23:22 -07:00
Dmitry Kovalev
26e5b5e25d Removing unused or redundant arguments from *_args structures.
Redundant dst, pre[2] from build_inter_predictors_args, unused cm from
encode_b_args.

Change-Id: I2c476cd328c5c0cca4c78ba451ca6ba2a2c37e2d
2013-08-16 12:51:20 -07:00
Dmitry Kovalev
367cb10fcf Merge "Moving from ss_txfrm_size to tx_size." 2013-08-16 12:46:45 -07:00
Dmitry Kovalev
1462433370 Merge "Renaming d27 predictor to d207." 2013-08-16 12:07:24 -07:00
Johann
d514b778c4 Merge "Reduce the instructions of idct8x8. Also add the saving and restoring of D registers." 2013-08-16 11:30:21 -07:00
Johann
65aa89af1a Merge "Reduce instructions of idct4x4." 2013-08-16 11:28:35 -07:00
Frank Galligan
bdc785e976 Merge "vp9: neon: optimise vp9_wide_mbfilter_neon" 2013-08-16 11:16:48 -07:00
hkuang
df0715204c Reduce instructions of idct4x4.
Change-Id: Ia26a2526804e7e2f656b0051618a615fca8fc79d
2013-08-16 10:54:56 -07:00
hkuang
60ecd60c9a Reduce the instructions of idct8x8. Also add the
saving and restoring of D registers.

Change-Id: Id3630c90fcb160ef939fef55411342608af5f990
2013-08-16 10:32:12 -07:00
Johann
bba68342ce Merge "vp9: neon: use aligned stores in convolve functions" 2013-08-16 10:29:59 -07:00
Adrian Grange
79f4c1b9a4 Fixed typos and formatting
Change-Id: I3814984a624bc64147c57efa74fbdda8eda47262
2013-08-16 09:15:26 -07:00
Adrian Grange
3e340880a8 Merge "Added resizing & initialization of last frame segment map" 2013-08-16 09:07:36 -07:00
Mans Rullgard
4fa93bcef4 vp9: neon: use aligned stores in convolve functions
The destination is block-aligned so it is safe to use aligned
stores.

Change-Id: I38261e4fa40bc60e6472edffece59e372908da7e
2013-08-16 14:25:08 +01:00
Dmitry Kovalev
afd9bd3e3c Moving from ss_txfrm_size to tx_size.
Updating foreach_transformed_block_visitor and corresponding functions
to accept tx_size instead of ss_txfrm_size. List of functions per file:

vp9_decodframe.c
  decode_block
  decode_block_intra

vp9_detokenize.c
  decode_block

vp9_encodemb.c
  optimize_block
  vp9_xform_quant
  vp9_encode_block_intra

vp9_rdopt.c
  dist_block
  rate_block
  block_yrd_txfm

vp9_tokenize.c
  set_entropy_context_b
  tokenize_b
  is_skippable

Change-Id: I351bf563eb36cf34db71c3f06b9bbc9a61b55b73
2013-08-15 17:03:03 -07:00
Jingning Han
5e80a49307 Merge "Refactor rd loop for chroma components" 2013-08-15 16:02:12 -07:00
Adrian Grange
d5bec522da Added resizing & initialization of last frame segment map
When the frame size changes the last frame segment map must
be resized to match and initialized to 0.

Change-Id: Idc10de109f55dbe9af3a6caae355a2974712243d
2013-08-15 15:35:21 -07:00
Dmitry Kovalev
9451e8d37e Merge "Converting code from using ss_txfrm_size to tx_size." 2013-08-15 15:21:09 -07:00
Dmitry Kovalev
939b1e4a8c Merge "Moving segmentation struct from MACROBLOCKD to VP9_COMMON." 2013-08-15 15:14:32 -07:00
Johann
a9aa7d07d0 Merge "vp9: neon: add vp9_convolve_avg_neon" 2013-08-15 14:55:15 -07:00
Johann
63e140eaa7 Merge "vp9: neon: add vp9_convolve_copy_neon" 2013-08-15 14:55:08 -07:00
Jingning Han
68369ca897 Refactor rd loop for chroma components
This commit makes the rate-distortion optimization search of chroma
components consistent across all block sizes. It removes redundant
codes.

Change-Id: I7e76f54d045e8efdd41d84a164c71f55b484471b
2013-08-15 14:54:48 -07:00
Jingning Han
c2ff1882ff Merge "Remove unused RDCOST_8X8 macro" 2013-08-15 13:48:25 -07:00
Jingning Han
ca983f34f7 Merge "Unify luma and chroma rd-cost estimation" 2013-08-15 13:48:15 -07:00
Dmitry Kovalev
bb3b817c1e Converting code from using ss_txfrm_size to tx_size.
Updated function signatures:
  txfrm_block_to_raster_block
  txfrm_block_to_raster_xy
  extend_for_intra
  vp9_optimize_b

Change-Id: I7213f4c4b1b9ec802f90621d5ba61d5e4dac5e0a
2013-08-15 11:44:57 -07:00