Commit Graph

6282 Commits

Author SHA1 Message Date
James Zern
3c8cce353f vp9: make some static tables const
Change-Id: I8bcae51271673da8755c66a51aea005dfe6a3739
2013-07-22 19:19:13 -07:00
Frank Galligan
e88db77892 Merge "Speedup loopfilter neon code." 2013-07-22 17:39:42 -07:00
Dmitry Kovalev
0ad079e583 Cleanup inside vp9_get_pred_context_tx_size.
Using max_txsize_lookup to get max transform size.

Change-Id: If4b39beba3c06a581effd8cab698ea90727dc2c9
2013-07-22 17:18:11 -07:00
James Zern
ab139094ed Merge "VP9_COMMON: drop cur_tile_{row,col}_idx" 2013-07-22 17:12:39 -07:00
Frank Galligan
5af6bf6c43 Speedup loopfilter neon code.
Try and cut down the cycle count by rearranging the instructions
so there are less stalls.

Change-Id: Ic1383335ee0f05e656477d9ee9c179ec231285d5
2013-07-22 17:00:01 -07:00
James Zern
37da8ea693 Merge "vp9: apply loopfilter inline if possible" 2013-07-22 16:32:20 -07:00
Ronald S. Bultje
e20fcd9585 More optimizations for cost_coeffs().
4x4:    163 ->  123 cycles (33% faster)
8x8:    491 ->  399 cycles (23% faster)
16x16: 1889 -> 1763 cycles (7% faster)
32x32: 8311 -> 8180 cycles (1.6% faster)

Overall encoding time of first 50 frames of bus (speed 0) @ 1500kbps
goes from 1min4.33 to 1min3.00, i.e. 2.11% faster.

Change-Id: Ib52d1dbb5649b14de769d3e7a74af67440b5284f
2013-07-22 16:09:09 -07:00
James Zern
38a4412e1b vp9: apply loopfilter inline if possible
excludes tiled content currently

Change-Id: I44155253e8d6771e5e039d663be5f21cc9d0355d
2013-07-22 15:52:10 -07:00
Yunqing Wang
f9e8167ba9 libyuv: fix SSSE3 code in scale.c
This patch was provided by Frank.

Change-Id: Icebcbd96016a51a85dbe5e8a351ab7624ace962b
2013-07-22 15:42:23 -07:00
Dmitry Kovalev
b2fc6fa969 Adding update_tx_counts function.
Moving common encoder/decoder code to update_tx_counts. Also renaming
vp9_get_pred_probs_tx_size to get_tx_probs2 and adding get_tx_probs to
call vp9_get_pred_context_tx_size inside read_selected_tx_size only once
(twice before).

Change-Id: Ia50247f3893de88ef8e9041b0d44be44a40aaa4d
2013-07-22 14:57:43 -07:00
James Zern
746154d905 Merge "filter_block_plane: remove MACROBLOCKD param" 2013-07-22 13:43:34 -07:00
James Zern
0a58f462b8 VP9_COMMON: remove unused temp_scale_frame
Change-Id: I696a0dca1d02d365e283029d1d077710bd5680e0
2013-07-22 13:42:11 -07:00
Dmitry Kovalev
0c5a383b2a Merge "Using update_ct and update_ct2 functions for probability update." 2013-07-22 13:34:30 -07:00
James Zern
ccf6710dc2 VP9_COMMON: drop cur_tile_{row,col}_idx
these were only being written in one location and never read.

Change-Id: If59f3c09aa1485cf89bac0099a8a79e99688b5d1
2013-07-22 13:23:33 -07:00
Yaowu Xu
6261d79206 Merge "fix a build error" 2013-07-22 13:02:15 -07:00
James Zern
32bca36f51 Merge "configure: default configure log to config.log" 2013-07-22 12:55:29 -07:00
James Zern
76db4d599a Merge "VP[89]_COMMON: remove golden/altref frame counts" 2013-07-22 12:55:07 -07:00
Yaowu Xu
fc186dcad6 fix a build error
Change-Id: I3b05687f439ff6a7c426d2c97a6c58c831fa51ac
2013-07-22 12:37:30 -07:00
Jingning Han
416f315e82 Merge "Skip buffer update in sub8x8 rd loop" 2013-07-22 12:08:22 -07:00
Jingning Han
a5a9f5f7f3 Merge "Optimize operation flow in sub8x8 rd loop" 2013-07-22 12:08:15 -07:00
Dmitry Kovalev
8c5ca9ff14 Using update_ct and update_ct2 functions for probability update.
Update logic for both mode and mvref was the same, so using MODE_COUNT_SAT,
MODE_MAX_UPDATE_FACTOR, update_ct, update_ct2 for both cases. Removing
function update_tx_ct because it was identical to update_mode_ct2.

Change-Id: Iff566be27dbd6cde4c2ec04e8d988f207046b8f0
2013-07-22 12:06:43 -07:00
James Zern
1197d6736c Merge "tests: silence a few type related warnings" 2013-07-22 11:50:22 -07:00
James Zern
4a688b26f7 Merge "cosmetics: idct_test.cc: fix formatting" 2013-07-22 11:49:23 -07:00
Deb Mukherjee
a1e2d50be9 Diamond search change to accelerate movement
Optional change in diamond search to continue in the best move
direction until that move turns worse.

This is still WIP since the exact way the new method is to be used is
under investigation. One option is to make it an option in diamond
search and use it only when motion is large.

Overall slightly positive on derfraw300 +0.02%, stdhdraw +0.13%,
but works a lot better for high motion sequences (ex. football : +1%).

Change-Id: If88e01a6021daa0cda934680cdc70be1ee04f798
2013-07-22 11:19:15 -07:00
Paul Wilkins
3798d7a641 Merge "Re-order mode search in rd." 2013-07-22 10:46:04 -07:00
Jingning Han
409e77f2d4 Optimize operation flow in sub8x8 rd loop
Stack the rate-distortion statistics in the sub8x8 rd loop. This allows
the encoder to skip the forward transform, quantization, and coeff cost
estimation, in the sub8x8 rd optimization search, if the motion
vector(s) are of integer pixel value, and have been tested in the
previous prediction filter type rd loops of the same block.

This gives about 2% speed-up for bus_cif at 2000 kpbs, for speed 0.
Its efficacy depends how frequently the motion search will select an
integer motion vector.

Change-Id: Iee15d4283ad4adea05522c1d40b198b127e6dd97
2013-07-22 10:40:33 -07:00
Paul Wilkins
1d189d6464 Re-order mode search in rd.
Mode search order in rd loop changed to better reflect
observed hit counts.

Also some adjustment of the baseline mode rd thresholds
to reflect the order change and observed frequencies.

Change-Id: I47a131cc83e11551df8add6d6d8d413d78d3a63c
2013-07-22 17:21:12 +01:00
Jim Bankoski
9ad604c6fb Merge "fix left over overflow" 2013-07-22 08:51:26 -07:00
Jim Bankoski
2ac8b50cd8 fix left over overflow
This cl fixes issues rbultje brought up. that I somehow neglected when I
submitted yaowu's patch.

Change-Id: I07ad18796317822510b96e951c88d29f194a3c2e
2013-07-22 06:39:39 -07:00
Paul Wilkins
888375d243 Fix build error.
When CONFIG_POSTPROC is set there was a now
invalid reference to cm->filter_level.

Changed to cpi->mb.e_mbd.lf.filter_level in line with
change Iaf5fb71c33719cdfa1b991f671caf071be9ea035

Change-Id: If746e60044903f7ba8d0d346225b3d015226c7d0
2013-07-22 14:01:43 +01:00
Dmitry Kovalev
ee1fe2f750 Merge "Removing pre probabilities from FRAME_CONTEXT." 2013-07-20 22:50:32 -07:00
Dmitry Kovalev
8962d975b2 Merge "Moving all loop filter related variables into new struct." 2013-07-20 22:45:24 -07:00
Dmitry Kovalev
39342db138 Merge "Consistent names for inter mode probabilities and encodings." 2013-07-20 22:40:51 -07:00
Dmitry Kovalev
f66821afbb Merge "Removing frame_type field from MACROBLOCKD struct." 2013-07-20 22:40:06 -07:00
Dmitry Kovalev
2b089f149a Merge "Removing unused static arrays from vp9_reatectrl.c." 2013-07-20 22:39:33 -07:00
Dmitry Kovalev
ad46753378 Merge "Moving vp9_reader into decode_tiles function." 2013-07-20 22:39:22 -07:00
Jingning Han
c725502bf3 Skip buffer update in sub8x8 rd loop
This commit allows the encoder to skip a few buffer update steps in
rd_pick_best_mbsegmentation, when early breakout has been triggered
in the rd_check_segment_txsize. It provides about 1% speed-up for
bus_cif at 2000 kbps, in the settings of speed 0.

Change-Id: Ica034f10a24dec572b397d8389a2b81020ebc0b9
2013-07-20 21:38:12 -07:00
Yaowu Xu
ea284d6281 added checks to prevent rate/distortion overflow
At speed 2, due to the threshold scheme used, it is possible the rate
and distortion assigned with INT_MAX value. The patch added checking
to prevent the INT_MAX value is used in further calculation of RD
scores. The patch also changed the assertion in rd_use_partition() to
be mirror similar assertion in rd_pick_partition().

Change-Id: Idb52c543cc1e10abdf6e6a5d6e9cb535a42214dc
2013-07-19 17:52:50 -07:00
Dmitry Kovalev
7e703de729 Removing pre probabilities from FRAME_CONTEXT.
Using cm->frame_contexts[cm->frame_context_idx] as source of previous
probabilities.

Change-Id: Ie03778acf0e7bebdc3a1f6a51854d4a0712f24a1
2013-07-19 17:33:10 -07:00
Dmitry Kovalev
ee1771ebaa Moving all loop filter related variables into new struct.
Adding loopfilter struct with fields from MACROBLOCKD and VP9Common.
Eventually it will be moved to vp9_loopfilter.h for better code structure.

Change-Id: Iaf5fb71c33719cdfa1b991f671caf071be9ea035
2013-07-19 16:19:10 -07:00
Dmitry Kovalev
f00a237a43 Merge "Fixing problem introduced in one of my previous commits." 2013-07-19 16:14:21 -07:00
Dmitry Kovalev
29f0f79317 Removing unused static arrays from vp9_reatectrl.c.
Removed arrays: kf_boost_seperation_adjustment,
                gf_adjust_table,
                gf_intra_usage_adjustment,
                gf_interval_table.

Change-Id: I62e400cb6e4d039787615169a3779e31ebf95893
2013-07-19 15:55:09 -07:00
Dmitry Kovalev
c3a56ee583 Merge "Moving Scale2Ration function from vp9_onyx.h to vp9_onyx_if.c." 2013-07-19 15:27:24 -07:00
Dmitry Kovalev
2fc927c66a Fixing problem introduced in one of my previous commits.
Changing fc->tx_probs back to fc->pre_tx_probs. This change actually
affects the bitstream but current test vectors work. Chrome branch is not
affected at all. Broken since:

cc662dd Adding struct tx_probs and struct tx_counts to cleanup the code.

Change-Id: I36dd4b3678e902e10aba8dd49b0012eb558c209d
2013-07-19 15:18:43 -07:00
Deb Mukherjee
302698fb12 Reworked the auto_mv_step_size speed feature
This patch modifies the auto_mv_step_size speed feature to
use a combination of the maximum magnitude mv from the last
inter frame, and the maximum magnitude mv for the two reference
mvs with the same reference. For arf frames, the max mav step
for the resolution is used.
The bounds therefore are slightly tighter. The feature is made
a speed 1 feature.

Rebased.

Results (when this feature is turned on over speed 0):
derfraw300: -0.046% psnr, about 5+% speedup
(tested on football: goes from 4m30.760s to 4m17.410s).

Change-Id: If492797a61b0b4b3e58c0b8f86afb880165fc9f6
2013-07-19 15:12:56 -07:00
James Zern
de012cec4f filter_block_plane: remove MACROBLOCKD param
replace with direct use of the plane and MODE_INFO

Change-Id: Icce57bc398a6e3607aedde0573d977e192040696
2013-07-19 14:19:55 -07:00
Morton Jonuschat
0d204f48b5 Merge "Make libvpx compile on OSX 10.9 (Mavericks)" 2013-07-19 12:37:26 -07:00
Dmitry Kovalev
d6e74e0d59 Moving vp9_reader into decode_tiles function.
Change-Id: Ic741054836d6c1b89c4f1c75cc6bd938a7d56723
2013-07-19 12:27:56 -07:00
Morton Jonuschat
fe4a52077f Make libvpx compile on OSX 10.9 (Mavericks)
Change-Id: Ibf2555f1c0d00e91d416eb39201a5a91df7fab27
2013-07-19 21:22:18 +02:00
Dmitry Kovalev
e71a4a77bb Merge "Renaming TXFM_MODE to TX_MODE (like TX_SIZE, TX_TYPE)." 2013-07-19 12:14:32 -07:00