Commit Graph

6449 Commits

Author SHA1 Message Date
Deb Mukherjee
6d0ee9860e Merge "Adds high bitdepth convolve, interpred & scaling" 2014-09-18 10:52:23 -07:00
Deb Mukherjee
0d3c3d3ce7 Adds high bitdepth convolve, interpred & scaling
Change-Id: Ie51c352a6b250547207cbc1ebba833a01ed053e3
2014-09-18 07:26:17 -07:00
Paul Wilkins
c389b37bb4 Substantial reworking of code for arf and kf groups.
Substantial restructuring of the way we estimate
the rate of decay in prediction quality and determine
the arf interval and amount of boost used.

Also other changes to support moving to a lower first pass
Q which exposes some new features and allows us to better
distinguish genuinely static blocks from low motion or noisy
blocks.

Net gains now visible on all the test sets with std-hd PSNR up
1.87%. There are still some bad outlier cases but most of these
are low motion or slide show type content where the metrics
are already high at any given rate. The best + case is up by
more than 10%.

Change-Id: I18e25170053bdf3188f493ff8062f48a74515815
2014-09-18 12:53:48 +01:00
Frank Galligan
4e066299d9 Merge "Improved mb_lpf_horizontal_edge_w_sse2_16() #2" 2014-09-17 18:52:30 -07:00
Scott LaVarnway
217e3cb1fb Improved mb_lpf_horizontal_edge_w_sse2_16() #2
The decoder performance improved up to 1% for the
test clips used.

Change-Id: I4621112bdccfba01640322facfa4ba8da8290ea5
2014-09-17 17:25:20 -07:00
Deb Mukherjee
7d0e4f9ad1 Resolves a few gcc warnings
clang is fine.

Change-Id: Ia4e9ff17ea3b86bc87dca35828ee7ce45bea6994
2014-09-16 22:44:40 -07:00
Deb Mukherjee
f7cf05cfe0 Merge "Adding high-bitdepth intra prediction functions" 2014-09-16 17:10:24 -07:00
Frank Galligan
ecd7e3d2b7 Merge "Remove memset of every external frame buffer." 2014-09-16 15:17:26 -07:00
Dmitry Kovalev
4f506358c4 Merge "Speeding up decode_coeffs()." 2014-09-16 15:13:14 -07:00
Deb Mukherjee
81a8138fc3 Adding high-bitdepth intra prediction functions
Change-Id: I6f5cb101e2dc57c3d3f4d7e0ffb4ddbed027d111
2014-09-16 15:04:39 -07:00
Deb Mukherjee
5cd0aab81a Adds high bitdepth quantization functions
Adds various high bitdepth quantization functions.

Change-Id: I36fc0bf75a1bd15128ed271df8723de0ac134b0c
2014-09-16 14:55:37 -07:00
Jingning Han
66f812fb56 Merge "Use non-zero mode threshold for NEARESTMV modes" 2014-09-16 13:39:54 -07:00
Yaowu Xu
73ef5360b5 Merge "Fix a performance regression" 2014-09-16 12:58:47 -07:00
Adrian Grange
2b3b63f422 Merge "Fix ARF construction when scaling" 2014-09-16 12:35:23 -07:00
Dmitry Kovalev
adaec4d0fb Speeding up decode_coeffs().
1080p decoding speedup -- 1.25%, 4K decoding speedup -- 2.5%.

Change-Id: I5f02f521cbf7758d4d1886a93bc5b074abdff03d
2014-09-16 12:04:09 -07:00
Adrian Grange
99df7ded95 Merge "Move call to vp9_rc_get_second_pass_params()." 2014-09-16 11:37:33 -07:00
Yaowu Xu
601f3a886e Fix a performance regression
This commit adds back sse2 or ssse3 optimized versio of a couple of
functions, fixes a ~10% performance regression.

Change-Id: I049786906e5a641224dced63c6492aec9d86d183
2014-09-16 11:18:46 -07:00
Adrian Grange
1def634f1a Fix ARF construction when scaling
The ARF frame should always be the same size as the
native resolution of the input frames.

It will be scaled to the required resolution at
encode time.

Change-Id: I0afe858129aa6ef65b1648f43476331715346896
2014-09-16 11:12:49 -07:00
Jingning Han
56fa3ab886 Use non-zero mode threshold for NEARESTMV modes
This commit makes the encoder to use non-zero mode threshold for
NEARESTMV modes. The runtime for test clips of speed 3 is reduced
by about 1%.

pedestrian 1080p 2000 kbps, 143239 ms -> 141989 ms
bus CIF 1000 kbps, 7835 ms -> 7749 ms

The compression performance change is about -0.02% for both derf
and stdhd.

Change-Id: Ib71808922c41ae2997100cb7c561f68dcebfa08e
2014-09-16 09:56:10 -07:00
Jingning Han
ffaebfc7b4 Merge "Add ARF validation for compound inter mode check" 2014-09-15 21:26:37 -07:00
Jingning Han
c50256c157 Merge "Remove redundant reference frame check in sub8x8 RD search" 2014-09-15 21:26:11 -07:00
Jingning Han
fe96932c69 Merge "Replace best_ref_index table fetch with best_mbmode" 2014-09-15 21:25:48 -07:00
Yunqing Wang
57eb2a4e83 Merge "Simplify the skip flag cost code" 2014-09-15 18:50:30 -07:00
Yunqing Wang
c60ef810a1 Merge "Set the skip flag to 1 for skippable blocks" 2014-09-15 18:50:19 -07:00
Yunqing Wang
200ec69abb Simplify the skip flag cost code
Code refactoring.

Change-Id: Idad53cb80497d13551a142a642f7529fc305b0bc
2014-09-15 17:11:16 -07:00
Yunqing Wang
46aed7b8d0 Set the skip flag to 1 for skippable blocks
If the partition block is skippable, which means no coefficients
for Y, U, and V planes, its skip flag is set to 1. No quality
change (verified by borg tests), and no noticeable speed change.

Change-Id: I9231f720f8dd6364384cf05aa148ca24d75450f1
2014-09-15 16:50:19 -07:00
Frank Galligan
175d9dfe0a Remove memset of every external frame buffer.
Libvpx was memseting every external frame buffer before decode. This
was to work around a valgrind issue in our C loop filter. Most of
the time this was not needed and we have noticed some significant
performance loss on some platforms. Now we require the application to
zero out the buffers if it is using external frame buffers.

Change-Id: I7330d00a315e65137ed30edd5f813e8929b76242
2014-09-15 15:37:36 -07:00
Jingning Han
f897dd5f09 Merge "Fix format in vp9_rd_pick_inter_mode_sub8x8" 2014-09-15 15:34:22 -07:00
Jingning Han
f1581b3b2e Add ARF validation for compound inter mode check
This commit enforces ARF validation check for compound inter modes.
It avoids potential access to ARF in the encoding process if it
is not allowed.

Change-Id: I055fec946b5d19d97937dc9001e1e564923e2439
2014-09-15 12:20:57 -07:00
Jingning Han
252822e81c Remove redundant reference frame check in sub8x8 RD search
The valid reference frame check in sub8x8 rate-distortion
optimization search has been included in the ref_frame_skip_mask
scheme. This commit removes the later further validation checks
that are not in effect.

Change-Id: I853b477c44037d3dc0afec6cbfce08a96c597a75
2014-09-15 12:20:04 -07:00
Jingning Han
cc00eea676 Replace best_ref_index table fetch with best_mbmode
This commit replaces the best_ref_index table fetch with the use
of best_mbmode in vp9_rd_pick_inter_mode_sub8x8.

Change-Id: I882ee9ee6a8c0e61befcca1f4dba6d2ea8de8f13
2014-09-15 09:59:20 -07:00
Jingning Han
73805bfa70 Fix format in vp9_rd_pick_inter_mode_sub8x8
Change-Id: I9b6a74bdf003b39235f14f8b5b7f3b861f6bf131
2014-09-15 09:44:09 -07:00
Yunqing Wang
10a9456ade Merge "Refactor encode_superblock function" 2014-09-15 09:28:31 -07:00
Paul Wilkins
cd95543ee4 Move call to vp9_rc_get_second_pass_params().
Call to vp9_rc_get_second_pass_params() moved from
Pass2Encode() to earlier in vp9_get_compressed_data(),
to ensure that two pass stats and parameters are
available before decisions such as frame scaling.

Change-Id: If21537f0073919b04696a7d5e9aac78e23d76f39
2014-09-15 12:45:42 +01:00
Jingning Han
95f67f09ac Merge "Remove redundant reference frame threshold settings" 2014-09-13 10:44:00 -07:00
Jingning Han
59dd83a3ea Merge "Refactor reference frame control in sub8x8 block RD search" 2014-09-13 10:43:36 -07:00
Jingning Han
e6d927343e Merge "Format fixes in vp9_rd_pick_inter_mode_sb" 2014-09-13 10:43:24 -07:00
Jingning Han
ad3c92b9b7 Merge "Remove unused best_inter_rd variable" 2014-09-13 10:43:14 -07:00
Jingning Han
f02e0b6cf6 Merge "Remove unused speed feature" 2014-09-13 10:43:03 -07:00
Jingning Han
82fad6f4b6 Merge "Add a note for enum values of MV_REFERENCE_FRAME" 2014-09-13 10:42:45 -07:00
JackyChen
282fac96ca Merge "Change the control function of VP9 denoiser." 2014-09-12 19:18:41 -07:00
Deb Mukherjee
c0dfecfb89 Merge "Use bigdia search with pruned subpel search" 2014-09-12 16:42:18 -07:00
JackyChen
bb1a23656c Change the control function of VP9 denoiser.
Change from VP8E_SET_NOISE_SENSITIVITY to VP9E_SET_NOISE_SENSITIVITY

Change-Id: Ia210a7029b26924e30973f0f9798a338e0412407
2014-09-12 16:34:22 -07:00
Yunqing Wang
1bf0beb5fc Refactor encode_superblock function
The code covers both x->skip=0 & x->skip=1 cases.

Change-Id: I09745c10e5994dc700ae4c01b4b62979cdaf3306
2014-09-12 15:58:17 -07:00
Jingning Han
888a848453 Remove redundant reference frame threshold settings
When a reference frame type is not in the frame buffer, the mode
search threshold will be set to INT_MAX, so as to effectively
turn off the mode entries in the rate-distortion optimization loop
that involves this reference frame type. This operation is now
integrated in the ref_frame_skip_mask scheme. This commit hence
removes the redundant mode search threshold setting.

Change-Id: Ib18f45da611afda2af275201efd367df7f5101ab
2014-09-12 14:36:51 -07:00
Jingning Han
adb20849b6 Refactor reference frame control in sub8x8 block RD search
This commit unifies the reference frame control in the rate-
distortion optimization search loop of sub8x8 block size to remove
the control dependency on mode search order.

Change-Id: I3a174099f71a7cc176ede9fd60e2374243ae9232
2014-09-12 11:03:03 -07:00
Minghai Shang
3e7b04af54 Merge "[spatial svc] Output psnr for all layers in one packet." 2014-09-12 10:52:42 -07:00
Deb Mukherjee
83c76118eb Use bigdia search with pruned subpel search
Improves function to return sad of integer pels by reusing integer
pels already visited in the smallest scale.
Turns on BIGDIA search for speed 4. Also, turns on the
first version of the pruned subpel search at this speed.

derf: -0.32% (speed 4)

Speed seems to improve by at least 5% but subject to verification.

Change-Id: Iaec8eaffd61d6237ac029e6a2a1b0a88b2a35271
2014-09-12 10:25:12 -07:00
Jingning Han
7f77a1c3c9 Merge "Unify intra mode mask into mode_skip_mask scheme" 2014-09-12 09:06:35 -07:00
Deb Mukherjee
10783d4f3a Adds high bitdepth transform functions and tests
Adds various high bitdepth transform functions and tests.
Much of the changes are related to using typedefs tran_low_t
and tran_high_t for the final transform cofficients and intermediate
stages of the transform computation respectively rather than fixed
types int16_t/int. When vp9_highbitdepth configure flag is off,
these map tp int16_t/int32_t, but when the flag is on, they map
to int32_t/int64_t to make space for needed extra precision.

Change-Id: I3c56de79e15b904d6f655b62ffae170729befdd8
2014-09-11 19:56:33 -07:00