607048d606
Merge "Added generic SIMD library supporting x86 SSE2+ and ARM NEON." into nextgenv2
2016-10-10 18:17:50 +00:00
abe0484cee
Merge "New CLPF: New kernel and RDO for strength and block size" into nextgenv2
2016-10-10 18:17:41 +00:00
3a8217f21b
Merge "Hybrid forward transforms 16x16 AVX2 optimization" into nextgenv2
2016-10-07 01:52:11 +00:00
609453e7e4
Merge "Added sse2 inverse 8x16 and 16x8 transforms" into nextgenv2
2016-10-07 00:03:34 +00:00
e4dc5f8dc9
Merge "A bug fix for var-tx" into nextgenv2
2016-10-07 00:02:31 +00:00
e8e8cd8f1b
Hybrid forward transforms 16x16 AVX2 optimization
...
- Unit tests are added for AVX2 SIMD.
- Encoder speed improvement:
AV1 baseline and EXT_TX, three 1080p sequences at bitrate:
800 Kbps, 2 Mbps, 6 Mbps, on i7-6700 CPU, average
user level time reduction: 3.86%.
Change-Id: Ibbd7837ee3a831c6b1e4e471bf6c8d3fa3a19ff4
2016-10-06 15:33:15 -07:00
24aa59cc51
Fix left shift of negative integer in hbd directional predictors
...
Change-Id: Id78139ae2dfa2d521bd50618b4a81cf24e09e391
2016-10-06 11:41:47 -07:00
1baecfeb03
Added sse2 inverse 8x16 and 16x8 transforms
...
Change-Id: I43628407b11e5c8e6af4df69f2acdc67ac827834
2016-10-06 11:23:14 -07:00
29804479b5
Merge "Silence some warnings" into nextgenv2
2016-10-06 18:15:16 +00:00
28d924b7b8
A bug fix for var-tx
...
Fixes a crash with supertx, ext-tx and rect-tx
Change-Id: I6b5f4cfd6e209558541a791be685b55156aa0138
2016-10-06 11:14:27 -07:00
a5f8ea1109
Added generic SIMD library supporting x86 SSE2+ and ARM NEON.
...
Change-Id: I037f4c44f621a7e909b82ccb6a299d41bcbf8607
2016-10-06 16:37:08 +00:00
d06588ab18
New CLPF: New kernel and RDO for strength and block size
...
This commit ports a CLPF change from aom/master by manually
cherry-picking:
7560123c06
2016-10-06 09:36:03 -07:00
3b22d1a875
Merge "Make ref_mv_idx syntax context dependent on block distance only" into nextgenv2
2016-10-06 15:55:40 +00:00
9c2d401ca0
Merge "Simplify file dependencies of SIMD implementation of interpolation filters" into nextgenv2
2016-10-05 16:26:26 +00:00
8205b78552
Make ref_mv_idx syntax context dependent on block distance only
...
This allows the hardware decoder to start decoding ref_mv_idx
syntax prior to the sorting stage and hide the latency of entropy
decoding. The compression performance change is about 0.01% level.
Change-Id: I86b34f31f6c99a36ae2780416175cc0bd90ff492
2016-10-05 09:09:00 -07:00
1ae9f2cfab
Silence some warnings
...
Change-Id: I8efb64eac3438484e7a77a8a1db198223fc52bfa
2016-10-04 14:30:16 -07:00
cb603790b0
Fix a compiler warning in ext-inter experiment
...
Change-Id: If36417c1384646da57453344b208e7653a4d31e5
2016-10-04 13:22:21 -07:00
1a16a987ee
Fix an integer overflow issue in restoration
...
https://bugs.chromium.org/p/webm/issues/detail?id=1306
Change-Id: Icd11d373ff08954121c097728e4c7791791e223f
2016-10-04 11:50:00 -07:00
438b1dcb72
Merge "ext_tx: fix a signed overflow" into nextgenv2
2016-10-04 17:24:06 +00:00
2b47628903
Merge "Fix high bitdepth variance overflow on uint32_t" into nextgenv2
2016-10-04 17:11:07 +00:00
b9ba5c251b
Simplify file dependencies of SIMD implementation of interpolation filters
...
This is a similar change to following aom CL
https://aomedia-review.googlesource.com/#/c/1961/
Move SIMD related functions from filter.c/h to following files
av1_convolve_ssse3.c
av1_highbd_convolve_filters_sse4.c
Change following c files to header files.
av1_highbd_convolve_filters_sse4.c
av1_convolve_filters_ssse3.c
Change-Id: I41a3cc6b0789e632451aeda82f5eb97a4d78e370
2016-10-03 18:43:23 -07:00
a674ba93fe
Fix high bitdepth variance overflow on uint32_t
...
BUG=webm:1305
Change-Id: I4c56631359e298b99e618c07bcbae9f793c5e2ac
2016-10-03 16:37:00 -07:00
8e46b860c6
Fix filter type mismatch warning on Visual Studio
...
- Move filter look-up functions to corresponding optimization modules.
BUG=webm:1296
Change-Id: I87f399609052db2dbc7e5a590afb08b82e3fa89f
2016-10-03 16:24:25 -07:00
aa77b5168f
ext_tx: fix a signed overflow
...
Change-Id: I9a08bc5da1a84c3d4b8fe2d457bb80406c0bc028
2016-10-03 16:17:24 -07:00
bf0431276d
Merge "Further changes to new-quant tables" into nextgenv2
2016-10-03 21:10:30 +00:00
0badd0201e
Merge "decode_with_drops.sh : make sample test work for av1" into nextgenv2
2016-10-03 19:57:43 +00:00
6f745a2795
Merge "decode_with_drop.sh: vp8->aom" into nextgenv2
2016-10-03 19:57:30 +00:00
f54733ad25
Merge "decode_to_md5_test: fixes and runs quick encode and checks decode" into nextgenv2
2016-10-03 19:57:17 +00:00
4707c75a5b
Merge "decode_to_md5.sh: vp8->aom" into nextgenv2
2016-10-03 19:56:59 +00:00
ddb90bb445
decode_with_drops.sh : make sample test work for av1
...
Change-Id: I4175070840a6561c1cec5f5a50b64e425f3e2926
2016-10-03 11:13:13 -07:00
a7c2e5c3f5
decode_with_drop.sh: vp8->aom
...
Change-Id: I22dacbc2e4933a60ce7151204af9ee253990ca1f
2016-10-03 11:13:08 -07:00
0d730f95f0
decode_to_md5_test: fixes and runs quick encode and checks decode
...
This test checks if there's any basic change to the bitstream or default
encoder by running an encode and checking that the md5 from the decode
doesn't change.
Any change to the default encoder or bitstream should be accompanied by
a change to the md5 in this file.
Change-Id: Ibdd5a1442296fd3e946823ec1f43e8ac4e66dd34
2016-10-03 11:12:13 -07:00
8982e20889
decode_to_md5.sh: vp8->aom
...
Change-Id: I0dcb0643cf83ee99b63336df851cbca749c11b68
2016-10-03 11:11:54 -07:00
42bc3a9ef3
Sync ref-mv experiment between aom and nextgenv2
...
Change-Id: I134d276234b3b8aa7df1ab647892b5d739647f4c
2016-10-03 09:02:20 -07:00
3c42c09608
Further changes to new-quant tables
...
Refactor to streamline the number of profiles needed, in
preparation for the next steps.
NO change in performance.
Change-Id: I753b89299897857f3c250c316b4cdc4fedcb90e8
2016-10-01 17:59:28 -07:00
1f470046aa
Merge "Rename aom_write_nmv_probs as av1_write_nmv_probs" into nextgenv2
2016-10-01 01:06:09 +00:00
d59fb48bc7
Add notes for an option
...
cherry-picked from aom/master:
2b40739490
2016-09-30 15:39:53 -07:00
671f2bd3f5
Rename AOM_ENC/DEC_BORDER_IN_PIXELS
...
Cherry-picked from aom/master:
e2721a65cb
2016-09-30 15:17:16 -07:00
71e4553c3b
Clean up av1_adapt_mv_probs format
...
Change-Id: Ib5226d4fe3dcf916fe8954c7240966e3a32eed31
2016-09-30 17:58:21 +00:00
5c60cdf23f
Sync assign_mv format
...
Change-Id: I4fea280d72d7e428f2ab0820fd728997d5a903c9
2016-09-30 17:58:06 +00:00
3b0a3f3ab3
Merge "Set spatial neighbor search resolution 16x16 for block size 64x64" into nextgenv2
2016-09-30 17:57:52 +00:00
dcf1b40d91
Merge "Search collocated reference block in 16x16 unit" into nextgenv2
2016-09-30 17:45:09 +00:00
fd0cf16d7f
Rename aom_write_nmv_probs as av1_write_nmv_probs
...
Change-Id: Ia33ce4918d3d40eba331f81909f3f1f0f3ab7a58
2016-09-30 10:34:33 -07:00
75e513f126
Set spatial neighbor search resolution 16x16 for block size 64x64
...
When the block has width/height above or equal to 64, use 16x16
block search step for reference motion vector search in the non-
immediate rows and columns.
Change-Id: If11ce97a9328b879f30ef87115086aa0cd985a2f
2016-09-30 10:00:10 -07:00
883c63ca57
Search collocated reference block in 16x16 unit
...
Use 16x16 block resolution for collocated reference motion vector
search.
Change-Id: I1091b5b178e255eb6cc0b994de360994f7661b79
2016-09-30 09:04:21 -07:00
770911d48c
Merge changes I319cb856,Ib009b6b6 into nextgenv2
...
* changes:
Remove multi-entropy coder hacks from the treewriter
Rename rans_dec_lut to rans_lut
2016-09-29 21:54:28 +00:00
d54e5a04c4
Merge "more ref_mv changes from aom/master" into nextgenv2
2016-09-29 21:46:56 +00:00
7dc7703bcb
Merge "Fix unit test failure for RECT_TX + VAR_TX" into nextgenv2
2016-09-29 21:41:10 +00:00
4306b6e599
more ref_mv changes from aom/master
...
Change-Id: I9152f898dfacdf3877ed719f193bb1e0dbee0a1a
2016-09-29 12:41:55 -07:00
235133a22e
Fix compiler error for GLOBAL_MOTION+WARPED_MOTION
...
Fix the logical OR computation in .mk file. Otherwise, when both
experiments are on, the output of $(filter... will be two 'yes',
which will cause missing library issue.
Change-Id: I53c44e925dc9ea77c7467217c20e4f1bc7e20fc3
2016-09-29 12:12:47 -07:00
Yaowu Xu
Yi Luo
Debargha Mukherjee
Alex Converse
Peter de Rivaz
Steinar Midtskogen
Jingning Han
Angie Chiang
Jim Bankoski
Yue Chen