generic-library/vpx
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
17,188 Commits 55 Branches 16 Tags 63 MiB
3453c8d6c4
Commit Graph

17188 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Jerome Jiang
3453c8d6c4 Merge "vp9: Neon optimization for denoiser. Add unit tests." 2017-05-06 01:28:32 +00:00
Jerome Jiang
83a2bfd7dc Merge "Change target bitrate thresh in denoiser test." 2017-05-06 01:28:15 +00:00
Jerome Jiang
fff358fb06 Change target bitrate thresh in denoiser test. 
An intended behavior change disabling exhaustive searches in speed
feature causes VP9/DatarateTestVP9LargeDenoiser.4threads test failure.
Change the threshold to make it pass.

BUG=webm:1429

Change-Id: Ibcbe2314c6b2525799894f5d7204fc8eb4ec2a1e
 2017-05-05 16:50:19 -07:00
Jerome Jiang
069eedb3a0 vp9: Neon optimization for denoiser. Add unit tests. 
Denoiser on Neon is 5x faster than C code.

BUG=webm:1420

Change-Id: I805ab64f809ff2137354116be6213e7ec29c1dcb
 2017-05-05 16:40:52 -07:00
Marco Paniconi
a082c562d0 Merge "vp9: Adjust some thresholds for noise estimation." 2017-05-05 20:02:41 +00:00
Marco
34cce144d8 vp9: Adjust some thresholds for noise estimation. 
Adjust thresholds for noise estimation, for resolutions above VGA.
Tends to push cleaner/low noise clips to LowLow state.

No change in RTC metrics.

Change-Id: I739ca6b797d0a60ccd1c6c6a2775269b1f007e5e
 2017-05-05 12:00:12 -07:00
Johann Koenig
38f440120c Merge "fdct 8x8 neon: minor comment cleanup" 2017-05-05 18:22:45 +00:00
Jerome Jiang
af69ed20c4 vp9: Enable noise estimation on low res. 
Set noise level to kLowLow for high motion low res clips.
Change the normalization in noise metric for low res.
Reduce the initial time-window for all resolutions.

Change-Id: Iaed39dbb50b205cd9c735dc5b84822304fb01987
 2017-05-04 15:38:23 -07:00
Johann
462e29703c fdct 8x8 neon: minor comment cleanup 
Simplify HBD/non distinction in test.

Document why transpose_neon.h is not used

Change-Id: I17659414206ddbb8c2f1ef0d9f4a17f1745d5a52
 2017-05-04 15:14:23 -07:00
Yi Luo
a24e1e8027 Merge "High bit depth inter prediction horizontal/vertical filters AVX2" 2017-05-04 15:43:21 +00:00
Hui Su
5048d6e7ee Merge "vp9 level: add tentative max cpb values for high levels" 2017-05-03 20:51:03 +00:00
Hui Su
f701a44305 Merge "Adjust alt-ref selection in define_gf_group()" 2017-05-03 20:50:29 +00:00
Yi Luo
a3452996a1 High bit depth inter prediction horizontal/vertical filters AVX2 
User level speed improvement on i7-6700, cpu-used=1,
  x86_64 Linux, bitrate, 1080p, 8Mbps, 4K, 16Mbps:
- Decoder:
  1080p: ~4%
  4K: ~5%
- Encoder:
  1080p: ~1%
  4K: ~3%

Change-Id: I51b48f9c5de0d62487d5a11aa579c97bd03dd640
 2017-05-03 12:18:01 -07:00
Linfeng Zhang
a10a5cb356 Merge changes I8bb660de,Ica51d780,I6037525d 
* changes:
  Clean specializes of idct functions
  Clean add_protos of highbd idct functions
  Clean add_protos of idct functions
 2017-05-03 19:17:55 +00:00
James Zern
5599e4275a Merge changes Ia5293d94,I90d481d3,Ia509d622,I54549b03,I89b635d6 
* changes:
  ppc: Add convolve8_vsx and convolve8_avg_vsx
  ppc: Add convolve8_avg_vert_vsx
  ppc: Add convolve8_vert
  ppc: Add convolve8_horiz_avg
  ppc: Add convolve8_horiz
 2017-05-03 03:31:19 +00:00
Luca Barbato
e2ad89092d ppc: Add convolve8_vsx and convolve8_avg_vsx 
Change-Id: Ia5293d948003a7fff5a7cbad6e83d8a72717c857
 2017-05-02 20:27:47 -07:00
Luca Barbato
e6ca81ee67 ppc: Add convolve8_avg_vert_vsx 
Only the generic one again, speedups for 8x8 and larger blocks to
come later.

Change-Id: I90d481d3a602d1e277ead8f3934eca126b86b72d
 2017-05-02 20:27:42 -07:00
Luca Barbato
a65f1771ad ppc: Add convolve8_vert 
Only the generic one again, speedups for 8x8 and larger blocks
to come later.

Change-Id: Ia509d6225984b4930ec03928c9bcbf51486da99f
 2017-05-02 20:27:33 -07:00
Luca Barbato
77772350f3 ppc: Add convolve8_horiz_avg 
The 8x8 and larger blocks cases can be sped up further.

Change-Id: I54549b03ac6c7a4e3f485738b100c3cac7ac2e15
 2017-05-02 20:27:28 -07:00
Luca Barbato
08edb85bd0 ppc: Add convolve8_horiz 
The 8x8 and larger blocks cases can be sped up further.

Change-Id: I89b635d6b01c59f523f2d54b1284ed32916c5046
 2017-05-02 20:27:16 -07:00
Linfeng Zhang
0178d974e5 Clean specializes of idct functions 
Change-Id: I8bb660de47b5f97263ec381dc428db96e9c9a4b2
 2017-05-02 18:01:19 -07:00
Linfeng Zhang
4412996d59 Clean add_protos of highbd idct functions 
Change-Id: Ica51d780b92b316ce9112740c56cdf7670816371
 2017-05-02 17:59:38 -07:00
Linfeng Zhang
a7a57d9756 Clean add_protos of idct functions 
Change-Id: I6037525d92ec172810edab720389eb1865ed3b1a
 2017-05-02 17:58:40 -07:00
Johann Koenig
240a5a15ef Merge "block error sse2: sum in 32 bits when possible" 2017-05-02 14:16:47 +00:00
Johann
cd94d5f68e block error avx2: rename variables 
Change-Id: I2b8a9253f2c3d1fd85304c2970ebe70213870fe9
 2017-05-01 17:54:29 -07:00
Johann Koenig
b1a31f8066 Merge "block error avx2: sum in 32 bits when possible" 2017-05-02 00:52:59 +00:00
Marco Paniconi
1e112bce37 Merge "vp9: SVC: Early exit on golden ref in non-rd pickmode." 2017-05-01 21:04:52 +00:00
Linfeng Zhang
e8655d49f5 Merge "Clean vp9_highbd_build_inter_predictor() and highbd_inter_predictor()" 2017-05-01 19:54:40 +00:00
Johann Koenig
3d33a462b3 Merge "move vp9_error_intrin_avx2.c" 2017-05-01 19:52:36 +00:00
Kyle Siefring
760c214519 block error avx2: sum in 32 bits when possible 
Add 31bit pairs before unpacking in x86 block error code

AVX2 code provides a very minor performance improvement.

BUG=webm:1210

Change-Id: I4c82308eaf65741dca2f5c6db9be9c85f905073a
 2017-05-01 12:51:33 -07:00
James Zern
ee3df31d74 Merge "vpx_scale_test: fix segfault on alloc failure" 2017-05-01 19:22:22 +00:00
Marco
ae0215f945 vp9: SVC: Early exit on golden ref in non-rd pickmode. 
For SVC 1 pass real-time: add condition to skip the
golden (spatial) reference mode in non-rd pickmode.
Condition is to skip golden if the sse of zeromv-last mode
is below threshold. And change order in ref_mode_set_svc
to make sure golden zeromv is tested after last-nearest.

Speedup ~3-4% with little/negligible quality loss.

Change-Id: I6cbe314a93210454ba2997945f714015f1b2fca3
 2017-05-01 10:36:54 -07:00
Kyle Siefring
8394990b27 block error sse2: sum in 32 bits when possible 
Add 31bit pairs before unpacking in x86 block error code

BUG=webm:1210

Change-Id: I5ca8c7f7775585a17fe09d6bbfc25e1f2955eb0a
 2017-05-01 09:59:18 -07:00
Johann
2ff01aa1e4 move vp9_error_intrin_avx2.c 
There is only one avx2 implementation. Drop '_intrin'

Change-Id: I887a0d27d58567eaad49f749f127eca61313f312
 2017-05-01 09:13:01 -07:00
James Zern
2930903d51 vpx_scale_test: fix segfault on alloc failure 
check the return of ResetImage() before continuing

Change-Id: Iff0b038f7b9761113b8cf33a511a5306640d1273
 2017-04-29 13:12:53 -07:00
Luca Barbato
d51d3934f5 ppc: Add convolve_avg 
Change-Id: Ib203c444c708f42072e38301ee3db97b5b53d014
 2017-04-29 15:47:25 +02:00
Luca Barbato
63860ba7b8 ppc: Add convolve_copy 
Change-Id: Ie26d6dbe090e711d84bac01ba7da270db983f405
 2017-04-29 15:47:25 +02:00
Johann Koenig
ef5918098d Merge "Use uint32_t for accumulator" 2017-04-28 18:32:09 +00:00
Jerome Jiang
ce2e278059 Merge "vp9: Fix condition for disabling adaptive_rd_thresh." 2017-04-28 18:10:36 +00:00
Jerome Jiang
04de501229 vp9: Fix condition for disabling adaptive_rd_thresh. 
Add speed constrains for disabling adaptive_rd_thresh when
row_mt_bit_exact is set.

Change-Id: I2445115c2f9a2e46b8a0966031a0fea488d4964e
 2017-04-28 10:26:20 -07:00
Jerome Jiang
bea27a5809 Merge "Generalize vp9 sse2 denoiser test for other platforms." 2017-04-28 15:45:52 +00:00
Johann
657f3e9f14 Use uint32_t for accumulator 
Be specific about the data type size.

Use convenience macro vp9_zero_array.

Change-Id: I5fadf7dbd408befb73820d85db0be4832e8cfcbd
 2017-04-28 06:36:59 -07:00
Johann Koenig
94ebdba71d Merge "vp9 temporal filter: sse4 implementation" 2017-04-28 13:22:41 +00:00
Jerome Jiang
26aebd77b8 Generalize vp9 sse2 denoiser test for other platforms. 
Renamed to vp9_denoiser_test.

Change-Id: I0d8f4c94bcb81a60949a13d9fe839cee95d03f77
 2017-04-27 22:47:41 -07:00
Yaowu Xu
0e8fea6c13 Merge "VP9: enable trellis for high bitdepth intra" 2017-04-28 00:16:56 +00:00
James Zern
ef15d38df0 Merge "webm_read_frame: avoid NULL dereference" 2017-04-27 21:47:10 +00:00
Johann
6dfeea6592 vp9 temporal filter: sse4 implementation 
Approximates division using multiply and shift.

Speeds up both sizes (8x8 and 16x16) by 30 times.

Fix the call sites to use the RTCD function.

Delete sse2 and mips implementation. They were based on a previous
implementation of the filter. It was changed in Dec 2015:
ece4fd5d22

BUG=webm:1378

Change-Id: I0818e767a802966520b5c6e7999584ad13159276
 2017-04-26 22:03:05 -07:00
Jerome Jiang
43e0e082d1 vp9: Don't force disabling of adaptive_rd_thresh for realtime. 
Don't force disabling of adaptive_rd_thresh for realtime when
row_mt_bit_exact is set.

Row based adaptive rd is made usable in CL
454882(https://chromium-review.googlesource.com/c/454882) for REALTIME.

Change-Id: Ief023414f0fd6eb86f299dd46ae58f4436875af5
 2017-04-26 13:17:57 -07:00
Yunqing Wang
b68f14d0ed Merge "Make the row based multi-threaded encoder deterministic" 2017-04-26 16:12:14 +00:00
Linfeng Zhang
54c4e0f7a5 Merge "Update highbd convolve functions arguments to use uint16_t src/dst" 2017-04-26 15:50:46 +00:00