Commit Graph

17809 Commits

Author SHA1 Message Date
James Zern
c12b39626f Merge "Revert "Specialize 4 to 3 scaling in vp9_scale_and_extend_frame_c()"" 2017-09-15 00:27:41 +00:00
Hui Su
293734b755 Merge "VP9 level targeting: add a new AUTO mode" 2017-09-14 21:02:38 +00:00
James Zern
baf658ec4c Revert "Specialize 4 to 3 scaling in vp9_scale_and_extend_frame_c()"
This reverts commit afee58f2c4.

This causes ~8x slowdown in 4:3 in the C-code

Change-Id: I60a7ead12dc4ec1548b1b12cfe4b0be42ef04e0e
2017-09-14 13:07:21 -07:00
Hui Su
c3a6943c16 VP9 level targeting: add a new AUTO mode
In the new AUTO mode, restrict the minimum alt-ref interval and max column
tiles adaptively based on picture size, while not applying any rate control
constraints.

This mode aims to produce encodings that fit into levels corresponding to
the source picture size, with minimum compression quality lost. However, the
bitstream is not guaranteed to be level compatible, e.g., the average bitrate
may exceed level limit.

BUG=b/64451920

Change-Id: I02080b169cbbef4ab2e08c0df4697ce894aad83c
2017-09-14 16:20:29 +00:00
Shiyou Yin
5b558592f5 vp8: [loongson] optimize idctllm with mmi
1. vp8_short_idct4x4llm_mmi
2. vp8_short_inv_walsh4x4_mmi
3. vp8_dc_only_idct_add_mmi

Change-Id: I616923681e79d78607a4988608fc39df77b093f4
2017-09-14 16:51:11 +08:00
Linfeng Zhang
0726dd97d3 Merge "Specialize 4 to 3 scaling in vp9_scale_and_extend_frame_c()" 2017-09-13 17:21:45 +00:00
Johann Koenig
ed3a80cb5e Merge "Revert "Revert "quantize avx: copy 32x32 implementation""" 2017-09-13 14:44:53 +00:00
Kaustubh Raste
83e59914e5 Merge "Optimize mips msa vp9 average mc functions" 2017-09-13 06:02:49 +00:00
Shiyou Yin
fa01426ade Merge "vp8: [loongson] optimize loopfilter with mmi" 2017-09-13 01:05:46 +00:00
Johann
eb4238ac70 Revert "Revert "quantize avx: copy 32x32 implementation""
This reverts commit 8c42237bb2.

Because ssse3 code is used for the reference, the qcoeff and dqcoeff
reference buffers must be aligned.

Original change's description:
> quantize avx: copy 32x32 implementation
>
> Ensure avx and ssse3 stay in sync by testing them against each other.
>
> Change-Id: I699f3b48785c83260825402d7826231f475f697c

Change-Id: Ieeef11b9406964194028b0d81d84bcb63296ae06
2017-09-12 14:25:38 -07:00
Linfeng Zhang
afee58f2c4 Specialize 4 to 3 scaling in vp9_scale_and_extend_frame_c()
Scale 3x3 block instead of 16x16 block in each loop.

Benefits:
1. Reduced number of different phase_scaler from 16 to 3. Optimization code
   will be smaller and faster.
2. The maximum phase_scaler drifting will be reduced from 5/16 to 1/24.
   (The drifting is 1/(3*16) in each step.)

BUG=webm:1419

Change-Id: Ibb9242a629ddb03e1ff93b859bece738255e698c
2017-09-12 12:05:16 -07:00
Kaustubh Raste
30f1ff94e0 Optimize mips msa vp9 average mc functions
Load the specific destination loads instead of vector load

Change-Id: I65ca13ae8f608fad07121fef848e2a18f54171fe
2017-09-12 16:12:11 +05:30
Scott LaVarnway
c39cd9235e Merge "vpxdsp: [x86] add highbd_d207_predictor functions" 2017-09-11 22:32:23 +00:00
Linfeng Zhang
a9bbe53dbb Add 4 to 1 scaling NEON optimization
BUG=webm:1419

Change-Id: If82a93935d2453e61b7647aae70983db1740bec7
2017-09-11 10:17:28 -07:00
Scott LaVarnway
d6c9bbc2b6 vpxdsp: [x86] add highbd_d207_predictor functions
C vs SSE2 speed gains:
_4x4 : ~2.31x

C vs SSSE3 speed gains:
_8x8 : ~4.73x
_16x16 : ~10.88x
_32x32 : ~4.80x

BUG=webm:1411

Change-Id: I0bac29db261079181ddabc6814bd62c463109caf
2017-09-11 07:36:24 -07:00
Shiyou Yin
761f2f5cb4 vp8: [loongson] optimize loopfilter with mmi
1. vp8_loop_filter_horizontal_edge_mmi
2. vp8_loop_filter_vertical_edge_mmi
3. vp8_mbloop_filter_horizontal_edge_mmi
4. vp8_mbloop_filter_vertical_edge_mmi
5. vp8_loop_filter_simple_horizontal_edge_mmi
6. vp8_loop_filter_simple_vertical_edge_mmi

Change-Id: Ie34bbff3a16cff64e39a50798afd2b7dac9bcdc3
2017-09-11 11:08:09 +08:00
James Zern
fb40b5d7a7 intrapred: sync highbd_d63_predictor w/d63_
8/16/32: ~6%/~18%/~33% faster

previously:
7012ba639 vp9_reconintra: simplify d63_predictor

BUG=webm:1411

Change-Id: Ie775f3a4f7fd74df44754e65686d826a51c2cdc2
2017-09-08 19:28:01 -07:00
James Zern
9dfa76f948 vpx_mem: make vpx_memset16 inline
Change-Id: Ibb2cab930c95836e6d6e66300c33e7d08e4474d4
2017-09-08 19:11:46 -07:00
James Zern
5c95fd921e intrapred: sync highbd_d45_predictor w/d45_
8/16/32:: ~19%/~54%/~75.5% faster

previously:
acc481eaa vp9_reconintra: simplify d45_predictor

BUG=webm:1411

Change-Id: Ie8340b0c5070ae640f124733f025e4e749b660d8
2017-09-08 19:09:07 -07:00
James Zern
9a2dd7e67e Merge changes I9ec438aa,I99c954ff
* changes:
  Update convolve functions' assertions
  Add 2 to 1 scaling NEON optimization
2017-09-08 19:23:40 +00:00
James Zern
d7caee2170 vpx_scale_test.h: remove #if from inside macro
fixes visual studio error

Change-Id: I86206f17ca951b15e247c1b92561847d8c21ec7a
2017-09-08 00:06:25 -07:00
Shiyou Yin
43cbdc216d Merge "vp8: [loongson] optimize sixtap predict with mmi" 2017-09-08 00:59:31 +00:00
Shiyou Yin
2c7b7424c5 Merge "vpxdsp: [loongson] optimize sad functions with mmi" 2017-09-08 00:55:14 +00:00
Linfeng Zhang
ef41c6286d Update convolve functions' assertions
So that 4 to 1 frame scaling can call them.

Change-Id: I9ec438aa63b923ba164ad3c59d7ecfa12789eab5
2017-09-07 12:33:58 -07:00
Linfeng Zhang
71b38a144e Add 2 to 1 scaling NEON optimization
BUG=webm:1419

Change-Id: I99c954ffa50a62ccff2c4ab54162916141826d9b
2017-09-07 12:33:50 -07:00
Linfeng Zhang
3ec20445b2 Refactor convolve8 NEON functions
Change-Id: I4ac576875c91fee7cb150d298fae4a2c156d374c
2017-09-06 15:55:17 -07:00
Linfeng Zhang
d5d2cbcc75 Add ScaleFrameTest
Move class VpxScaleBase to new file test/vpx_scale_test.h.
Add new file test/vp9_scale_test.cc with ScaleFrameTest.

BUG=webm:1419

Change-Id: Iec2098eafcef99b94047de525e5da47bcab519c1
2017-09-06 15:54:58 -07:00
Linfeng Zhang
7219f31904 Merge "Remove get_filter_base() and get_filter_offset() in convolve" 2017-09-06 22:39:15 +00:00
Scott LaVarnway
0e95039bd9 Merge "vpxdsp: [x86] add highbd_dc_128_predictor functions" 2017-09-06 21:53:32 +00:00
Peter Boström
6822fb2f09 Remove support for stdatomic.h.
This header doesn't build on g++ v6 as it's a C and not C++ header
(_Atomic is not a keyword in C++11). Since the C and C++ invocations
cannot be guaranteed to point to the same underlying atomic_int
implementation, remove support for them and use compiler intrinsics
instead.

BUG=webm:1461

Change-Id: Ie1cd6759c258042efc87f51f036b9aa53e4ea9d5
2017-09-06 11:59:50 -04:00
Linfeng Zhang
d331e7a1c0 Remove get_filter_base() and get_filter_offset() in convolve
so that the convolve functions are independent of table alignment.

Change-Id: Ieab132a30d72c6e75bbe9473544fbe2cf51541ee
2017-09-05 15:22:36 -07:00
Scott LaVarnway
bc4bcca3fd vpxdsp: [x86] add highbd_dc_128_predictor functions
C vs SSE2 speed gains:
_4x4 : ~7.64x
_8x8 : ~16.60x
_16x16 : ~8.15x
_32x32 : ~5.05x

BUG=webm:1411

Change-Id: If165d419711cfda901bd428a05ca1560a009e62e
2017-09-05 07:57:42 -07:00
Shiyou Yin
0095213790 vp8: [loongson] optimize sixtap predict with mmi
1. vp8_sixtap_predict16x16_mmi
2. vp8_sixtap_predict8x8_mmi
3. vp8_sixtap_predict8x4_mmi
4. vp8_sixtap_predict4x4_mmi

Change-Id: I186669d1a1d998a0f3ba3a548e25eee8b52c251b
2017-09-02 19:08:20 +00:00
Shiyou Yin
f4150163a2 vpxdsp: [loongson] optimize sad functions with mmi
1. vpx_sadWxH_c
2. vpx_sadWxH_avg_c
3. vpx_sadWxHx3_c
4. vpx_sadWxHx8_c
5. vpx_sadWxHx4d_c

Change-Id: Ie13161e3d73a052ea6ea7bac9cfadf55598fea7a
2017-09-02 15:11:32 +00:00
James Zern
d49a1a5329 test,Android.mk: export gtest include path
fixes test file builds

Change-Id: Iaa725ad95d56cf77d9fef8994981a80102e9a966
2017-09-01 19:44:12 -07:00
clang-format
7587a97551 apply clang-format
Change-Id: If4c3e8a396d0fcb304f407b44e28cac3219f038c
2017-09-01 01:24:03 -07:00
James Zern
053bd263eb .clang-format: update to 4.0.1
based on Google style with the following differences:

3a4
> # Generated with clang-format 4.0.1
13c14
< AllowShortCaseLabelsOnASingleLine: false
---
> AllowShortCaseLabelsOnASingleLine: true
23c24
< BraceWrapping:
---
> BraceWrapping:
43c44
< ConstructorInitializerAllOnOneLineOrOnePerLine: true
---
> ConstructorInitializerAllOnOneLineOrOnePerLine: false
46,47c47,48
< Cpp11BracedListStyle: true
< DerivePointerAlignment: true
---
> Cpp11BracedListStyle: false
> DerivePointerAlignment: false
51c52
< IncludeCategories:
---
> IncludeCategories:
78c79
< PointerAlignment: Left
---
> PointerAlignment: Right
80c81
< SortIncludes:    true
---
> SortIncludes:    false

Change-Id: Ibc0ef87a516b8eae88d426dfdd7624be57e7b87c
2017-09-01 01:24:03 -07:00
Peter Boström
be2ba48cac Merge "Prevent data race from low-pass filter." 2017-09-01 05:37:51 +00:00
James Zern
334e9abb0b Merge "inv_txfm_vsx: fix loads in high-bitdepth" 2017-09-01 03:09:49 +00:00
Peter Boström
9ab4d9df38 Prevent data race from low-pass filter.
Makes main thread wait for the filter level to be picked to avoid a race
between the LPF thread and update_reference_frames(). This also
re-enables the failing tests under thread_sanitizer where this data race
was detected.

BUG=webm:1460

Change-Id: I7f5797142ea0200394309842ce3e91a480be4fbc
2017-08-31 18:37:55 -07:00
Peter Boström
03191f738e Merge "Add atomics to vp8 synchronization primitives." 2017-09-01 01:36:22 +00:00
Peter Boström
d42e876164 Add atomics to vp8 synchronization primitives.
Fixes issue on iPad Pro 10.5 (and probably other places) where threads
are not properly synchronized. On x86 this data race was benign as load
and store instructions are atomic, they were being atomic in practice as
the program hasn't been observed to be miscompiled.

Such guarantees are not made outside x86, and real problems manifested
where libvpx reliably reproduced a broken bitstream for even just the
initial keyframe. This was detected in WebRTC where this device started
using multithreading (as its CPU count is higher than earlier devices,
where the problem did not manifest as single-threading was used in
practice).

This issue was not detected under thread-sanitizer bots as mutexes were
conditionally used under this platform to simulate the protected read
and write semantics that were in practice provided on x86 platforms.

This change also removes several mutexes, so encoder/decoder state is
lighter-weight after this change and we do not need to initialize so
many mutexes (this was done even on non-thread-sanitizer platforms where
they were unused).

Change-Id: If41fcb0d99944f7bbc8ec40877cdc34d672ae72a
2017-08-31 17:55:57 -07:00
Scott LaVarnway
ab5704f02c Merge "vpxdsp: [x86] add highbd_dc_left_predictor functions" 2017-08-31 21:34:27 +00:00
Jerome Jiang
20973508da Merge "vp9: Skip testing duplicate zero mv in nonrd-pickmode." 2017-08-31 17:16:19 +00:00
Jerome Jiang
ebf3ae1a29 vp9: Skip testing duplicate zero mv in nonrd-pickmode.
Neutral on rtc set for speed 8. Neutral on ytlive for speed 5.

Saves some computation cycles but no speed gain observed on Pixel.

Change-Id: I34c4642cd543aa89c5b9c4bff6b7113577c64c91
2017-08-31 17:13:31 +00:00
James Zern
f8f64c309b inv_txfm_vsx: fix loads in high-bitdepth
vec_vsx_ld -> load_tran_low

Change-Id: Id3144cdd528d2d406a515e5812e2ea9e4db64bf1
2017-08-30 23:47:56 -07:00
Jerome Jiang
297c110dcb Merge "Revert "Re-enable disabled tests under TSan."" 2017-08-31 01:52:42 +00:00
Jerome Jiang
d7ba519b9f Revert "Re-enable disabled tests under TSan."
This reverts commit df9ce12259.

Reason for revert: 

Re-enabled tests still fail tsan in high bitdepth.

Original change's description:
> Re-enable disabled tests under TSan.
> 
> These tests point to an already-fixed bug, this should no longer have a
> data race.
> 
> BUG=webm:1049
> 
> Change-Id: Iaedc5db8df99362bdc501b70ff7fdebf8756fdb8

TBR=jzern@google.com,pbos@chromium.org,builds@webmproject.org

# Not skipping CQ checks because original CL landed > 1 day ago.

Bug: webm:1049
Change-Id: I232f1f7726bf795b301abfb2e07cad6756642e53
2017-08-30 23:44:21 +00:00
Scott LaVarnway
c39a05ff61 vpxdsp: [x86] add highbd_dc_left_predictor functions
C vs SSE2 speed gains:
_4x4 : ~6.49x
_8x8 : ~10.82x
_16x16 : ~7.61x
_32x32 : ~5.29x

BUG=webm:1411

Change-Id: Ibc30c50cb7139049bf05298010803499e6ef949b
2017-08-30 09:29:06 -07:00
Scott LaVarnway
2d0c11093e Merge "vpxdsp: [x86] add highbd_dc_top_predictor functions" 2017-08-30 11:25:07 +00:00