James Zern [Fri, 3 Mar 2023 23:33:16 +0000 (15:33 -0800)]
disable vp8_sixtap_predict16x16_neon
This causes various buffer overflows in the tests:
[ RUN ] NEON/SixtapPredictTest.TestWithPresetData/0
=================================================================
==22346==ERROR: AddressSanitizer: global-buffer-overflow on address
0x0000012b4a5b at pc 0x000000df0f60 bp 0xffffcf6e64b0 sp 0xffffcf6e64a8
READ of size 8 at 0x0000012b4a5b thread T0
#0 0xdf0f5c in vp8_sixtap_predict16x16_neon
vp8/common/arm/neon/sixtappredict_neon.c:1507:13
#1 0x8819e4 in (anonymous
namespace)::SixtapPredictTest_TestWithPresetData_Test::TestBody()
test/predict_test.cc:293:3
...
0x0000012b4a5b is located 2 bytes to the right of global variable
'kTestData' defined in '../test/predict_test.cc:237:24' (0x12b48a0) of
size 441
[ RUN ] NEON/SixtapPredictTest.TestWithRandomData/0
=================================================================
==22338==ERROR: AddressSanitizer: heap-buffer-overflow on address
0xffff8b5321fb at pc 0x000000df0f60 bp 0xfffff7e0cf30 sp 0xfffff7e0cf28
READ of size 8 at 0xffff8b5321fb thread T0
#0 0xdf0f5c in vp8_sixtap_predict16x16_neon
vp8/common/arm/neon/sixtappredict_neon.c:1507:13
#1 0x87d4c0 in (anonymous
namespace)::PredictTestBase::TestWithRandomData(void (*)(unsigned
char*, int, int, int, unsigned char*, int))
test/predict_test.cc:170:9
...
0xffff8b5321fb is located 2 bytes to the right of 441-byte region
[0xffff8b532040,0xffff8b5321f9)
allocated by thread T0 here:
#0 0x5fd4f0 in operator new[](unsigned long) (test_libvpx+0x5fd4f0)
#1 0x87c2e0 in (anonymous namespace)::PredictTestBase::SetUp()
test/predict_test.cc:47:12
#2 0x87d074 in non-virtual thunk to (anonymous
namespace)::PredictTestBase::SetUp() test/predict_test.cc
...
James Zern [Fri, 3 Mar 2023 20:56:29 +0000 (20:56 +0000)]
disable vpx_get4x4sse_cs_neon
This function causes a heap overflow in the tests:
[ RUN ] NEON/VpxSseTest.RefSse/0
=================================================================
==876922==ERROR: AddressSanitizer: heap-buffer-overflow on address
0xffff8949d903 at pc 0x000000dd95d4 bp 0xfffffdd7f260 sp 0xfffffdd7f258
READ of size 8 at 0xffff8949d903 thread T0
#0 0xdd95d0 in vpx_get4x4sse_cs_neon
vpx_dsp/arm/variance_neon.c:556:10
#1 0x9d4894 in (anonymous namespace)::MainTestClass<unsigned int
(*)(unsigned char const*, int, unsigned char const*,
int)>::RefTestSse() test/variance_test.cc:531:5
#2 0x9d4894 in (anonymous
namespace)::VpxSseTest_RefSse_Test::TestBody()
test/variance_test.cc:772:30
...
0xffff8949d903 is located 3 bytes to the right of 16-byte region
[0xffff8949d8f0,0xffff8949d900)
allocated by thread T0 here:
#0 0x5fd050 in operator new[](unsigned long) (test_libvpx+0x5fd050)
#1 0x9d3e04 in (anonymous namespace)::MainTestClass<unsigned int
(*)(unsigned char const*, int, unsigned char const*,
int)>::SetUp() test/variance_test.cc:299:12
This causes ASan errors:
[ RUN ] VP9/TestVectorTest.MD5Match/1
=================================================================
==837858==ERROR: AddressSanitizer: stack-buffer-overflow on address
0xffff82ecad40 at pc 0x000000c494d4 bp 0xffffe1695800 sp 0xffffe16957f8
READ of size 16 at 0xffff82ecad40 thread T0
#0 0xc494d0 in vpx_d117_predictor_32x32_neon (test_libvpx+0xc494d0)
#1 0x1040b34 in vp9_predict_intra_block (test_libvpx+0x1040b34)
#2 0xf8feec in decode_block (test_libvpx+0xf8feec)
#3 0xf8f588 in decode_partition (test_libvpx+0xf8f588)
#4 0xf7be5c in vp9_decode_frame (test_libvpx+0xf7be5c)
...
Address 0xffff82ecad40 is located in stack of thread T0 at offset 64 in
frame
#0 0x103fd3c in vp9_predict_intra_block (test_libvpx+0x103fd3c)
This frame has 2 object(s):
[32, 64) 'left_col.i' <== Memory access at offset 64 overflows this
variable
[96, 176) 'above_data.i'
Original change's description:
> Allow macroblock_plane to have its own rounding buffer
>
> Add 8 bytes buffer to macroblock_plane to support rounding factor.
>
> Change-Id: I3751689e4449c0caea28d3acf6cd17d7f39508ed
Salome Thirot [Mon, 27 Feb 2023 17:58:18 +0000 (17:58 +0000)]
Optimize Neon implementation of high bitdepth MSE functions
Currently MSE functions just call the variance helpers but don't
actually use the computed sum. This patch adds dedicated helpers to
perform the computation of sse.
James Zern [Tue, 28 Feb 2023 21:50:11 +0000 (21:50 +0000)]
Merge changes I892fbd2c,Ic59df16c,I7228327b,Ib4a1a2cb into main
* changes:
Implement highbd_d117_predictor using Neon
Implement highbd_d63_predictor using Neon
Implement d117_predictor using Neon
Implement d63_predictor using Neon
Salome Thirot [Fri, 24 Feb 2023 18:05:43 +0000 (18:05 +0000)]
Add Neon implementations of standard bitdepth MSE functions
Currently only vpx_mse16x16 has a Neon implementation. This patch adds
optimized Armv8.0 and Armv8.4 dot-product paths for all block sizes:
8x8, 8x16, 16x8 and 16x16.
Jonathan Wright [Sat, 25 Feb 2023 00:43:46 +0000 (00:43 +0000)]
Optimize transpose_neon.h helper functions
1) Use vtrn[12]q_[su]64 in vpx_vtrnq_[su]64* helpers on AArch64
targets. This produces half as many TRN1/2 instructions compared to
the number of MOVs that result from vcombine.
2) Use vpx_vtrnq_[su]64* helpers wherever applicable.
3) Refactor transpose_4x8_s16 to operate on 128-bit vectors.
James Zern [Fri, 24 Feb 2023 17:58:15 +0000 (17:58 +0000)]
Merge changes I65d86038,If3299fe5,I3ef1ff19 into main
* changes:
Add Neon implementation of high bitdepth 32x32 hadamard transform
Add Neon implementation of high bitdepth 16x16 hadamard transform
Add Neon implementation of high bitdepth 8x8 hadamard transform
James Zern [Wed, 22 Feb 2023 19:34:30 +0000 (11:34 -0800)]
vp9_block.h: rename diff struct to Diff
This matches the style guide and fixes some -Wshadow warnings related to
variables with the same name. Something similar was done in libaom in: 863b04994b Fix warnings reported by -Wshadow: Part2: av1 directory
Deepa K G [Thu, 16 Feb 2023 16:17:24 +0000 (21:47 +0530)]
Skip redundant iterations in joint motion searchÂ
In joint_motion_search, there are four iterations.
Even iterations search in the first reference frame
and odd iterations search in the second. The last two
iterations use the search result of the first two
iterations as the start point. If the search result does
not change,last two iterations are not necessary and can
be skipped.
James Zern [Tue, 14 Feb 2023 02:46:51 +0000 (02:46 +0000)]
Merge changes Id74a6d9c,I5c31e0e9,Id5a2b2d9,I73182c97,I2f5916d5, ... into main
* changes:
Optimize vpx_highbd_comp_avg_pred_neon
Add Neon AvgPredTestHBD test suite
Specialize Neon high bitdepth avg subpel variance by filter value
Specialize Neon high bitdepth subpel variance by filter value
Refactor Neon high bitdepth avg subpel variance functions
Optimize Neon high bitdepth subpel variance functions
Salome Thirot [Thu, 9 Feb 2023 16:45:01 +0000 (16:45 +0000)]
Specialize Neon high bitdepth avg subpel variance by filter value
Use the same specialization as for standard bitdepth. The rationale for
the specialization is as follows:
The optimal implementation of the bilinear interpolation depends on the
filter values being used. For both horizontal and vertical interpolation
this can simplify to just taking the source values, or averaging the
source and reference values - which can be computed more easily than a
bilinear interpolation with arbitrary filter values.
This patch introduces tests to find the most optimal bilinear
interpolation implementation based on the filter values being used.
This new specialization is only used for larger block sizes.
Salome Thirot [Thu, 9 Feb 2023 14:16:30 +0000 (14:16 +0000)]
Specialize Neon high bitdepth subpel variance by filter value
Use the same specialization as for standard bitdepth. The rationale for
the specialization is as follows:
The optimal implementation of the bilinear interpolation depends on the
filter values being used. For both horizontal and vertical interpolation
this can simplify to just taking the source values, or averaging the
source and reference values - which can be computed more easily than a
bilinear interpolation with arbitrary filter values.
This patch introduces tests to find the most optimal bilinear
interpolation implementation based on the filter values being used.
This new specialization is only used for larger block sizes.
Salome Thirot [Wed, 8 Feb 2023 16:50:59 +0000 (16:50 +0000)]
Refactor Neon high bitdepth avg subpel variance functions
Use the same general code style as in the standard bitdepth Neon
implementation - merging the computation of vpx_highbd_comp_avg_pred
with the second pass of the bilinear filter to avoid storing and loading
the block again.
Also move vpx_highbd_comp_avg_pred_neon to its own file (like the
standard bitdepth implementation) since we're no longer using it for
averaging sub-pixel variance.
Salome Thirot [Tue, 7 Feb 2023 14:08:33 +0000 (14:08 +0000)]
Optimize Neon high bitdepth subpel variance functions
Use the same general code style as in the standard bitdepth Neon
implementation. Additionally, do not unnecessarily widen to 32-bit data
types when doing bilinear filtering - allowing us to process twice as
many elements per instruction.
chiyotsai [Wed, 8 Feb 2023 21:54:46 +0000 (13:54 -0800)]
Remove CONFIG_CONSISTENT_RECODE flag
Currently, libvpx does not properly clear and re-initialize the memories
when it re-encodes a frame. As a result, out-of-date values are used in
the encoding process, and re-encoding a frame with the same parameter
will give different outputs.
This commit enables the code under CONFIG_CONSISTENT_RECODE to correct
this behavior. This change has minor effect on the coding performance,
but it ensures valid values are used in the encoding process.
Furthermore, the flag is removed as it is now always turned on.
Jerome Jiang [Thu, 9 Feb 2023 19:37:33 +0000 (14:37 -0500)]
Merge tag 'v1.13.0'
Release v1.13.0 Ugly Duckling
2023-01-31 v1.13.0 "Ugly Duckling"
This release includes more Neon and AVX2 optimizations, adds a new codec
control to set per frame QP, upgrades GoogleTest to v1.12.1, and includes
numerous bug fixes.
- Upgrading:
This release is ABI incompatible with the previous release.
New codec control VP9E_SET_QUANTIZER_ONE_PASS to set per frame QP.
GoogleTest is upgraded to v1.12.1.
.clang-format is upgraded to clang-format-11.
VPX_EXT_RATECTRL_ABI_VERSION was bumped due to incompatible changes to the
feature of using external rate control models for vp9.
- Enhancement:
Numerous improvements on Neon optimizations.
Numerous improvements on AVX2 optimizations.
Additional ARM targets added for Visual Studio.
- Bug fixes:
Fix to calculating internal stats when frame dropped.
Fix to segfault for external resize test in vp9.
Fix to build system with replacing egrep with grep -E.
Fix to a few bugs with external RTC rate control library.
Fix to make SVC work with VBR.
Fix to key frame setting in VP9 external RC.
Fix to -Wimplicit-int (Clang 16).
Fix to VP8 external RC for buffer levels.
Fix to VP8 external RC for dynamic update of layers.
Fix to VP9 auto level.
Fix to off-by-one error of max w/h in validate_config.
Fix to make SVC work for Profile 1.
Jonathan Wright [Thu, 9 Feb 2023 11:57:10 +0000 (11:57 +0000)]
Optimize Neon high bitdepth convolve copy
Use standard loads and stores instead of the significantly slower
interleaving/de-interleaving variants. Also move all loads in loop
bodies above all stores as a mitigation against the compiler thinking
that the src and dst pointers alias (since we can't use restrict in
C89.)
Salome Thirot [Tue, 7 Feb 2023 11:28:15 +0000 (11:28 +0000)]
Use 4D reduction Neon helper for standard bitdepth SAD4D
Move the 4D reduction helper function to sum_neon.h and use this for
both standard and high bitdepth SAD4D paths. This also removes the
AArch64 requirement for using the UDOT Neon SAD4D paths.
James Zern [Tue, 7 Feb 2023 01:32:03 +0000 (01:32 +0000)]
Merge changes Ica45c44f,I75c5f099,I9e626d7f into main
* changes:
Optimize Neon implementation of high bitdepth SAD4D functions
Optimize Neon implementation of high bitdepth avg SAD functions
Optimize Neon implementation of high bitdepth SAD functions
Salome Thirot [Thu, 2 Feb 2023 16:06:38 +0000 (16:06 +0000)]
Optimize Neon implementation of high bitdepth SAD4D functions
Optimizations take a similar form to those implemented for Armv8.0
standard bitdepth SAD4D:
- Use ABD, UADALP instead of ABAL, ABAL2 (double the throughput on
modern out-of-order Arm-designed cores.)
- Use more accumulator registers to make better use of Neon pipeline
resources on Arm CPUs that have four Neon pipes.
- Compute the four SAD sums in parallel so that we only load the source
block once - instead of four times.
Salome Thirot [Fri, 3 Feb 2023 11:00:19 +0000 (11:00 +0000)]
Optimize Neon implementation of high bitdepth avg SAD functions
Optimizations take a similar form to those implemented for standard
bitdepth averaging SAD:
- Use ABD, UADALP instead of ABAL, ABAL2 (double the throughput on
modern out-of-order Arm-designed cores.)
- Use more accumulator registers to make better use of Neon pipeline
resources on Arm CPUs that have four Neon pipes.
Salome Thirot [Wed, 1 Feb 2023 16:37:24 +0000 (16:37 +0000)]
Optimize Neon implementation of high bitdepth SAD functions
Optimizations take a similar form to those implemented for standard
bitdepth SAD:
- Use ABD, UADALP instead of ABAL, ABAL2 (double the throughput on
modern out-of-order Arm-designed cores.)
- Use more accumulator registers to make better use of Neon pipeline
resources on Arm CPUs that have four Neon pipes.
Yunqing Wang [Fri, 3 Feb 2023 00:30:09 +0000 (16:30 -0800)]
Fix uninitialized mesh feature for BEST mode
At BEST encoding mode, the mesh search range wasn't initialized for
non FC_GRAPHICS_ANIMATION content type, which actually/mistakenly
used speed 0's setting. Fixed it by adding the initialization.
There were 2 ways to fix this. Patchset 1 set to use speed 0's setting
for non FC_GRAPHICS_ANIMATION type. This didn't change BEST mode's
encoding results much, and only a couple of clips' results were changed.
Borg result for BEST mode:
avg_psnr: ovr_psnr: ssim: encoding_spdup:
lowres2: -0.004 -0.003 -0.000 0.030
midres2: -0.006 -0.009 -0.012 0.033
hdres2: 0.002 0.002 0.004 0.015
Patchset 2 set to use BEST's setting for non FC_GRAPHICS_ANIMATION type.
However, the majority of test clips' BDrate got changed up to
~0.5% (gain or loss), and overall it didn't give better performance
than patchset 1. So, we chose to use patchset 1.
Jonathan Wright [Tue, 31 Jan 2023 13:32:33 +0000 (13:32 +0000)]
Use load_unaligned mem_neon.h helpers in SAD and SAD4D
Use the load_unaligned helper functions in mem_neon.h to load strided
sequences of 4 bytes where alignment is not guaranteed in the Neon
SAD and SAD4D paths.
Refactor the Neon implementation of transpose_s16_8x8(q) and
transpose_u16_8x8 so that the final step compiles to 8 ZIP1/ZIP2
instructions as opposed to 8 EXT, MOV pairs. This change removes 8
instructions per call to transpose_s16_8x8(q), transpose_u16_8x8
where the result stays in registers for further processing - rather
than being stored to memory - like in vpx_hadamard_8x8_neon, for
example.
This is a backport of this libaom patch[1].
[1] https://aomedia-review.googlesource.com/c/aom/+/169426
projects / libvpx / log