1. source/convert_from_argb.cc should include libyuv/convert.h because
it calls ARGBToI420Matrix().
2. Include <string.h> for memset().
Change-Id: I3f4841fe604639c7357148ef4788fe0415f0b81b
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8255654
Commit-Queue: Wan-Teh Chang <wtc@google.com>
Reviewed-by: Frank Barchard <fbarchard@google.com>
Reduces include/libyuv/basic_types.h to only define LIBYUV_API.
Directly includes <stdint.h> and <stddef.h> where needed in public
headers.
Replaces LIBYUV_BOOL, LIBYUV_FALSE, and LIBYUV_TRUE with C++ bool,
true, and false in C++ code (MJpegDecoder, unit tests) and int (0, 1)
for C API functions.
Updates documentation and unit tests.
Test: ninja -C out/Release libyuv_unittest && ./out/Release/libyuv_unittest --gtest_filter=*
Change-Id: I2d58e872f0f976263bcda546dcc3b1b5f7e53d58
TAG=agy
CONV=2730bc56-93ff-48ed-b615-dcde1b834394
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8280662
Commit-Queue: Wan-Teh Chang <wtc@google.com>
Reviewed-by: Wan-Teh Chang <wtc@google.com>
libyuv/scale_rgb.h declares an API function, so it is a public header
and should be included by the umbrella header libyuv.h.
libyuv/scale_row.h should be an internal header. It should not be
included by the umbrella header libyuv.h.
Fixed: 553139990, 553143607
Change-Id: I5c1a61296a06a96a36c33ec470513ab7bd1f0e66
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8301033
Reviewed-by: Frank Barchard <fbarchard@google.com>
Commit-Queue: Wan-Teh Chang <wtc@google.com>
CPU / Architecture Before (C) After (NEON) Improvement
----------------------------------------------------------------------
Cortex-A53 (Pixel 2 XL Little) 3248 ms 792 ms 4.10x
Cortex-A73 (Pixel 2 XL Big) 432 ms 392 ms 1.10x
Cortex-A55 (Pixel 7 Little) 780 ms 563 ms 1.39x
Cortex-A78 (Pixel 7 Mid) 254 ms 170 ms 1.49x
Cortex-X1 (Pixel 7 Big) 158 ms 129 ms 1.22x
Cortex-A510 (Galaxy S22 Little) 816 ms 441 ms 1.85x
Cortex-A710 (Galaxy S22 Mid) 270 ms 129 ms 2.09x
Cortex-X2 (Galaxy S22 Big) 116 ms 80 ms 1.45x
Cortex-A510 (Galaxy S23 Little) 723 ms 373 ms 1.94x
Cortex-A715 (Galaxy S23 Mid) 183 ms 119 ms 1.54x
Cortex-X3 (Galaxy S23 Big) 122 ms 72 ms 1.69x
Lumix C1 Pro (PD2509 Little) 246 ms 156 ms 1.58x
Lumix C1 Premium (PD2509 Mid) 211 ms 112 ms 1.88x
Lumix C1 Ultra (PD2509 Big) 82 ms 50 ms 1.64x
Oryon-v3M (OnePlus Mid) 233 ms 150 ms 1.55x
Oryon-v3L (OnePlus Big) 103 ms 85 ms 1.21x
On Icelake
Function (1280x720) C SSSE3 AVX2 AVX-512BW Gain
----------------------------------------------------------------------
BlendPlane 901 ms 165 ms 135 ms 115 ms 1.17x
I420Blend 1398 ms 287 ms 198 ms 187 ms 1.06x
Bug: 546077674
Change-Id: I189c44cc757c0e26838a7b6fdb2db1cbe5f96f20
TAG=agy
CONV=0f82c25c-616e-4bb3-beeb-981decb0f40c
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8297264
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: richard winterton <rrwinterton@gmail.com>
LIBYUV_UNBIASED_DATA is a new configuration macro introduced in
commit ba68378. It fixes the AR30 rounding bias offset (+24 / -24) for
10-bit YUV to RGB conversions.
Bug: 551985141
Change-Id: Id724d8cabaee441147d998f77034bc3e31c25a9d
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8298160
Reviewed-by: Frank Barchard <fbarchard@google.com>
CPU / Arch Before (Kernel) After (Kernel) Delta
----------------------------------------------------------------------
Haswell (x86_64) 263 ms (SSSE3) 263 ms (AVX2) 0.0%
Milan (Zen 3) 115 ms (SSSE3) 138 ms (AVX2) -20.0%
SapphRap (x86_64) 173 ms (SSSE3) 178 ms (AVX512VBMI) -2.9%
GNR (Granite R) 191 ms (SSSE3) 189 ms (AVX512VBMI) +1.0%
Turin (Zen 5) 69 ms (SSSE3) 55 ms (AVX512VBMI) +20.3%
Icelake (x86_64) 204 ms (SSSE3) 186 ms (AVX512VBMI) +8.8%
Cascade Lake 237 ms (SSSE3) 229 ms (AVX512BW) +3.4%
Neoverse (aarch64)* 103 ms (SVE2) 103 ms (SVE2) 0.0%
Bug: None
Change-Id: Ib218632e16b3308a214e9ffcbc745d6c41116c6e
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8280536
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
ScalePlane's same-width vertical fast path used the endpoint-oriented
FixedDiv1 step for all upsampling. That stepping is appropriate for
bilinear interpolation, but not for point sampling, where source rows
should cover equally sized destination cells.
Use the same centered FixedDiv stepping as the generic point sampler.
Allow the point path to select the final source row while passing a
zero interpolation stride so row kernels cannot form a pointer beyond
it. Add 8-bit and 16-bit point regression coverage and verify that
bilinear upsampling remains unchanged.
Bug: 537818862
Change-Id: I7bee21b85913b31c146ecf7fe9f5f08608a8a17d
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8264449
Reviewed-by: Wan-Teh Chang <wtc@google.com>
Commit-Queue: Wan-Teh Chang <wtc@google.com>
Reviewed-by: Frank Barchard <fbarchard@google.com>
The READYUV444, READYUVA444, READYUVA422, and STOREARGB macros are
defined but not used.
Change-Id: Ic1174b5b9c7dc8554f362871de73080c32a58537
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8279223
Reviewed-by: Frank Barchard <fbarchard@google.com>
Commit-Queue: Wan-Teh Chang <wtc@google.com>
- reduced shifts to isolate 10 bits
- permi2w instead of packlwd to combine words (ARG) (GB) into ARGB
- vpternlogd to combine A,R,G into 1 register
Saphhire Rapids 10000 iterations of 1280x720P:
Conversion Kernel │ Was │ Now │ Speedup
──────────────────────┼────────────────────────┼────────────────
I420ToAR30_Opt │ 1675 ms │ 1568 ms │ +7.1%
H420ToAR30_Opt │ 1632 ms │ 1555 ms │ +5.2%
I210ToAR30_Opt │ 2459 ms │ 2167 ms │ +13.5%
P010ToAR30_Opt │ 2054 ms │ 1926 ms │ +6.6%
P016ToAR30_Opt │ 2043 ms │ 1938 ms │ +5.4%
Total Test Suite Time │ 9,866 ms │ 9,155 ms │ +7.8% overall
Bug: None
Change-Id: I7972f98408a65a2bb51c506145e4c0c63824c424
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8259796
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Add src/third_party/cpython3 CIPD packages for Linux and host platforms
('\''infra/3pp/tools/cpython3/${platform}'\'' at '\''version:3@3.11.9.chromium.38'\'').
This enables hermetic Python execution in Siso builds where Siso configs
inherited from build/ require the hermetic Python binary at
src/third_party/cpython3/linux-amd64/bin/python3 on remote workers.
Bug: chromium:537680330
Change-Id: I439b2af56dcc5f325ec6f3dbe2837cf550e5c0d2
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8266781
Reviewed-by: Mirko Bonadei <mbonadei@chromium.org>
Reviewed-by: Wan-Teh Chang <wtc@google.com>
Commit-Queue: Alex Ovsienko <ovsienko@google.com>
In P010ToARGBMatrixFilterOverflow, P210ToARGBMatrixFilterOverflow,
P010ToAR30MatrixFilterOverflow, and P210ToAR30MatrixFilterOverflow,
the tests set src_stride_uv to width (1039) and allocated
width * src_uv_height elements. For odd widths, the interleaved UV
row requires (width + 1) & ~1 elements (1040). Using width for the
stride and buffer size caused the second row to read past the allocated
buffer and access uninitialized memory under MSan.
Fix this by computing src_stride_uv = (width + 1) & ~1 and sizing the
allocated buffer to src_stride_uv * src_uv_height.
In TestI400LargeSize, the test attempts large allocations totaling
over 10 GB (~2 GB for source and ~8.5 GB for destination). Under
MemorySanitizer (MSan), large allocations can exceed shadow memory
virtual address limits or assert. Skip this test under MSan by checking
__SANITIZE_MEMORY__ and __has_feature(memory_sanitizer).
Test: libyuv_unittest --gtest_filter=*FilterOverflow*:*I400Large*
Bug: 549112862
Change-Id: I679b7c67d93822e83f066b1895924589fc7242e7
TAG=agy
CONV=dd635180-175b-4e35-b7f0-2e38105d3506
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8269585
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: Wan-Teh Chang <wtc@google.com>
The INCP instructions are particularly slow on some CPUs and in this
case can be replaced by a simple ADD instruction, so use that instead.
Reduction in time taken relative to the existing SVE2 code for
{YUY2,UYVY}ToUVRow_SVE2:
Cortex-A510: −12.1%
Lumex C1-Nano: 0.0%
Cortex-A720: 0.0%
Lumex C1-Pro: 0.0%
Cortex-X4: −20.9%
Lumex C1-Ultra: −20.3%
Bug: 546962730
Change-Id: Iea3d75f7b70fe8a29f12afdd877ac02d43e49f04
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8252282
Reviewed-by: Frank Barchard <fbarchard@google.com>
Reviewed-by: Wan-Teh Chang <wtc@google.com>
Commit-Queue: Wan-Teh Chang <wtc@google.com>
- improves I420ToRAW performance
I420ToRAW on Skylake
Was AVX2
I420ToRAW_Opt (262 ms)
Now AVX512
I420ToRAW_Opt (212 ms)
I420ToRAW on Icelake with avx512vbmi
Was I420ToRAW_Opt (200 ms)
Now I420ToRAW_Opt (187 ms)
Bug: None
Change-Id: If5b171801ba931557d379696fc128d9b155f7c44
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8267746
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: richard winterton <rrwinterton@gmail.com>
The tail LD2B predicate previously used the raw remaining width, however
for odd widths this is incorrect. We already calculate the correct
halved predicate for the UV store part so just compute the load
predicate from that directly.
Bug: 546962730
Change-Id: I59654208ea48eb5bcc6261a63cb90abae58c1668
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8252280
Reviewed-by: Frank Barchard <fbarchard@google.com>
Commit-Queue: Wan-Teh Chang <wtc@google.com>
Reviewed-by: Wan-Teh Chang <wtc@google.com>
The "Disabled:" comment for HAS_ARGBTOYMATRIXROW_SME was left behind
when we re-enabled HAS_ARGBTOYMATRIXROW_SME.
Bug: 546962730
Change-Id: Id21fb368a5233bed9f9733d8a54bce3ed0751f47
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8263125
Reviewed-by: George Steed <george.steed@arm.com>
Reviewed-by: Frank Barchard <fbarchard@google.com>
Commit-Queue: Wan-Teh Chang <wtc@google.com>
This reverts commit 87c797b3c29cc6fb233fc329a93aace2942ba2d9.
Reason for revert: Only commit 8aeb3a9 needs the workaround
Original change's description:
> Add the ARGBToRGB565Row_SSE2() function back
>
> Add the ARGBToRGB565Row_SSE2() and ARGBToRGB565Row_Any_SSE2() functions
> back because they hide the unaligned access in ARGBToRGB565Row_C().
>
> To reproduce the unalgined access error, run the following command in
> Google's internal repository:
> blaze test --config=asan third_party/libyuv:libyuv_test \
> --test_filter=LibYUVConvertTest.I420ToARGBToRGB565_Unaligned
>
> Bug: b:547803993
> Change-Id: I9cc6b643bc007c100dfc092ef3ec814428789219
> Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8265046
> Commit-Queue: Wan-Teh Chang <wtc@google.com>
> Reviewed-by: Frank Barchard <fbarchard@google.com>
Bug: b:547803993
Change-Id: I904126f032f4ed37c470d8972152a137ca315168
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8258919
Reviewed-by: Frank Barchard <fbarchard@google.com>
Bot-Commit: rubber-stamper@appspot.gserviceaccount.com <rubber-stamper@appspot.gserviceaccount.com>
Commit-Queue: Wan-Teh Chang <wtc@google.com>
Add the ARGBToRGB565Row_SSE2() and ARGBToRGB565Row_Any_SSE2() functions
back because they hide the unaligned access in ARGBToRGB565Row_C().
To reproduce the unalgined access error, run the following command in
Google's internal repository:
blaze test --config=asan third_party/libyuv:libyuv_test \
--test_filter=LibYUVConvertTest.I420ToARGBToRGB565_Unaligned
Bug: b:547803993
Change-Id: I9cc6b643bc007c100dfc092ef3ec814428789219
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8265046
Commit-Queue: Wan-Teh Chang <wtc@google.com>
Reviewed-by: Frank Barchard <fbarchard@google.com>
It is the temporary input buffer, not the temporary output buffer, that
needs to be zero-initialized for msan.
This mistake may have been introduced because dst_temp was declared
before src_temp. So swap their declarations.
Change-Id: I74691afe51a7d84187fc0decbc83f2c970cf52b7
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8261587
Reviewed-by: Frank Barchard <fbarchard@google.com>
Commit-Queue: Wan-Teh Chang <wtc@google.com>
The following macros are disabled because they caused test failures:
HAS_ARGBTOYMATRIXROW_SVE2
HAS_HALFMERGEUVROW_SVE2
HAS_UYVYTOUVROW_SVE2
HAS_YUY2TOUVROW_SVE2
HAS_ARGBTOYMATRIXROW_SME is also disabled because ARGBToYMatrixRow_SME()
has the same code as ARGBToYMatrixRow_SVE2().
Bug: 546962730
Change-Id: Ic590e809443585ee66c609ff8ba6b6f0e40300c9
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8261763
Commit-Queue: Wan-Teh Chang <wtc@google.com>
Reviewed-by: Frank Barchard <fbarchard@google.com>
Copy dither4x4 (16 bytes) into an aligned local uint32_t dither4[4] array
using memcpy and index using dither4[y & 3] to avoid unaligned 32-bit
pointer dereference traps in fastbuild / UB sanitizers.
Bug: None
Test: LibYUVConvertTest.TestNoDither, LibYUVConvertTest.TestDither
Change-Id: I4447cd2924b16739a9bce2792d57a550dedeb345
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8262354
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: Wan-Teh Chang <wtc@google.com>
- Add register z2 to the inline assembly clobber list in ARGBToRGB565DitherRow_SVE2.
- Fix operand constraints and register indexes for src_argb, dst_rgb, and width in ARGBToRGB565DitherRow_NEON to properly use '+r' for modified
operands.
Bug: None
Change-Id: I521c5b37dc37e2bcbe910f72c389144b1491e9dc
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8261579
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: Wan-Teh Chang <wtc@google.com>
HalfWidthRow_16To8 downsamples 2x2 16-bit pixels to 8-bit.
For width output pixels, row 0 and row 1 each require width * 2 uint16_t
elements (4 * width bytes).
With two rows separated by src_uv_stride, total source buffer requirement
is 8 * width bytes (4 * width uint16_t elements).
The previous buffer allocation only allocated kPixels * 4 bytes
(2 * kPixels uint16_t elements).
Because align_buffer_page_end places the buffer at the end of a page,
reading the second row caused an out-of-bounds access past the page
boundary, failing the test:
[ RUN ] LibYUVPlanarTest.HalfWidthRow_16To8_Opt
[ FAILED ] LibYUVPlanarTest.HalfWidthRow_16To8_Opt
[----------] Global test environment tear-down
[==========] 3603 tests from 8 test suites ran.
[ PASSED ] 3602 tests.
[ FAILED ] 1 test, listed below:
[ FAILED ] LibYUVPlanarTest.HalfWidthRow_16To8_Opt
1 FAILED TEST.
Use align_buffer_page_end_16 to allocate 4 * width uint16_t elements
(8 * width bytes) and set src_uv_stride to 2 * width elements
in HalfWidthRow_16To8_Opt and HalfWidthRow_16To8_Any.
Bug: None
Test: LibYUVPlanarTest.HalfWidthRow_16To8_*
Change-Id: Ieba81ec211a34cc315e60fc26aad64fb41a88641
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8252627
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: Wan-Teh Chang <wtc@google.com>
In ScaleARGBBilinearUp, ScalePlaneBilinearUp, ScalePlaneBilinearUp_16,
and ScaleUVBilinearUp, dy is strictly < 65536 (dy < 1.0 in 16.16 fixed
point), so yi (y >> 16) advances strictly in unit increments (0 -> 1 ->
2 -> ... -> H - 1).
Because yi transitions across each integer row in sequence:
- src is primed at row 2 and incrementally advanced by 1 row on each
integer transition while (y + 65536) < max_y.
- When y >= max_y - 65536, src increments stop, leaving src pointing to
the final row (H - 1).
- Therefore, src is always pointing to row yi + 1 before each buffer
swap, making the inner 'src = src_ptr + yi * src_stride' recomputation
and nested 'if (yi != lasty)' checks redundant.
Bug: 540206290, 539110937
Test: LibYUVScaleTest.*
Change-Id: Ic5cc5c601d4771e9df8b9a882df2f7f3e6777b23
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8252878
Commit-Queue: Dale Curtis <dalecurtis@chromium.org>
Reviewed-by: Frank Barchard <fbarchard@google.com>
Reviewed-by: Wan-Teh Chang <wtc@google.com>
In ScaleARGBBilinearDown and ScaleARGBBilinearUp, adding dy to y can
overflow signed 32-bit int when scaling down large height images (e.g.,
src_height = 32768 down to 2). Check if max_y - dy < y before adding dy
to y to prevent signed integer overflow.
R=wtc
Fixed: 540206290, 539110937
Test: LibYUVScaleTest.ARGBScale_LargeHeightOverflow
Change-Id: If353d002714481ce0018653798047066663f1fb9
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8175358
Reviewed-by: Frank Barchard <fbarchard@google.com>
Reviewed-by: Wan-Teh Chang <wtc@google.com>
Commit-Queue: Dale Curtis <dalecurtis@chromium.org>
Replace rshrn2 with 2 8 byte registers and stp
All benchmarks run at 1280×720, 1000 iterations (taskset c0):
Function (1280x720 1000x) | OldNEON | NewNEON | OldSVE2 | NewSVE2
-------------------------------+---------+---------+---------+--------
TestInterpolatePlane (8-bit) | 76 ms | 66 ms | 125 ms | 34 ms
TestInterpolatePlane_16 | 195 ms | 66 ms | 195 ms | 64 ms
TestARGBInterpolate (50/50) | 104 ms | 104 ms | 128 ms | 89 ms
ARGBInterpolate0_Opt (0%) | 133 ms | 128 ms | 148 ms | 145 ms
ARGBInterpolate64_Opt (25%) | 211 ms | 181 ms | 244 ms | 222 ms
ARGBInterpolate128_Opt (50%) | 182 ms | 178 ms | 278 ms | 176 ms
ARGBInterpolate192_Opt (75%) | 211 ms | 173 ms | 223 ms | 209 ms
ARGBInterpolate255_Opt (99%) | 211 ms | 183 ms | 315 ms | 221 ms
──────
Function (1280x720 1000x) | OldNEON | NewNEON | OldSVE2 | NewSVE2
-------------------------------+---------+---------+---------+--------
TestInterpolatePlane (8-bit) | 164 ms | 124 ms | 119 ms | 50 ms
TestInterpolatePlane_16 | 211 ms | 129 ms | 138 ms | 75 ms
TestARGBInterpolate (50/50) | 159 ms | 159 ms | 210 ms | 166 ms
ARGBInterpolate0_Opt (0%) | 92 ms | 92 ms | 148 ms | 138 ms
ARGBInterpolate64_Opt (25%) | 223 ms | 223 ms | 232 ms | 232 ms
ARGBInterpolate128_Opt (50%) | 130 ms | 130 ms | 232 ms | 195 ms
ARGBInterpolate192_Opt (75%) | 223 ms | 223 ms | 232 ms | 232 ms
ARGBInterpolate255_Opt (99%) | 223 ms | 223 ms | 232 ms | 232 ms
Platform | NEON | SVE2 | Result
--------------------+--------+--------+---------------
MediaTek Cortex-C1 | 47 ms | 34 ms | SVE2 1.38x win
Qualcomm Oryon v3 | 87 ms | 73 ms | SVE2 1.19x win
Testing:
blaze test --config=android_arm64 //third_party/libyuv:libyuv_test --test_filter="*TestInterpolatePlane*"
Bug: None
Change-Id: I503ce5a1269da5e1c5950c6a2c5ce81ddf4aaca5
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8216829
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: George Steed <george.steed@arm.com>
Reviewed-by: Wan-Teh Chang <wtc@google.com>
- MergeUVRow_SVE2: Interleaves U and V
- SplitUVRow_SVE2: De-interleaves UV
- InterpolateRow_SVE2: Bilinear row interpolation
- YUY2ToYRow_SVE2, YUY2ToUVRow_SVE2, UYVYToYRow_SVE2, UYVYToUVRow_SVE2
- HalfMergeUVRow_SVE2: 2:1 vertical averaging of U and V
OnePlus 15 with Qualcomm Snapdragon 8 Elite Gen 5 Oryon V3
Benchmark (1280x720 1000x) | SVE2 | NEON | Result
-------------------------------+--------+--------+------------------
TestInterpolatePlane | 119 ms | 164 ms | SVE2 is 1.38x win
TestInterpolatePlane_16 | 138 ms | 172 ms | SVE2 is 1.25x win
SplitUVPlane_Opt | 68 ms | 69 ms | SVE2 is 1.01x win
MergeUVPlane_Opt | 40 ms | 40 ms | Tied
SwapUVPlane_Opt | 72 ms | 72 ms | Tied
HalfMergeUVPlane_Opt | 50 ms | 50 ms | Tied
I420ToNV12_Opt | 25 ms | 26 ms | SVE2 is faster
I420ToNV21_Opt | 26 ms | 26 ms | Tied
YUY2ToNV12_Opt | 79 ms | 81 ms | SVE2 is faster
NV21ToNV12_Opt | 36 ms | 35 ms | Tied
Android420ToI420ToNV12_Opt | 53 ms | 53 ms | Tied
Android420ToI420ToNV21_Opt | 35 ms | 33 ms | NEON is faster
YUY2ToI420_Opt | 87 ms | 84 ms | NEON is faster
UYVYToI420_Opt | 87 ms | 83 ms | NEON is faster
YUY2ToI422_Opt | 101 ms | 97 ms | NEON is faster
UYVYToI422_Opt | 101 ms | 97 ms | NEON is faster
UYVYToNV12_Opt | 111 ms | 108 ms | NEON is faster
ARGBToNV21_Opt | 279 ms | 279 ms | Tied
ABGRToNV21_Opt | 279 ms | 280 ms | SVE2 is faster
ARGBToNV12_Opt | 285 ms | 280 ms | NEON is faster
ABGRToNV12_Opt | 284 ms | 281 ms | NEON is faster
Bug: 42280902
Change-Id: I53f633fe453f2853f7bc9fe17280e938912c4e8f
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8196068
Reviewed-by: Justin Green <greenjustin@google.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
