I420ScaleTo569x480_Bilinear (LIBYUV_WIDTH=569 LIBYUV_REPEAT=5000):
CPU AVX2 AVX512 Speedup
Intel Emerald Rapids 124 ms 63 ms 1.97x
Intel Sapphire Rapids 134 ms 69 ms 1.94x
Intel Skylake-X 219 ms 129 ms 1.70x
Intel Granite Rapids 124 ms 76 ms 1.63x
Intel Ice Lake 164 ms 101 ms 1.62x
Bug: None
Change-Id: I7a10446eb4dbcebae68380c2a186d4e3badec551
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8483371
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Add ComputeCumulativeSumRow_AVX2, CumulativeSumToAverageRow_AVX2,
ComputeCumulativeSumRow_NEON, and CumulativeSumToAverageRow_NEON to
accelerate ARGBBlur and ARGBComputeCumulativeSum on x86_64 and aarch64.
Update ARGBBlurSmall_Opt to benchmark 320x180 with radius 1 and use a
circular cumsum buffer of height radius * 2 + 2 in TestBlur.
ARGBBlurSmall_Opt (320x180, r=1, 10000 iterations):
CPU Was C/SSE2 Now AVX2/NEON Speedup
-------------------- -------------- --------------- ---------------
Intel Granite Rapids 29 ms (SSE2) 24 ms (AVX2) 1.21x
Intel Emerald Rapids 30 ms (SSE2) 23 ms (AVX2) 1.30x
Intel Sapphire Rapid 32 ms (SSE2) 28 ms (AVX2) 1.14x
Intel Ice Lake 43 ms (SSE2) 34 ms (AVX2) 1.26x
Intel Skylake-X 54 ms (SSE2) 45 ms (AVX2) 1.20x
Intel Haswell 59 ms (SSE2) 54 ms (AVX2) 1.09x
AMD Zen 5 32 ms (SSE2) 19 ms (AVX2) 1.68x
AMD Zen 4 36 ms (SSE2) 26 ms (AVX2) 1.38x
AMD Zen 3 42 ms (SSE2) 28 ms (AVX2) 1.50x
ARM Neoverse-V2 256 ms (C) 40 ms (NEON) 6.40x
ARGBBlur_Opt (1280x720, r=55, 1000 iterations):
CPU Was C/SSE2 Now AVX2/NEON Speedup
-------------------- -------------- --------------- ---------------
Intel Granite Rapids 1150 ms (SSE2) 984 ms (AVX2) 1.17x
Intel Emerald Rapids 1081 ms (SSE2) 953 ms (AVX2) 1.13x
Intel Sapphire Rapid 1124 ms (SSE2) 973 ms (AVX2) 1.16x
Intel Ice Lake 1450 ms (SSE2) 1167 ms (AVX2) 1.24x
Intel Skylake-X 1935 ms (SSE2) 1630 ms (AVX2) 1.19x
Intel Haswell 2211 ms (SSE2) 1982 ms (AVX2) 1.12x
AMD Zen 5 1089 ms (SSE2) 694 ms (AVX2) 1.57x
AMD Zen 4 1045 ms (SSE2) 929 ms (AVX2) 1.12x
AMD Zen 3 1215 ms (SSE2) 967 ms (AVX2) 1.26x
ARM Neoverse-V2 6529 ms (C) 1544 ms (NEON) 4.23x
Bug: b/456384776
Change-Id: I39c463c791826d3adb05f0b0845b0b1f56f0e4da
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8464496
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: richard winterton <rrwinterton@gmail.com>
- AVX2 uses vpmulhrsw to compute ((128 * a * b) + 16384) >> 15.
- RVV uses e8, m2 (widening to e16, m4) with vwmulu.vv, vwaddu.wx 128,
and vnsrl.wi by 8.
CPU C Intrinsics Inline ASM Speedup (Inline)
------------------------------------------------------------------------
SiFive X390 gen 2 (est.) 2150 ms 29 ms 27 ms 79.63x (1.07x)
SpacemiT K3 (est.) 980 ms 41 ms 38 ms 25.79x (1.08x)
T-Head C908 (est.) 2060 ms 100 ms 94 ms 21.91x (1.06x)
Google Coral (est.) 2680 ms 94 ms 88 ms 30.45x (1.07x)
Test: libyuv_unittest --gtest_filter=*ARGBMultiply*
Bug: None
Change-Id: Iff65794623a6f29e5cb6bda7bd3084c8a5f676d1
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8422278
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
Add SwapUVRow_RVV using RVV intrinsics by default and unit-stride
e16, m4 inline assembly (vle16.v, vsrl.vi, vsll.vi, vor.vv, vse16.v)
under #ifdef RVV_ASM.
CPU C Intrinsics Inline ASM Speedup (Inline)
--------------------------------------------------------------------
SiFive X280 (est.) 980 ms 115 ms 38 ms 25.79x (3.03x)
SpacemiT K3 (est.) 420 ms 68 ms 28 ms 15.00x (2.43x)
T-Head C908 (est.) 860 ms 145 ms 62 ms 13.87x (2.34x)
Google Coral (est.) 1120 ms 190 ms 58 ms 19.31x (3.28x)
Original author: Matteo Forzan <matteo.forzan95@gmail.com>
R=wtc@google.comCC=matteo.forzan95@gmail.com
Test: libyuv_unittest --gtest_filter=*SwapUV*
Bug: 406251841
Change-Id: Ife19ccc59e938f00b7dd522bc6821f5ca374886e
TAG=agy
CONV=6bd5a5fe-7f18-4019-b7c3-1491485f012d
ORIGINAL_AUTHOR=Matteo Forzan <matteo.forzan95@gmail.com>
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8339302
Reviewed-by: David Gao <davidgao@google.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
The existing SVE2 path only computes the average for a pair of input
values instead of groups of four as done in the Neon implementation.
The average of two values must be retained for the final odd element if
present. Existing code just handles this by falling back to the C
implementation, so mirror that for SVE2 as well.
Reduction in time taken relative to the existing Neon code, the SVE2
code remains faster even with the correct averaging:
Cortex-A510: -12.66%
Lumex C1-Nano: -6.38%
Cortex-A720: -9.73%
Lumex C1-Pro: +0.99%
Cortex-X4: -3.05%
Lumex C1-Ultra: -18.98%
Bug: 546962730
Change-Id: I7ab348e64a9d079b81d070cea5fd575243b037d2
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8252281
Reviewed-by: Wan-Teh Chang <wtc@google.com>
Reviewed-by: Justin Green <greenjustin@google.com>
Commit-Queue: Wan-Teh Chang <wtc@google.com>
Add SwapUVRow_AVX2 implementation in row_win.cc for MSVC and enable
HAS_SWAPUVROW_AVX2 under USE_ROW_WIN.
Share kShuffleUVToVU shuffle table between SSSE3 and AVX2 in row_gcc.cc.
Make NV12ToNV21 the primary implementation and alias NV21ToNV12 to it.
Add NV12ToNV21 test in convert_test.cc and benchmark dispatch for
SSSE3 and AVX2 in planar_test.cc.
CPU Before After Speedup
----------------------------------------------------------------
Intel Granite Rapids 282 ms 125 ms 2.26x
Intel Emerald Rapids 264 ms 108 ms 2.44x
Intel Sapphire Rapids 276 ms 122 ms 2.26x
Intel Ice Lake 310 ms 122 ms 2.54x
Intel Skylake-X 573 ms 157 ms 3.65x
Intel Haswell 620 ms 162 ms 3.83x
AMD Zen 4 (Genoa) 266 ms 52 ms 5.12x
AMD Zen 6 (Venice) 229 ms 43 ms 5.33x
ARM Neoverse-N1 140 ms 71 ms 1.97x
NVIDIA Grace (Neoverse-V2) 62 ms 69 ms 0.90x
R=wtc@google.com
Test: libyuv_unittest --gtest_filter=*SwapUV*:*NV12ToNV21*:*NV21ToNV12*
Bug: 406251841
Change-Id: I9bed5522aedadea13cdf69c27e3cbe633e31dd5b
TAG=agy
CONV=bb50ac62-0c55-4969-8fff-c71ab3d9a79f
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8356968
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
- Also remove redundant neon check for I8MM kernels
======================================================================
CPU Before After Speedup
----------------------------------------------------------------------
Intel Granite Rapids (AVX10.1) 251 ms 141 ms 1.78x (+43.8%)
Intel Emerald Rapids (AVX512) 199 ms 108 ms 1.84x (+45.7%)
Intel Sapphire Rapids (AVX512) 230 ms 112 ms 2.05x (+51.3%)
AMD Turin Zen 5 (AVX512) 156 ms 99 ms 1.58x (+36.5%)
AMD Venice Zen 6 (AVX512) 204 ms 106 ms 1.92x (+48.0%)
Intel Skylake-X (AVX512) 320 ms 156 ms 2.05x (+51.2%)
AMD Genoa Zen 4 (AVX512) 236 ms 346 ms 0.68x (-46.6%)
Intel Ice Lake (AVX512) 242 ms 316 ms 0.77x (-30.6%)
AMD Milan Zen 3 (AVX2) 252 ms 230 ms 1.10x (+8.7%)
Intel Haswell (AVX2) 369 ms 456 ms 0.81x (-23.6%)
NVIDIA Grace (SVE2) 336 ms 337 ms 1.00x (-0.3%)
ARM Neoverse-N1 (NEON) 1081 ms 1105 ms 0.98x (-2.2%)
======================================================================
Bug: 537818862
Change-Id: I3ddeddb040fc52a30dabe7ae2c71d16dda021568
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8343467
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
- NV16/24 FOURCC and document
- Rotate take uint8* for ubsan
Bug: 537818862
Change-Id: I2bc7109abaffe2464e031e33c22296c007077d82
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8339427
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: richard winterton <rrwinterton@gmail.com>
- Add avx512bw, neon 32 bit and RVV versions
- Adapt SSE2 to psrlw instead of pmulhuw
CPU Before After Improvement
---------------------------------------------------------------
Granite Rapids (AVX10) 77 ms 75 ms +2.6% (1.03x)
Emerald Rapids (AVX512) 75 ms 67 ms +10.7% (1.12x)
Sapphire Rapids (AVX512) 91 ms 85 ms +6.6% (1.07x)
AMD Venice Zen 6 (AVX512) 30 ms 30 ms 0.0% (1.00x)
AMD Turin Zen 5 (AVX512) 32 ms 32 ms 0.0% (1.00x)
AMD Genoa Zen 4 (AVX512) 35 ms 36 ms -2.9% (0.97x)
Skylake-X (AVX512) 119 ms 119 ms 0.0% (1.00x)
Ice Lake (AVX512) 93 ms 104 ms -11.8% (0.89x)
AMD Milan Zen 3 (AVX2) 43 ms 44 ms -2.3% (0.98x)
Haswell (AVX2) 129 ms 138 ms -7.0% (0.93x)
NVIDIA Grace (SVE2) 42 ms 43 ms -2.4% (0.98x)
Neoverse-N1 (NEON) 87 ms 87 ms 0.0% (1.00x)
---------------------------------------------------------------
Bug: None
Change-Id: Ia8f310a70c8b1229927fcdf117fe22e131d70ea9
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8330912
Commit-Queue: Frank Barchard <fbarchard@google.com>
Reviewed-by: richard winterton <rrwinterton@gmail.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>
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>
- 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>
Treat height == INT_MIN as invalid. Omit explicit height == INT_MIN
check if we disallow height < 32768.
Perform multiplications of stride in the ptrdiff_t type.
Add checks for invalid width and height to some functions.
Bug: 518806561
Change-Id: I5e39fffed7f806852a8758d4b59df919839c0a3b
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/7891415
Reviewed-by: Frank Barchard <fbarchard@google.com>
Commit-Queue: Wan-Teh Chang <wtc@google.com>
Audit all occurrences of "stride *" in the libyuv source tree. Ensure
that these multiplications are performed in the ptrdiff_t type.
For functions not declared in a public header (such as static
functions), prefer to declare the stride parameters (typically named
src_stride and dst_stride) and related stride local variables as
ptrdiff_t. If this is not possible, add ptrdiff_t casts to the stride
parameters in multiplications. If intptr_t or int64_t casts were used,
change them to ptrdiff_t casts.
Bug: chromium:516986556
Change-Id: I6cd8a8eb00cbb5380db828bf83e4d89ff95891f3
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/7882967
Commit-Queue: Wan-Teh Chang <wtc@google.com>
Reviewed-by: Frank Barchard <fbarchard@google.com>
- Standardize libyuv ARGB-family (ARGB, ABGR, RGBA, BGRA) to YUV conversion by utilizing the generic MatrixRow architecture and explicit ArgbConstants.
- Consolidated ARGBToI420, ABGRToI420, BGRAToI420, and RGBAToI420 as wrappers for ARGBToI420Matrix.
- Refactored ABGRToJ420, ABGRToJ422, and ABGRToI422 to use generic matrix functions.
- Added matrix-based versions for NV21, I400, YUY2, and UYVY.
- Updated RAW and RGB24 to I420/I422/I444 dispatchers to use MatrixRow logic and explicit constants.
- Fixed parameter swap bugs in ARGBToI422, ARGBToJ422, and ABGRToJ422.
- Fixed a bug in the generic C implementation of matrix row functions ensuring all 4 channels are processed correctly for all ARGB-family formats.
- Moved kShuffleAARRGGBB in row_gcc.cc to the top of the libyuv namespace for visibility.
- Cleaned up redundant format-specific row implementations.
Bug: libyuv:42280902
Change-Id: I67ffa4c476abc0d2dcc4650510d7bda91b65988e
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/7830291
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
This consolidation standardizes conversion logic, improves code
maintainability, and provides flexible support for various color spaces
(e.g., BT.601, JPEG full
range).
Key Modifications:
- Function Consolidation: Refactored several high-level conversion functions into lightweight wrappers around generic Matrix variants:
- ARGBToI420 → ARGBToI420Matrix
- ARGBToI444 → ARGBToI444Matrix
- ARGBToI422 → ARGBToI422Matrix
- ARGBToNV12 → ARGBToNV12Matrix
- RAWToJ400, RGB24ToJ400 → RGBToI400Matrix
- RAWToI444, RAWToJ444 → RGBToI444Matrix
- 2-Pass Conversions: Updated RGB565ToI420, ARGB1555ToI420, and ARGB4444ToI420 to utilize 2-pass conversions via RGBToI420Matrix.
- Standardization: Refactored ARGBToNV21, ARGBToYUY2, and ARGBToUYVY to use parameterized matrix row functions (ARGBToYMatrixRow,
ARGBToUVMatrixRow).
- Legacy Cleanup: Replaced legacy calls to ARGBToYJRow with the parameterized ARGBToYMatrixRow in the ARGBSobelize helper.
- Internal Integration: Included libyuv/convert_from_argb.h in planar_functions.cc and ensured all new matrix symbols are properly
declared/exported (LIBYUV_API).
Bug: libyuv:42280902
Change-Id: Ied5fd9899767427e3a03cdcfbeaff3e9d502374a
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/7822033
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
Here are the functions flagged for mixing both SSE and AVX (or AVX-512)
instructions, which can trigger an AVX transition/assist performance
penalty:
Libyuv Functions addressed in this CL
* I422ToARGBRow_AVX512BW
* HalfFloatRow_SSE2
Not addressed:
* ScaleFilterCols_SSSE3
Bug: libyuv:509681367
Change-Id: I8ced6065dfe0c516d05857086393782c8590062a
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/7814945
Reviewed-by: richard winterton <rrwinterton@gmail.com>
In all functions that start with ARGB, BGRA, RGBA or ABGR in the include/libyuv/ headers, make sure the parameter variable name has the same 4 letters, but lower case, and the comment before the function should have the same matching name. Then make sure the implementation in source/ folder has the same variable names.
Change-Id: Idadbbbb993156eea16e318719f4888cb3bed5f6a
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/7760057
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@chromium.org>
- add ARGBToYMatrixRow_AVX512BW
- refactor SSE and AVX to use Matrix functions, making old functions
call the new ones.
Zen5 1280x720
Was AVX2 LibYUVConvertTest.ARGBToI444_Opt (1125 ms)
Now AVX512 LibYUVConvertTest.ARGBToI444_Opt (641 ms)
Details by Gemini:
1. Created 3 new Matrix functions:
Added ARGBToYMatrixRow_SSSE3, ARGBToYMatrixRow_AVX2, and
ARGBToYMatrixRow_AVX512BW to source/row_gcc.cc. These take the
const struct ArgbConstants* c parameter similarly to
ARGBToUV444MatrixRow_*. The x86 vector instructions dynamically
calculate the needed values using the properties of the constants
struct, including using vpmaddwd inside the AVX512 code to offset
the lack of a native vphaddw.
2. Replaced Old Functions with Wrappers:
Modified the existing implementations of ARGBToYRow_SSSE3,
ARGBToYJRow_SSSE3, ABGRToYRow_SSSE3, ABGRToYJRow_SSSE3,
RGBAToYRow_SSSE3, RGBAToYJRow_SSSE3, BGRAToYRow_SSSE3 (and their
_AVX2 equivalents) in source/row_gcc.cc to act as inline wrappers
calling the new ARGBToYMatrixRow_* functions, passing the right
matrix parameters (e.g. &kArgbI601Constants, &kArgbJPEGConstants,
&kAbgrI601Constants).
3. Added row_any.cc Handlers:
Added ANY11MC definitions to source/row_any.cc to autogenerate
ARGBToYMatrixRow_Any_SSSE3, ARGBToYMatrixRow_Any_AVX2, and
ARGBToYMatrixRow_Any_AVX512BW which safely handles non-aligned
tails.
4. Updated include/libyuv/row.h:
Updated the headers with the proper void declarations for all newly
generated Matrix and Any_ variants. Also defined
HAS_ARGBTOYROW_AVX512BW in the CPU macros.
5. Tested the Implementations:
Compiled and tested on Linux x86, which resulted in all tests passing
cleanly. Also successfully completed all Windows 32-bit build checks
ensuring 32-bit regression prevention without issues.
Bug: 477295731
Change-Id: I4f5eec9a961e24a9d760d0a1c0810fb5e29a0bd1
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/7759494
Reviewed-by: Dale Curtis <dalecurtis@chromium.org>
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Mostly just a straightforward copy of the Neon code ported to
Streaming-SVE. There is no benefit from this kernel when the SVE vector
length is only 128 bits, so skip writing a non-streaming SVE
implementation.
Change-Id: Ide34dbb7125b5f2a1edda6ef7111a1a49aad324f
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/6651565
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
Add a Neon implementation of the Convert8To16Row kernel. Compared to the
C implementation we can take advantage of knowing that the "scale"
parameter is always an unsigned power of two and fits in 16-bits,
allowing us to combine this with the shift and avoid needing to widen
the input data.
Reduction in run times observed compared to the existing C
implementation:
Cortex-A55: -44.5%
Cortex-A510: -26.1%
Cortex-A520: -30.6%
Cortex-A76: -61.6%
Cortex-A710: -57.6%
Cortex-X1: -46.5%
Cortex-X2: -54.4%
Cortex-X3: -57.1%
Cortex-X4: -55.0%
Cortex-X925: -49.3%
Change-Id: I34b858605ece47e46588c0680a1d2afa7a90d7a0
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/6516186
Reviewed-by: Justin Green <greenjustin@google.com>
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
SVE can make use of the UMULH instruction to avoid needing separate
widening multiply and narrowing steps for the scale application.
Reduction in runtime for Convert8To8Row_SVE2 observed compared to the
existing Neon implementation:
Cortex-A510: -13.2%
Cortex-A520: -16.4%
Cortex-A710: -37.1%
Cortex-A715: -38.5%
Cortex-A720: -38.4%
Cortex-X2: -33.2%
Cortex-X3: -31.8%
Cortex-X4: -31.8%
Cortex-X925: -13.9%
Change-Id: I17c0cb81661c5fbce786b47cdf481549cfdcbfc7
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/6207692
Reviewed-by: Wan-Teh Chang <wtc@google.com>
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
Commit-Queue: Frank Barchard <fbarchard@chromium.org>
- Replace ScalePlane with CopyPlane for Y channel
- Vertical mirroring is supported, but not horizontal mirroring.
- Check src_y is not null when dst_y is not null for all libyuv functions that allow a null dst_y.
- Apply clang-format
- Bump version to 1899
Bug: None
Change-Id: Id1805b52b8024ba95a7f1b098dabf45af48670eb
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/6128599
Reviewed-by: Wan-Teh Chang <wtc@google.com>
InterpolateRow_SME and InterpolateRow_16_SME need special cases to
handle if source_y_fraction is 256 since this would overflow a byte and
can just be a call to memcpy instead.
InterpolateRow_16To8_SME is never called with a source_y_fraction value
of 256 so there is no need for a special case here.
Change-Id: I67805b5db2c411acb93ada626cf414b35620f467
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/6074375
Reviewed-by: Justin Green <greenjustin@google.com>
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
Add a streaming-SVE implementation of CopyRow using normal vector
load/store instructions.
Change-Id: Ia551413f9740a96473fa2e8a0958953be2f4b04e
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/6074374
Reviewed-by: Justin Green <greenjustin@google.com>
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
Mostly just a straightforward copy of the Neon code ported to
Streaming-SVE, we can use predication to avoid needing an `Any` kernel.
SVE has a "widening multiply get high half" instruction in UMULH,
however using the same technique as the Neon code to avoid the need for
a widening multiply at all is more performant here.
These is no benefit from this kernel when the SVE vector length is only
128 bits, so skip writing a non-streaming SVE implementation.
Change-Id: Ib12699c5b8b168d004ebc74c0281ea3772ca8d32
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/6070786
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
Reviewed-by: Justin Green <greenjustin@google.com>
Mostly just a straightforward copy of the Neon code ported to
Streaming-SVE, we can use predication to avoid needing an `Any` kernel
and use ST2 to avoid needing a separate ZIP instruction.
These is no benefit from this kernel when the SVE vector length is only
128 bits, so skip writing a non-streaming SVE implementation.
Change-Id: I5ae36afe699b88f119dc545e49c59c5d85e98742
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/6070785
Reviewed-by: Justin Green <greenjustin@google.com>
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
- Remove special case Scale of 1 which used fp16 cvt but requires cpuid
- Port aarch64 to aarch32
- Use C for aarch32 with small (denormal) scale value
Bug: 377693555
Change-Id: I38e207e79ac54907ed6e65118b8109288fddb207
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/6043392
Reviewed-by: Wan-Teh Chang <wtc@google.com>
For HalfFloat1Row, SVE has direct 16-bit integer to half-float
conversion instructions so there is no need to widen to 32-bits.
For HalfFloatRow, SVE zero-extending loads avoid the need for seperate
UXTL(2) instructions.
Observed reductions in runtime compared to the existing Neon code:
| HalfFloat1Row | HalfFloatRow
Cortex-A510 | -38.3% | -17.3%
Cortex-A520 | -37.6% | -18.8%
Cortex-A720 | -50.1% | -7.8%
Cortex-X2 | -50.2% | -0.4%
Cortex-X4 | -51.5% | -12.5%
Bug: b/42280942
Change-Id: I445071ccd453113144ce42d465ba03c9ee89ec9e
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/5975319
Reviewed-by: Justin Green <greenjustin@google.com>
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
SVE contains the UMULH instruction which allows us to multiply and take
the high half of the result in a single instruction rather than needing
separate widening multiply and then narrowing shift steps.
Observed reduction in runtime compared to the existing Neon code:
Cortex-A510: -21.2%
Cortex-A520: -20.9%
Cortex-A715: -47.9%
Cortex-A720: -47.6%
Cortex-X2: -5.2%
Cortex-X3: -2.6%
Cortex-X4: -32.4%
Cortex-X925: -1.5%
Bug: b/42280942
Change-Id: I25154699b17772db1fb5cb84c049919181d86f4b
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/5975318
Reviewed-by: Justin Green <greenjustin@google.com>
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
The existing C implementation compiled with a recent LLVM is
auto-vectorised and unrolled to process four vectors per loop iteration,
making the Neon implementation slower than the C implementation on
little cores. To avoid this, unroll the Neon implementation to also
process four vectors per iteration.
Reduction in cycle counts observed compared to the existing Neon
implementation:
| HalfFloat1Row_NEON | HalfFloatRow_NEON
Cortex-A510 | -37.1% | -40.8%
Cortex-A520 | -32.3% | -37.4%
Cortex-A720 | 0.0% | -10.6%
Cortex-X2 | 0.0% | -7.8%
Cortex-X4 | +0.3% | -6.9%
Bug: b/42280945
Change-Id: I12b474c970fc4355d75ed924c4ca6169badda2bc
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/5872805
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
Reviewed-by: Justin Green <greenjustin@google.com>
We can use the dot product instructions to apply the coefficients
directly without the need for LD4 de-interleaving load instructions,
since these are known to be slow on some micro-architectures.
ST4 is also known to be slow on more modern micro-architectures, however
avoiding this is left for a future SVE implementation where we can make
use of interleaving-narrowing instructions.
Reduction in cycle counts observed compared to existing Neon code:
Cortex-A55: -5.8%
Cortex-A510: -18.9%
Cortex-A76: -21.8%
Cortex-A720: -30.2%
Cortex-X1: -28.6%
Cortex-X2: -23.4%
Bug: b/42280946
Change-Id: I5887559649cc805a810d867b652c85d48285657d
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/5790970
Reviewed-by: Justin Green <greenjustin@google.com>
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
We can use dot product instructions to apply the coefficients without
needing to use LD4 deinterleaving load instructions, and then TBL to mix
in the original alpha component. This is significantly faster on some
micro-architectures where LD4 instructions are known to be slow compared
to normal loads.
Reduction in cycle counts observed compared to existing Neon code:
Cortex-A55: -12.6%
Cortex-A510: -48.6%
Cortex-A76: -39.7%
Cortex-A720: -52.3%
Cortex-X1: -63.5%
Cortex-X2: -67.0%
Bug: b/42280946
Change-Id: I3641785e74873438acc00d675f5bc490dfa95b50
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/5785972
Reviewed-by: Justin Green <greenjustin@google.com>
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
- avx2 is pack/perm is mutating order
- cvt method maintains channel order on avx512
Sapphire Rapids
Benchmark of 640x360 on Sapphire Rapids
AVX512BW
[ OK ] LibYUVConvertTest.I010ToNV12_Opt (3547 ms)
[ OK ] LibYUVConvertTest.P010ToNV12_Opt (3186 ms)
AVX2
[ OK ] LibYUVConvertTest.I010ToNV12_Opt (4000 ms)
[ OK ] LibYUVConvertTest.P010ToNV12_Opt (3190 ms)
SSE2
[ OK ] LibYUVConvertTest.I010ToNV12_Opt (5433 ms)
[ OK ] LibYUVConvertTest.P010ToNV12_Opt (4840 ms)
Skylake Xeon
Now vpmovuswb
[ OK ] LibYUVConvertTest.I010ToNV12_Opt (7946 ms)
[ OK ] LibYUVConvertTest.P010ToNV12_Opt (7071 ms)
Was vpackuswb
[ OK ] LibYUVConvertTest.I010ToNV12_Opt (7684 ms)
[ OK ] LibYUVConvertTest.P010ToNV12_Opt (7059 ms)
Switch from vpunpcklwd to vpbroadcastw for scale value parameter
Was
vpunpcklwd %%xmm2,%%xmm2,%%xmm2
vbroadcastss %%xmm2,%%ymm2
Now
vpbroadcastw %%xmm2,%%ymm2
Bug: 357439226, 357721018
Change-Id: Ifc9c82ab70dba58af6efa0f57f5f7a344014652e
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/5787040
Reviewed-by: Wan-Teh Chang <wtc@google.com>
