Add AVX-512 VNNI (VPDPBUSD / _mm512_dpbusd_epi32) row kernels for 64-bit
x86 targets alongside existing AVX-512BW implementations in both
row_gcc.cc (inline assembly) and row_win.cc (C++ intrinsics):
- ARGBToYMatrixRow_AVX512VNNI and ARGBToYMatrixRow_Any_AVX512VNNI:
Pre-computes the 32-bit signed-pixel bias once per row and replaces
vpmaddubsw + vpmaddwd + vpaddw with a single vpdpbusd per 16 pixels.
- ARGBToUV444MatrixRow_AVX512VNNI and
ARGBToUV444MatrixRow_Any_AVX512VNNI: Loads 64 ARGB pixels once instead
of twice and computes 32-bit U and V dot products directly via
vpdpbusd with signed UV matrix coefficients.
- ARGBToUVMatrixRow_AVX512VNNI: Computes 2x2 box-filtered ARGB to U and
V conversion using vpdpbusd with k-masked tail handling for arbitrary
widths.
- ARGBGrayRow_AVX512VNNI: Computes BT.601 grayscale luminance using a
single vpdpbusd per 16 pixels, broadcasts Y to RGB via vpshufb, and
preserves alpha via vpternlogd with k-masked tail handling.
- Wire runtime dispatch via TestCpuFlag(kCpuHasAVX512VNNI) across
convert.cc, convert_from_argb.cc, and planar_functions.cc.
Add AVX512VNNIVBMI variants of the Y, UV444 and UV kernels. These use
both AVX-512 VNNI (vpdpbusd) and AVX-512 VBMI (vpermt2b) and are only
selected when the CPU has both features; there are no VBMI versions
without VNNI. The AVX512VNNI kernels remain for CPUs with VNNI but no
VBMI (Cascade Lake, Cooper Lake).
- The 32-bit sums are always in [0, 65535], so Y, U and V are byte 1 of
each int32. Two vpermt2b gather 64 results from 4 accumulators,
replacing vpackusdw/vpackssdw + vpsrlw + vpackuswb + vpermd.
- U and V accumulators start at ~kAddUV so they hold ~(kAddUV - dot).
The inverse is folded into the vpternlogd that merges the two
256-bit halves. kAddUV is loaded from ArgbConstants rather than
hard coded as 0x8000.
- Y folds the source loads into vpxorq.
- row_win.cc hides the vpermt2b indices from clang, which otherwise
constant folds them into a longer vpshufb + vpor + vpermd sequence.
Performance (1280x720, 5000 iterations, AVX512BW -> AVX512VNNI):
uArch / Benchmark AVX512BW AVX512VNNI Speedup
--------------------------- -------- ---------- -------
Intel Ice Lake ARGBToI420 941 ms 862 ms +9.2%
Intel Ice Lake ARGBToI422 1059 ms 947 ms +11.8%
Intel Ice Lake ARGBToI444 1140 ms 1038 ms +9.8%
Intel Ice Lake ARGBGray 357 ms 273 ms +30.8%
Intel Sapphire Rapids GrayTo 317 ms 218 ms +45.4%
Intel Emerald Rapids GrayTo 310 ms 213 ms +45.5%
Intel Granite Rapids GrayTo 349 ms 241 ms +44.8%
AMD Zen 4 ARGBToI420 648 ms 517 ms +25.3%
AMD Zen 4 ARGBToI444 695 ms 526 ms +32.1%
AMD Zen 4 ARGBGray 403 ms 227 ms +77.5%
AMD Zen 5 ARGBToI422 460 ms 403 ms +14.1%
AMD Zen 5 ARGBToI444 382 ms 321 ms +19.0%
Performance (row_gcc, AVX512VNNI -> AVX512VNNIVBMI):
uArch / Benchmark AVX512VNNI VNNIVBMI Speedup
---------------------------- ---------- -------- -------
AMD Zen 6 ARGBToI420 1280x720 327 ms 284 ms +15.1%
AMD Zen 6 ARGBToI422 1280x720 372 ms 330 ms +12.7%
AMD Zen 6 ARGBToI444 1280x720 357 ms 334 ms +6.9%
AMD Zen 6 ARGBToI400 256x24 94 ms 76 ms +23.7%
AMD Zen 5 ARGBToI422 1280x720 406 ms 350 ms +16.0%
AMD Zen 5 ARGBToI444 1280x720 330 ms 301 ms +9.6%
AMD Zen 5 ARGBToI400 256x24 100 ms 90 ms +11.1%
AMD Zen 4 ARGBToI420 1280x720 631 ms 540 ms +16.9%
AMD Zen 4 ARGBToI422 1280x720 993 ms 825 ms +20.4%
AMD Zen 4 ARGBToI400 256x24 245 ms 218 ms +12.4%
Intel GNR ARGBToI422 256x24 654 ms 616 ms +6.2%
Intel SPR ARGBToI422 256x24 653 ms 613 ms +6.5%
Intel GNR, EMR, SPR and Ice Lake are within +/-3% at 1280x720.
R=rrwinterton@gmail.com
Bug: none
Test: out/Release/libyuv_unittest --gtest_filter=*ARGBToI4*:*ARGBGray*
Test: LIBYUV_DISABLE_AVX512VBMI=1 out/Release/libyuv_unittest
Test: sde64 -gnr / -clx with is_msan=true (row_win.cc)
Change-Id: Ia7a37b39dd2948fe4055a8a7694dd1ff8ac3e55c
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8647811
Reviewed-by: richard winterton <rrwinterton@gmail.com>
1. Fix multi-bit TestCpuFlag(A | B) checks in AYUVToNV12, AYUVToNV21,
RAWToRGBA, NV12ToRGB24Matrix, NV21ToRGB24Matrix, MergeRGBPlane, and
MergeXR30Plane to compare == (A | B) so AVX-512 VBMI/BW kernels are
not dispatched when AVX512VBMI or AVX512VL is absent.
2. Fix 2-byte SVE2 heap buffer overflow on odd widths in
I422ToARGB1555Row_SVE_SC and I422ToARGB4444Row_SVE_SC using
trn1/trn2 + st2b under .b predicates.
3. Fix ARGBPolynomialRow_SSE2 to use packssdw before packuswb, and add
missing vzeroupper to SplitRGBRow_AVX2.
4. Fix CalcFrameSsim to return 0.0 instead of 0.0 / 0 (NaN) when
width <= 8 || height <= 8 so I420Ssim stays finite on small frames.
5. Fix negative-height vertical inversion in ConvertFromI420,
SplitARGBPlane (when dst_a is NULL), I422Rotate, I010Rotate, and
I210Rotate.
6. Fix horizontal flip (negative x/dx) in ScaleFilterCols_NEON (signed
sbfx #16, #16 offset extraction) and ScaleAddCols1_16_C (shift
x >>= 16 before indexing src_ptr).
7. Fix ConvertToARGB odd crop_x chroma alignment in NV12/NV21, src_u
offset in I420/YV12/J420/H420/U420, and FOURCC_U422 calling
U422ToARGB instead of H422ToARGB.
8. Remove dead 14-instruction block in ScaleRowUp2_Bilinear_16_SSE2.
9. Fix UVScale_16 for src_width == 1 (P010ToP410/P210ToP410), enable
and fix column order in TransposeWx4_32_SVE2, fix ByteToFloatRow
NEON Any BPP (3 -> 4), fix AB64ToARGBRow_Any_*, ScaleColsUp2_SSE2,
ScaleUVRowDown2Box_SME, and UYVYToARGBRow_SME macro guards, fix SVE2
loop tail branches (b.lt/b.ge), and remove duplicate HAS_* macros.
10. Fix ConvertFP16ToFP32Column_NEON loop condition and unsigned b.lo
underflow on widths < 8 or not multiples of 8.
11. Fix UYVYToNV12 IS_ALIGNED(awidth, ...) checks and WASM SIMD
IS_ALIGNED(width, 16) checks in I420ToRGB24Matrix /
I422ToRGB24Matrix.
12. Wire SplitUVRow_SVE2, SplitUVRow_LSX, and SplitUVRow_LASX in
NV24ToARGB.
13. Fix MJpegDecoder heap buffer overflows in LoadFrame (reallocate
databuf_[i] when scanlines_size changes), DecodeToBuffers, and
DecodeToCallback (clamp scanlines_to_copy to lines_left and align
skip to max_v_samp_factor).
14. Replace width & (vl - 1) tail calculations with post-loop remainder
across 18 SVE2 functions in row_sve.h for non-power-of-2 SVE VL,
and remove duplicate label 2: in UYVYToARGBRow_SVE_SC.
15. Handle width & 15 tail pixels in DetileToYUY2_C and validate
IS_POWEROFTWO(tile_height) in DetileSplitUVPlane and DetileToYUY2.
16. Avoid signed 32-bit overflow in DivideRow_16_C and C16TO8, fix
ClampFloatToZero_SSE2 pointer increment (lea 0x4) and loop counter
(sub $0x1), and initialize xmm3 in ARGBCopyYToAlphaRow_SSE2.
17. Check max leaf 7 subleaf and max extended CPUID leaf in GetCpuFlags
before querying subleaf 7:1 and extended leaf 0x80000021.
18. Free plane_u on error in I422ToNV21, and fix 4x/2x scratch row
over-allocation in ScaleARGBBilinearDown and ScaleUVBilinearDown.
19. Add ARGBSetRow_RVV and ARGBShuffleRow_RVV in row_rvv.cc.
20. Fix NEON mask (15 -> 7) in ScaleUVRowUp2_Linear_Any_NEON /
_16_Any_NEON, use SIMD InterpolateRow + SplitUVRow in NV16ToI420,
wire SSSE3/SSE2 in ARGBToI400Matrix / ARGBToYUY2Matrix /
ARGBToUYVYMatrix and RGB24Mirror, and split HalfFloatRow multiply
into (src * scale) * 2^-112 to avoid 50x Intel denormal stalls.
Bug: b/574714081
Test: libyuv_unittest
Change-Id: Iec3ae5c58d52bee3ef13cf9b765ac84b733aa576
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8601931
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
1275x1650 (US Letter 150 DPI, 1000 iterations) speedup:
CPU ARGBExtractAlpha ARGBCopyYToAlpha ARGBMirror RGB24Mirror
-----------------------------------------------------------------------
Intel Granite Rapids 1.00x 1.00x 1.00x 1.04x
Intel Emerald Rapids 1.01x 0.97x 1.03x 1.07x
Intel Sapphire Rapids 0.97x 1.01x 1.08x 1.26x
Intel Ice Lake 0.99x 1.02x 0.97x 1.08x
Intel Skylake-X 1.04x 1.03x 1.01x NA
Intel Haswell NA NA NA NA
AMD Turin (Zen 5) 1.01x 1.10x 1.25x 1.31x
AMD Genoa (Zen 4) 0.97x 1.04x 1.09x 1.42x
AMD Milan (Zen 3) NA NA NA NA
AMD Rome (Zen 2) NA NA NA NA
NVIDIA Grace (V2) 1.57x 2.51x NA NA
Google Axion 2 1.12x 3.17x NA NA
Ampere Siryn 1.06x 1.70x NA NA
ARM Neoverse-N1 1.49x 2.01x NA NA
Google Axion (Maple) 1.47x 2.03x NA NA
ARM Cortex-A53 1.06x 1.69x NA NA
Add AVX512BW ARGBExtractAlphaRow, ARGBCopyYToAlphaRow and
ARGBMirrorRow, and AVX512VBMI RGB24MirrorRow, in row_gcc.cc and as
intrinsics in row_win.cc. They are x64 only. The remainder is done
with a k-mask (bzhi) zero-masked load and a masked store, so they
handle any width without an Any wrapper and never access memory
outside the row.
RGB24MirrorRow_AVX512VBMI loads and stores 3 full zmm vectors per
64 pixels using 3 vpermi2b. The one output byte that comes from the
third input vector is merged with a masked vpbroadcastb. The 1 to 63
pixel tail rebases the same tables by 192 - 3 * r; indices >= 128 are
taken from the third vector with vpmovb2m and a masked vpermb.
Add ARGBCopyYToAlphaRow_NEON for Arm 32 bit (vld4 + vst4) and
AArch64 (zip + sli), and rewrite AArch64 ARGBExtractAlphaRow_NEON
with ldp + uzp2. Both prefetch source and destination, which is
2.5x faster on Neoverse-N1 and 1.2x to 1.5x faster on Cortex-A53
for 1280x720. Add WASM SIMD ARGBExtractAlphaRow and
ARGBCopyYToAlphaRow, using a swizzle table for CopyYToAlpha. Rework
the RVV versions to use unit stride loads with vnsrl and vzext.vf4.
R=rrwinterton@gmail.com
Bug: None
Change-Id: I436f27d70a3db0a2b176c91eb789a9491133cfcb
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8523531
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
Implement RAWToRGB24Row_WASMSIMD and RAWToRGB24Row_Any_WASMSIMD in
source/row_wasm.cc for RGB24ToRAW and RAWToRGB24 conversions:
- Process 16 pixels (48 bytes) per loop iteration using three 128-bit
loads, three byte-wise shuffles, and four 2-way blends.
- Use wasm_i8x16_relaxed_swizzle when __wasm_relaxed_simd__ is enabled
(compiling to a single vpshufb on x86 without bounds-checking
overhead) and fall back to wasm_i8x16_swizzle for baseline SIMD128.
- Add kCpuHasWASM (0x100) and kCpuHasWASMSIMD (0x101) CPU feature
flags and enable -msimd128 in BUILD.bazel, BUILD.gn, and
CMakeLists.txt for WebAssembly targets.
Performance (RAWToRGB24_Opt, 1280x720, V8 d8):
CPU WASM C SIMD128 Relaxed SIMD Spd Rlx Spd
-------------------------------------------------------------------
AMD Zen 4 595.0 us 137.0 us 84.0 us 4.34x 7.08x
AMD Zen 3 708.0 us 148.0 us 107.0 us 4.78x 6.62x
AMD Zen 5 375.0 us 107.0 us 67.0 us 3.50x 5.60x
ARM Neoverse-V2 638.0 us 118.0 us 116.0 us 5.41x 5.50x
ARM Neoverse-N1 1046.0 us 294.0 us 294.0 us 3.56x 3.56x
Intel Ice Lake 707.0 us 209.0 us 220.0 us 3.38x 3.21x
Intel Haswell 1110.0 us 344.0 us 360.0 us 3.23x 3.08x
Intel Emerald Rapids 519.0 us 207.0 us 208.0 us 2.51x 2.50x
Intel Sapphire Rapids 551.0 us 220.0 us 255.0 us 2.50x 2.16x
ARM Cortex-A53 14440.0 us 8660.0us 6920.0us 1.67x 2.09x
Intel Granite Rapids 453.0 us 225.0 us 221.0 us 2.01x 2.05x
Bug: 42271072
Test: libyuv_test --gunit_filter=*RAWToRGB24*:*RGB24ToRAW*:*Cpu*
Change-Id: Id902668263a2ab70aa300eeeea18851490c917b5
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/8515581
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@google.com>
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>
