mirror of
https://chromium.googlesource.com/libyuv/libyuv
synced 2026-10-29 02:17:13 +08:00
10a3335a74
Implement 32-bit and 64-bit Arm NEON versions (in row_neon.cc and row_neon64.cc) for the 12 remaining row functions that previously fell back to C on Arm: - AR30ToAB30Row_NEON (and AR30ToAB30Row_Any_NEON) - AR30ToABGRRow_NEON (and AR30ToABGRRow_Any_NEON) - AR30ToARGBRow_NEON (and AR30ToARGBRow_Any_NEON) - ARGBAffineRow_NEON - ARGBColorTableRow_NEON - ARGBCopyAlphaRow_NEON (and ARGBCopyAlphaRow_Any_NEON) - ARGBLumaColorTableRow_NEON - ARGBPolynomialRow_NEON (and ARGBPolynomialRow_Any_NEON) - ARGBUnattenuateRow_NEON (and ARGBUnattenuateRow_Any_NEON) - CopyRow_16_NEON (and CopyRow_16_Any_NEON) - MirrorRow_16_NEON (and MirrorRow_16_Any_NEON) - RGBColorTableRow_NEON Add HAS_*_NEON macros, prototypes, _Any wrappers, NEON dispatches in convert.cc, convert_argb.cc, and planar_functions.cc, and enable unit tests in planar_test.cc. Arm row function SIMD coverage is now 164/164 (100%). Maximum SIMD ISA supported per C row function: ------------------------------------------------------------------------ C Row Function arm x86 riscv wasm loongson hexagon ------------------------------------------------------------------------ AB64ToARGBRow_C NEON AVX2 RVV - - HVX ABGRToAR30Row_C NEON AVX512BW - - - - AR30ToAB30Row_C NEON AVX512BW - - - - AR30ToABGRRow_C NEON AVX512BW - - - - AR30ToARGBRow_C NEON AVX512BW - - - - AR64ShuffleRow_C NEON AVX512BW RVV WASMSIMD - - AR64ToAB64Row_C NEON AVX512BW RVV WASMSIMD - HVX AR64ToARGBRow_C NEON AVX2 RVV - - HVX ARGB1555ToARGBRow_C SVE2 AVX2 - WASMSIMD LASX - ARGB1555ToUVMatrixRow_C NEON AVX2 - WASMSIMD - - ARGB1555ToUVRow_C NEON - - - LASX - ARGB1555ToYMatrixRow_C NEON AVX2 - WASMSIMD - - ARGB1555ToYRow_C NEON - - - LASX - ARGB4444ToARGBRow_C NEON AVX2 - WASMSIMD LASX - ARGB4444ToUVMatrixRow_C NEON AVX2 - WASMSIMD - - ARGB4444ToUVRow_C NEON - - - - - ARGB4444ToYMatrixRow_C NEON AVX2 - WASMSIMD - - ARGB4444ToYRow_C NEON - - - - - ARGBAddRow_C NEON AVX2 - - LASX HVX ARGBAffineRow_C NEON SSE2 - - - - ARGBAlphaBlendRow_C SME AVX512BW RVV WASMSIMD LASX HVX ARGBAttenuateRow_C NEON AVX512BW RVV - LASX HVX ARGBBlendRow_C NEON AVX512BW RVV WASMSIMD LASX HVX ARGBColorMatrixRow_C I8MM SSSE3 - - LASX - ARGBColorTableRow_C NEON X86 - - - - ARGBCopyAlphaRow_C NEON AVX2 - - - HVX ARGBCopyYToAlphaRow_C NEON AVX512BW RVV WASMSIMD - HVX ARGBExtractAlphaRow_C NEON AVX512BW RVV WASMSIMD LASX HVX ARGBGrayRow_C DOTPROD AVX512VNNI - - LASX - ARGBLumaColorTableRow_C NEON SSSE3 - - - - ARGBMirrorRow_C NEON AVX512BW RVV WASMSIMD LASX HVX ARGBMultiplyRow_C SME AVX512BW RVV - LASX HVX ARGBOrRow_C SME AVX512BW RVV WASMSIMD LASX HVX ARGBPolynomialRow_C NEON AVX2 - - - - ARGBQuantizeRow_C NEON SSE2 - - LASX - ARGBSepiaRow_C DOTPROD SSSE3 - - LASX - ARGBSetRow_C NEON X86 RVV - LASX HVX ARGBShadeRow_C NEON SSE2 - - LASX - ARGBShuffleRow_C NEON AVX512BW RVV WASMSIMD LASX - ARGBSubtractRow_C NEON AVX2 - - LASX HVX ARGBToAB64Row_C NEON AVX2 RVV - - HVX ARGBToABGRRow_C NEON AVX512BW RVV WASMSIMD LASX HVX ARGBToAR30Row_C NEON AVX512BW - - - - ARGBToAR64Row_C NEON AVX2 RVV - - HVX ARGBToARGB1555Row_C NEON AVX2 - WASMSIMD LASX - ARGBToARGB4444Row_C NEON AVX2 - WASMSIMD LASX - ARGBToBGRARow_C NEON AVX512BW RVV WASMSIMD LASX HVX ARGBToRAWRow_C SVE2 AVX512BW RVV - LASX - ARGBToRGB24Row_C SVE2 AVX512BW RVV - LASX - ARGBToRGB565DitherRow_C SVE2 AVX2 - WASMSIMD LASX - ARGBToRGB565Row_C SVE2 AVX2 - WASMSIMD LASX - ARGBToRGBARow_C NEON AVX512BW RVV WASMSIMD LASX HVX ARGBToUV444MatrixRow_C I8MM AVX512VNNI RVV WASMSIMD - HVX ARGBToUVMatrixRow_C SME AVX512VNNI RVV WASMSIMD - HVX ARGBToYMatrixRow_C SME AVX512VNNI RVV WASMSIMD LASX HVX ARGBUnattenuateRow_C NEON AVX2 - - - - AYUVToUVRow_C SVE2 AVX512VBMI - - - - AYUVToVURow_C SVE2 AVX512VBMI - - - - AYUVToYRow_C NEON AVX512VBMI - - - - BlendPlaneRow_C NEON AVX512BW RVV WASMSIMD - HVX ByteToFloatRow_C NEON - - - - - ComputeCumulativeSumRow_C NEON AVX2 - - - - Convert16To8Row_C SME AVX512BW RVV - - HVX Convert8To16Row_C SME AVX512BW RVV WASMSIMD - HVX Convert8To8Row_C SME AVX2 - - - HVX CopyRow_C SME AVX512BW RVV - LASX HVX CopyRow_16_C NEON - - - - HVX CumulativeSumToAverageRow_C NEON AVX2 - - - - DetileRow_C NEON SSE2 - - - - DetileRow_16_C NEON AVX - - - - DetileSplitUVRow_C NEON SSSE3 - - - - DivideRow_16_C SVE2 AVX2 - - - HVX GaussRow_C NEON - - - - - GaussRow_F32_C NEON - - - - - HalfFloatRow_C SVE2 AVX2 - - LASX - HalfMergeUVRow_C SVE2 AVX512BW - - - - HalfRow_16To8_C SME AVX512BW RVV - - HVX HalfWidthRow_16To8_C SME AVX512BW RVV - - - I210AlphaToARGBRow_C SME AVX2 - - - - I210ToAR30Row_C SME AVX2 - - - - I210ToARGBRow_C SME AVX2 - - - - I212ToAR30Row_C SME AVX2 - - - - I212ToARGBRow_C SME AVX2 - - - - I400ToARGBRow_C SME AVX512BW RVV - LASX HVX I410AlphaToARGBRow_C SME AVX2 - - - - I410ToAR30Row_C SME AVX2 - - - - I410ToARGBRow_C SME AVX2 - - - - I422AlphaToARGBRow_C SME AVX512BW RVV - LASX HVX I422ToAR30Row_C SME AVX512BW RVV WASMSIMD - - I422ToARGB1555Row_C SME AVX2 - WASMSIMD LASX - I422ToARGB4444Row_C SME AVX2 - WASMSIMD LASX - I422ToARGBRow_C SME AVX512BW RVV WASMSIMD LASX HVX I422ToRGB24Row_C SME AVX512VBMI RVV WASMSIMD LASX - I422ToRGB565Row_C SME AVX2 - WASMSIMD LASX - I422ToRGBARow_C SME AVX2 RVV - LASX HVX I422ToUYVYRow_C NEON AVX2 - - LASX - I422ToYUY2Row_C NEON AVX2 - - LASX - I444AlphaToARGBRow_C SME AVX2 RVV - - HVX I444ToARGBRow_C SME AVX2 RVV - LASX HVX I444ToRGB24Row_C SME AVX2 RVV - - - InterpolateRow_C SME AVX512BW RVV WASMSIMD LASX HVX InterpolateRow_16_C SME AVX512BW - WASMSIMD - HVX J400ToARGBRow_C NEON AVX512BW RVV WASMSIMD LASX HVX MergeAR64Row_C NEON AVX2 - - - - MergeARGB16To8Row_C NEON AVX2 - - - - MergeARGBRow_C NEON AVX2 RVV - - HVX MergeRGBRow_C NEON AVX512VBMI RVV - - - MergeUVRow_C SME AVX512BW RVV WASMSIMD LASX HVX MergeUVRow_16_C SME AVX2 - - - HVX MergeXR30Row_C NEON AVX512BW - - - - MergeXR64Row_C NEON AVX2 - - - - MergeXRGB16To8Row_C NEON AVX2 - - - - MergeXRGBRow_C NEON AVX2 RVV - - HVX MirrorRow_C NEON AVX512BW - WASMSIMD LASX HVX MirrorRow_16_C NEON AVX512BW - - - HVX MirrorSplitUVRow_C NEON AVX512BW - WASMSIMD LASX HVX MirrorUVRow_C NEON AVX512BW RVV WASMSIMD LASX HVX MultiplyRow_16_C SME AVX512BW RVV WASMSIMD - HVX NV12ToARGBRow_C SME AVX512BW RVV WASMSIMD LASX HVX NV12ToRGB24Row_C SME AVX512VBMI RVV - - - NV12ToRGB565Row_C NEON AVX2 - WASMSIMD LASX - NV21ToARGBRow_C SME AVX512BW RVV WASMSIMD LASX HVX NV21ToRGB24Row_C SME AVX512VBMI RVV - - - NV21ToYUV24Row_C NEON AVX2 - - - - P210ToAR30Row_C SME AVX2 - - - - P210ToARGBRow_C SME AVX2 - - - - P410ToAR30Row_C SME AVX2 - - - - P410ToARGBRow_C SME AVX2 - - - - RAWToARGBRow_C SVE2 AVX512BW RVV WASMSIMD LASX - RAWToRGB24Row_C SVE2 AVX512VBMI RVV WASMSIMD LASX - RAWToRGBARow_C SVE2 AVX512VBMI RVV - - - RGB24MirrorRow_C NEON AVX512VBMI - WASMSIMD - - RGB24ToARGBRow_C SVE2 AVX512BW RVV WASMSIMD LASX - RGB565ToARGBRow_C NEON AVX2 - WASMSIMD LASX - RGB565ToUVMatrixRow_C NEON AVX2 - WASMSIMD - - RGB565ToUVRow_C NEON - - - LASX - RGB565ToYMatrixRow_C NEON AVX2 - WASMSIMD - - RGB565ToYRow_C NEON - - - LASX - RGBAToARGBRow_C NEON AVX512BW RVV WASMSIMD LASX HVX RGBColorTableRow_C NEON X86 - - - - RGBToUV444MatrixRow_C NEON AVX512BW RVV WASMSIMD - - RGBToUVMatrixRow_C NEON AVX512BW RVV WASMSIMD - - RGBToYMatrixRow_C DOTPROD AVX512BW RVV WASMSIMD LASX - SetRow_C NEON ERMS - - LASX HVX SobelRow_C NEON SSE2 - - LASX - SobelToPlaneRow_C NEON SSE2 - - LASX - SobelXRow_C NEON SSE2 - - - - SobelXYRow_C NEON SSE2 - - LASX - SobelYRow_C NEON SSE2 - - - - SplitARGBRow_C NEON AVX2 RVV - - HVX SplitRGBRow_C NEON AVX2 RVV - - - SplitUVRow_C SVE2 AVX512BW RVV - LASX HVX SplitUVRow_16_C NEON AVX2 - - - HVX SplitXRGBRow_C NEON AVX2 RVV - - HVX SwapUVRow_C NEON AVX512BW RVV WASMSIMD - HVX UYVYToARGBRow_C SME AVX2 - - LASX - UYVYToUV422Row_C NEON AVX2 - - LASX HVX UYVYToUVRow_C SVE2 AVX2 - - LASX HVX UYVYToYRow_C SVE2 AVX2 - - LASX HVX YUY2ToARGBRow_C SME AVX2 - - LASX - YUY2ToNVUVRow_C NEON AVX2 - - - - YUY2ToUV422Row_C NEON AVX2 - - LASX HVX YUY2ToUVRow_C SVE2 AVX2 - - LASX HVX YUY2ToYRow_C SVE2 AVX2 - - LASX HVX ------------------------------------------------------------------------ SIMD (164/164 100%) 164 100% 154 94% 64 39% 56 34% 73 45% 64 39% ------------------------------------------------------------------------ Test: libyuv_unittest --gtest_filter=*AR30*:*Affine*:*ColorTable*:*CopyAlpha*:*Polynomial*:*Unattenuate*:*MirrorPlane_16* Bug: None Change-Id: Ib8b68beb77b47de6b996d41fd080397c61539ffb |
||
|---|---|---|
| .. | ||
| compare_common.cc | ||
| compare_gcc.cc | ||
| compare_hvx.cc | ||
| compare_neon64.cc | ||
| compare_neon.cc | ||
| compare_wasm.cc | ||
| compare_win.cc | ||
| compare.cc | ||
| convert_argb.cc | ||
| convert_from_argb.cc | ||
| convert_from.cc | ||
| convert_jpeg.cc | ||
| convert_to_argb.cc | ||
| convert_to_i420.cc | ||
| convert.cc | ||
| cpu_id.cc | ||
| mjpeg_decoder.cc | ||
| mjpeg_validate.cc | ||
| planar_functions.cc | ||
| rotate_any.cc | ||
| rotate_argb.cc | ||
| rotate_common.cc | ||
| rotate_gcc.cc | ||
| rotate_hvx.cc | ||
| rotate_lasx.cc | ||
| rotate_lsx.cc | ||
| rotate_neon64.cc | ||
| rotate_neon.cc | ||
| rotate_rvv.cc | ||
| rotate_sme.cc | ||
| rotate_sve.cc | ||
| rotate_wasm.cc | ||
| rotate_win.cc | ||
| rotate.cc | ||
| row_any.cc | ||
| row_common.cc | ||
| row_gcc.cc | ||
| row_hvx.cc | ||
| row_lasx.cc | ||
| row_lsx.cc | ||
| row_neon64.cc | ||
| row_neon.cc | ||
| row_rvv.cc | ||
| row_sme.cc | ||
| row_sve.cc | ||
| row_wasm.cc | ||
| row_win.cc | ||
| scale_any.cc | ||
| scale_argb.cc | ||
| scale_common.cc | ||
| scale_gcc.cc | ||
| scale_hvx.cc | ||
| scale_lsx.cc | ||
| scale_neon64.cc | ||
| scale_neon.cc | ||
| scale_rgb.cc | ||
| scale_rvv.cc | ||
| scale_sme.cc | ||
| scale_uv.cc | ||
| scale_wasm.cc | ||
| scale_win.cc | ||
| scale.cc | ||
| test.sh | ||
| video_common.cc | ||