Download Latest Version Simd v7.0.160 source code.tar.gz (4.8 MB)
Email in envelope

Get an email when there's a new version of Simd Library

Home / v7.0.160
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2026-04-01 5.2 kB
0
Simd v7.0.160 source code.tar.gz 2026-04-01 4.8 MB
0
Simd v7.0.160 source code.zip 2026-04-01 6.5 MB
1 1 weekly downloads
Totals: 3 Items   11.4 MB 1

Algorithms

New features
  • Possibility to use non constant B matrix in framework SynetInnerProduct32f.
  • Function SimdSynetInnerProduct32fExternalBufferSize.
  • Parameter 'activation' to function SimdSynetInnerProduct16bInit.
  • Parameter 'params' to function SimdSynetInnerProduct16bSetParams.
  • Base implementation of class SynetGatherElements.
  • Base implementation, SSE4.1, AVX2, AVX-512BW optimizations of function SynetNormalizeLayerForward16bV2.
  • Base implementation, SSE4.1, AVX2, AVX-512BW optimizations of function SynetSoftmax16b.
  • Support of HVX extension (Hexagon platform).
  • HVX optimizations of function AbsDifference.
  • HVX optimizations of function AbsDifferenceSum.
  • HVX optimizations of function AbsGradientSaturatedSum.
  • HVX optimizations of function AddFeatureDifference.
  • HVX optimizations of function BgrToGray.
  • HVX optimizations of function BgrToRgb.
  • HVX optimizations of function FillBgra.
  • HVX optimizations of function FillPixel.
  • HVX optimizations of function AbsSecondDerivativeHistogram.
  • HVX optimizations of function HistogramMasked.
  • HVX optimizations of function HistogramConditional.
  • HVX optimizations of function OperationBinary8u.
  • HVX optimizations of function GetStatistic.
  • HVX optimizations of function GetRowSums.
  • HVX optimizations of function GetColSums.
  • HVX optimizations of function GetAbsDyRowSums.
  • HVX optimizations of function GetAbsDxColSums.
  • HVX optimizations of function ValueSum.
  • HVX optimizations of function SquareSum.
  • HVX optimizations of function ValueSquareSum.
  • HVX optimizations of function ValueSquareSums.
  • HVX optimizations of function CorrelationSum.
  • SSE4.1, AVX2, AVX-512BW optimizations of function BgrToHsl.
Improving
  • AMX-BF16 optimizations of class SynetMergedConvolution16bCdc.
  • AMX-BF16 optimizations of class SynetMergedConvolution16bCd.
  • AMX-BF16 optimizations of class SynetMergedConvolution16bDc.
  • AMX-BF16 optimizations of class SynetInnerProduct16bGemmNN.
Bug fixing
  • Error in SSE4.1, AVX2, AVX-512BW optimizations of function SynetQuantizedPreluLayerForward (possible aligned read of unaligned memory).
  • Error in SSE4.1, AVX2, AVX-512BW optimizations of function SynetQuantizedScaleLayerForward (possible aligned read of unaligned memory).
  • Error in SSE4.1 optimizations of class ResizerFloatBilinear (possible aligned read of unaligned memory).
  • Error in SSE4.1 optimizations of class ResizerBf16Bilinear (possible aligned read of unaligned memory).
  • Error in SSE4.1, AVX2 optimizations of class ResizerByteBilinear (possible aligned read of unaligned memory).
  • Error in SSE4.1 optimizations of class ResizerByteBilinear (possible aligned write to unaligned memory).
  • Error in SSE4.1 optimizations of class ResizerFloatBilinear (possible aligned write to unaligned memory).
  • Memory leak in function Simd::Detection::LoadStringXml.
  • Possible crash in function Simd::ImageLoadFromFile.
  • Possible crash in function Simd::Base64Decode.
  • Possible crash in AVX-512BW optimization of function TransformImageRotate270.
  • Performance bug in AVX-512BW optimization of class SynetMergedConvolution32fCdc.
  • Performance bug in AMX-BF16 optimization of class SynetMergedConvolution16bCdc.
  • Compiler error in assert conditions in function Simd::DeinterleaveBgra.
  • Compiler error in assert conditions in function Simd::DeinterleaveRgb.
  • Compiler error in assert conditions in function Simd::DeinterleaveRgba.
  • Compiler error in assert conditions in function Simd::GetObjectMoments.
  • MSVS compiler bug in Base implementation of function BgrToHsl (Release, x64).
  • MSVS compiler bug in Base implementation of function SynetQuantizedScaleLayerForward (Release, Win32).
Renaming
  • Function SynetSoftmaxLayerForward to SynetSoftmax32f.

Test framework

New features
  • Tests for verifying functionality of class SynetGatherElements.
  • Tests for verifying functionality of function SynetNormalizeLayerForward16bV2.
  • Tests for verifying functionality of function SynetSoftmax16b.
Improving
  • Add thread save state to functions Test::Rand and Test::Srand.
  • Add smoothing to function Test::CreateTestImage.
Bug fixing
  • Wrong parsing of 'testStatistics' command line option.
  • Wrong parsing of 'testRepeats' command line option.
  • Too long github action test step in msbuild.yml.
  • Too long github action test step in cmake.yml.

Documentation

Bug fixing
  • Syntax and lexical errors in project documentation.
Source: README.md, updated 2026-04-01