Simd Library Release Notes (2018).

Home | Release Notes | Download | Documentation | Issues | GitHub

2024 | 2023 | 2022 | 2021 | 2020 | 2019 | 2018 | 2017 | 2016 | 2015 | 2014 | 2013

December 3, 2018 (version 4.2.72)

Algorithms

New features
  • PReLU activation function in convolution framework.
  • DepthwiseDotProduct optimization in convolution framework.
  • AVX2 and AVX-512F optimizations of ImgToCol function in convolution framework.
  • Transposed flag in function SynetAddBias.
  • Transposed flag in function SynetScaleLayerForward.
  • Base implementation, SSE, AVX and AVX-512F optimizations of function SynetPreluLayerForward.
  • Transposed flag in function FusedLayerForward0.
  • Transposed flag in function FusedLayerForward1.
  • Transposed flag in function FusedLayerForward2.
  • SIMD_NO_MANS_LAND macro.
Bug fixing
  • Memory reading outside of input array in SSE, AVX and AVX-512F optimizations of function Winograd2x3pSetInput.

Test framework

New features
  • Tests for verifying functionality of function SynetPreluLayerForward.
Home

November 1, 2018 (version 4.2.71)

Algorithms

New features
  • Base implementation, SSE3, AVX and AVX-512F optimizations of function SynetRestrictRange.
  • Base implementation, SSE, AVX and AVX-512F optimizations of function Fill32f.
  • Base implementation, SSE, AVX and AVX-512F optimizations of function ConvolutionSetActivation
  • Base implementation, SSE, AVX and AVX-512F optimizations of function FusedLayerForward0
  • Base implementation, SSE, AVX and AVX-512F optimizations of function FusedLayerForward1
  • Base implementation, SSE, AVX, AVX2 and AVX-512F optimizations of function SynetInnerProductLayerForward
  • Base implementation, SSE, AVX and AVX-512F optimizations of function FusedLayerForward2
Improving
  • Base implementation, SSE, SSE3, AVX, AVX2 and AVX-512F optimizations of function ConvolutionForward.
  • Add output parameter 'internal' to function ConvolutionSetWeight.
Bug fixing
  • Compiler error in function Gemm32fNN (32 bit mode).
  • Error in Relu when slope > 1.

Test framework

New features
  • Tests for verifying functionality of function SynetRestrictRange.
  • Tests for verifying functionality of function Fill32f.
  • Tests for verifying functionality of function FusedLayerForward0.
  • Tests for verifying functionality of function FusedLayerForward1.
  • Tests for verifying functionality of function SynetInnerProductLayerForward.
  • Tests for verifying functionality of function FusedLayerForward1.

Infrastructure

New features
  • PRINT_INFO option for CMake.
  • UpdateCopyrights.sh script.
Bug fixing
  • CMake build error when Simd is used as external project.
Home

October 1, 2018 (version 4.2.70)

Algorithms

New features
  • AVX optimization of function Winograd2x3iSetInput.
  • AVX and AVX-512F optimizations of function Winograd2x3pSetInput.
  • AVX and AVX-512F optimizations of function Winograd2x3pSetOutput.
  • Base implementation and SSE and AVX optimizations of function Winograd2x3iSetOutput.
  • Own implementation of XML instead of tinyxml2.
  • Base implementation of function ConvolutionInit.
  • Base implementation of function ConvolutionBufferSize.
  • Base implementation and SSE optimization of function ConvolutionSetWeight.
  • Base implementation, SSE, AVX, AVX2 and AVX-512F optimizations of function ConvolutionForward.
  • Base implementation, SSE3, AVX, AVX2 and AVX-512F optimizations of function Gemm32fNT.

Test framework

New features
  • Tests for verifying of AVX optimization of function Winograd2x3iSetInput.
  • Tests for verifying of AVX and AVX-512F optimizations of function Winograd2x3pSetInput.
  • Tests for verifying of AVX and AVX-512F optimizations of function Winograd2x3pSetOutput.
  • Tests for verifying functionality of function Winograd2x3iSetOutput.
  • Tests for verifying functionality of function ConvolutionInit.
  • Tests for verifying functionality of function ConvolutionBufferSize.
  • Tests for verifying functionality of function ConvolutionSetWeight.
  • Tests for verifying functionality of function ConvolutionForward.
  • Tests for verifying functionality of function Gemm32fNT.
Home

September 3, 2018 (version 4.2.69)

Algorithms

New features
  • SSE2, SSSE3, AVX2, AVX-512BW optimizations of function ReduceColor2x2.
  • Function Simd::Reduce2x2.
  • Function Simd::ResizeArea.
  • Conversion Sim::Point to cv::Point2f.
  • Base implementation and SSE optimization of function Winograd2x3iSetInput.
  • Base implementation and SSE optimization of function Winograd2x3pSetFilter.
  • Base implementation and SSE optimization of function Winograd2x3pSetInput.
  • Base implementation and SSE optimization of function Winograd2x3pSetOutput.
  • Base implementation and SSE optimization of function Winograd4x3pSetFilter.
  • Base implementation of function Winograd4x3pSetInput.
  • Base implementation of function Winograd4x3pSetOutput.
Bug fixing
  • Error in AVX2 optimization of function ReduceGray2x2 for Visual Studio 2013.
  • Assert in function Font::Draw.
  • Linker error when used options -march=native and -DAVX512=0 for SkylakeX.
  • Compiler error (Visual Studio 2017 for Android).

Test framework

New features
  • Tests for verifying functionality of SSE2, SSSE3, AVX2 and AVX-512BW optimizations of function ReduceColor2x2.
  • Tests for verifying functionality of function Winograd2x3iSetInput.
  • Tests for verifying functionality of function Winograd2x3pSetFilter.
  • Tests for verifying functionality of function Winograd2x3pSetInput.
  • Tests for verifying functionality of function Winograd2x3pSetOutput.
  • Tests for verifying functionality of function Winograd4x3pSetFilter.
  • Tests for verifying functionality of function Winograd4x3pSetInput.
  • Tests for verifying functionality of function Winograd4x3pSetOutput.

Infrastructure

New features
  • Compilation without generation of file SimdVersion.h.
Home

August 6, 2018 (version 4.2.68)

Algorithms

New features
  • Error message in function Allocate.
Bug fixing
  • Error in AVX-512F optimization of function HogLiteCompressFeatures.
  • Error in AVX-512F optimization of function HogLiteFilterSeparable.
  • Error in AVX-512F optimization of function HogLiteFilterFeatures.

Test framework

Bug fixing
  • Test error for function CosineDistance32f.
  • Error in test for function HogLiteFilterSeparable.
  • Error in test for function ReduceGray4x4.

Infrastructure

Removing
  • Extraction of current SVN revision.

Documentation

Removing
  • References to old project on sourceforge.net.
Home

July 3, 2018 (version 4.2.67)

Algorithms

New features
  • NEON optimization of function NeuralConvolutionForward.
  • Extension of functionality of SynetEltwiseLayerForward.
  • SSE2, AVX2 and AVX-512BW optimizations of function BayerToBgra.
  • SSSE3, AVX2 and AVX-512BW optimizations of function BayerToBgr.
Bug fixing
  • Visual Studio warning (NOMINMAX macro redefinition) in file SimdEnable.h.

Test framework

New features
  • Tests for verifying functionality of NEON optimization of function NeuralConvolutionForward.
  • Tests for verifying functionality of SSE2, AVX2 and AVX-512BW optimizations of function BayerToBgra.
  • Tests for verifying functionality of SSSE3, AVX2 and AVX-512BW optimizations of function BayerToBgr.

Infrastructure

New features
  • SIMD_TEST option in CMakeLists.txt.
  • Library building in arbitrary directory.
  • Library building with using of MinGW.
  • New release storing site (github.com).

Documentation

New features
  • An example for function View::Ref.
Home

June 1, 2018 (version 4.2.66.1415)

Algorithms

Bug fixing
  • GCC-5.4.0 compiler error in file SimdAvx512bwResizeBilinear.cpp.
  • Assert in function Avx2::BackgroundIncrementCount.
  • Assert in function Avx512bw::GrayToBgra.
  • Error in function View::Region.
  • Assert in function Avx512bw::AlphaFilling.
  • Error in function Base::FillPixel.
  • GCC 4.8.5 compiler error in function Sse::Load.
  • Error in function SimdLbpEstimate.
  • Error in function SimdHogLiteExtractFeatures.

Test framework

Bug fixing
New features
  • Include (test parameter '-fi') and exclude (test parameter '-fe') filters for tests.
  • Checking for minimal size of test image.
Home

May 14, 2018 (version 4.2.65.1405)

Algorithms

New features
  • Function SimdGetThreadNumber.
  • Function SimdSetThreadNumber.
  • Multithreading of function Gemm32fNN.
  • Function SimdGetFlushToZero.
  • Function SimdSetFlushToZero.
  • Base implementation, SSE AVX, AVX2 and AVX-512F optimizations of functions ResizerInit and ResizerRun.
Improving
  • AVX-512BW optimization of function ResizeBilinear.
Changing
  • Changed parameters of function HogLiteFilterFeatures.
  • Renamed function SimdDetectionFree to SimdRelease.

Test framework

New features
  • Multithreading of test execution (test parameter '-tt').
  • Multithreading of algorithm work (test parameter '-wt').
  • Tests for verifying functionality of functions ResizerInit and ResizerRun.
Bug fixing
  • HTML performance report.
Home

April 2, 2018 (version 4.1.64.1388)

Algorithms

New features
  • Optional including of SimdVersion.h file in SimdLib.cpp.
  • Conversion of Simd::View to Tensorflow::Tensor.
  • Base implementation, SSE, AVX, AVX2 and AVX-512F optimizations of function Gemm32fNN.
  • Function ResizeAreaGray
Bug fixing
  • Error in base implementation, SSE2, AVX2 and AVX-512F optimizations of function Uint8ToFloat32.
  • Error in SSE2 optimization of function ReduceGray2x2.

Test framework

New features
  • Tests for verifying functionality of function Gemm32fNN.
Bug fixing
  • Error in special test of Simd::Detection (Debug only).
Home

March 1, 2018 (version 4.1.63.1372)

Algorithms

New features
  • Base implementation, SSE, AVX, AVX2 and AVX-512BW optimizations of function CosineDistance32f.
  • Base implementation, AVX2 and AVX-512BW optimizations of function CosineDistance16f.
  • NEON optimization of function ValueSquareSum.
  • Base implementation, SSE, AVX and AVX-512F optimizations of function SynetAddBias.
  • Base implementation, SSE, AVX, AVX2 and AVX-512F optimizations of function SynetScaleLayerForward.
  • Base implementation, SSE, AVX, AVX2 and AVX-512F optimizations of function SynetEltwiseLayerForward.
  • Base implementation, SSE, AVX, AVX2 and AVX-512F optimizations of function SynetScaleLayerForward.
  • Base implementation, SSE2, AVX2 and AVX-512F optimizations of function SynetLrnLayerCrossChannels.
Improving
  • NEON optimization of function ResizeBilinear.
Bug fixing
  • Visual Studio 2012 compiler errors.
  • Clang compiler warning in file TestCheckC.c.

Test framework

New features
  • Tests for verifying functionality of function CosineDistance32f.
  • Tests for verifying functionality of function CosineDistance16f.
  • Tests for verifying functionality of NEON optimization of function ValueSquareSum.
  • Tests for verifying functionality of function SynetAddBias.
  • Tests for verifying functionality of function SynetScaleLayerForward.
  • Tests for verifying functionality of function SynetEltwiseLayerForward.
  • Tests for verifying functionality of function SynetLrnLayerCrossChannels.
Home

February 1, 2018 (version 4.1.62.1359)

Algorithms

New features
  • Base implementation, SSE2, AVX2 and AVX-512BW optimizations of function ValueSquareSum.
Improving
  • AVX2 and AVX-512F optimizations of function NeuralConvolutionForward.
  • Updated tinyxml2 library.
Bug fixing
  • Crash in function NeuralConvolutionForward for small images.

Test framework

New features
  • Tests for verifying functionality of function ValueSquareSum.
Home

January 3, 2018 (version 4.1.61.1351)

Algorithms

New features
  • Method Font::Draw.
  • Base implementation, SSE2, AVX2 and AVX-512BW optimizations of function FillPixel.
  • Base implementation, SSE2, SSSE3, AVX2 and AVX-512BW optimizations of function AlphaFilling.
  • Base implementation, SSE2, AVX2 and AVX-512F optimizations of function NeuralPow.
  • SSE2, AVX2 and AVX-512F optimizations of function NeuralSigmoid.
  • SSE2, AVX2 and AVX-512F optimizations of function NeuralTanh.
Bug fixing
  • Crash in AVX-512BW optimization of function ConditionalSquareGradientSum.
  • Error in AVX-512BW optimization of function NeuralAddConvolution3x3Sum.
  • Error in AVX-512BW optimization of function NeuralAddConvolution4x4Sum.
  • Error in AVX-512BW optimization of function NeuralAddConvolution5x5Sum.
  • Clang compiler bug in file SimdFont.hpp.
  • GCC-6 compiler warning for Array typedef.
  • Visual Studio 2013 compiler error in file SimdSse2Neural.cpp.
  • Visual Studio 2013 compiler error in file SimdSse3Neural.cpp.
  • Visual Studio 2013 compiler error in file SimdSse41HogLite.cpp.
  • Visual Studio 2013 compiler error in file SimdAvx2Neural.cpp.
Improving
  • AVX-512BW optimization of function AbsDifferenceSums3x3 for Visual Studio.
  • AVX-512BW optimization of function AbsDifferenceSums3x3Masked for Visual Studio.
  • SSE3, AVX, AVX2 and AVX-512F optimizations of function NeuralConvolutionForward.

Test framework

New features
  • Tests for verifying functionality of function FillPixel.
  • Tests for verifying functionality of function AlphaFilling.
  • Tests for verifying functionality of function NeuralPow.
  • Tests for verifying SSE2, AVX2 and AVX-512F optimizations of function NeuralSigmoid.
  • Tests for verifying SSE2, AVX2 and AVX-512F optimizations of function NeuralTanh.
Bug fixing
  • Wrong data tests of function HogLiteFilterFeatures.
  • Wrong data tests of function HogLiteResizeFeatures.
  • Wrong data tests of function HogLiteCompressFeatures.
  • Wrong data tests of function HogLiteFilterSeparable.
  • Wrong data tests of function NeuralAddConvolution5x5Forward.
  • Wrong data tests of function HogFilterSeparable.
  • Wrong data tests of function SquaredDifferenceSum16f.
  • Wrong data tests of function SquaredDifferenceKahanSum32f.
  • Visual Studio 2013 compiler error in file TestData.cpp.

Infrastructure

New features
  • LIBRARY parameter to build Simd Library as STATIC or SHARED library.
  • AVX512 parameter to build Simd Library with (or without) AVX-512.
  • Visual Studio 2012 project files.
  • Visual Studio 2013 project files.

The use examples

New features
  • An example how to detect motion with using of Simd::Motion in the video captured by OpenCV.

Documentation

New features
  • An example how to detect motion with using of Simd::Motion in the video captured by OpenCV.
Home
2024 | 2023 | 2022 | 2021 | 2020 | 2019 | 2018 | 2017 | 2016 | 2015 | 2014 | 2013