umappp 0.1.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/LICENSE.txt +25 -0
- data/README.md +110 -0
- data/ext/umappp/extconf.rb +25 -0
- data/ext/umappp/numo.hpp +867 -0
- data/ext/umappp/umappp.cpp +225 -0
- data/lib/umappp/version.rb +5 -0
- data/lib/umappp.rb +41 -0
- data/vendor/Eigen/Cholesky +45 -0
- data/vendor/Eigen/CholmodSupport +48 -0
- data/vendor/Eigen/Core +384 -0
- data/vendor/Eigen/Dense +7 -0
- data/vendor/Eigen/Eigen +2 -0
- data/vendor/Eigen/Eigenvalues +60 -0
- data/vendor/Eigen/Geometry +59 -0
- data/vendor/Eigen/Householder +29 -0
- data/vendor/Eigen/IterativeLinearSolvers +48 -0
- data/vendor/Eigen/Jacobi +32 -0
- data/vendor/Eigen/KLUSupport +41 -0
- data/vendor/Eigen/LU +47 -0
- data/vendor/Eigen/MetisSupport +35 -0
- data/vendor/Eigen/OrderingMethods +70 -0
- data/vendor/Eigen/PaStiXSupport +49 -0
- data/vendor/Eigen/PardisoSupport +35 -0
- data/vendor/Eigen/QR +50 -0
- data/vendor/Eigen/QtAlignedMalloc +39 -0
- data/vendor/Eigen/SPQRSupport +34 -0
- data/vendor/Eigen/SVD +50 -0
- data/vendor/Eigen/Sparse +34 -0
- data/vendor/Eigen/SparseCholesky +37 -0
- data/vendor/Eigen/SparseCore +69 -0
- data/vendor/Eigen/SparseLU +50 -0
- data/vendor/Eigen/SparseQR +36 -0
- data/vendor/Eigen/StdDeque +27 -0
- data/vendor/Eigen/StdList +26 -0
- data/vendor/Eigen/StdVector +27 -0
- data/vendor/Eigen/SuperLUSupport +64 -0
- data/vendor/Eigen/UmfPackSupport +40 -0
- data/vendor/Eigen/src/Cholesky/LDLT.h +688 -0
- data/vendor/Eigen/src/Cholesky/LLT.h +558 -0
- data/vendor/Eigen/src/Cholesky/LLT_LAPACKE.h +99 -0
- data/vendor/Eigen/src/CholmodSupport/CholmodSupport.h +682 -0
- data/vendor/Eigen/src/Core/ArithmeticSequence.h +413 -0
- data/vendor/Eigen/src/Core/Array.h +417 -0
- data/vendor/Eigen/src/Core/ArrayBase.h +226 -0
- data/vendor/Eigen/src/Core/ArrayWrapper.h +209 -0
- data/vendor/Eigen/src/Core/Assign.h +90 -0
- data/vendor/Eigen/src/Core/AssignEvaluator.h +1010 -0
- data/vendor/Eigen/src/Core/Assign_MKL.h +178 -0
- data/vendor/Eigen/src/Core/BandMatrix.h +353 -0
- data/vendor/Eigen/src/Core/Block.h +448 -0
- data/vendor/Eigen/src/Core/BooleanRedux.h +162 -0
- data/vendor/Eigen/src/Core/CommaInitializer.h +164 -0
- data/vendor/Eigen/src/Core/ConditionEstimator.h +175 -0
- data/vendor/Eigen/src/Core/CoreEvaluators.h +1741 -0
- data/vendor/Eigen/src/Core/CoreIterators.h +132 -0
- data/vendor/Eigen/src/Core/CwiseBinaryOp.h +183 -0
- data/vendor/Eigen/src/Core/CwiseNullaryOp.h +1001 -0
- data/vendor/Eigen/src/Core/CwiseTernaryOp.h +197 -0
- data/vendor/Eigen/src/Core/CwiseUnaryOp.h +103 -0
- data/vendor/Eigen/src/Core/CwiseUnaryView.h +132 -0
- data/vendor/Eigen/src/Core/DenseBase.h +701 -0
- data/vendor/Eigen/src/Core/DenseCoeffsBase.h +685 -0
- data/vendor/Eigen/src/Core/DenseStorage.h +652 -0
- data/vendor/Eigen/src/Core/Diagonal.h +258 -0
- data/vendor/Eigen/src/Core/DiagonalMatrix.h +391 -0
- data/vendor/Eigen/src/Core/DiagonalProduct.h +28 -0
- data/vendor/Eigen/src/Core/Dot.h +318 -0
- data/vendor/Eigen/src/Core/EigenBase.h +160 -0
- data/vendor/Eigen/src/Core/ForceAlignedAccess.h +150 -0
- data/vendor/Eigen/src/Core/Fuzzy.h +155 -0
- data/vendor/Eigen/src/Core/GeneralProduct.h +465 -0
- data/vendor/Eigen/src/Core/GenericPacketMath.h +1040 -0
- data/vendor/Eigen/src/Core/GlobalFunctions.h +194 -0
- data/vendor/Eigen/src/Core/IO.h +258 -0
- data/vendor/Eigen/src/Core/IndexedView.h +237 -0
- data/vendor/Eigen/src/Core/Inverse.h +117 -0
- data/vendor/Eigen/src/Core/Map.h +171 -0
- data/vendor/Eigen/src/Core/MapBase.h +310 -0
- data/vendor/Eigen/src/Core/MathFunctions.h +2057 -0
- data/vendor/Eigen/src/Core/MathFunctionsImpl.h +200 -0
- data/vendor/Eigen/src/Core/Matrix.h +565 -0
- data/vendor/Eigen/src/Core/MatrixBase.h +547 -0
- data/vendor/Eigen/src/Core/NestByValue.h +85 -0
- data/vendor/Eigen/src/Core/NoAlias.h +109 -0
- data/vendor/Eigen/src/Core/NumTraits.h +335 -0
- data/vendor/Eigen/src/Core/PartialReduxEvaluator.h +232 -0
- data/vendor/Eigen/src/Core/PermutationMatrix.h +605 -0
- data/vendor/Eigen/src/Core/PlainObjectBase.h +1128 -0
- data/vendor/Eigen/src/Core/Product.h +191 -0
- data/vendor/Eigen/src/Core/ProductEvaluators.h +1179 -0
- data/vendor/Eigen/src/Core/Random.h +218 -0
- data/vendor/Eigen/src/Core/Redux.h +515 -0
- data/vendor/Eigen/src/Core/Ref.h +381 -0
- data/vendor/Eigen/src/Core/Replicate.h +142 -0
- data/vendor/Eigen/src/Core/Reshaped.h +454 -0
- data/vendor/Eigen/src/Core/ReturnByValue.h +119 -0
- data/vendor/Eigen/src/Core/Reverse.h +217 -0
- data/vendor/Eigen/src/Core/Select.h +164 -0
- data/vendor/Eigen/src/Core/SelfAdjointView.h +365 -0
- data/vendor/Eigen/src/Core/SelfCwiseBinaryOp.h +47 -0
- data/vendor/Eigen/src/Core/Solve.h +188 -0
- data/vendor/Eigen/src/Core/SolveTriangular.h +235 -0
- data/vendor/Eigen/src/Core/SolverBase.h +168 -0
- data/vendor/Eigen/src/Core/StableNorm.h +251 -0
- data/vendor/Eigen/src/Core/StlIterators.h +463 -0
- data/vendor/Eigen/src/Core/Stride.h +116 -0
- data/vendor/Eigen/src/Core/Swap.h +68 -0
- data/vendor/Eigen/src/Core/Transpose.h +464 -0
- data/vendor/Eigen/src/Core/Transpositions.h +386 -0
- data/vendor/Eigen/src/Core/TriangularMatrix.h +1001 -0
- data/vendor/Eigen/src/Core/VectorBlock.h +96 -0
- data/vendor/Eigen/src/Core/VectorwiseOp.h +784 -0
- data/vendor/Eigen/src/Core/Visitor.h +381 -0
- data/vendor/Eigen/src/Core/arch/AVX/Complex.h +372 -0
- data/vendor/Eigen/src/Core/arch/AVX/MathFunctions.h +228 -0
- data/vendor/Eigen/src/Core/arch/AVX/PacketMath.h +1574 -0
- data/vendor/Eigen/src/Core/arch/AVX/TypeCasting.h +115 -0
- data/vendor/Eigen/src/Core/arch/AVX512/Complex.h +422 -0
- data/vendor/Eigen/src/Core/arch/AVX512/MathFunctions.h +362 -0
- data/vendor/Eigen/src/Core/arch/AVX512/PacketMath.h +2303 -0
- data/vendor/Eigen/src/Core/arch/AVX512/TypeCasting.h +89 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/Complex.h +417 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/MathFunctions.h +90 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/MatrixProduct.h +2937 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/MatrixProductCommon.h +221 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/MatrixProductMMA.h +629 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/PacketMath.h +2711 -0
- data/vendor/Eigen/src/Core/arch/CUDA/Complex.h +258 -0
- data/vendor/Eigen/src/Core/arch/Default/BFloat16.h +700 -0
- data/vendor/Eigen/src/Core/arch/Default/ConjHelper.h +117 -0
- data/vendor/Eigen/src/Core/arch/Default/GenericPacketMathFunctions.h +1649 -0
- data/vendor/Eigen/src/Core/arch/Default/GenericPacketMathFunctionsFwd.h +110 -0
- data/vendor/Eigen/src/Core/arch/Default/Half.h +942 -0
- data/vendor/Eigen/src/Core/arch/Default/Settings.h +49 -0
- data/vendor/Eigen/src/Core/arch/Default/TypeCasting.h +120 -0
- data/vendor/Eigen/src/Core/arch/GPU/MathFunctions.h +103 -0
- data/vendor/Eigen/src/Core/arch/GPU/PacketMath.h +1685 -0
- data/vendor/Eigen/src/Core/arch/GPU/TypeCasting.h +80 -0
- data/vendor/Eigen/src/Core/arch/HIP/hcc/math_constants.h +23 -0
- data/vendor/Eigen/src/Core/arch/MSA/Complex.h +648 -0
- data/vendor/Eigen/src/Core/arch/MSA/MathFunctions.h +387 -0
- data/vendor/Eigen/src/Core/arch/MSA/PacketMath.h +1233 -0
- data/vendor/Eigen/src/Core/arch/NEON/Complex.h +584 -0
- data/vendor/Eigen/src/Core/arch/NEON/GeneralBlockPanelKernel.h +183 -0
- data/vendor/Eigen/src/Core/arch/NEON/MathFunctions.h +75 -0
- data/vendor/Eigen/src/Core/arch/NEON/PacketMath.h +4587 -0
- data/vendor/Eigen/src/Core/arch/NEON/TypeCasting.h +1419 -0
- data/vendor/Eigen/src/Core/arch/SSE/Complex.h +351 -0
- data/vendor/Eigen/src/Core/arch/SSE/MathFunctions.h +199 -0
- data/vendor/Eigen/src/Core/arch/SSE/PacketMath.h +1505 -0
- data/vendor/Eigen/src/Core/arch/SSE/TypeCasting.h +142 -0
- data/vendor/Eigen/src/Core/arch/SVE/MathFunctions.h +44 -0
- data/vendor/Eigen/src/Core/arch/SVE/PacketMath.h +752 -0
- data/vendor/Eigen/src/Core/arch/SVE/TypeCasting.h +49 -0
- data/vendor/Eigen/src/Core/arch/SYCL/InteropHeaders.h +232 -0
- data/vendor/Eigen/src/Core/arch/SYCL/MathFunctions.h +301 -0
- data/vendor/Eigen/src/Core/arch/SYCL/PacketMath.h +670 -0
- data/vendor/Eigen/src/Core/arch/SYCL/SyclMemoryModel.h +694 -0
- data/vendor/Eigen/src/Core/arch/SYCL/TypeCasting.h +85 -0
- data/vendor/Eigen/src/Core/arch/ZVector/Complex.h +426 -0
- data/vendor/Eigen/src/Core/arch/ZVector/MathFunctions.h +233 -0
- data/vendor/Eigen/src/Core/arch/ZVector/PacketMath.h +1060 -0
- data/vendor/Eigen/src/Core/functors/AssignmentFunctors.h +177 -0
- data/vendor/Eigen/src/Core/functors/BinaryFunctors.h +541 -0
- data/vendor/Eigen/src/Core/functors/NullaryFunctors.h +189 -0
- data/vendor/Eigen/src/Core/functors/StlFunctors.h +166 -0
- data/vendor/Eigen/src/Core/functors/TernaryFunctors.h +25 -0
- data/vendor/Eigen/src/Core/functors/UnaryFunctors.h +1131 -0
- data/vendor/Eigen/src/Core/products/GeneralBlockPanelKernel.h +2645 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixMatrix.h +517 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixMatrixTriangular.h +317 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixMatrixTriangular_BLAS.h +145 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixMatrix_BLAS.h +124 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixVector.h +518 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixVector_BLAS.h +136 -0
- data/vendor/Eigen/src/Core/products/Parallelizer.h +180 -0
- data/vendor/Eigen/src/Core/products/SelfadjointMatrixMatrix.h +544 -0
- data/vendor/Eigen/src/Core/products/SelfadjointMatrixMatrix_BLAS.h +295 -0
- data/vendor/Eigen/src/Core/products/SelfadjointMatrixVector.h +262 -0
- data/vendor/Eigen/src/Core/products/SelfadjointMatrixVector_BLAS.h +118 -0
- data/vendor/Eigen/src/Core/products/SelfadjointProduct.h +133 -0
- data/vendor/Eigen/src/Core/products/SelfadjointRank2Update.h +94 -0
- data/vendor/Eigen/src/Core/products/TriangularMatrixMatrix.h +472 -0
- data/vendor/Eigen/src/Core/products/TriangularMatrixMatrix_BLAS.h +317 -0
- data/vendor/Eigen/src/Core/products/TriangularMatrixVector.h +350 -0
- data/vendor/Eigen/src/Core/products/TriangularMatrixVector_BLAS.h +255 -0
- data/vendor/Eigen/src/Core/products/TriangularSolverMatrix.h +337 -0
- data/vendor/Eigen/src/Core/products/TriangularSolverMatrix_BLAS.h +167 -0
- data/vendor/Eigen/src/Core/products/TriangularSolverVector.h +148 -0
- data/vendor/Eigen/src/Core/util/BlasUtil.h +583 -0
- data/vendor/Eigen/src/Core/util/ConfigureVectorization.h +512 -0
- data/vendor/Eigen/src/Core/util/Constants.h +563 -0
- data/vendor/Eigen/src/Core/util/DisableStupidWarnings.h +106 -0
- data/vendor/Eigen/src/Core/util/ForwardDeclarations.h +322 -0
- data/vendor/Eigen/src/Core/util/IndexedViewHelper.h +186 -0
- data/vendor/Eigen/src/Core/util/IntegralConstant.h +272 -0
- data/vendor/Eigen/src/Core/util/MKL_support.h +137 -0
- data/vendor/Eigen/src/Core/util/Macros.h +1464 -0
- data/vendor/Eigen/src/Core/util/Memory.h +1163 -0
- data/vendor/Eigen/src/Core/util/Meta.h +812 -0
- data/vendor/Eigen/src/Core/util/NonMPL2.h +3 -0
- data/vendor/Eigen/src/Core/util/ReenableStupidWarnings.h +31 -0
- data/vendor/Eigen/src/Core/util/ReshapedHelper.h +51 -0
- data/vendor/Eigen/src/Core/util/StaticAssert.h +221 -0
- data/vendor/Eigen/src/Core/util/SymbolicIndex.h +293 -0
- data/vendor/Eigen/src/Core/util/XprHelper.h +856 -0
- data/vendor/Eigen/src/Eigenvalues/ComplexEigenSolver.h +346 -0
- data/vendor/Eigen/src/Eigenvalues/ComplexSchur.h +462 -0
- data/vendor/Eigen/src/Eigenvalues/ComplexSchur_LAPACKE.h +91 -0
- data/vendor/Eigen/src/Eigenvalues/EigenSolver.h +622 -0
- data/vendor/Eigen/src/Eigenvalues/GeneralizedEigenSolver.h +418 -0
- data/vendor/Eigen/src/Eigenvalues/GeneralizedSelfAdjointEigenSolver.h +226 -0
- data/vendor/Eigen/src/Eigenvalues/HessenbergDecomposition.h +374 -0
- data/vendor/Eigen/src/Eigenvalues/MatrixBaseEigenvalues.h +158 -0
- data/vendor/Eigen/src/Eigenvalues/RealQZ.h +657 -0
- data/vendor/Eigen/src/Eigenvalues/RealSchur.h +558 -0
- data/vendor/Eigen/src/Eigenvalues/RealSchur_LAPACKE.h +77 -0
- data/vendor/Eigen/src/Eigenvalues/SelfAdjointEigenSolver.h +904 -0
- data/vendor/Eigen/src/Eigenvalues/SelfAdjointEigenSolver_LAPACKE.h +87 -0
- data/vendor/Eigen/src/Eigenvalues/Tridiagonalization.h +561 -0
- data/vendor/Eigen/src/Geometry/AlignedBox.h +486 -0
- data/vendor/Eigen/src/Geometry/AngleAxis.h +247 -0
- data/vendor/Eigen/src/Geometry/EulerAngles.h +114 -0
- data/vendor/Eigen/src/Geometry/Homogeneous.h +501 -0
- data/vendor/Eigen/src/Geometry/Hyperplane.h +282 -0
- data/vendor/Eigen/src/Geometry/OrthoMethods.h +235 -0
- data/vendor/Eigen/src/Geometry/ParametrizedLine.h +232 -0
- data/vendor/Eigen/src/Geometry/Quaternion.h +870 -0
- data/vendor/Eigen/src/Geometry/Rotation2D.h +199 -0
- data/vendor/Eigen/src/Geometry/RotationBase.h +206 -0
- data/vendor/Eigen/src/Geometry/Scaling.h +188 -0
- data/vendor/Eigen/src/Geometry/Transform.h +1563 -0
- data/vendor/Eigen/src/Geometry/Translation.h +202 -0
- data/vendor/Eigen/src/Geometry/Umeyama.h +166 -0
- data/vendor/Eigen/src/Geometry/arch/Geometry_SIMD.h +168 -0
- data/vendor/Eigen/src/Householder/BlockHouseholder.h +110 -0
- data/vendor/Eigen/src/Householder/Householder.h +176 -0
- data/vendor/Eigen/src/Householder/HouseholderSequence.h +545 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/BasicPreconditioners.h +226 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/BiCGSTAB.h +212 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/ConjugateGradient.h +229 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/IncompleteCholesky.h +394 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/IncompleteLUT.h +453 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/IterativeSolverBase.h +444 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/LeastSquareConjugateGradient.h +198 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/SolveWithGuess.h +117 -0
- data/vendor/Eigen/src/Jacobi/Jacobi.h +483 -0
- data/vendor/Eigen/src/KLUSupport/KLUSupport.h +358 -0
- data/vendor/Eigen/src/LU/Determinant.h +117 -0
- data/vendor/Eigen/src/LU/FullPivLU.h +877 -0
- data/vendor/Eigen/src/LU/InverseImpl.h +432 -0
- data/vendor/Eigen/src/LU/PartialPivLU.h +624 -0
- data/vendor/Eigen/src/LU/PartialPivLU_LAPACKE.h +83 -0
- data/vendor/Eigen/src/LU/arch/InverseSize4.h +351 -0
- data/vendor/Eigen/src/MetisSupport/MetisSupport.h +137 -0
- data/vendor/Eigen/src/OrderingMethods/Amd.h +435 -0
- data/vendor/Eigen/src/OrderingMethods/Eigen_Colamd.h +1863 -0
- data/vendor/Eigen/src/OrderingMethods/Ordering.h +153 -0
- data/vendor/Eigen/src/PaStiXSupport/PaStiXSupport.h +678 -0
- data/vendor/Eigen/src/PardisoSupport/PardisoSupport.h +545 -0
- data/vendor/Eigen/src/QR/ColPivHouseholderQR.h +674 -0
- data/vendor/Eigen/src/QR/ColPivHouseholderQR_LAPACKE.h +97 -0
- data/vendor/Eigen/src/QR/CompleteOrthogonalDecomposition.h +635 -0
- data/vendor/Eigen/src/QR/FullPivHouseholderQR.h +713 -0
- data/vendor/Eigen/src/QR/HouseholderQR.h +434 -0
- data/vendor/Eigen/src/QR/HouseholderQR_LAPACKE.h +68 -0
- data/vendor/Eigen/src/SPQRSupport/SuiteSparseQRSupport.h +335 -0
- data/vendor/Eigen/src/SVD/BDCSVD.h +1366 -0
- data/vendor/Eigen/src/SVD/JacobiSVD.h +812 -0
- data/vendor/Eigen/src/SVD/JacobiSVD_LAPACKE.h +91 -0
- data/vendor/Eigen/src/SVD/SVDBase.h +376 -0
- data/vendor/Eigen/src/SVD/UpperBidiagonalization.h +414 -0
- data/vendor/Eigen/src/SparseCholesky/SimplicialCholesky.h +697 -0
- data/vendor/Eigen/src/SparseCholesky/SimplicialCholesky_impl.h +174 -0
- data/vendor/Eigen/src/SparseCore/AmbiVector.h +378 -0
- data/vendor/Eigen/src/SparseCore/CompressedStorage.h +274 -0
- data/vendor/Eigen/src/SparseCore/ConservativeSparseSparseProduct.h +352 -0
- data/vendor/Eigen/src/SparseCore/MappedSparseMatrix.h +67 -0
- data/vendor/Eigen/src/SparseCore/SparseAssign.h +270 -0
- data/vendor/Eigen/src/SparseCore/SparseBlock.h +571 -0
- data/vendor/Eigen/src/SparseCore/SparseColEtree.h +206 -0
- data/vendor/Eigen/src/SparseCore/SparseCompressedBase.h +370 -0
- data/vendor/Eigen/src/SparseCore/SparseCwiseBinaryOp.h +722 -0
- data/vendor/Eigen/src/SparseCore/SparseCwiseUnaryOp.h +150 -0
- data/vendor/Eigen/src/SparseCore/SparseDenseProduct.h +342 -0
- data/vendor/Eigen/src/SparseCore/SparseDiagonalProduct.h +138 -0
- data/vendor/Eigen/src/SparseCore/SparseDot.h +98 -0
- data/vendor/Eigen/src/SparseCore/SparseFuzzy.h +29 -0
- data/vendor/Eigen/src/SparseCore/SparseMap.h +305 -0
- data/vendor/Eigen/src/SparseCore/SparseMatrix.h +1518 -0
- data/vendor/Eigen/src/SparseCore/SparseMatrixBase.h +398 -0
- data/vendor/Eigen/src/SparseCore/SparsePermutation.h +178 -0
- data/vendor/Eigen/src/SparseCore/SparseProduct.h +181 -0
- data/vendor/Eigen/src/SparseCore/SparseRedux.h +49 -0
- data/vendor/Eigen/src/SparseCore/SparseRef.h +397 -0
- data/vendor/Eigen/src/SparseCore/SparseSelfAdjointView.h +659 -0
- data/vendor/Eigen/src/SparseCore/SparseSolverBase.h +124 -0
- data/vendor/Eigen/src/SparseCore/SparseSparseProductWithPruning.h +198 -0
- data/vendor/Eigen/src/SparseCore/SparseTranspose.h +92 -0
- data/vendor/Eigen/src/SparseCore/SparseTriangularView.h +189 -0
- data/vendor/Eigen/src/SparseCore/SparseUtil.h +186 -0
- data/vendor/Eigen/src/SparseCore/SparseVector.h +478 -0
- data/vendor/Eigen/src/SparseCore/SparseView.h +254 -0
- data/vendor/Eigen/src/SparseCore/TriangularSolver.h +315 -0
- data/vendor/Eigen/src/SparseLU/SparseLU.h +923 -0
- data/vendor/Eigen/src/SparseLU/SparseLUImpl.h +66 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_Memory.h +226 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_Structs.h +110 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_SupernodalMatrix.h +375 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_Utils.h +80 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_column_bmod.h +181 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_column_dfs.h +179 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_copy_to_ucol.h +107 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_gemm_kernel.h +280 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_heap_relax_snode.h +126 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_kernel_bmod.h +130 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_panel_bmod.h +223 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_panel_dfs.h +258 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_pivotL.h +137 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_pruneL.h +136 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_relax_snode.h +83 -0
- data/vendor/Eigen/src/SparseQR/SparseQR.h +758 -0
- data/vendor/Eigen/src/StlSupport/StdDeque.h +116 -0
- data/vendor/Eigen/src/StlSupport/StdList.h +106 -0
- data/vendor/Eigen/src/StlSupport/StdVector.h +131 -0
- data/vendor/Eigen/src/StlSupport/details.h +84 -0
- data/vendor/Eigen/src/SuperLUSupport/SuperLUSupport.h +1025 -0
- data/vendor/Eigen/src/UmfPackSupport/UmfPackSupport.h +642 -0
- data/vendor/Eigen/src/misc/Image.h +82 -0
- data/vendor/Eigen/src/misc/Kernel.h +79 -0
- data/vendor/Eigen/src/misc/RealSvd2x2.h +55 -0
- data/vendor/Eigen/src/misc/blas.h +440 -0
- data/vendor/Eigen/src/misc/lapack.h +152 -0
- data/vendor/Eigen/src/misc/lapacke.h +16292 -0
- data/vendor/Eigen/src/misc/lapacke_mangling.h +17 -0
- data/vendor/Eigen/src/plugins/ArrayCwiseBinaryOps.h +358 -0
- data/vendor/Eigen/src/plugins/ArrayCwiseUnaryOps.h +696 -0
- data/vendor/Eigen/src/plugins/BlockMethods.h +1442 -0
- data/vendor/Eigen/src/plugins/CommonCwiseBinaryOps.h +115 -0
- data/vendor/Eigen/src/plugins/CommonCwiseUnaryOps.h +177 -0
- data/vendor/Eigen/src/plugins/IndexedViewMethods.h +262 -0
- data/vendor/Eigen/src/plugins/MatrixCwiseBinaryOps.h +152 -0
- data/vendor/Eigen/src/plugins/MatrixCwiseUnaryOps.h +95 -0
- data/vendor/Eigen/src/plugins/ReshapedMethods.h +149 -0
- data/vendor/aarand/aarand.hpp +114 -0
- data/vendor/annoy/annoylib.h +1495 -0
- data/vendor/annoy/kissrandom.h +120 -0
- data/vendor/annoy/mman.h +242 -0
- data/vendor/hnswlib/bruteforce.h +152 -0
- data/vendor/hnswlib/hnswalg.h +1192 -0
- data/vendor/hnswlib/hnswlib.h +108 -0
- data/vendor/hnswlib/space_ip.h +282 -0
- data/vendor/hnswlib/space_l2.h +281 -0
- data/vendor/hnswlib/visited_list_pool.h +79 -0
- data/vendor/irlba/irlba.hpp +575 -0
- data/vendor/irlba/lanczos.hpp +212 -0
- data/vendor/irlba/parallel.hpp +474 -0
- data/vendor/irlba/utils.hpp +224 -0
- data/vendor/irlba/wrappers.hpp +228 -0
- data/vendor/kmeans/Base.hpp +75 -0
- data/vendor/kmeans/Details.hpp +79 -0
- data/vendor/kmeans/HartiganWong.hpp +492 -0
- data/vendor/kmeans/InitializeKmeansPP.hpp +144 -0
- data/vendor/kmeans/InitializeNone.hpp +44 -0
- data/vendor/kmeans/InitializePCAPartition.hpp +309 -0
- data/vendor/kmeans/InitializeRandom.hpp +91 -0
- data/vendor/kmeans/Kmeans.hpp +161 -0
- data/vendor/kmeans/Lloyd.hpp +134 -0
- data/vendor/kmeans/MiniBatch.hpp +269 -0
- data/vendor/kmeans/QuickSearch.hpp +179 -0
- data/vendor/kmeans/compute_centroids.hpp +32 -0
- data/vendor/kmeans/compute_wcss.hpp +27 -0
- data/vendor/kmeans/is_edge_case.hpp +42 -0
- data/vendor/kmeans/random.hpp +55 -0
- data/vendor/knncolle/Annoy/Annoy.hpp +193 -0
- data/vendor/knncolle/BruteForce/BruteForce.hpp +120 -0
- data/vendor/knncolle/Hnsw/Hnsw.hpp +225 -0
- data/vendor/knncolle/Kmknn/Kmknn.hpp +286 -0
- data/vendor/knncolle/VpTree/VpTree.hpp +256 -0
- data/vendor/knncolle/knncolle.hpp +34 -0
- data/vendor/knncolle/utils/Base.hpp +100 -0
- data/vendor/knncolle/utils/NeighborQueue.hpp +94 -0
- data/vendor/knncolle/utils/distances.hpp +98 -0
- data/vendor/knncolle/utils/find_nearest_neighbors.hpp +112 -0
- data/vendor/powerit/PowerIterations.hpp +157 -0
- data/vendor/umappp/NeighborList.hpp +37 -0
- data/vendor/umappp/Umap.hpp +662 -0
- data/vendor/umappp/combine_neighbor_sets.hpp +95 -0
- data/vendor/umappp/find_ab.hpp +157 -0
- data/vendor/umappp/neighbor_similarities.hpp +136 -0
- data/vendor/umappp/optimize_layout.hpp +285 -0
- data/vendor/umappp/spectral_init.hpp +181 -0
- data/vendor/umappp/umappp.hpp +13 -0
- metadata +465 -0
@@ -0,0 +1,387 @@
|
|
1
|
+
// This file is part of Eigen, a lightweight C++ template library
|
2
|
+
// for linear algebra.
|
3
|
+
//
|
4
|
+
// Copyright (C) 2007 Julien Pommier
|
5
|
+
// Copyright (C) 2014 Pedro Gonnet (pedro.gonnet@gmail.com)
|
6
|
+
// Copyright (C) 2016 Gael Guennebaud <gael.guennebaud@inria.fr>
|
7
|
+
//
|
8
|
+
// Copyright (C) 2018 Wave Computing, Inc.
|
9
|
+
// Written by:
|
10
|
+
// Chris Larsen
|
11
|
+
// Alexey Frunze (afrunze@wavecomp.com)
|
12
|
+
//
|
13
|
+
// This Source Code Form is subject to the terms of the Mozilla
|
14
|
+
// Public License v. 2.0. If a copy of the MPL was not distributed
|
15
|
+
// with this file, You can obtain one at http://mozilla.org/MPL/2.0/.
|
16
|
+
|
17
|
+
/* The sin, cos, exp, and log functions of this file come from
|
18
|
+
* Julien Pommier's sse math library: http://gruntthepeon.free.fr/ssemath/
|
19
|
+
*/
|
20
|
+
|
21
|
+
/* The tanh function of this file is an adaptation of
|
22
|
+
* template<typename T> T generic_fast_tanh_float(const T&)
|
23
|
+
* from MathFunctionsImpl.h.
|
24
|
+
*/
|
25
|
+
|
26
|
+
#ifndef EIGEN_MATH_FUNCTIONS_MSA_H
|
27
|
+
#define EIGEN_MATH_FUNCTIONS_MSA_H
|
28
|
+
|
29
|
+
namespace Eigen {
|
30
|
+
|
31
|
+
namespace internal {
|
32
|
+
|
33
|
+
template <>
|
34
|
+
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS EIGEN_UNUSED Packet4f
|
35
|
+
plog<Packet4f>(const Packet4f& _x) {
|
36
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_SQRTHF, 0.707106781186547524f);
|
37
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_log_p0, 7.0376836292e-2f);
|
38
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_log_p1, -1.1514610310e-1f);
|
39
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_log_p2, 1.1676998740e-1f);
|
40
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_log_p3, -1.2420140846e-1f);
|
41
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_log_p4, +1.4249322787e-1f);
|
42
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_log_p5, -1.6668057665e-1f);
|
43
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_log_p6, +2.0000714765e-1f);
|
44
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_log_p7, -2.4999993993e-1f);
|
45
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_log_p8, +3.3333331174e-1f);
|
46
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_log_q1, -2.12194440e-4f);
|
47
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_log_q2, 0.693359375f);
|
48
|
+
static _EIGEN_DECLARE_CONST_Packet4f(half, 0.5f);
|
49
|
+
static _EIGEN_DECLARE_CONST_Packet4f(1, 1.0f);
|
50
|
+
|
51
|
+
// Convert negative argument into NAN (quiet negative, to be specific).
|
52
|
+
Packet4f zero = (Packet4f)__builtin_msa_ldi_w(0);
|
53
|
+
Packet4i neg_mask = __builtin_msa_fclt_w(_x, zero);
|
54
|
+
Packet4i zero_mask = __builtin_msa_fceq_w(_x, zero);
|
55
|
+
Packet4f non_neg_x_or_nan = padd(_x, (Packet4f)neg_mask); // Add 0.0 or NAN.
|
56
|
+
Packet4f x = non_neg_x_or_nan;
|
57
|
+
|
58
|
+
// Extract exponent from x = mantissa * 2**exponent, where 1.0 <= mantissa < 2.0.
|
59
|
+
// N.B. the exponent is one less of what frexpf() would return.
|
60
|
+
Packet4i e_int = __builtin_msa_ftint_s_w(__builtin_msa_flog2_w(x));
|
61
|
+
// Multiply x by 2**(-exponent-1) to get 0.5 <= x < 1.0 as from frexpf().
|
62
|
+
x = __builtin_msa_fexp2_w(x, (Packet4i)__builtin_msa_nori_b((v16u8)e_int, 0));
|
63
|
+
|
64
|
+
/*
|
65
|
+
if (x < SQRTHF) {
|
66
|
+
x = x + x - 1.0;
|
67
|
+
} else {
|
68
|
+
e += 1;
|
69
|
+
x = x - 1.0;
|
70
|
+
}
|
71
|
+
*/
|
72
|
+
Packet4f xx = padd(x, x);
|
73
|
+
Packet4i ge_mask = __builtin_msa_fcle_w(p4f_cephes_SQRTHF, x);
|
74
|
+
e_int = psub(e_int, ge_mask);
|
75
|
+
x = (Packet4f)__builtin_msa_bsel_v((v16u8)ge_mask, (v16u8)xx, (v16u8)x);
|
76
|
+
x = psub(x, p4f_1);
|
77
|
+
Packet4f e = __builtin_msa_ffint_s_w(e_int);
|
78
|
+
|
79
|
+
Packet4f x2 = pmul(x, x);
|
80
|
+
Packet4f x3 = pmul(x2, x);
|
81
|
+
|
82
|
+
Packet4f y, y1, y2;
|
83
|
+
y = pmadd(p4f_cephes_log_p0, x, p4f_cephes_log_p1);
|
84
|
+
y1 = pmadd(p4f_cephes_log_p3, x, p4f_cephes_log_p4);
|
85
|
+
y2 = pmadd(p4f_cephes_log_p6, x, p4f_cephes_log_p7);
|
86
|
+
y = pmadd(y, x, p4f_cephes_log_p2);
|
87
|
+
y1 = pmadd(y1, x, p4f_cephes_log_p5);
|
88
|
+
y2 = pmadd(y2, x, p4f_cephes_log_p8);
|
89
|
+
y = pmadd(y, x3, y1);
|
90
|
+
y = pmadd(y, x3, y2);
|
91
|
+
y = pmul(y, x3);
|
92
|
+
|
93
|
+
y = pmadd(e, p4f_cephes_log_q1, y);
|
94
|
+
x = __builtin_msa_fmsub_w(x, x2, p4f_half);
|
95
|
+
x = padd(x, y);
|
96
|
+
x = pmadd(e, p4f_cephes_log_q2, x);
|
97
|
+
|
98
|
+
// x is now the logarithm result candidate. We still need to handle the
|
99
|
+
// extreme arguments of zero and positive infinity, though.
|
100
|
+
// N.B. if the argument is +INFINITY, x is NAN because the polynomial terms
|
101
|
+
// contain infinities of both signs (see the coefficients and code above).
|
102
|
+
// INFINITY - INFINITY is NAN.
|
103
|
+
|
104
|
+
// If the argument is +INFINITY, make it the new result candidate.
|
105
|
+
// To achieve that we choose the smaller of the result candidate and the
|
106
|
+
// argument.
|
107
|
+
// This is correct for all finite pairs of values (the logarithm is smaller
|
108
|
+
// than the argument).
|
109
|
+
// This is also correct in the special case when the argument is +INFINITY
|
110
|
+
// and the result candidate is NAN. This is because the fmin.df instruction
|
111
|
+
// prefers non-NANs to NANs.
|
112
|
+
x = __builtin_msa_fmin_w(x, non_neg_x_or_nan);
|
113
|
+
|
114
|
+
// If the argument is zero (including -0.0), the result becomes -INFINITY.
|
115
|
+
Packet4i neg_infs = __builtin_msa_slli_w(zero_mask, 23);
|
116
|
+
x = (Packet4f)__builtin_msa_bsel_v((v16u8)zero_mask, (v16u8)x, (v16u8)neg_infs);
|
117
|
+
|
118
|
+
return x;
|
119
|
+
}
|
120
|
+
|
121
|
+
template <>
|
122
|
+
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS EIGEN_UNUSED Packet4f
|
123
|
+
pexp<Packet4f>(const Packet4f& _x) {
|
124
|
+
// Limiting single-precision pexp's argument to [-128, +128] lets pexp
|
125
|
+
// reach 0 and INFINITY naturally.
|
126
|
+
static _EIGEN_DECLARE_CONST_Packet4f(exp_lo, -128.0f);
|
127
|
+
static _EIGEN_DECLARE_CONST_Packet4f(exp_hi, +128.0f);
|
128
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_LOG2EF, 1.44269504088896341f);
|
129
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_exp_C1, 0.693359375f);
|
130
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_exp_C2, -2.12194440e-4f);
|
131
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_exp_p0, 1.9875691500e-4f);
|
132
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_exp_p1, 1.3981999507e-3f);
|
133
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_exp_p2, 8.3334519073e-3f);
|
134
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_exp_p3, 4.1665795894e-2f);
|
135
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_exp_p4, 1.6666665459e-1f);
|
136
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_exp_p5, 5.0000001201e-1f);
|
137
|
+
static _EIGEN_DECLARE_CONST_Packet4f(half, 0.5f);
|
138
|
+
static _EIGEN_DECLARE_CONST_Packet4f(1, 1.0f);
|
139
|
+
|
140
|
+
Packet4f x = _x;
|
141
|
+
|
142
|
+
// Clamp x.
|
143
|
+
x = (Packet4f)__builtin_msa_bsel_v((v16u8)__builtin_msa_fclt_w(x, p4f_exp_lo), (v16u8)x,
|
144
|
+
(v16u8)p4f_exp_lo);
|
145
|
+
x = (Packet4f)__builtin_msa_bsel_v((v16u8)__builtin_msa_fclt_w(p4f_exp_hi, x), (v16u8)x,
|
146
|
+
(v16u8)p4f_exp_hi);
|
147
|
+
|
148
|
+
// Round to nearest integer by adding 0.5 (with x's sign) and truncating.
|
149
|
+
Packet4f x2_add = (Packet4f)__builtin_msa_binsli_w((v4u32)p4f_half, (v4u32)x, 0);
|
150
|
+
Packet4f x2 = pmadd(x, p4f_cephes_LOG2EF, x2_add);
|
151
|
+
Packet4i x2_int = __builtin_msa_ftrunc_s_w(x2);
|
152
|
+
Packet4f x2_int_f = __builtin_msa_ffint_s_w(x2_int);
|
153
|
+
|
154
|
+
x = __builtin_msa_fmsub_w(x, x2_int_f, p4f_cephes_exp_C1);
|
155
|
+
x = __builtin_msa_fmsub_w(x, x2_int_f, p4f_cephes_exp_C2);
|
156
|
+
|
157
|
+
Packet4f z = pmul(x, x);
|
158
|
+
|
159
|
+
Packet4f y = p4f_cephes_exp_p0;
|
160
|
+
y = pmadd(y, x, p4f_cephes_exp_p1);
|
161
|
+
y = pmadd(y, x, p4f_cephes_exp_p2);
|
162
|
+
y = pmadd(y, x, p4f_cephes_exp_p3);
|
163
|
+
y = pmadd(y, x, p4f_cephes_exp_p4);
|
164
|
+
y = pmadd(y, x, p4f_cephes_exp_p5);
|
165
|
+
y = pmadd(y, z, x);
|
166
|
+
y = padd(y, p4f_1);
|
167
|
+
|
168
|
+
// y *= 2**exponent.
|
169
|
+
y = __builtin_msa_fexp2_w(y, x2_int);
|
170
|
+
|
171
|
+
return y;
|
172
|
+
}
|
173
|
+
|
174
|
+
template <>
|
175
|
+
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS EIGEN_UNUSED Packet4f
|
176
|
+
ptanh<Packet4f>(const Packet4f& _x) {
|
177
|
+
static _EIGEN_DECLARE_CONST_Packet4f(tanh_tiny, 1e-4f);
|
178
|
+
static _EIGEN_DECLARE_CONST_Packet4f(tanh_hi, 9.0f);
|
179
|
+
// The monomial coefficients of the numerator polynomial (odd).
|
180
|
+
static _EIGEN_DECLARE_CONST_Packet4f(alpha_1, 4.89352455891786e-3f);
|
181
|
+
static _EIGEN_DECLARE_CONST_Packet4f(alpha_3, 6.37261928875436e-4f);
|
182
|
+
static _EIGEN_DECLARE_CONST_Packet4f(alpha_5, 1.48572235717979e-5f);
|
183
|
+
static _EIGEN_DECLARE_CONST_Packet4f(alpha_7, 5.12229709037114e-8f);
|
184
|
+
static _EIGEN_DECLARE_CONST_Packet4f(alpha_9, -8.60467152213735e-11f);
|
185
|
+
static _EIGEN_DECLARE_CONST_Packet4f(alpha_11, 2.00018790482477e-13f);
|
186
|
+
static _EIGEN_DECLARE_CONST_Packet4f(alpha_13, -2.76076847742355e-16f);
|
187
|
+
// The monomial coefficients of the denominator polynomial (even).
|
188
|
+
static _EIGEN_DECLARE_CONST_Packet4f(beta_0, 4.89352518554385e-3f);
|
189
|
+
static _EIGEN_DECLARE_CONST_Packet4f(beta_2, 2.26843463243900e-3f);
|
190
|
+
static _EIGEN_DECLARE_CONST_Packet4f(beta_4, 1.18534705686654e-4f);
|
191
|
+
static _EIGEN_DECLARE_CONST_Packet4f(beta_6, 1.19825839466702e-6f);
|
192
|
+
|
193
|
+
Packet4f x = pabs(_x);
|
194
|
+
Packet4i tiny_mask = __builtin_msa_fclt_w(x, p4f_tanh_tiny);
|
195
|
+
|
196
|
+
// Clamp the inputs to the range [-9, 9] since anything outside
|
197
|
+
// this range is -/+1.0f in single-precision.
|
198
|
+
x = (Packet4f)__builtin_msa_bsel_v((v16u8)__builtin_msa_fclt_w(p4f_tanh_hi, x), (v16u8)x,
|
199
|
+
(v16u8)p4f_tanh_hi);
|
200
|
+
|
201
|
+
// Since the polynomials are odd/even, we need x**2.
|
202
|
+
Packet4f x2 = pmul(x, x);
|
203
|
+
|
204
|
+
// Evaluate the numerator polynomial p.
|
205
|
+
Packet4f p = pmadd(x2, p4f_alpha_13, p4f_alpha_11);
|
206
|
+
p = pmadd(x2, p, p4f_alpha_9);
|
207
|
+
p = pmadd(x2, p, p4f_alpha_7);
|
208
|
+
p = pmadd(x2, p, p4f_alpha_5);
|
209
|
+
p = pmadd(x2, p, p4f_alpha_3);
|
210
|
+
p = pmadd(x2, p, p4f_alpha_1);
|
211
|
+
p = pmul(x, p);
|
212
|
+
|
213
|
+
// Evaluate the denominator polynomial q.
|
214
|
+
Packet4f q = pmadd(x2, p4f_beta_6, p4f_beta_4);
|
215
|
+
q = pmadd(x2, q, p4f_beta_2);
|
216
|
+
q = pmadd(x2, q, p4f_beta_0);
|
217
|
+
|
218
|
+
// Divide the numerator by the denominator.
|
219
|
+
p = pdiv(p, q);
|
220
|
+
|
221
|
+
// Reinstate the sign.
|
222
|
+
p = (Packet4f)__builtin_msa_binsli_w((v4u32)p, (v4u32)_x, 0);
|
223
|
+
|
224
|
+
// When the argument is very small in magnitude it's more accurate to just return it.
|
225
|
+
p = (Packet4f)__builtin_msa_bsel_v((v16u8)tiny_mask, (v16u8)p, (v16u8)_x);
|
226
|
+
|
227
|
+
return p;
|
228
|
+
}
|
229
|
+
|
230
|
+
template <bool sine>
|
231
|
+
Packet4f psincos_inner_msa_float(const Packet4f& _x) {
|
232
|
+
static _EIGEN_DECLARE_CONST_Packet4f(sincos_max_arg, 13176795.0f); // Approx. (2**24) / (4/Pi).
|
233
|
+
static _EIGEN_DECLARE_CONST_Packet4f(minus_cephes_DP1, -0.78515625f);
|
234
|
+
static _EIGEN_DECLARE_CONST_Packet4f(minus_cephes_DP2, -2.4187564849853515625e-4f);
|
235
|
+
static _EIGEN_DECLARE_CONST_Packet4f(minus_cephes_DP3, -3.77489497744594108e-8f);
|
236
|
+
static _EIGEN_DECLARE_CONST_Packet4f(sincof_p0, -1.9515295891e-4f);
|
237
|
+
static _EIGEN_DECLARE_CONST_Packet4f(sincof_p1, 8.3321608736e-3f);
|
238
|
+
static _EIGEN_DECLARE_CONST_Packet4f(sincof_p2, -1.6666654611e-1f);
|
239
|
+
static _EIGEN_DECLARE_CONST_Packet4f(coscof_p0, 2.443315711809948e-5f);
|
240
|
+
static _EIGEN_DECLARE_CONST_Packet4f(coscof_p1, -1.388731625493765e-3f);
|
241
|
+
static _EIGEN_DECLARE_CONST_Packet4f(coscof_p2, 4.166664568298827e-2f);
|
242
|
+
static _EIGEN_DECLARE_CONST_Packet4f(cephes_FOPI, 1.27323954473516f); // 4/Pi.
|
243
|
+
static _EIGEN_DECLARE_CONST_Packet4f(half, 0.5f);
|
244
|
+
static _EIGEN_DECLARE_CONST_Packet4f(1, 1.0f);
|
245
|
+
|
246
|
+
Packet4f x = pabs(_x);
|
247
|
+
|
248
|
+
// Translate infinite arguments into NANs.
|
249
|
+
Packet4f zero_or_nan_if_inf = psub(_x, _x);
|
250
|
+
x = padd(x, zero_or_nan_if_inf);
|
251
|
+
// Prevent sin/cos from generating values larger than 1.0 in magnitude
|
252
|
+
// for very large arguments by setting x to 0.0.
|
253
|
+
Packet4i small_or_nan_mask = __builtin_msa_fcult_w(x, p4f_sincos_max_arg);
|
254
|
+
x = pand(x, (Packet4f)small_or_nan_mask);
|
255
|
+
|
256
|
+
// Scale x by 4/Pi to find x's octant.
|
257
|
+
Packet4f y = pmul(x, p4f_cephes_FOPI);
|
258
|
+
// Get the octant. We'll reduce x by this number of octants or by one more than it.
|
259
|
+
Packet4i y_int = __builtin_msa_ftrunc_s_w(y);
|
260
|
+
// x's from even-numbered octants will translate to octant 0: [0, +Pi/4].
|
261
|
+
// x's from odd-numbered octants will translate to octant -1: [-Pi/4, 0].
|
262
|
+
// Adjustment for odd-numbered octants: octant = (octant + 1) & (~1).
|
263
|
+
Packet4i y_int1 = __builtin_msa_addvi_w(y_int, 1);
|
264
|
+
Packet4i y_int2 = (Packet4i)__builtin_msa_bclri_w((Packet4ui)y_int1, 0); // bclri = bit-clear
|
265
|
+
y = __builtin_msa_ffint_s_w(y_int2);
|
266
|
+
|
267
|
+
// Compute the sign to apply to the polynomial.
|
268
|
+
Packet4i sign_mask = sine ? pxor(__builtin_msa_slli_w(y_int1, 29), (Packet4i)_x)
|
269
|
+
: __builtin_msa_slli_w(__builtin_msa_addvi_w(y_int, 3), 29);
|
270
|
+
|
271
|
+
// Get the polynomial selection mask.
|
272
|
+
// We'll calculate both (sin and cos) polynomials and then select from the two.
|
273
|
+
Packet4i poly_mask = __builtin_msa_ceqi_w(__builtin_msa_slli_w(y_int2, 30), 0);
|
274
|
+
|
275
|
+
// Reduce x by y octants to get: -Pi/4 <= x <= +Pi/4.
|
276
|
+
// The magic pass: "Extended precision modular arithmetic"
|
277
|
+
// x = ((x - y * DP1) - y * DP2) - y * DP3
|
278
|
+
Packet4f tmp1 = pmul(y, p4f_minus_cephes_DP1);
|
279
|
+
Packet4f tmp2 = pmul(y, p4f_minus_cephes_DP2);
|
280
|
+
Packet4f tmp3 = pmul(y, p4f_minus_cephes_DP3);
|
281
|
+
x = padd(x, tmp1);
|
282
|
+
x = padd(x, tmp2);
|
283
|
+
x = padd(x, tmp3);
|
284
|
+
|
285
|
+
// Evaluate the cos(x) polynomial.
|
286
|
+
y = p4f_coscof_p0;
|
287
|
+
Packet4f z = pmul(x, x);
|
288
|
+
y = pmadd(y, z, p4f_coscof_p1);
|
289
|
+
y = pmadd(y, z, p4f_coscof_p2);
|
290
|
+
y = pmul(y, z);
|
291
|
+
y = pmul(y, z);
|
292
|
+
y = __builtin_msa_fmsub_w(y, z, p4f_half);
|
293
|
+
y = padd(y, p4f_1);
|
294
|
+
|
295
|
+
// Evaluate the sin(x) polynomial.
|
296
|
+
Packet4f y2 = p4f_sincof_p0;
|
297
|
+
y2 = pmadd(y2, z, p4f_sincof_p1);
|
298
|
+
y2 = pmadd(y2, z, p4f_sincof_p2);
|
299
|
+
y2 = pmul(y2, z);
|
300
|
+
y2 = pmadd(y2, x, x);
|
301
|
+
|
302
|
+
// Select the correct result from the two polynomials.
|
303
|
+
y = sine ? (Packet4f)__builtin_msa_bsel_v((v16u8)poly_mask, (v16u8)y, (v16u8)y2)
|
304
|
+
: (Packet4f)__builtin_msa_bsel_v((v16u8)poly_mask, (v16u8)y2, (v16u8)y);
|
305
|
+
|
306
|
+
// Update the sign.
|
307
|
+
sign_mask = pxor(sign_mask, (Packet4i)y);
|
308
|
+
y = (Packet4f)__builtin_msa_binsli_w((v4u32)y, (v4u32)sign_mask, 0); // binsli = bit-insert-left
|
309
|
+
return y;
|
310
|
+
}
|
311
|
+
|
312
|
+
template <>
|
313
|
+
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS EIGEN_UNUSED Packet4f
|
314
|
+
psin<Packet4f>(const Packet4f& x) {
|
315
|
+
return psincos_inner_msa_float</* sine */ true>(x);
|
316
|
+
}
|
317
|
+
|
318
|
+
template <>
|
319
|
+
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS EIGEN_UNUSED Packet4f
|
320
|
+
pcos<Packet4f>(const Packet4f& x) {
|
321
|
+
return psincos_inner_msa_float</* sine */ false>(x);
|
322
|
+
}
|
323
|
+
|
324
|
+
template <>
|
325
|
+
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS EIGEN_UNUSED Packet2d
|
326
|
+
pexp<Packet2d>(const Packet2d& _x) {
|
327
|
+
// Limiting double-precision pexp's argument to [-1024, +1024] lets pexp
|
328
|
+
// reach 0 and INFINITY naturally.
|
329
|
+
static _EIGEN_DECLARE_CONST_Packet2d(exp_lo, -1024.0);
|
330
|
+
static _EIGEN_DECLARE_CONST_Packet2d(exp_hi, +1024.0);
|
331
|
+
static _EIGEN_DECLARE_CONST_Packet2d(cephes_LOG2EF, 1.4426950408889634073599);
|
332
|
+
static _EIGEN_DECLARE_CONST_Packet2d(cephes_exp_C1, 0.693145751953125);
|
333
|
+
static _EIGEN_DECLARE_CONST_Packet2d(cephes_exp_C2, 1.42860682030941723212e-6);
|
334
|
+
static _EIGEN_DECLARE_CONST_Packet2d(cephes_exp_p0, 1.26177193074810590878e-4);
|
335
|
+
static _EIGEN_DECLARE_CONST_Packet2d(cephes_exp_p1, 3.02994407707441961300e-2);
|
336
|
+
static _EIGEN_DECLARE_CONST_Packet2d(cephes_exp_p2, 9.99999999999999999910e-1);
|
337
|
+
static _EIGEN_DECLARE_CONST_Packet2d(cephes_exp_q0, 3.00198505138664455042e-6);
|
338
|
+
static _EIGEN_DECLARE_CONST_Packet2d(cephes_exp_q1, 2.52448340349684104192e-3);
|
339
|
+
static _EIGEN_DECLARE_CONST_Packet2d(cephes_exp_q2, 2.27265548208155028766e-1);
|
340
|
+
static _EIGEN_DECLARE_CONST_Packet2d(cephes_exp_q3, 2.00000000000000000009e0);
|
341
|
+
static _EIGEN_DECLARE_CONST_Packet2d(half, 0.5);
|
342
|
+
static _EIGEN_DECLARE_CONST_Packet2d(1, 1.0);
|
343
|
+
static _EIGEN_DECLARE_CONST_Packet2d(2, 2.0);
|
344
|
+
|
345
|
+
Packet2d x = _x;
|
346
|
+
|
347
|
+
// Clamp x.
|
348
|
+
x = (Packet2d)__builtin_msa_bsel_v((v16u8)__builtin_msa_fclt_d(x, p2d_exp_lo), (v16u8)x,
|
349
|
+
(v16u8)p2d_exp_lo);
|
350
|
+
x = (Packet2d)__builtin_msa_bsel_v((v16u8)__builtin_msa_fclt_d(p2d_exp_hi, x), (v16u8)x,
|
351
|
+
(v16u8)p2d_exp_hi);
|
352
|
+
|
353
|
+
// Round to nearest integer by adding 0.5 (with x's sign) and truncating.
|
354
|
+
Packet2d x2_add = (Packet2d)__builtin_msa_binsli_d((v2u64)p2d_half, (v2u64)x, 0);
|
355
|
+
Packet2d x2 = pmadd(x, p2d_cephes_LOG2EF, x2_add);
|
356
|
+
Packet2l x2_long = __builtin_msa_ftrunc_s_d(x2);
|
357
|
+
Packet2d x2_long_d = __builtin_msa_ffint_s_d(x2_long);
|
358
|
+
|
359
|
+
x = __builtin_msa_fmsub_d(x, x2_long_d, p2d_cephes_exp_C1);
|
360
|
+
x = __builtin_msa_fmsub_d(x, x2_long_d, p2d_cephes_exp_C2);
|
361
|
+
|
362
|
+
x2 = pmul(x, x);
|
363
|
+
|
364
|
+
Packet2d px = p2d_cephes_exp_p0;
|
365
|
+
px = pmadd(px, x2, p2d_cephes_exp_p1);
|
366
|
+
px = pmadd(px, x2, p2d_cephes_exp_p2);
|
367
|
+
px = pmul(px, x);
|
368
|
+
|
369
|
+
Packet2d qx = p2d_cephes_exp_q0;
|
370
|
+
qx = pmadd(qx, x2, p2d_cephes_exp_q1);
|
371
|
+
qx = pmadd(qx, x2, p2d_cephes_exp_q2);
|
372
|
+
qx = pmadd(qx, x2, p2d_cephes_exp_q3);
|
373
|
+
|
374
|
+
x = pdiv(px, psub(qx, px));
|
375
|
+
x = pmadd(p2d_2, x, p2d_1);
|
376
|
+
|
377
|
+
// x *= 2**exponent.
|
378
|
+
x = __builtin_msa_fexp2_d(x, x2_long);
|
379
|
+
|
380
|
+
return x;
|
381
|
+
}
|
382
|
+
|
383
|
+
} // end namespace internal
|
384
|
+
|
385
|
+
} // end namespace Eigen
|
386
|
+
|
387
|
+
#endif // EIGEN_MATH_FUNCTIONS_MSA_H
|