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 +1,317 @@
|
|
1
|
+
// This file is part of Eigen, a lightweight C++ template library
|
2
|
+
// for linear algebra.
|
3
|
+
//
|
4
|
+
// Copyright (C) 2009-2010 Gael Guennebaud <gael.guennebaud@inria.fr>
|
5
|
+
//
|
6
|
+
// This Source Code Form is subject to the terms of the Mozilla
|
7
|
+
// Public License v. 2.0. If a copy of the MPL was not distributed
|
8
|
+
// with this file, You can obtain one at http://mozilla.org/MPL/2.0/.
|
9
|
+
|
10
|
+
#ifndef EIGEN_GENERAL_MATRIX_MATRIX_TRIANGULAR_H
|
11
|
+
#define EIGEN_GENERAL_MATRIX_MATRIX_TRIANGULAR_H
|
12
|
+
|
13
|
+
namespace Eigen {
|
14
|
+
|
15
|
+
template<typename Scalar, typename Index, int StorageOrder, int UpLo, bool ConjLhs, bool ConjRhs>
|
16
|
+
struct selfadjoint_rank1_update;
|
17
|
+
|
18
|
+
namespace internal {
|
19
|
+
|
20
|
+
/**********************************************************************
|
21
|
+
* This file implements a general A * B product while
|
22
|
+
* evaluating only one triangular part of the product.
|
23
|
+
* This is a more general version of self adjoint product (C += A A^T)
|
24
|
+
* as the level 3 SYRK Blas routine.
|
25
|
+
**********************************************************************/
|
26
|
+
|
27
|
+
// forward declarations (defined at the end of this file)
|
28
|
+
template<typename LhsScalar, typename RhsScalar, typename Index, int mr, int nr, bool ConjLhs, bool ConjRhs, int ResInnerStride, int UpLo>
|
29
|
+
struct tribb_kernel;
|
30
|
+
|
31
|
+
/* Optimized matrix-matrix product evaluating only one triangular half */
|
32
|
+
template <typename Index,
|
33
|
+
typename LhsScalar, int LhsStorageOrder, bool ConjugateLhs,
|
34
|
+
typename RhsScalar, int RhsStorageOrder, bool ConjugateRhs,
|
35
|
+
int ResStorageOrder, int ResInnerStride, int UpLo, int Version = Specialized>
|
36
|
+
struct general_matrix_matrix_triangular_product;
|
37
|
+
|
38
|
+
// as usual if the result is row major => we transpose the product
|
39
|
+
template <typename Index, typename LhsScalar, int LhsStorageOrder, bool ConjugateLhs,
|
40
|
+
typename RhsScalar, int RhsStorageOrder, bool ConjugateRhs,
|
41
|
+
int ResInnerStride, int UpLo, int Version>
|
42
|
+
struct general_matrix_matrix_triangular_product<Index,LhsScalar,LhsStorageOrder,ConjugateLhs,RhsScalar,RhsStorageOrder,ConjugateRhs,RowMajor,ResInnerStride,UpLo,Version>
|
43
|
+
{
|
44
|
+
typedef typename ScalarBinaryOpTraits<LhsScalar, RhsScalar>::ReturnType ResScalar;
|
45
|
+
static EIGEN_STRONG_INLINE void run(Index size, Index depth,const LhsScalar* lhs, Index lhsStride,
|
46
|
+
const RhsScalar* rhs, Index rhsStride, ResScalar* res, Index resIncr, Index resStride,
|
47
|
+
const ResScalar& alpha, level3_blocking<RhsScalar,LhsScalar>& blocking)
|
48
|
+
{
|
49
|
+
general_matrix_matrix_triangular_product<Index,
|
50
|
+
RhsScalar, RhsStorageOrder==RowMajor ? ColMajor : RowMajor, ConjugateRhs,
|
51
|
+
LhsScalar, LhsStorageOrder==RowMajor ? ColMajor : RowMajor, ConjugateLhs,
|
52
|
+
ColMajor, ResInnerStride, UpLo==Lower?Upper:Lower>
|
53
|
+
::run(size,depth,rhs,rhsStride,lhs,lhsStride,res,resIncr,resStride,alpha,blocking);
|
54
|
+
}
|
55
|
+
};
|
56
|
+
|
57
|
+
template <typename Index, typename LhsScalar, int LhsStorageOrder, bool ConjugateLhs,
|
58
|
+
typename RhsScalar, int RhsStorageOrder, bool ConjugateRhs,
|
59
|
+
int ResInnerStride, int UpLo, int Version>
|
60
|
+
struct general_matrix_matrix_triangular_product<Index,LhsScalar,LhsStorageOrder,ConjugateLhs,RhsScalar,RhsStorageOrder,ConjugateRhs,ColMajor,ResInnerStride,UpLo,Version>
|
61
|
+
{
|
62
|
+
typedef typename ScalarBinaryOpTraits<LhsScalar, RhsScalar>::ReturnType ResScalar;
|
63
|
+
static EIGEN_STRONG_INLINE void run(Index size, Index depth,const LhsScalar* _lhs, Index lhsStride,
|
64
|
+
const RhsScalar* _rhs, Index rhsStride,
|
65
|
+
ResScalar* _res, Index resIncr, Index resStride,
|
66
|
+
const ResScalar& alpha, level3_blocking<LhsScalar,RhsScalar>& blocking)
|
67
|
+
{
|
68
|
+
typedef gebp_traits<LhsScalar,RhsScalar> Traits;
|
69
|
+
|
70
|
+
typedef const_blas_data_mapper<LhsScalar, Index, LhsStorageOrder> LhsMapper;
|
71
|
+
typedef const_blas_data_mapper<RhsScalar, Index, RhsStorageOrder> RhsMapper;
|
72
|
+
typedef blas_data_mapper<typename Traits::ResScalar, Index, ColMajor, Unaligned, ResInnerStride> ResMapper;
|
73
|
+
LhsMapper lhs(_lhs,lhsStride);
|
74
|
+
RhsMapper rhs(_rhs,rhsStride);
|
75
|
+
ResMapper res(_res, resStride, resIncr);
|
76
|
+
|
77
|
+
Index kc = blocking.kc();
|
78
|
+
Index mc = (std::min)(size,blocking.mc());
|
79
|
+
|
80
|
+
// !!! mc must be a multiple of nr:
|
81
|
+
if(mc > Traits::nr)
|
82
|
+
mc = (mc/Traits::nr)*Traits::nr;
|
83
|
+
|
84
|
+
std::size_t sizeA = kc*mc;
|
85
|
+
std::size_t sizeB = kc*size;
|
86
|
+
|
87
|
+
ei_declare_aligned_stack_constructed_variable(LhsScalar, blockA, sizeA, blocking.blockA());
|
88
|
+
ei_declare_aligned_stack_constructed_variable(RhsScalar, blockB, sizeB, blocking.blockB());
|
89
|
+
|
90
|
+
gemm_pack_lhs<LhsScalar, Index, LhsMapper, Traits::mr, Traits::LhsProgress, typename Traits::LhsPacket4Packing, LhsStorageOrder> pack_lhs;
|
91
|
+
gemm_pack_rhs<RhsScalar, Index, RhsMapper, Traits::nr, RhsStorageOrder> pack_rhs;
|
92
|
+
gebp_kernel<LhsScalar, RhsScalar, Index, ResMapper, Traits::mr, Traits::nr, ConjugateLhs, ConjugateRhs> gebp;
|
93
|
+
tribb_kernel<LhsScalar, RhsScalar, Index, Traits::mr, Traits::nr, ConjugateLhs, ConjugateRhs, ResInnerStride, UpLo> sybb;
|
94
|
+
|
95
|
+
for(Index k2=0; k2<depth; k2+=kc)
|
96
|
+
{
|
97
|
+
const Index actual_kc = (std::min)(k2+kc,depth)-k2;
|
98
|
+
|
99
|
+
// note that the actual rhs is the transpose/adjoint of mat
|
100
|
+
pack_rhs(blockB, rhs.getSubMapper(k2,0), actual_kc, size);
|
101
|
+
|
102
|
+
for(Index i2=0; i2<size; i2+=mc)
|
103
|
+
{
|
104
|
+
const Index actual_mc = (std::min)(i2+mc,size)-i2;
|
105
|
+
|
106
|
+
pack_lhs(blockA, lhs.getSubMapper(i2, k2), actual_kc, actual_mc);
|
107
|
+
|
108
|
+
// the selected actual_mc * size panel of res is split into three different part:
|
109
|
+
// 1 - before the diagonal => processed with gebp or skipped
|
110
|
+
// 2 - the actual_mc x actual_mc symmetric block => processed with a special kernel
|
111
|
+
// 3 - after the diagonal => processed with gebp or skipped
|
112
|
+
if (UpLo==Lower)
|
113
|
+
gebp(res.getSubMapper(i2, 0), blockA, blockB, actual_mc, actual_kc,
|
114
|
+
(std::min)(size,i2), alpha, -1, -1, 0, 0);
|
115
|
+
|
116
|
+
sybb(_res+resStride*i2 + resIncr*i2, resIncr, resStride, blockA, blockB + actual_kc*i2, actual_mc, actual_kc, alpha);
|
117
|
+
|
118
|
+
if (UpLo==Upper)
|
119
|
+
{
|
120
|
+
Index j2 = i2+actual_mc;
|
121
|
+
gebp(res.getSubMapper(i2, j2), blockA, blockB+actual_kc*j2, actual_mc,
|
122
|
+
actual_kc, (std::max)(Index(0), size-j2), alpha, -1, -1, 0, 0);
|
123
|
+
}
|
124
|
+
}
|
125
|
+
}
|
126
|
+
}
|
127
|
+
};
|
128
|
+
|
129
|
+
// Optimized packed Block * packed Block product kernel evaluating only one given triangular part
|
130
|
+
// This kernel is built on top of the gebp kernel:
|
131
|
+
// - the current destination block is processed per panel of actual_mc x BlockSize
|
132
|
+
// where BlockSize is set to the minimal value allowing gebp to be as fast as possible
|
133
|
+
// - then, as usual, each panel is split into three parts along the diagonal,
|
134
|
+
// the sub blocks above and below the diagonal are processed as usual,
|
135
|
+
// while the triangular block overlapping the diagonal is evaluated into a
|
136
|
+
// small temporary buffer which is then accumulated into the result using a
|
137
|
+
// triangular traversal.
|
138
|
+
template<typename LhsScalar, typename RhsScalar, typename Index, int mr, int nr, bool ConjLhs, bool ConjRhs, int ResInnerStride, int UpLo>
|
139
|
+
struct tribb_kernel
|
140
|
+
{
|
141
|
+
typedef gebp_traits<LhsScalar,RhsScalar,ConjLhs,ConjRhs> Traits;
|
142
|
+
typedef typename Traits::ResScalar ResScalar;
|
143
|
+
|
144
|
+
enum {
|
145
|
+
BlockSize = meta_least_common_multiple<EIGEN_PLAIN_ENUM_MAX(mr,nr),EIGEN_PLAIN_ENUM_MIN(mr,nr)>::ret
|
146
|
+
};
|
147
|
+
void operator()(ResScalar* _res, Index resIncr, Index resStride, const LhsScalar* blockA, const RhsScalar* blockB, Index size, Index depth, const ResScalar& alpha)
|
148
|
+
{
|
149
|
+
typedef blas_data_mapper<ResScalar, Index, ColMajor, Unaligned, ResInnerStride> ResMapper;
|
150
|
+
typedef blas_data_mapper<ResScalar, Index, ColMajor, Unaligned> BufferMapper;
|
151
|
+
ResMapper res(_res, resStride, resIncr);
|
152
|
+
gebp_kernel<LhsScalar, RhsScalar, Index, ResMapper, mr, nr, ConjLhs, ConjRhs> gebp_kernel1;
|
153
|
+
gebp_kernel<LhsScalar, RhsScalar, Index, BufferMapper, mr, nr, ConjLhs, ConjRhs> gebp_kernel2;
|
154
|
+
|
155
|
+
Matrix<ResScalar,BlockSize,BlockSize,ColMajor> buffer((internal::constructor_without_unaligned_array_assert()));
|
156
|
+
|
157
|
+
// let's process the block per panel of actual_mc x BlockSize,
|
158
|
+
// again, each is split into three parts, etc.
|
159
|
+
for (Index j=0; j<size; j+=BlockSize)
|
160
|
+
{
|
161
|
+
Index actualBlockSize = std::min<Index>(BlockSize,size - j);
|
162
|
+
const RhsScalar* actual_b = blockB+j*depth;
|
163
|
+
|
164
|
+
if(UpLo==Upper)
|
165
|
+
gebp_kernel1(res.getSubMapper(0, j), blockA, actual_b, j, depth, actualBlockSize, alpha,
|
166
|
+
-1, -1, 0, 0);
|
167
|
+
|
168
|
+
// selfadjoint micro block
|
169
|
+
{
|
170
|
+
Index i = j;
|
171
|
+
buffer.setZero();
|
172
|
+
// 1 - apply the kernel on the temporary buffer
|
173
|
+
gebp_kernel2(BufferMapper(buffer.data(), BlockSize), blockA+depth*i, actual_b, actualBlockSize, depth, actualBlockSize, alpha,
|
174
|
+
-1, -1, 0, 0);
|
175
|
+
|
176
|
+
// 2 - triangular accumulation
|
177
|
+
for(Index j1=0; j1<actualBlockSize; ++j1)
|
178
|
+
{
|
179
|
+
typename ResMapper::LinearMapper r = res.getLinearMapper(i,j+j1);
|
180
|
+
for(Index i1=UpLo==Lower ? j1 : 0;
|
181
|
+
UpLo==Lower ? i1<actualBlockSize : i1<=j1; ++i1)
|
182
|
+
r(i1) += buffer(i1,j1);
|
183
|
+
}
|
184
|
+
}
|
185
|
+
|
186
|
+
if(UpLo==Lower)
|
187
|
+
{
|
188
|
+
Index i = j+actualBlockSize;
|
189
|
+
gebp_kernel1(res.getSubMapper(i, j), blockA+depth*i, actual_b, size-i,
|
190
|
+
depth, actualBlockSize, alpha, -1, -1, 0, 0);
|
191
|
+
}
|
192
|
+
}
|
193
|
+
}
|
194
|
+
};
|
195
|
+
|
196
|
+
} // end namespace internal
|
197
|
+
|
198
|
+
// high level API
|
199
|
+
|
200
|
+
template<typename MatrixType, typename ProductType, int UpLo, bool IsOuterProduct>
|
201
|
+
struct general_product_to_triangular_selector;
|
202
|
+
|
203
|
+
|
204
|
+
template<typename MatrixType, typename ProductType, int UpLo>
|
205
|
+
struct general_product_to_triangular_selector<MatrixType,ProductType,UpLo,true>
|
206
|
+
{
|
207
|
+
static void run(MatrixType& mat, const ProductType& prod, const typename MatrixType::Scalar& alpha, bool beta)
|
208
|
+
{
|
209
|
+
typedef typename MatrixType::Scalar Scalar;
|
210
|
+
|
211
|
+
typedef typename internal::remove_all<typename ProductType::LhsNested>::type Lhs;
|
212
|
+
typedef internal::blas_traits<Lhs> LhsBlasTraits;
|
213
|
+
typedef typename LhsBlasTraits::DirectLinearAccessType ActualLhs;
|
214
|
+
typedef typename internal::remove_all<ActualLhs>::type _ActualLhs;
|
215
|
+
typename internal::add_const_on_value_type<ActualLhs>::type actualLhs = LhsBlasTraits::extract(prod.lhs());
|
216
|
+
|
217
|
+
typedef typename internal::remove_all<typename ProductType::RhsNested>::type Rhs;
|
218
|
+
typedef internal::blas_traits<Rhs> RhsBlasTraits;
|
219
|
+
typedef typename RhsBlasTraits::DirectLinearAccessType ActualRhs;
|
220
|
+
typedef typename internal::remove_all<ActualRhs>::type _ActualRhs;
|
221
|
+
typename internal::add_const_on_value_type<ActualRhs>::type actualRhs = RhsBlasTraits::extract(prod.rhs());
|
222
|
+
|
223
|
+
Scalar actualAlpha = alpha * LhsBlasTraits::extractScalarFactor(prod.lhs().derived()) * RhsBlasTraits::extractScalarFactor(prod.rhs().derived());
|
224
|
+
|
225
|
+
if(!beta)
|
226
|
+
mat.template triangularView<UpLo>().setZero();
|
227
|
+
|
228
|
+
enum {
|
229
|
+
StorageOrder = (internal::traits<MatrixType>::Flags&RowMajorBit) ? RowMajor : ColMajor,
|
230
|
+
UseLhsDirectly = _ActualLhs::InnerStrideAtCompileTime==1,
|
231
|
+
UseRhsDirectly = _ActualRhs::InnerStrideAtCompileTime==1
|
232
|
+
};
|
233
|
+
|
234
|
+
internal::gemv_static_vector_if<Scalar,Lhs::SizeAtCompileTime,Lhs::MaxSizeAtCompileTime,!UseLhsDirectly> static_lhs;
|
235
|
+
ei_declare_aligned_stack_constructed_variable(Scalar, actualLhsPtr, actualLhs.size(),
|
236
|
+
(UseLhsDirectly ? const_cast<Scalar*>(actualLhs.data()) : static_lhs.data()));
|
237
|
+
if(!UseLhsDirectly) Map<typename _ActualLhs::PlainObject>(actualLhsPtr, actualLhs.size()) = actualLhs;
|
238
|
+
|
239
|
+
internal::gemv_static_vector_if<Scalar,Rhs::SizeAtCompileTime,Rhs::MaxSizeAtCompileTime,!UseRhsDirectly> static_rhs;
|
240
|
+
ei_declare_aligned_stack_constructed_variable(Scalar, actualRhsPtr, actualRhs.size(),
|
241
|
+
(UseRhsDirectly ? const_cast<Scalar*>(actualRhs.data()) : static_rhs.data()));
|
242
|
+
if(!UseRhsDirectly) Map<typename _ActualRhs::PlainObject>(actualRhsPtr, actualRhs.size()) = actualRhs;
|
243
|
+
|
244
|
+
|
245
|
+
selfadjoint_rank1_update<Scalar,Index,StorageOrder,UpLo,
|
246
|
+
LhsBlasTraits::NeedToConjugate && NumTraits<Scalar>::IsComplex,
|
247
|
+
RhsBlasTraits::NeedToConjugate && NumTraits<Scalar>::IsComplex>
|
248
|
+
::run(actualLhs.size(), mat.data(), mat.outerStride(), actualLhsPtr, actualRhsPtr, actualAlpha);
|
249
|
+
}
|
250
|
+
};
|
251
|
+
|
252
|
+
template<typename MatrixType, typename ProductType, int UpLo>
|
253
|
+
struct general_product_to_triangular_selector<MatrixType,ProductType,UpLo,false>
|
254
|
+
{
|
255
|
+
static void run(MatrixType& mat, const ProductType& prod, const typename MatrixType::Scalar& alpha, bool beta)
|
256
|
+
{
|
257
|
+
typedef typename internal::remove_all<typename ProductType::LhsNested>::type Lhs;
|
258
|
+
typedef internal::blas_traits<Lhs> LhsBlasTraits;
|
259
|
+
typedef typename LhsBlasTraits::DirectLinearAccessType ActualLhs;
|
260
|
+
typedef typename internal::remove_all<ActualLhs>::type _ActualLhs;
|
261
|
+
typename internal::add_const_on_value_type<ActualLhs>::type actualLhs = LhsBlasTraits::extract(prod.lhs());
|
262
|
+
|
263
|
+
typedef typename internal::remove_all<typename ProductType::RhsNested>::type Rhs;
|
264
|
+
typedef internal::blas_traits<Rhs> RhsBlasTraits;
|
265
|
+
typedef typename RhsBlasTraits::DirectLinearAccessType ActualRhs;
|
266
|
+
typedef typename internal::remove_all<ActualRhs>::type _ActualRhs;
|
267
|
+
typename internal::add_const_on_value_type<ActualRhs>::type actualRhs = RhsBlasTraits::extract(prod.rhs());
|
268
|
+
|
269
|
+
typename ProductType::Scalar actualAlpha = alpha * LhsBlasTraits::extractScalarFactor(prod.lhs().derived()) * RhsBlasTraits::extractScalarFactor(prod.rhs().derived());
|
270
|
+
|
271
|
+
if(!beta)
|
272
|
+
mat.template triangularView<UpLo>().setZero();
|
273
|
+
|
274
|
+
enum {
|
275
|
+
IsRowMajor = (internal::traits<MatrixType>::Flags&RowMajorBit) ? 1 : 0,
|
276
|
+
LhsIsRowMajor = _ActualLhs::Flags&RowMajorBit ? 1 : 0,
|
277
|
+
RhsIsRowMajor = _ActualRhs::Flags&RowMajorBit ? 1 : 0,
|
278
|
+
SkipDiag = (UpLo&(UnitDiag|ZeroDiag))!=0
|
279
|
+
};
|
280
|
+
|
281
|
+
Index size = mat.cols();
|
282
|
+
if(SkipDiag)
|
283
|
+
size--;
|
284
|
+
Index depth = actualLhs.cols();
|
285
|
+
|
286
|
+
typedef internal::gemm_blocking_space<IsRowMajor ? RowMajor : ColMajor,typename Lhs::Scalar,typename Rhs::Scalar,
|
287
|
+
MatrixType::MaxColsAtCompileTime, MatrixType::MaxColsAtCompileTime, _ActualRhs::MaxColsAtCompileTime> BlockingType;
|
288
|
+
|
289
|
+
BlockingType blocking(size, size, depth, 1, false);
|
290
|
+
|
291
|
+
internal::general_matrix_matrix_triangular_product<Index,
|
292
|
+
typename Lhs::Scalar, LhsIsRowMajor ? RowMajor : ColMajor, LhsBlasTraits::NeedToConjugate,
|
293
|
+
typename Rhs::Scalar, RhsIsRowMajor ? RowMajor : ColMajor, RhsBlasTraits::NeedToConjugate,
|
294
|
+
IsRowMajor ? RowMajor : ColMajor, MatrixType::InnerStrideAtCompileTime, UpLo&(Lower|Upper)>
|
295
|
+
::run(size, depth,
|
296
|
+
&actualLhs.coeffRef(SkipDiag&&(UpLo&Lower)==Lower ? 1 : 0,0), actualLhs.outerStride(),
|
297
|
+
&actualRhs.coeffRef(0,SkipDiag&&(UpLo&Upper)==Upper ? 1 : 0), actualRhs.outerStride(),
|
298
|
+
mat.data() + (SkipDiag ? (bool(IsRowMajor) != ((UpLo&Lower)==Lower) ? mat.innerStride() : mat.outerStride() ) : 0),
|
299
|
+
mat.innerStride(), mat.outerStride(), actualAlpha, blocking);
|
300
|
+
}
|
301
|
+
};
|
302
|
+
|
303
|
+
template<typename MatrixType, unsigned int UpLo>
|
304
|
+
template<typename ProductType>
|
305
|
+
EIGEN_DEVICE_FUNC TriangularView<MatrixType,UpLo>& TriangularViewImpl<MatrixType,UpLo,Dense>::_assignProduct(const ProductType& prod, const Scalar& alpha, bool beta)
|
306
|
+
{
|
307
|
+
EIGEN_STATIC_ASSERT((UpLo&UnitDiag)==0, WRITING_TO_TRIANGULAR_PART_WITH_UNIT_DIAGONAL_IS_NOT_SUPPORTED);
|
308
|
+
eigen_assert(derived().nestedExpression().rows() == prod.rows() && derived().cols() == prod.cols());
|
309
|
+
|
310
|
+
general_product_to_triangular_selector<MatrixType, ProductType, UpLo, internal::traits<ProductType>::InnerSize==1>::run(derived().nestedExpression().const_cast_derived(), prod, alpha, beta);
|
311
|
+
|
312
|
+
return derived();
|
313
|
+
}
|
314
|
+
|
315
|
+
} // end namespace Eigen
|
316
|
+
|
317
|
+
#endif // EIGEN_GENERAL_MATRIX_MATRIX_TRIANGULAR_H
|
@@ -0,0 +1,145 @@
|
|
1
|
+
/*
|
2
|
+
Copyright (c) 2011, Intel Corporation. All rights reserved.
|
3
|
+
|
4
|
+
Redistribution and use in source and binary forms, with or without modification,
|
5
|
+
are permitted provided that the following conditions are met:
|
6
|
+
|
7
|
+
* Redistributions of source code must retain the above copyright notice, this
|
8
|
+
list of conditions and the following disclaimer.
|
9
|
+
* Redistributions in binary form must reproduce the above copyright notice,
|
10
|
+
this list of conditions and the following disclaimer in the documentation
|
11
|
+
and/or other materials provided with the distribution.
|
12
|
+
* Neither the name of Intel Corporation nor the names of its contributors may
|
13
|
+
be used to endorse or promote products derived from this software without
|
14
|
+
specific prior written permission.
|
15
|
+
|
16
|
+
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
17
|
+
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
18
|
+
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
19
|
+
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
|
20
|
+
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
|
21
|
+
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
22
|
+
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
|
23
|
+
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
24
|
+
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
25
|
+
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
26
|
+
|
27
|
+
********************************************************************************
|
28
|
+
* Content : Eigen bindings to BLAS F77
|
29
|
+
* Level 3 BLAS SYRK/HERK implementation.
|
30
|
+
********************************************************************************
|
31
|
+
*/
|
32
|
+
|
33
|
+
#ifndef EIGEN_GENERAL_MATRIX_MATRIX_TRIANGULAR_BLAS_H
|
34
|
+
#define EIGEN_GENERAL_MATRIX_MATRIX_TRIANGULAR_BLAS_H
|
35
|
+
|
36
|
+
namespace Eigen {
|
37
|
+
|
38
|
+
namespace internal {
|
39
|
+
|
40
|
+
template <typename Index, typename Scalar, int AStorageOrder, bool ConjugateA, int ResStorageOrder, int UpLo>
|
41
|
+
struct general_matrix_matrix_rankupdate :
|
42
|
+
general_matrix_matrix_triangular_product<
|
43
|
+
Index,Scalar,AStorageOrder,ConjugateA,Scalar,AStorageOrder,ConjugateA,ResStorageOrder,1,UpLo,BuiltIn> {};
|
44
|
+
|
45
|
+
|
46
|
+
// try to go to BLAS specialization
|
47
|
+
#define EIGEN_BLAS_RANKUPDATE_SPECIALIZE(Scalar) \
|
48
|
+
template <typename Index, int LhsStorageOrder, bool ConjugateLhs, \
|
49
|
+
int RhsStorageOrder, bool ConjugateRhs, int UpLo> \
|
50
|
+
struct general_matrix_matrix_triangular_product<Index,Scalar,LhsStorageOrder,ConjugateLhs, \
|
51
|
+
Scalar,RhsStorageOrder,ConjugateRhs,ColMajor,1,UpLo,Specialized> { \
|
52
|
+
static EIGEN_STRONG_INLINE void run(Index size, Index depth,const Scalar* lhs, Index lhsStride, \
|
53
|
+
const Scalar* rhs, Index rhsStride, Scalar* res, Index resIncr, Index resStride, Scalar alpha, level3_blocking<Scalar, Scalar>& blocking) \
|
54
|
+
{ \
|
55
|
+
if ( lhs==rhs && ((UpLo&(Lower|Upper))==UpLo) ) { \
|
56
|
+
general_matrix_matrix_rankupdate<Index,Scalar,LhsStorageOrder,ConjugateLhs,ColMajor,UpLo> \
|
57
|
+
::run(size,depth,lhs,lhsStride,rhs,rhsStride,res,resStride,alpha,blocking); \
|
58
|
+
} else { \
|
59
|
+
general_matrix_matrix_triangular_product<Index, \
|
60
|
+
Scalar, LhsStorageOrder, ConjugateLhs, \
|
61
|
+
Scalar, RhsStorageOrder, ConjugateRhs, \
|
62
|
+
ColMajor, 1, UpLo, BuiltIn> \
|
63
|
+
::run(size,depth,lhs,lhsStride,rhs,rhsStride,res,resIncr,resStride,alpha,blocking); \
|
64
|
+
} \
|
65
|
+
} \
|
66
|
+
};
|
67
|
+
|
68
|
+
EIGEN_BLAS_RANKUPDATE_SPECIALIZE(double)
|
69
|
+
EIGEN_BLAS_RANKUPDATE_SPECIALIZE(float)
|
70
|
+
// TODO handle complex cases
|
71
|
+
// EIGEN_BLAS_RANKUPDATE_SPECIALIZE(dcomplex)
|
72
|
+
// EIGEN_BLAS_RANKUPDATE_SPECIALIZE(scomplex)
|
73
|
+
|
74
|
+
// SYRK for float/double
|
75
|
+
#define EIGEN_BLAS_RANKUPDATE_R(EIGTYPE, BLASTYPE, BLASFUNC) \
|
76
|
+
template <typename Index, int AStorageOrder, bool ConjugateA, int UpLo> \
|
77
|
+
struct general_matrix_matrix_rankupdate<Index,EIGTYPE,AStorageOrder,ConjugateA,ColMajor,UpLo> { \
|
78
|
+
enum { \
|
79
|
+
IsLower = (UpLo&Lower) == Lower, \
|
80
|
+
LowUp = IsLower ? Lower : Upper, \
|
81
|
+
conjA = ((AStorageOrder==ColMajor) && ConjugateA) ? 1 : 0 \
|
82
|
+
}; \
|
83
|
+
static EIGEN_STRONG_INLINE void run(Index size, Index depth,const EIGTYPE* lhs, Index lhsStride, \
|
84
|
+
const EIGTYPE* /*rhs*/, Index /*rhsStride*/, EIGTYPE* res, Index resStride, EIGTYPE alpha, level3_blocking<EIGTYPE, EIGTYPE>& /*blocking*/) \
|
85
|
+
{ \
|
86
|
+
/* typedef Matrix<EIGTYPE, Dynamic, Dynamic, RhsStorageOrder> MatrixRhs;*/ \
|
87
|
+
\
|
88
|
+
BlasIndex lda=convert_index<BlasIndex>(lhsStride), ldc=convert_index<BlasIndex>(resStride), n=convert_index<BlasIndex>(size), k=convert_index<BlasIndex>(depth); \
|
89
|
+
char uplo=((IsLower) ? 'L' : 'U'), trans=((AStorageOrder==RowMajor) ? 'T':'N'); \
|
90
|
+
EIGTYPE beta(1); \
|
91
|
+
BLASFUNC(&uplo, &trans, &n, &k, (const BLASTYPE*)&numext::real_ref(alpha), lhs, &lda, (const BLASTYPE*)&numext::real_ref(beta), res, &ldc); \
|
92
|
+
} \
|
93
|
+
};
|
94
|
+
|
95
|
+
// HERK for complex data
|
96
|
+
#define EIGEN_BLAS_RANKUPDATE_C(EIGTYPE, BLASTYPE, RTYPE, BLASFUNC) \
|
97
|
+
template <typename Index, int AStorageOrder, bool ConjugateA, int UpLo> \
|
98
|
+
struct general_matrix_matrix_rankupdate<Index,EIGTYPE,AStorageOrder,ConjugateA,ColMajor,UpLo> { \
|
99
|
+
enum { \
|
100
|
+
IsLower = (UpLo&Lower) == Lower, \
|
101
|
+
LowUp = IsLower ? Lower : Upper, \
|
102
|
+
conjA = (((AStorageOrder==ColMajor) && ConjugateA) || ((AStorageOrder==RowMajor) && !ConjugateA)) ? 1 : 0 \
|
103
|
+
}; \
|
104
|
+
static EIGEN_STRONG_INLINE void run(Index size, Index depth,const EIGTYPE* lhs, Index lhsStride, \
|
105
|
+
const EIGTYPE* /*rhs*/, Index /*rhsStride*/, EIGTYPE* res, Index resStride, EIGTYPE alpha, level3_blocking<EIGTYPE, EIGTYPE>& /*blocking*/) \
|
106
|
+
{ \
|
107
|
+
typedef Matrix<EIGTYPE, Dynamic, Dynamic, AStorageOrder> MatrixType; \
|
108
|
+
\
|
109
|
+
BlasIndex lda=convert_index<BlasIndex>(lhsStride), ldc=convert_index<BlasIndex>(resStride), n=convert_index<BlasIndex>(size), k=convert_index<BlasIndex>(depth); \
|
110
|
+
char uplo=((IsLower) ? 'L' : 'U'), trans=((AStorageOrder==RowMajor) ? 'C':'N'); \
|
111
|
+
RTYPE alpha_, beta_; \
|
112
|
+
const EIGTYPE* a_ptr; \
|
113
|
+
\
|
114
|
+
alpha_ = alpha.real(); \
|
115
|
+
beta_ = 1.0; \
|
116
|
+
/* Copy with conjugation in some cases*/ \
|
117
|
+
MatrixType a; \
|
118
|
+
if (conjA) { \
|
119
|
+
Map<const MatrixType, 0, OuterStride<> > mapA(lhs,n,k,OuterStride<>(lhsStride)); \
|
120
|
+
a = mapA.conjugate(); \
|
121
|
+
lda = a.outerStride(); \
|
122
|
+
a_ptr = a.data(); \
|
123
|
+
} else a_ptr=lhs; \
|
124
|
+
BLASFUNC(&uplo, &trans, &n, &k, &alpha_, (BLASTYPE*)a_ptr, &lda, &beta_, (BLASTYPE*)res, &ldc); \
|
125
|
+
} \
|
126
|
+
};
|
127
|
+
|
128
|
+
#ifdef EIGEN_USE_MKL
|
129
|
+
EIGEN_BLAS_RANKUPDATE_R(double, double, dsyrk)
|
130
|
+
EIGEN_BLAS_RANKUPDATE_R(float, float, ssyrk)
|
131
|
+
#else
|
132
|
+
EIGEN_BLAS_RANKUPDATE_R(double, double, dsyrk_)
|
133
|
+
EIGEN_BLAS_RANKUPDATE_R(float, float, ssyrk_)
|
134
|
+
#endif
|
135
|
+
|
136
|
+
// TODO hanlde complex cases
|
137
|
+
// EIGEN_BLAS_RANKUPDATE_C(dcomplex, double, double, zherk_)
|
138
|
+
// EIGEN_BLAS_RANKUPDATE_C(scomplex, float, float, cherk_)
|
139
|
+
|
140
|
+
|
141
|
+
} // end namespace internal
|
142
|
+
|
143
|
+
} // end namespace Eigen
|
144
|
+
|
145
|
+
#endif // EIGEN_GENERAL_MATRIX_MATRIX_TRIANGULAR_BLAS_H
|
@@ -0,0 +1,124 @@
|
|
1
|
+
/*
|
2
|
+
Copyright (c) 2011, Intel Corporation. All rights reserved.
|
3
|
+
|
4
|
+
Redistribution and use in source and binary forms, with or without modification,
|
5
|
+
are permitted provided that the following conditions are met:
|
6
|
+
|
7
|
+
* Redistributions of source code must retain the above copyright notice, this
|
8
|
+
list of conditions and the following disclaimer.
|
9
|
+
* Redistributions in binary form must reproduce the above copyright notice,
|
10
|
+
this list of conditions and the following disclaimer in the documentation
|
11
|
+
and/or other materials provided with the distribution.
|
12
|
+
* Neither the name of Intel Corporation nor the names of its contributors may
|
13
|
+
be used to endorse or promote products derived from this software without
|
14
|
+
specific prior written permission.
|
15
|
+
|
16
|
+
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
17
|
+
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
18
|
+
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
19
|
+
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
|
20
|
+
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
|
21
|
+
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
22
|
+
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
|
23
|
+
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
24
|
+
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
25
|
+
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
26
|
+
|
27
|
+
********************************************************************************
|
28
|
+
* Content : Eigen bindings to BLAS F77
|
29
|
+
* General matrix-matrix product functionality based on ?GEMM.
|
30
|
+
********************************************************************************
|
31
|
+
*/
|
32
|
+
|
33
|
+
#ifndef EIGEN_GENERAL_MATRIX_MATRIX_BLAS_H
|
34
|
+
#define EIGEN_GENERAL_MATRIX_MATRIX_BLAS_H
|
35
|
+
|
36
|
+
namespace Eigen {
|
37
|
+
|
38
|
+
namespace internal {
|
39
|
+
|
40
|
+
/**********************************************************************
|
41
|
+
* This file implements general matrix-matrix multiplication using BLAS
|
42
|
+
* gemm function via partial specialization of
|
43
|
+
* general_matrix_matrix_product::run(..) method for float, double,
|
44
|
+
* std::complex<float> and std::complex<double> types
|
45
|
+
**********************************************************************/
|
46
|
+
|
47
|
+
// gemm specialization
|
48
|
+
|
49
|
+
#define GEMM_SPECIALIZATION(EIGTYPE, EIGPREFIX, BLASTYPE, BLASFUNC) \
|
50
|
+
template< \
|
51
|
+
typename Index, \
|
52
|
+
int LhsStorageOrder, bool ConjugateLhs, \
|
53
|
+
int RhsStorageOrder, bool ConjugateRhs> \
|
54
|
+
struct general_matrix_matrix_product<Index,EIGTYPE,LhsStorageOrder,ConjugateLhs,EIGTYPE,RhsStorageOrder,ConjugateRhs,ColMajor,1> \
|
55
|
+
{ \
|
56
|
+
typedef gebp_traits<EIGTYPE,EIGTYPE> Traits; \
|
57
|
+
\
|
58
|
+
static void run(Index rows, Index cols, Index depth, \
|
59
|
+
const EIGTYPE* _lhs, Index lhsStride, \
|
60
|
+
const EIGTYPE* _rhs, Index rhsStride, \
|
61
|
+
EIGTYPE* res, Index resIncr, Index resStride, \
|
62
|
+
EIGTYPE alpha, \
|
63
|
+
level3_blocking<EIGTYPE, EIGTYPE>& /*blocking*/, \
|
64
|
+
GemmParallelInfo<Index>* /*info = 0*/) \
|
65
|
+
{ \
|
66
|
+
using std::conj; \
|
67
|
+
\
|
68
|
+
EIGEN_ONLY_USED_FOR_DEBUG(resIncr); \
|
69
|
+
eigen_assert(resIncr == 1); \
|
70
|
+
char transa, transb; \
|
71
|
+
BlasIndex m, n, k, lda, ldb, ldc; \
|
72
|
+
const EIGTYPE *a, *b; \
|
73
|
+
EIGTYPE beta(1); \
|
74
|
+
MatrixX##EIGPREFIX a_tmp, b_tmp; \
|
75
|
+
\
|
76
|
+
/* Set transpose options */ \
|
77
|
+
transa = (LhsStorageOrder==RowMajor) ? ((ConjugateLhs) ? 'C' : 'T') : 'N'; \
|
78
|
+
transb = (RhsStorageOrder==RowMajor) ? ((ConjugateRhs) ? 'C' : 'T') : 'N'; \
|
79
|
+
\
|
80
|
+
/* Set m, n, k */ \
|
81
|
+
m = convert_index<BlasIndex>(rows); \
|
82
|
+
n = convert_index<BlasIndex>(cols); \
|
83
|
+
k = convert_index<BlasIndex>(depth); \
|
84
|
+
\
|
85
|
+
/* Set lda, ldb, ldc */ \
|
86
|
+
lda = convert_index<BlasIndex>(lhsStride); \
|
87
|
+
ldb = convert_index<BlasIndex>(rhsStride); \
|
88
|
+
ldc = convert_index<BlasIndex>(resStride); \
|
89
|
+
\
|
90
|
+
/* Set a, b, c */ \
|
91
|
+
if ((LhsStorageOrder==ColMajor) && (ConjugateLhs)) { \
|
92
|
+
Map<const MatrixX##EIGPREFIX, 0, OuterStride<> > lhs(_lhs,m,k,OuterStride<>(lhsStride)); \
|
93
|
+
a_tmp = lhs.conjugate(); \
|
94
|
+
a = a_tmp.data(); \
|
95
|
+
lda = convert_index<BlasIndex>(a_tmp.outerStride()); \
|
96
|
+
} else a = _lhs; \
|
97
|
+
\
|
98
|
+
if ((RhsStorageOrder==ColMajor) && (ConjugateRhs)) { \
|
99
|
+
Map<const MatrixX##EIGPREFIX, 0, OuterStride<> > rhs(_rhs,k,n,OuterStride<>(rhsStride)); \
|
100
|
+
b_tmp = rhs.conjugate(); \
|
101
|
+
b = b_tmp.data(); \
|
102
|
+
ldb = convert_index<BlasIndex>(b_tmp.outerStride()); \
|
103
|
+
} else b = _rhs; \
|
104
|
+
\
|
105
|
+
BLASFUNC(&transa, &transb, &m, &n, &k, (const BLASTYPE*)&numext::real_ref(alpha), (const BLASTYPE*)a, &lda, (const BLASTYPE*)b, &ldb, (const BLASTYPE*)&numext::real_ref(beta), (BLASTYPE*)res, &ldc); \
|
106
|
+
}};
|
107
|
+
|
108
|
+
#ifdef EIGEN_USE_MKL
|
109
|
+
GEMM_SPECIALIZATION(double, d, double, dgemm)
|
110
|
+
GEMM_SPECIALIZATION(float, f, float, sgemm)
|
111
|
+
GEMM_SPECIALIZATION(dcomplex, cd, MKL_Complex16, zgemm)
|
112
|
+
GEMM_SPECIALIZATION(scomplex, cf, MKL_Complex8, cgemm)
|
113
|
+
#else
|
114
|
+
GEMM_SPECIALIZATION(double, d, double, dgemm_)
|
115
|
+
GEMM_SPECIALIZATION(float, f, float, sgemm_)
|
116
|
+
GEMM_SPECIALIZATION(dcomplex, cd, double, zgemm_)
|
117
|
+
GEMM_SPECIALIZATION(scomplex, cf, float, cgemm_)
|
118
|
+
#endif
|
119
|
+
|
120
|
+
} // end namespase internal
|
121
|
+
|
122
|
+
} // end namespace Eigen
|
123
|
+
|
124
|
+
#endif // EIGEN_GENERAL_MATRIX_MATRIX_BLAS_H
|