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 +1,179 @@
|
|
1
|
+
// This file is part of Eigen, a lightweight C++ template library
|
2
|
+
// for linear algebra.
|
3
|
+
//
|
4
|
+
// Copyright (C) 2012 Désiré Nuentsa-Wakam <desire.nuentsa_wakam@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
|
+
/*
|
11
|
+
|
12
|
+
* NOTE: This file is the modified version of [s,d,c,z]column_dfs.c file in SuperLU
|
13
|
+
|
14
|
+
* -- SuperLU routine (version 2.0) --
|
15
|
+
* Univ. of California Berkeley, Xerox Palo Alto Research Center,
|
16
|
+
* and Lawrence Berkeley National Lab.
|
17
|
+
* November 15, 1997
|
18
|
+
*
|
19
|
+
* Copyright (c) 1994 by Xerox Corporation. All rights reserved.
|
20
|
+
*
|
21
|
+
* THIS MATERIAL IS PROVIDED AS IS, WITH ABSOLUTELY NO WARRANTY
|
22
|
+
* EXPRESSED OR IMPLIED. ANY USE IS AT YOUR OWN RISK.
|
23
|
+
*
|
24
|
+
* Permission is hereby granted to use or copy this program for any
|
25
|
+
* purpose, provided the above notices are retained on all copies.
|
26
|
+
* Permission to modify the code and to distribute modified code is
|
27
|
+
* granted, provided the above notices are retained, and a notice that
|
28
|
+
* the code was modified is included with the above copyright notice.
|
29
|
+
*/
|
30
|
+
#ifndef SPARSELU_COLUMN_DFS_H
|
31
|
+
#define SPARSELU_COLUMN_DFS_H
|
32
|
+
|
33
|
+
template <typename Scalar, typename StorageIndex> class SparseLUImpl;
|
34
|
+
namespace Eigen {
|
35
|
+
|
36
|
+
namespace internal {
|
37
|
+
|
38
|
+
template<typename IndexVector, typename ScalarVector>
|
39
|
+
struct column_dfs_traits : no_assignment_operator
|
40
|
+
{
|
41
|
+
typedef typename ScalarVector::Scalar Scalar;
|
42
|
+
typedef typename IndexVector::Scalar StorageIndex;
|
43
|
+
column_dfs_traits(Index jcol, Index& jsuper, typename SparseLUImpl<Scalar, StorageIndex>::GlobalLU_t& glu, SparseLUImpl<Scalar, StorageIndex>& luImpl)
|
44
|
+
: m_jcol(jcol), m_jsuper_ref(jsuper), m_glu(glu), m_luImpl(luImpl)
|
45
|
+
{}
|
46
|
+
bool update_segrep(Index /*krep*/, Index /*jj*/)
|
47
|
+
{
|
48
|
+
return true;
|
49
|
+
}
|
50
|
+
void mem_expand(IndexVector& lsub, Index& nextl, Index chmark)
|
51
|
+
{
|
52
|
+
if (nextl >= m_glu.nzlmax)
|
53
|
+
m_luImpl.memXpand(lsub, m_glu.nzlmax, nextl, LSUB, m_glu.num_expansions);
|
54
|
+
if (chmark != (m_jcol-1)) m_jsuper_ref = emptyIdxLU;
|
55
|
+
}
|
56
|
+
enum { ExpandMem = true };
|
57
|
+
|
58
|
+
Index m_jcol;
|
59
|
+
Index& m_jsuper_ref;
|
60
|
+
typename SparseLUImpl<Scalar, StorageIndex>::GlobalLU_t& m_glu;
|
61
|
+
SparseLUImpl<Scalar, StorageIndex>& m_luImpl;
|
62
|
+
};
|
63
|
+
|
64
|
+
|
65
|
+
/**
|
66
|
+
* \brief Performs a symbolic factorization on column jcol and decide the supernode boundary
|
67
|
+
*
|
68
|
+
* A supernode representative is the last column of a supernode.
|
69
|
+
* The nonzeros in U[*,j] are segments that end at supernodes representatives.
|
70
|
+
* The routine returns a list of the supernodal representatives
|
71
|
+
* in topological order of the dfs that generates them.
|
72
|
+
* The location of the first nonzero in each supernodal segment
|
73
|
+
* (supernodal entry location) is also returned.
|
74
|
+
*
|
75
|
+
* \param m number of rows in the matrix
|
76
|
+
* \param jcol Current column
|
77
|
+
* \param perm_r Row permutation
|
78
|
+
* \param maxsuper Maximum number of column allowed in a supernode
|
79
|
+
* \param [in,out] nseg Number of segments in current U[*,j] - new segments appended
|
80
|
+
* \param lsub_col defines the rhs vector to start the dfs
|
81
|
+
* \param [in,out] segrep Segment representatives - new segments appended
|
82
|
+
* \param repfnz First nonzero location in each row
|
83
|
+
* \param xprune
|
84
|
+
* \param marker marker[i] == jj, if i was visited during dfs of current column jj;
|
85
|
+
* \param parent
|
86
|
+
* \param xplore working array
|
87
|
+
* \param glu global LU data
|
88
|
+
* \return 0 success
|
89
|
+
* > 0 number of bytes allocated when run out of space
|
90
|
+
*
|
91
|
+
*/
|
92
|
+
template <typename Scalar, typename StorageIndex>
|
93
|
+
Index SparseLUImpl<Scalar,StorageIndex>::column_dfs(const Index m, const Index jcol, IndexVector& perm_r, Index maxsuper, Index& nseg,
|
94
|
+
BlockIndexVector lsub_col, IndexVector& segrep, BlockIndexVector repfnz, IndexVector& xprune,
|
95
|
+
IndexVector& marker, IndexVector& parent, IndexVector& xplore, GlobalLU_t& glu)
|
96
|
+
{
|
97
|
+
|
98
|
+
Index jsuper = glu.supno(jcol);
|
99
|
+
Index nextl = glu.xlsub(jcol);
|
100
|
+
VectorBlock<IndexVector> marker2(marker, 2*m, m);
|
101
|
+
|
102
|
+
|
103
|
+
column_dfs_traits<IndexVector, ScalarVector> traits(jcol, jsuper, glu, *this);
|
104
|
+
|
105
|
+
// For each nonzero in A(*,jcol) do dfs
|
106
|
+
for (Index k = 0; ((k < m) ? lsub_col[k] != emptyIdxLU : false) ; k++)
|
107
|
+
{
|
108
|
+
Index krow = lsub_col(k);
|
109
|
+
lsub_col(k) = emptyIdxLU;
|
110
|
+
Index kmark = marker2(krow);
|
111
|
+
|
112
|
+
// krow was visited before, go to the next nonz;
|
113
|
+
if (kmark == jcol) continue;
|
114
|
+
|
115
|
+
dfs_kernel(StorageIndex(jcol), perm_r, nseg, glu.lsub, segrep, repfnz, xprune, marker2, parent,
|
116
|
+
xplore, glu, nextl, krow, traits);
|
117
|
+
} // for each nonzero ...
|
118
|
+
|
119
|
+
Index fsupc;
|
120
|
+
StorageIndex nsuper = glu.supno(jcol);
|
121
|
+
StorageIndex jcolp1 = StorageIndex(jcol) + 1;
|
122
|
+
Index jcolm1 = jcol - 1;
|
123
|
+
|
124
|
+
// check to see if j belongs in the same supernode as j-1
|
125
|
+
if ( jcol == 0 )
|
126
|
+
{ // Do nothing for column 0
|
127
|
+
nsuper = glu.supno(0) = 0 ;
|
128
|
+
}
|
129
|
+
else
|
130
|
+
{
|
131
|
+
fsupc = glu.xsup(nsuper);
|
132
|
+
StorageIndex jptr = glu.xlsub(jcol); // Not yet compressed
|
133
|
+
StorageIndex jm1ptr = glu.xlsub(jcolm1);
|
134
|
+
|
135
|
+
// Use supernodes of type T2 : see SuperLU paper
|
136
|
+
if ( (nextl-jptr != jptr-jm1ptr-1) ) jsuper = emptyIdxLU;
|
137
|
+
|
138
|
+
// Make sure the number of columns in a supernode doesn't
|
139
|
+
// exceed threshold
|
140
|
+
if ( (jcol - fsupc) >= maxsuper) jsuper = emptyIdxLU;
|
141
|
+
|
142
|
+
/* If jcol starts a new supernode, reclaim storage space in
|
143
|
+
* glu.lsub from previous supernode. Note we only store
|
144
|
+
* the subscript set of the first and last columns of
|
145
|
+
* a supernode. (first for num values, last for pruning)
|
146
|
+
*/
|
147
|
+
if (jsuper == emptyIdxLU)
|
148
|
+
{ // starts a new supernode
|
149
|
+
if ( (fsupc < jcolm1-1) )
|
150
|
+
{ // >= 3 columns in nsuper
|
151
|
+
StorageIndex ito = glu.xlsub(fsupc+1);
|
152
|
+
glu.xlsub(jcolm1) = ito;
|
153
|
+
StorageIndex istop = ito + jptr - jm1ptr;
|
154
|
+
xprune(jcolm1) = istop; // initialize xprune(jcol-1)
|
155
|
+
glu.xlsub(jcol) = istop;
|
156
|
+
|
157
|
+
for (StorageIndex ifrom = jm1ptr; ifrom < nextl; ++ifrom, ++ito)
|
158
|
+
glu.lsub(ito) = glu.lsub(ifrom);
|
159
|
+
nextl = ito; // = istop + length(jcol)
|
160
|
+
}
|
161
|
+
nsuper++;
|
162
|
+
glu.supno(jcol) = nsuper;
|
163
|
+
} // if a new supernode
|
164
|
+
} // end else: jcol > 0
|
165
|
+
|
166
|
+
// Tidy up the pointers before exit
|
167
|
+
glu.xsup(nsuper+1) = jcolp1;
|
168
|
+
glu.supno(jcolp1) = nsuper;
|
169
|
+
xprune(jcol) = StorageIndex(nextl); // Initialize upper bound for pruning
|
170
|
+
glu.xlsub(jcolp1) = StorageIndex(nextl);
|
171
|
+
|
172
|
+
return 0;
|
173
|
+
}
|
174
|
+
|
175
|
+
} // end namespace internal
|
176
|
+
|
177
|
+
} // end namespace Eigen
|
178
|
+
|
179
|
+
#endif
|
@@ -0,0 +1,107 @@
|
|
1
|
+
// This file is part of Eigen, a lightweight C++ template library
|
2
|
+
// for linear algebra.
|
3
|
+
//
|
4
|
+
// Copyright (C) 2012 Désiré Nuentsa-Wakam <desire.nuentsa_wakam@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
|
+
|
11
|
+
* NOTE: This file is the modified version of [s,d,c,z]copy_to_ucol.c file in SuperLU
|
12
|
+
|
13
|
+
* -- SuperLU routine (version 2.0) --
|
14
|
+
* Univ. of California Berkeley, Xerox Palo Alto Research Center,
|
15
|
+
* and Lawrence Berkeley National Lab.
|
16
|
+
* November 15, 1997
|
17
|
+
*
|
18
|
+
* Copyright (c) 1994 by Xerox Corporation. All rights reserved.
|
19
|
+
*
|
20
|
+
* THIS MATERIAL IS PROVIDED AS IS, WITH ABSOLUTELY NO WARRANTY
|
21
|
+
* EXPRESSED OR IMPLIED. ANY USE IS AT YOUR OWN RISK.
|
22
|
+
*
|
23
|
+
* Permission is hereby granted to use or copy this program for any
|
24
|
+
* purpose, provided the above notices are retained on all copies.
|
25
|
+
* Permission to modify the code and to distribute modified code is
|
26
|
+
* granted, provided the above notices are retained, and a notice that
|
27
|
+
* the code was modified is included with the above copyright notice.
|
28
|
+
*/
|
29
|
+
#ifndef SPARSELU_COPY_TO_UCOL_H
|
30
|
+
#define SPARSELU_COPY_TO_UCOL_H
|
31
|
+
|
32
|
+
namespace Eigen {
|
33
|
+
namespace internal {
|
34
|
+
|
35
|
+
/**
|
36
|
+
* \brief Performs numeric block updates (sup-col) in topological order
|
37
|
+
*
|
38
|
+
* \param jcol current column to update
|
39
|
+
* \param nseg Number of segments in the U part
|
40
|
+
* \param segrep segment representative ...
|
41
|
+
* \param repfnz First nonzero column in each row ...
|
42
|
+
* \param perm_r Row permutation
|
43
|
+
* \param dense Store the full representation of the column
|
44
|
+
* \param glu Global LU data.
|
45
|
+
* \return 0 - successful return
|
46
|
+
* > 0 - number of bytes allocated when run out of space
|
47
|
+
*
|
48
|
+
*/
|
49
|
+
template <typename Scalar, typename StorageIndex>
|
50
|
+
Index SparseLUImpl<Scalar,StorageIndex>::copy_to_ucol(const Index jcol, const Index nseg, IndexVector& segrep,
|
51
|
+
BlockIndexVector repfnz ,IndexVector& perm_r, BlockScalarVector dense, GlobalLU_t& glu)
|
52
|
+
{
|
53
|
+
Index ksub, krep, ksupno;
|
54
|
+
|
55
|
+
Index jsupno = glu.supno(jcol);
|
56
|
+
|
57
|
+
// For each nonzero supernode segment of U[*,j] in topological order
|
58
|
+
Index k = nseg - 1, i;
|
59
|
+
StorageIndex nextu = glu.xusub(jcol);
|
60
|
+
Index kfnz, isub, segsize;
|
61
|
+
Index new_next,irow;
|
62
|
+
Index fsupc, mem;
|
63
|
+
for (ksub = 0; ksub < nseg; ksub++)
|
64
|
+
{
|
65
|
+
krep = segrep(k); k--;
|
66
|
+
ksupno = glu.supno(krep);
|
67
|
+
if (jsupno != ksupno ) // should go into ucol();
|
68
|
+
{
|
69
|
+
kfnz = repfnz(krep);
|
70
|
+
if (kfnz != emptyIdxLU)
|
71
|
+
{ // Nonzero U-segment
|
72
|
+
fsupc = glu.xsup(ksupno);
|
73
|
+
isub = glu.xlsub(fsupc) + kfnz - fsupc;
|
74
|
+
segsize = krep - kfnz + 1;
|
75
|
+
new_next = nextu + segsize;
|
76
|
+
while (new_next > glu.nzumax)
|
77
|
+
{
|
78
|
+
mem = memXpand<ScalarVector>(glu.ucol, glu.nzumax, nextu, UCOL, glu.num_expansions);
|
79
|
+
if (mem) return mem;
|
80
|
+
mem = memXpand<IndexVector>(glu.usub, glu.nzumax, nextu, USUB, glu.num_expansions);
|
81
|
+
if (mem) return mem;
|
82
|
+
|
83
|
+
}
|
84
|
+
|
85
|
+
for (i = 0; i < segsize; i++)
|
86
|
+
{
|
87
|
+
irow = glu.lsub(isub);
|
88
|
+
glu.usub(nextu) = perm_r(irow); // Unlike the L part, the U part is stored in its final order
|
89
|
+
glu.ucol(nextu) = dense(irow);
|
90
|
+
dense(irow) = Scalar(0.0);
|
91
|
+
nextu++;
|
92
|
+
isub++;
|
93
|
+
}
|
94
|
+
|
95
|
+
} // end nonzero U-segment
|
96
|
+
|
97
|
+
} // end if jsupno
|
98
|
+
|
99
|
+
} // end for each segment
|
100
|
+
glu.xusub(jcol + 1) = nextu; // close U(*,jcol)
|
101
|
+
return 0;
|
102
|
+
}
|
103
|
+
|
104
|
+
} // namespace internal
|
105
|
+
} // end namespace Eigen
|
106
|
+
|
107
|
+
#endif // SPARSELU_COPY_TO_UCOL_H
|
@@ -0,0 +1,280 @@
|
|
1
|
+
// This file is part of Eigen, a lightweight C++ template library
|
2
|
+
// for linear algebra.
|
3
|
+
//
|
4
|
+
// Copyright (C) 2012 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_SPARSELU_GEMM_KERNEL_H
|
11
|
+
#define EIGEN_SPARSELU_GEMM_KERNEL_H
|
12
|
+
|
13
|
+
namespace Eigen {
|
14
|
+
|
15
|
+
namespace internal {
|
16
|
+
|
17
|
+
|
18
|
+
/** \internal
|
19
|
+
* A general matrix-matrix product kernel optimized for the SparseLU factorization.
|
20
|
+
* - A, B, and C must be column major
|
21
|
+
* - lda and ldc must be multiples of the respective packet size
|
22
|
+
* - C must have the same alignment as A
|
23
|
+
*/
|
24
|
+
template<typename Scalar>
|
25
|
+
EIGEN_DONT_INLINE
|
26
|
+
void sparselu_gemm(Index m, Index n, Index d, const Scalar* A, Index lda, const Scalar* B, Index ldb, Scalar* C, Index ldc)
|
27
|
+
{
|
28
|
+
using namespace Eigen::internal;
|
29
|
+
|
30
|
+
typedef typename packet_traits<Scalar>::type Packet;
|
31
|
+
enum {
|
32
|
+
NumberOfRegisters = EIGEN_ARCH_DEFAULT_NUMBER_OF_REGISTERS,
|
33
|
+
PacketSize = packet_traits<Scalar>::size,
|
34
|
+
PM = 8, // peeling in M
|
35
|
+
RN = 2, // register blocking
|
36
|
+
RK = NumberOfRegisters>=16 ? 4 : 2, // register blocking
|
37
|
+
BM = 4096/sizeof(Scalar), // number of rows of A-C per chunk
|
38
|
+
SM = PM*PacketSize // step along M
|
39
|
+
};
|
40
|
+
Index d_end = (d/RK)*RK; // number of columns of A (rows of B) suitable for full register blocking
|
41
|
+
Index n_end = (n/RN)*RN; // number of columns of B-C suitable for processing RN columns at once
|
42
|
+
Index i0 = internal::first_default_aligned(A,m);
|
43
|
+
|
44
|
+
eigen_internal_assert(((lda%PacketSize)==0) && ((ldc%PacketSize)==0) && (i0==internal::first_default_aligned(C,m)));
|
45
|
+
|
46
|
+
// handle the non aligned rows of A and C without any optimization:
|
47
|
+
for(Index i=0; i<i0; ++i)
|
48
|
+
{
|
49
|
+
for(Index j=0; j<n; ++j)
|
50
|
+
{
|
51
|
+
Scalar c = C[i+j*ldc];
|
52
|
+
for(Index k=0; k<d; ++k)
|
53
|
+
c += B[k+j*ldb] * A[i+k*lda];
|
54
|
+
C[i+j*ldc] = c;
|
55
|
+
}
|
56
|
+
}
|
57
|
+
// process the remaining rows per chunk of BM rows
|
58
|
+
for(Index ib=i0; ib<m; ib+=BM)
|
59
|
+
{
|
60
|
+
Index actual_b = std::min<Index>(BM, m-ib); // actual number of rows
|
61
|
+
Index actual_b_end1 = (actual_b/SM)*SM; // actual number of rows suitable for peeling
|
62
|
+
Index actual_b_end2 = (actual_b/PacketSize)*PacketSize; // actual number of rows suitable for vectorization
|
63
|
+
|
64
|
+
// Let's process two columns of B-C at once
|
65
|
+
for(Index j=0; j<n_end; j+=RN)
|
66
|
+
{
|
67
|
+
const Scalar* Bc0 = B+(j+0)*ldb;
|
68
|
+
const Scalar* Bc1 = B+(j+1)*ldb;
|
69
|
+
|
70
|
+
for(Index k=0; k<d_end; k+=RK)
|
71
|
+
{
|
72
|
+
|
73
|
+
// load and expand a RN x RK block of B
|
74
|
+
Packet b00, b10, b20, b30, b01, b11, b21, b31;
|
75
|
+
{ b00 = pset1<Packet>(Bc0[0]); }
|
76
|
+
{ b10 = pset1<Packet>(Bc0[1]); }
|
77
|
+
if(RK==4) { b20 = pset1<Packet>(Bc0[2]); }
|
78
|
+
if(RK==4) { b30 = pset1<Packet>(Bc0[3]); }
|
79
|
+
{ b01 = pset1<Packet>(Bc1[0]); }
|
80
|
+
{ b11 = pset1<Packet>(Bc1[1]); }
|
81
|
+
if(RK==4) { b21 = pset1<Packet>(Bc1[2]); }
|
82
|
+
if(RK==4) { b31 = pset1<Packet>(Bc1[3]); }
|
83
|
+
|
84
|
+
Packet a0, a1, a2, a3, c0, c1, t0, t1;
|
85
|
+
|
86
|
+
const Scalar* A0 = A+ib+(k+0)*lda;
|
87
|
+
const Scalar* A1 = A+ib+(k+1)*lda;
|
88
|
+
const Scalar* A2 = A+ib+(k+2)*lda;
|
89
|
+
const Scalar* A3 = A+ib+(k+3)*lda;
|
90
|
+
|
91
|
+
Scalar* C0 = C+ib+(j+0)*ldc;
|
92
|
+
Scalar* C1 = C+ib+(j+1)*ldc;
|
93
|
+
|
94
|
+
a0 = pload<Packet>(A0);
|
95
|
+
a1 = pload<Packet>(A1);
|
96
|
+
if(RK==4)
|
97
|
+
{
|
98
|
+
a2 = pload<Packet>(A2);
|
99
|
+
a3 = pload<Packet>(A3);
|
100
|
+
}
|
101
|
+
else
|
102
|
+
{
|
103
|
+
// workaround "may be used uninitialized in this function" warning
|
104
|
+
a2 = a3 = a0;
|
105
|
+
}
|
106
|
+
|
107
|
+
#define KMADD(c, a, b, tmp) {tmp = b; tmp = pmul(a,tmp); c = padd(c,tmp);}
|
108
|
+
#define WORK(I) \
|
109
|
+
c0 = pload<Packet>(C0+i+(I)*PacketSize); \
|
110
|
+
c1 = pload<Packet>(C1+i+(I)*PacketSize); \
|
111
|
+
KMADD(c0, a0, b00, t0) \
|
112
|
+
KMADD(c1, a0, b01, t1) \
|
113
|
+
a0 = pload<Packet>(A0+i+(I+1)*PacketSize); \
|
114
|
+
KMADD(c0, a1, b10, t0) \
|
115
|
+
KMADD(c1, a1, b11, t1) \
|
116
|
+
a1 = pload<Packet>(A1+i+(I+1)*PacketSize); \
|
117
|
+
if(RK==4){ KMADD(c0, a2, b20, t0) }\
|
118
|
+
if(RK==4){ KMADD(c1, a2, b21, t1) }\
|
119
|
+
if(RK==4){ a2 = pload<Packet>(A2+i+(I+1)*PacketSize); }\
|
120
|
+
if(RK==4){ KMADD(c0, a3, b30, t0) }\
|
121
|
+
if(RK==4){ KMADD(c1, a3, b31, t1) }\
|
122
|
+
if(RK==4){ a3 = pload<Packet>(A3+i+(I+1)*PacketSize); }\
|
123
|
+
pstore(C0+i+(I)*PacketSize, c0); \
|
124
|
+
pstore(C1+i+(I)*PacketSize, c1)
|
125
|
+
|
126
|
+
// process rows of A' - C' with aggressive vectorization and peeling
|
127
|
+
for(Index i=0; i<actual_b_end1; i+=PacketSize*8)
|
128
|
+
{
|
129
|
+
EIGEN_ASM_COMMENT("SPARSELU_GEMML_KERNEL1");
|
130
|
+
prefetch((A0+i+(5)*PacketSize));
|
131
|
+
prefetch((A1+i+(5)*PacketSize));
|
132
|
+
if(RK==4) prefetch((A2+i+(5)*PacketSize));
|
133
|
+
if(RK==4) prefetch((A3+i+(5)*PacketSize));
|
134
|
+
|
135
|
+
WORK(0);
|
136
|
+
WORK(1);
|
137
|
+
WORK(2);
|
138
|
+
WORK(3);
|
139
|
+
WORK(4);
|
140
|
+
WORK(5);
|
141
|
+
WORK(6);
|
142
|
+
WORK(7);
|
143
|
+
}
|
144
|
+
// process the remaining rows with vectorization only
|
145
|
+
for(Index i=actual_b_end1; i<actual_b_end2; i+=PacketSize)
|
146
|
+
{
|
147
|
+
WORK(0);
|
148
|
+
}
|
149
|
+
#undef WORK
|
150
|
+
// process the remaining rows without vectorization
|
151
|
+
for(Index i=actual_b_end2; i<actual_b; ++i)
|
152
|
+
{
|
153
|
+
if(RK==4)
|
154
|
+
{
|
155
|
+
C0[i] += A0[i]*Bc0[0]+A1[i]*Bc0[1]+A2[i]*Bc0[2]+A3[i]*Bc0[3];
|
156
|
+
C1[i] += A0[i]*Bc1[0]+A1[i]*Bc1[1]+A2[i]*Bc1[2]+A3[i]*Bc1[3];
|
157
|
+
}
|
158
|
+
else
|
159
|
+
{
|
160
|
+
C0[i] += A0[i]*Bc0[0]+A1[i]*Bc0[1];
|
161
|
+
C1[i] += A0[i]*Bc1[0]+A1[i]*Bc1[1];
|
162
|
+
}
|
163
|
+
}
|
164
|
+
|
165
|
+
Bc0 += RK;
|
166
|
+
Bc1 += RK;
|
167
|
+
} // peeled loop on k
|
168
|
+
} // peeled loop on the columns j
|
169
|
+
// process the last column (we now perform a matrix-vector product)
|
170
|
+
if((n-n_end)>0)
|
171
|
+
{
|
172
|
+
const Scalar* Bc0 = B+(n-1)*ldb;
|
173
|
+
|
174
|
+
for(Index k=0; k<d_end; k+=RK)
|
175
|
+
{
|
176
|
+
|
177
|
+
// load and expand a 1 x RK block of B
|
178
|
+
Packet b00, b10, b20, b30;
|
179
|
+
b00 = pset1<Packet>(Bc0[0]);
|
180
|
+
b10 = pset1<Packet>(Bc0[1]);
|
181
|
+
if(RK==4) b20 = pset1<Packet>(Bc0[2]);
|
182
|
+
if(RK==4) b30 = pset1<Packet>(Bc0[3]);
|
183
|
+
|
184
|
+
Packet a0, a1, a2, a3, c0, t0/*, t1*/;
|
185
|
+
|
186
|
+
const Scalar* A0 = A+ib+(k+0)*lda;
|
187
|
+
const Scalar* A1 = A+ib+(k+1)*lda;
|
188
|
+
const Scalar* A2 = A+ib+(k+2)*lda;
|
189
|
+
const Scalar* A3 = A+ib+(k+3)*lda;
|
190
|
+
|
191
|
+
Scalar* C0 = C+ib+(n_end)*ldc;
|
192
|
+
|
193
|
+
a0 = pload<Packet>(A0);
|
194
|
+
a1 = pload<Packet>(A1);
|
195
|
+
if(RK==4)
|
196
|
+
{
|
197
|
+
a2 = pload<Packet>(A2);
|
198
|
+
a3 = pload<Packet>(A3);
|
199
|
+
}
|
200
|
+
else
|
201
|
+
{
|
202
|
+
// workaround "may be used uninitialized in this function" warning
|
203
|
+
a2 = a3 = a0;
|
204
|
+
}
|
205
|
+
|
206
|
+
#define WORK(I) \
|
207
|
+
c0 = pload<Packet>(C0+i+(I)*PacketSize); \
|
208
|
+
KMADD(c0, a0, b00, t0) \
|
209
|
+
a0 = pload<Packet>(A0+i+(I+1)*PacketSize); \
|
210
|
+
KMADD(c0, a1, b10, t0) \
|
211
|
+
a1 = pload<Packet>(A1+i+(I+1)*PacketSize); \
|
212
|
+
if(RK==4){ KMADD(c0, a2, b20, t0) }\
|
213
|
+
if(RK==4){ a2 = pload<Packet>(A2+i+(I+1)*PacketSize); }\
|
214
|
+
if(RK==4){ KMADD(c0, a3, b30, t0) }\
|
215
|
+
if(RK==4){ a3 = pload<Packet>(A3+i+(I+1)*PacketSize); }\
|
216
|
+
pstore(C0+i+(I)*PacketSize, c0);
|
217
|
+
|
218
|
+
// aggressive vectorization and peeling
|
219
|
+
for(Index i=0; i<actual_b_end1; i+=PacketSize*8)
|
220
|
+
{
|
221
|
+
EIGEN_ASM_COMMENT("SPARSELU_GEMML_KERNEL2");
|
222
|
+
WORK(0);
|
223
|
+
WORK(1);
|
224
|
+
WORK(2);
|
225
|
+
WORK(3);
|
226
|
+
WORK(4);
|
227
|
+
WORK(5);
|
228
|
+
WORK(6);
|
229
|
+
WORK(7);
|
230
|
+
}
|
231
|
+
// vectorization only
|
232
|
+
for(Index i=actual_b_end1; i<actual_b_end2; i+=PacketSize)
|
233
|
+
{
|
234
|
+
WORK(0);
|
235
|
+
}
|
236
|
+
// remaining scalars
|
237
|
+
for(Index i=actual_b_end2; i<actual_b; ++i)
|
238
|
+
{
|
239
|
+
if(RK==4)
|
240
|
+
C0[i] += A0[i]*Bc0[0]+A1[i]*Bc0[1]+A2[i]*Bc0[2]+A3[i]*Bc0[3];
|
241
|
+
else
|
242
|
+
C0[i] += A0[i]*Bc0[0]+A1[i]*Bc0[1];
|
243
|
+
}
|
244
|
+
|
245
|
+
Bc0 += RK;
|
246
|
+
#undef WORK
|
247
|
+
}
|
248
|
+
}
|
249
|
+
|
250
|
+
// process the last columns of A, corresponding to the last rows of B
|
251
|
+
Index rd = d-d_end;
|
252
|
+
if(rd>0)
|
253
|
+
{
|
254
|
+
for(Index j=0; j<n; ++j)
|
255
|
+
{
|
256
|
+
enum {
|
257
|
+
Alignment = PacketSize>1 ? Aligned : 0
|
258
|
+
};
|
259
|
+
typedef Map<Matrix<Scalar,Dynamic,1>, Alignment > MapVector;
|
260
|
+
typedef Map<const Matrix<Scalar,Dynamic,1>, Alignment > ConstMapVector;
|
261
|
+
if(rd==1) MapVector(C+j*ldc+ib,actual_b) += B[0+d_end+j*ldb] * ConstMapVector(A+(d_end+0)*lda+ib, actual_b);
|
262
|
+
|
263
|
+
else if(rd==2) MapVector(C+j*ldc+ib,actual_b) += B[0+d_end+j*ldb] * ConstMapVector(A+(d_end+0)*lda+ib, actual_b)
|
264
|
+
+ B[1+d_end+j*ldb] * ConstMapVector(A+(d_end+1)*lda+ib, actual_b);
|
265
|
+
|
266
|
+
else MapVector(C+j*ldc+ib,actual_b) += B[0+d_end+j*ldb] * ConstMapVector(A+(d_end+0)*lda+ib, actual_b)
|
267
|
+
+ B[1+d_end+j*ldb] * ConstMapVector(A+(d_end+1)*lda+ib, actual_b)
|
268
|
+
+ B[2+d_end+j*ldb] * ConstMapVector(A+(d_end+2)*lda+ib, actual_b);
|
269
|
+
}
|
270
|
+
}
|
271
|
+
|
272
|
+
} // blocking on the rows of A and C
|
273
|
+
}
|
274
|
+
#undef KMADD
|
275
|
+
|
276
|
+
} // namespace internal
|
277
|
+
|
278
|
+
} // namespace Eigen
|
279
|
+
|
280
|
+
#endif // EIGEN_SPARSELU_GEMM_KERNEL_H
|
@@ -0,0 +1,126 @@
|
|
1
|
+
// This file is part of Eigen, a lightweight C++ template library
|
2
|
+
// for linear algebra.
|
3
|
+
//
|
4
|
+
// Copyright (C) 2012 Désiré Nuentsa-Wakam <desire.nuentsa_wakam@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
|
+
/* This file is a modified version of heap_relax_snode.c file in SuperLU
|
11
|
+
* -- SuperLU routine (version 3.0) --
|
12
|
+
* Univ. of California Berkeley, Xerox Palo Alto Research Center,
|
13
|
+
* and Lawrence Berkeley National Lab.
|
14
|
+
* October 15, 2003
|
15
|
+
*
|
16
|
+
* Copyright (c) 1994 by Xerox Corporation. All rights reserved.
|
17
|
+
*
|
18
|
+
* THIS MATERIAL IS PROVIDED AS IS, WITH ABSOLUTELY NO WARRANTY
|
19
|
+
* EXPRESSED OR IMPLIED. ANY USE IS AT YOUR OWN RISK.
|
20
|
+
*
|
21
|
+
* Permission is hereby granted to use or copy this program for any
|
22
|
+
* purpose, provided the above notices are retained on all copies.
|
23
|
+
* Permission to modify the code and to distribute modified code is
|
24
|
+
* granted, provided the above notices are retained, and a notice that
|
25
|
+
* the code was modified is included with the above copyright notice.
|
26
|
+
*/
|
27
|
+
|
28
|
+
#ifndef SPARSELU_HEAP_RELAX_SNODE_H
|
29
|
+
#define SPARSELU_HEAP_RELAX_SNODE_H
|
30
|
+
|
31
|
+
namespace Eigen {
|
32
|
+
namespace internal {
|
33
|
+
|
34
|
+
/**
|
35
|
+
* \brief Identify the initial relaxed supernodes
|
36
|
+
*
|
37
|
+
* This routine applied to a symmetric elimination tree.
|
38
|
+
* It assumes that the matrix has been reordered according to the postorder of the etree
|
39
|
+
* \param n The number of columns
|
40
|
+
* \param et elimination tree
|
41
|
+
* \param relax_columns Maximum number of columns allowed in a relaxed snode
|
42
|
+
* \param descendants Number of descendants of each node in the etree
|
43
|
+
* \param relax_end last column in a supernode
|
44
|
+
*/
|
45
|
+
template <typename Scalar, typename StorageIndex>
|
46
|
+
void SparseLUImpl<Scalar,StorageIndex>::heap_relax_snode (const Index n, IndexVector& et, const Index relax_columns, IndexVector& descendants, IndexVector& relax_end)
|
47
|
+
{
|
48
|
+
|
49
|
+
// The etree may not be postordered, but its heap ordered
|
50
|
+
IndexVector post;
|
51
|
+
internal::treePostorder(StorageIndex(n), et, post); // Post order etree
|
52
|
+
IndexVector inv_post(n+1);
|
53
|
+
for (StorageIndex i = 0; i < n+1; ++i) inv_post(post(i)) = i; // inv_post = post.inverse()???
|
54
|
+
|
55
|
+
// Renumber etree in postorder
|
56
|
+
IndexVector iwork(n);
|
57
|
+
IndexVector et_save(n+1);
|
58
|
+
for (Index i = 0; i < n; ++i)
|
59
|
+
{
|
60
|
+
iwork(post(i)) = post(et(i));
|
61
|
+
}
|
62
|
+
et_save = et; // Save the original etree
|
63
|
+
et = iwork;
|
64
|
+
|
65
|
+
// compute the number of descendants of each node in the etree
|
66
|
+
relax_end.setConstant(emptyIdxLU);
|
67
|
+
Index j, parent;
|
68
|
+
descendants.setZero();
|
69
|
+
for (j = 0; j < n; j++)
|
70
|
+
{
|
71
|
+
parent = et(j);
|
72
|
+
if (parent != n) // not the dummy root
|
73
|
+
descendants(parent) += descendants(j) + 1;
|
74
|
+
}
|
75
|
+
// Identify the relaxed supernodes by postorder traversal of the etree
|
76
|
+
Index snode_start; // beginning of a snode
|
77
|
+
StorageIndex k;
|
78
|
+
Index nsuper_et_post = 0; // Number of relaxed snodes in postordered etree
|
79
|
+
Index nsuper_et = 0; // Number of relaxed snodes in the original etree
|
80
|
+
StorageIndex l;
|
81
|
+
for (j = 0; j < n; )
|
82
|
+
{
|
83
|
+
parent = et(j);
|
84
|
+
snode_start = j;
|
85
|
+
while ( parent != n && descendants(parent) < relax_columns )
|
86
|
+
{
|
87
|
+
j = parent;
|
88
|
+
parent = et(j);
|
89
|
+
}
|
90
|
+
// Found a supernode in postordered etree, j is the last column
|
91
|
+
++nsuper_et_post;
|
92
|
+
k = StorageIndex(n);
|
93
|
+
for (Index i = snode_start; i <= j; ++i)
|
94
|
+
k = (std::min)(k, inv_post(i));
|
95
|
+
l = inv_post(j);
|
96
|
+
if ( (l - k) == (j - snode_start) ) // Same number of columns in the snode
|
97
|
+
{
|
98
|
+
// This is also a supernode in the original etree
|
99
|
+
relax_end(k) = l; // Record last column
|
100
|
+
++nsuper_et;
|
101
|
+
}
|
102
|
+
else
|
103
|
+
{
|
104
|
+
for (Index i = snode_start; i <= j; ++i)
|
105
|
+
{
|
106
|
+
l = inv_post(i);
|
107
|
+
if (descendants(i) == 0)
|
108
|
+
{
|
109
|
+
relax_end(l) = l;
|
110
|
+
++nsuper_et;
|
111
|
+
}
|
112
|
+
}
|
113
|
+
}
|
114
|
+
j++;
|
115
|
+
// Search for a new leaf
|
116
|
+
while (descendants(j) != 0 && j < n) j++;
|
117
|
+
} // End postorder traversal of the etree
|
118
|
+
|
119
|
+
// Recover the original etree
|
120
|
+
et = et_save;
|
121
|
+
}
|
122
|
+
|
123
|
+
} // end namespace internal
|
124
|
+
|
125
|
+
} // end namespace Eigen
|
126
|
+
#endif // SPARSELU_HEAP_RELAX_SNODE_H
|