Crate singe_cusparse_sys

Source

Expand description

Raw FFI bindings for cuSPARSE.

Prefer the safe singe-cusparse crate unless direct NVIDIA ABI access is required.

Structs§

Enums§

cusparseAction_t: This type indicates whether the operation is performed only on indices or on data and indices.
cusparseColorAlg_t
cusparseCsr2CscAlg_t
cusparseDenseToSparseAlg_t
cusparseDiagType_t: This type indicates if the matrix diagonal entries are unity. The diagonal elements are always assumed to be present, but if cusparseDiagType_t::CUSPARSE_DIAG_TYPE_UNIT is passed to an API routine, then the routine assumes that all diagonal entries are unity and will not read or modify those entries. Note that in this case the routine assumes the diagonal entries are equal to one, regardless of what those entries are actually set to in memory.
cusparseDirection_t: This type indicates whether the elements of a dense matrix should be parsed by rows or by columns (assuming column-major storage in memory of the dense matrix) in function cusparse[S|D|C|Z]nnz. Besides storage format of blocks in BSR format is also controlled by this type.
cusparseFillMode_t: This type indicates if the lower or upper part of a matrix is stored in sparse storage.
cusparseFormat_t: This type indicates the format of the sparse matrix. See cuSPARSE Storage Formats for their description.
cusparseIndexBase_t: This type indicates if the base of the matrix indices is zero or one.
cusparseIndexType_t: This type indicates the index type for representing the sparse matrix indices.
cusparseMatrixType_t: This type indicates the type of matrix stored in sparse storage. Notice that for symmetric, Hermitian and triangular matrices only their lower or upper part is assumed to be stored.
cusparseOperation_t: This type indicates which operations is applied to the related input (e.g. sparse matrix, or vector).
cusparseOrder_t: This type indicates the memory layout of a dense matrix.
cusparsePointerMode_t: This type indicates whether the scalar values are passed by reference on the host or device. It is important to point out that if several scalar values are passed by reference in the function call, all of them will conform to the same single pointer mode. The pointer mode can be set and retrieved using cusparseSetPointerMode and cusparseGetPointerMode routines, respectively.
cusparseSDDMMAlg_t
cusparseSolvePolicy_tDeprecated: This type indicates whether level information is generated and used in csrsv2, csric02, csrilu02, bsrsv2, bsric02 and bsrilu02.
cusparseSpGEMMAlg_t
cusparseSpMMAlg_t
cusparseSpMMOpAlg_t
cusparseSpMVAlg_t
cusparseSpMatAttribute_t
cusparseSpSMAlg_t
cusparseSpSMUpdate_t
cusparseSpSVAlg_t
cusparseSpSVUpdate_t
cusparseSparseToDenseAlg_t
cusparseStatus_t: This data type represents the status returned by the library functions and it can have the following values.

Constants§

CUSPARSE_VERSION
CUSPARSE_VER_BUILD
CUSPARSE_VER_MAJOR
CUSPARSE_VER_MINOR
CUSPARSE_VER_PATCH

Functions§

cusparseAxpby^⚠Deprecated: The function computes the sum of a sparse vector vecX and a dense vector vecY.
cusparseBlockedEllGet^⚠: This function returns the fields of the sparse matrix descriptor spMatDescr stored in Blocked-Ellpack (ELL) format.
cusparseBsrSetStridedBatch^⚠: This function sets the batchCount and the batchStride fields of the sparse matrix descriptor spMatDescr.
cusparseCbsr2csr^⚠: This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA) into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.
cusparseCbsric02^⚠: This function performs the solve phase of the incomplete-Cholesky factorization with 0 fill-in and no pivoting.
cusparseCbsric02_analysis^⚠: This function performs the analysis phase of the incomplete-Cholesky factorization with 0 fill-in and no pivoting
cusparseCbsric02_bufferSize^⚠: This function returns the size of a buffer used in computing the incomplete-Cholesky factorization with 0 fill-in and no pivoting
cusparseCbsric02_bufferSizeExt^⚠
cusparseCbsrilu02^⚠: This function performs the solve phase of the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseCbsrilu02_analysis^⚠: This function performs the analysis phase of the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseCbsrilu02_bufferSize^⚠: This function returns the size of the buffer used in computing the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseCbsrilu02_bufferSizeExt^⚠
cusparseCbsrilu02_numericBoost^⚠: The user can use a boost value to replace a numerical value in incomplete LU factorization. Parameter tol is used to determine a numerical zero, and boost_val is used to replace a numerical zero. The behavior is as follows:
cusparseCbsrmm^⚠: This function performs one of the following matrix-matrix operations:
cusparseCbsrmv^⚠: This function performs the matrix-vector operation
cusparseCbsrsm2_analysis^⚠: This function performs the analysis phase of bsrsm2(), a new sparse triangular linear system op(A)*op(X) =$\alpha$op(B).
cusparseCbsrsm2_bufferSize^⚠: This function returns size of buffer used in bsrsm2(), a new sparse triangular linear system op(A)*op(X)=$\alpha$op(B).
cusparseCbsrsm2_bufferSizeExt^⚠
cusparseCbsrsm2_solve^⚠: This function performs the solve phase of the solution of a sparse triangular linear system:
cusparseCbsrsv2_analysis^⚠: This function performs the analysis phase of bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseCbsrsv2_bufferSize^⚠: This function returns size of the buffer used in bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseCbsrsv2_bufferSizeExt^⚠
cusparseCbsrsv2_solve^⚠: This function performs the solve phase of bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseCbsrxmv^⚠: This function performs a bsrmv and a mask operation
cusparseCcsr2bsr^⚠
cusparseCcsr2csr_compress^⚠
cusparseCcsr2csru^⚠
cusparseCcsr2gebsr^⚠: This function converts a sparse matrix A in CSR format (that is defined by arrays csrValA, csrRowPtrA, and csrColIndA) into a sparse matrix C in general BSR format (that is defined by the three arrays bsrValC, bsrRowPtrC, and bsrColIndC).
cusparseCcsr2gebsr_bufferSize^⚠
cusparseCcsr2gebsr_bufferSizeExt^⚠
cusparseCcsrcolor^⚠: This function performs the coloring of the adjacency graph associated with the matrix A stored in CSR format. The coloring is an assignment of colors (integer numbers) to nodes, such that neighboring nodes have distinct colors. An approximate coloring algorithm is used in this routine, and is stopped when a certain percentage of nodes has been colored. The rest of the nodes are assigned distinct colors (an increasing sequence of integers numbers, starting from the last integer used previously). The last two auxiliary routines can be used to extract the resulting number of colors, their assignment and the associated reordering. The reordering is such that nodes that have been assigned the same color are reordered to be next to each other.
cusparseCcsrgeam2^⚠: This function performs following matrix-matrix operation
cusparseCcsrgeam2_bufferSizeExt^⚠
cusparseCcsric02^⚠: This function performs the solve phase of the computing the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseCcsric02_analysis^⚠: This function performs the analysis phase of the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseCcsric02_bufferSize^⚠: This function returns size of buffer used in computing the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseCcsric02_bufferSizeExt^⚠
cusparseCcsrilu02^⚠: This function performs the solve phase of the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseCcsrilu02_analysis^⚠: This function performs the analysis phase of the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseCcsrilu02_bufferSize^⚠: This function returns size of the buffer used in computing the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseCcsrilu02_bufferSizeExt^⚠
cusparseCcsrilu02_numericBoost^⚠: The user can use a boost value to replace a numerical value in incomplete LU factorization. The tol is used to determine a numerical zero, and the boost_val is used to replace a numerical zero. The behavior is
cusparseCcsru2csr^⚠
cusparseCcsru2csr_bufferSizeExt^⚠
cusparseCgebsr2csr^⚠: This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA) into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.
cusparseCgebsr2gebsc^⚠: This function can be seen as the same as csr2csc() when each block of size rowBlockDim*colBlockDim is regarded as a scalar.
cusparseCgebsr2gebsc_bufferSize^⚠
cusparseCgebsr2gebsc_bufferSizeExt^⚠
cusparseCgebsr2gebsr^⚠: This function converts a sparse matrix in general BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in another general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.
cusparseCgebsr2gebsr_bufferSize^⚠
cusparseCgebsr2gebsr_bufferSizeExt^⚠
cusparseCgemvi^⚠: This function performs the matrix-vector operation
cusparseCgemvi_bufferSize^⚠
cusparseCgpsvInterleavedBatch^⚠: This function computes the solution of multiple penta-diagonal linear systems for i=0,…,batchCount:
cusparseCgpsvInterleavedBatch_bufferSizeExt^⚠
cusparseCgtsv2^⚠: This function computes the solution of a tridiagonal linear system with multiple right-hand sides:
cusparseCgtsv2StridedBatch^⚠: This function computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseCgtsv2StridedBatch_bufferSizeExt^⚠: This function returns the size of the buffer used in gtsv2StridedBatch which computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseCgtsv2_bufferSizeExt^⚠
cusparseCgtsv2_nopivot^⚠: This function computes the solution of a tridiagonal linear system with multiple right-hand sides:
cusparseCgtsv2_nopivot_bufferSizeExt^⚠: This function returns the size of the buffer used in gtsv2_nopivot which computes the solution of a tridiagonal linear system with multiple right-hand sides.
cusparseCgtsvInterleavedBatch^⚠: This function computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseCgtsvInterleavedBatch_bufferSizeExt^⚠
cusparseCnnz^⚠: This function computes the number of nonzero elements per row or column and the total number of nonzero elements in a dense matrix.
cusparseCnnz_compress^⚠: This function is the step one to convert from csr format to compressed csr format.
cusparseConstBlockedEllGet^⚠
cusparseConstCooGet^⚠
cusparseConstCscGet^⚠
cusparseConstCsrGet^⚠
cusparseConstDnMatGet^⚠
cusparseConstDnMatGetValues^⚠
cusparseConstDnVecGet^⚠
cusparseConstDnVecGetValues^⚠
cusparseConstSpMatGetValues^⚠
cusparseConstSpVecGet^⚠
cusparseConstSpVecGetValues^⚠
cusparseCooGet^⚠: This function returns the fields of the sparse matrix descriptor spMatDescr stored in COO format (Array of Structures layout).
cusparseCooSetPointers^⚠: This function sets the pointers of the sparse matrix descriptor spMatDescr.
cusparseCooSetStridedBatch^⚠: This function sets the batchCount and the batchStride fields of the sparse matrix descriptor spMatDescr.
cusparseCreate^⚠: This function initializes the cuSPARSE library and creates a handle on the cuSPARSE context. It must be called before any other cuSPARSE API function is invoked. It allocates hardware resources necessary for accessing the GPU.
cusparseCreateBlockedEll^⚠: This function initializes the sparse matrix descriptor spMatDescr for the Blocked-Ellpack (ELL) format.
cusparseCreateBsr^⚠: This function initializes the sparse matrix descriptor spMatDescr for the Block Compressed Row (BSR) format.
cusparseCreateBsric02Info^⚠Deprecated: This function creates and initializes the solve and analysis structure of block incomplete Cholesky to default values.
cusparseCreateBsrilu02Info^⚠Deprecated: This function creates and initializes the solve and analysis structure of block incomplete LU to default values.
cusparseCreateBsrsm2Info^⚠Deprecated: This function creates and initializes the solve and analysis structure of bsrsm2 to default values.
cusparseCreateBsrsv2Info^⚠Deprecated: This function creates and initializes the solve and analysis structure of bsrsv2 to default values.
cusparseCreateColorInfo^⚠Deprecated: This function creates and initializes the cusparseColorInfo_t structure to default values.
cusparseCreateConstBlockedEll^⚠
cusparseCreateConstBsr^⚠
cusparseCreateConstCoo^⚠
cusparseCreateConstCsc^⚠
cusparseCreateConstCsr^⚠
cusparseCreateConstDnMat^⚠
cusparseCreateConstDnVec^⚠
cusparseCreateConstSlicedEll^⚠
cusparseCreateConstSpVec^⚠
cusparseCreateCoo^⚠: This function initializes the sparse matrix descriptor spMatDescr in the COO format (Structure of Arrays layout).
cusparseCreateCsc^⚠: This function initializes the sparse matrix descriptor spMatDescr in the CSC format.
cusparseCreateCsr^⚠: This function initializes the sparse matrix descriptor spMatDescr in the CSR format.
cusparseCreateCsric02Info^⚠Deprecated: This function creates and initializes the solve and analysis structure of incomplete Cholesky to default values.
cusparseCreateCsrilu02Info^⚠Deprecated: This function creates and initializes the solve and analysis structure of incomplete LU to default values.
cusparseCreateCsru2csrInfo^⚠
cusparseCreateDnMat^⚠: The function initializes the dense matrix descriptor dnMatDescr.
cusparseCreateDnVec^⚠: This function initializes the dense vector descriptor dnVecDescr.
cusparseCreateIdentityPermutation^⚠Deprecated: This function creates an identity map. The output parameter p represents such map by p = 0:1:(n-1).
cusparseCreateMatDescr^⚠: This function initializes the matrix descriptor. It sets the fields MatrixType and IndexBase to the default values cusparseMatrixType_t::CUSPARSE_MATRIX_TYPE_GENERAL and cusparseIndexBase_t::CUSPARSE_INDEX_BASE_ZERO, respectively, while leaving other fields uninitialized.
cusparseCreatePruneInfo^⚠Deprecated: This function creates and initializes structure of prune to default values.
cusparseCreateSlicedEll^⚠: This function initializes the sparse matrix descriptor spMatDescr for the Sliced Ellpack (SELL) format.
cusparseCreateSpVec^⚠: This function initializes the sparse matrix descriptor spVecDescr.
cusparseCscGet^⚠: This function returns the fields of the sparse matrix descriptor spMatDescr stored in CSC format.
cusparseCscSetPointers^⚠: This function sets the pointers of the sparse matrix descriptor spMatDescr.
cusparseCsr2cscEx2^⚠: This function converts a sparse matrix in CSR format (that is defined by the three arrays csrVal, csrRowPtr, and csrColInd) into a sparse matrix in CSC format (that is defined by arrays cscVal, cscRowInd, and cscColPtr). The resulting matrix can also be seen as the transpose of the original sparse matrix. Notice that this routine can also be used to convert a matrix in CSC format into a matrix in CSR format.
cusparseCsr2cscEx2_bufferSize^⚠
cusparseCsrGet^⚠: This function returns the fields of the sparse matrix descriptor spMatDescr stored in CSR format.
cusparseCsrSetPointers^⚠: This function sets the pointers of the sparse matrix descriptor spMatDescr.
cusparseCsrSetStridedBatch^⚠: This function sets the batchCount and the batchStride fields of the sparse matrix descriptor spMatDescr.
cusparseDbsr2csr^⚠: This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA) into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.
cusparseDbsric02^⚠: This function performs the solve phase of the incomplete-Cholesky factorization with 0 fill-in and no pivoting.
cusparseDbsric02_analysis^⚠: This function performs the analysis phase of the incomplete-Cholesky factorization with 0 fill-in and no pivoting
cusparseDbsric02_bufferSize^⚠: This function returns the size of a buffer used in computing the incomplete-Cholesky factorization with 0 fill-in and no pivoting
cusparseDbsric02_bufferSizeExt^⚠
cusparseDbsrilu02^⚠: This function performs the solve phase of the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseDbsrilu02_analysis^⚠: This function performs the analysis phase of the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseDbsrilu02_bufferSize^⚠: This function returns the size of the buffer used in computing the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseDbsrilu02_bufferSizeExt^⚠
cusparseDbsrilu02_numericBoost^⚠: The user can use a boost value to replace a numerical value in incomplete LU factorization. Parameter tol is used to determine a numerical zero, and boost_val is used to replace a numerical zero. The behavior is as follows:
cusparseDbsrmm^⚠: This function performs one of the following matrix-matrix operations:
cusparseDbsrmv^⚠: This function performs the matrix-vector operation
cusparseDbsrsm2_analysis^⚠: This function performs the analysis phase of bsrsm2(), a new sparse triangular linear system op(A)*op(X) =$\alpha$op(B).
cusparseDbsrsm2_bufferSize^⚠: This function returns size of buffer used in bsrsm2(), a new sparse triangular linear system op(A)*op(X)=$\alpha$op(B).
cusparseDbsrsm2_bufferSizeExt^⚠
cusparseDbsrsm2_solve^⚠: This function performs the solve phase of the solution of a sparse triangular linear system:
cusparseDbsrsv2_analysis^⚠: This function performs the analysis phase of bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseDbsrsv2_bufferSize^⚠: This function returns size of the buffer used in bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseDbsrsv2_bufferSizeExt^⚠
cusparseDbsrsv2_solve^⚠: This function performs the solve phase of bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseDbsrxmv^⚠: This function performs a bsrmv and a mask operation
cusparseDcsr2bsr^⚠
cusparseDcsr2csr_compress^⚠
cusparseDcsr2csru^⚠
cusparseDcsr2gebsr^⚠: This function converts a sparse matrix A in CSR format (that is defined by arrays csrValA, csrRowPtrA, and csrColIndA) into a sparse matrix C in general BSR format (that is defined by the three arrays bsrValC, bsrRowPtrC, and bsrColIndC).
cusparseDcsr2gebsr_bufferSize^⚠
cusparseDcsr2gebsr_bufferSizeExt^⚠
cusparseDcsrcolor^⚠: This function performs the coloring of the adjacency graph associated with the matrix A stored in CSR format. The coloring is an assignment of colors (integer numbers) to nodes, such that neighboring nodes have distinct colors. An approximate coloring algorithm is used in this routine, and is stopped when a certain percentage of nodes has been colored. The rest of the nodes are assigned distinct colors (an increasing sequence of integers numbers, starting from the last integer used previously). The last two auxiliary routines can be used to extract the resulting number of colors, their assignment and the associated reordering. The reordering is such that nodes that have been assigned the same color are reordered to be next to each other.
cusparseDcsrgeam2^⚠: This function performs following matrix-matrix operation
cusparseDcsrgeam2_bufferSizeExt^⚠
cusparseDcsric02^⚠: This function performs the solve phase of the computing the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseDcsric02_analysis^⚠: This function performs the analysis phase of the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseDcsric02_bufferSize^⚠: This function returns size of buffer used in computing the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseDcsric02_bufferSizeExt^⚠
cusparseDcsrilu02^⚠: This function performs the solve phase of the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseDcsrilu02_analysis^⚠: This function performs the analysis phase of the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseDcsrilu02_bufferSize^⚠: This function returns size of the buffer used in computing the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseDcsrilu02_bufferSizeExt^⚠
cusparseDcsrilu02_numericBoost^⚠: The user can use a boost value to replace a numerical value in incomplete LU factorization. The tol is used to determine a numerical zero, and the boost_val is used to replace a numerical zero. The behavior is
cusparseDcsru2csr^⚠
cusparseDcsru2csr_bufferSizeExt^⚠
cusparseDenseToSparse_analysis^⚠
cusparseDenseToSparse_bufferSize^⚠
cusparseDenseToSparse_convert^⚠
cusparseDestroy^⚠: This function releases CPU-side resources used by the cuSPARSE library. The release of GPU-side resources may be deferred until the application shuts down.
cusparseDestroyBsric02Info^⚠Deprecated: This function destroys and releases any memory required by the structure.
cusparseDestroyBsrilu02Info^⚠Deprecated: This function destroys and releases any memory required by the structure.
cusparseDestroyBsrsm2Info^⚠Deprecated: This function destroys and releases any memory required by the structure.
cusparseDestroyBsrsv2Info^⚠Deprecated: This function destroys and releases any memory required by the structure.
cusparseDestroyColorInfo^⚠Deprecated: This function destroys and releases any memory required by the structure.
cusparseDestroyCsric02Info^⚠Deprecated: This function destroys and releases any memory required by the structure.
cusparseDestroyCsrilu02Info^⚠Deprecated: This function destroys and releases any memory required by the structure.
cusparseDestroyCsru2csrInfo^⚠
cusparseDestroyDnMat^⚠: This function releases the host memory allocated for the dense matrix descriptor dnMatDescr.
cusparseDestroyDnVec^⚠: This function releases the host memory allocated for the dense vector descriptor dnVecDescr.
cusparseDestroyMatDescr^⚠: This function releases the memory allocated for the matrix descriptor.
cusparseDestroyPruneInfo^⚠Deprecated: This function destroys and releases any memory required by the structure.
cusparseDestroySpMat^⚠: This function releases the host memory allocated for the sparse matrix descriptor spMatDescr.
cusparseDestroySpVec^⚠: This function releases the host memory allocated for the sparse vector descriptor spVecDescr.
cusparseDgebsr2csr^⚠: This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA) into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.
cusparseDgebsr2gebsc^⚠: This function can be seen as the same as csr2csc() when each block of size rowBlockDim*colBlockDim is regarded as a scalar.
cusparseDgebsr2gebsc_bufferSize^⚠
cusparseDgebsr2gebsc_bufferSizeExt^⚠
cusparseDgebsr2gebsr^⚠: This function converts a sparse matrix in general BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in another general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.
cusparseDgebsr2gebsr_bufferSize^⚠
cusparseDgebsr2gebsr_bufferSizeExt^⚠
cusparseDgemvi^⚠: This function performs the matrix-vector operation
cusparseDgemvi_bufferSize^⚠
cusparseDgpsvInterleavedBatch^⚠: This function computes the solution of multiple penta-diagonal linear systems for i=0,…,batchCount:
cusparseDgpsvInterleavedBatch_bufferSizeExt^⚠
cusparseDgtsv2^⚠: This function computes the solution of a tridiagonal linear system with multiple right-hand sides:
cusparseDgtsv2StridedBatch^⚠: This function computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseDgtsv2StridedBatch_bufferSizeExt^⚠: This function returns the size of the buffer used in gtsv2StridedBatch which computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseDgtsv2_bufferSizeExt^⚠
cusparseDgtsv2_nopivot^⚠: This function computes the solution of a tridiagonal linear system with multiple right-hand sides:
cusparseDgtsv2_nopivot_bufferSizeExt^⚠: This function returns the size of the buffer used in gtsv2_nopivot which computes the solution of a tridiagonal linear system with multiple right-hand sides.
cusparseDgtsvInterleavedBatch^⚠: This function computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseDgtsvInterleavedBatch_bufferSizeExt^⚠
cusparseDnMatGet^⚠: This function returns the fields of the dense matrix descriptor dnMatDescr.
cusparseDnMatGetStridedBatch^⚠: The function returns the number of batches and the batch stride of the dense matrix descriptor dnMatDescr.
cusparseDnMatGetValues^⚠: This function returns the values field of the dense matrix descriptor dnMatDescr.
cusparseDnMatSetStridedBatch^⚠: The function sets the number of batches and the batch stride of the dense matrix descriptor dnMatDescr.
cusparseDnMatSetValues^⚠: This function sets the values field of the dense matrix descriptor dnMatDescr.
cusparseDnVecGet^⚠: This function returns the fields of the dense vector descriptor dnVecDescr.
cusparseDnVecGetValues^⚠: This function returns the values field of the dense vector descriptor dnVecDescr.
cusparseDnVecSetValues^⚠: This function sets the values field of the dense vector descriptor dnVecDescr.
cusparseDnnz^⚠: This function computes the number of nonzero elements per row or column and the total number of nonzero elements in a dense matrix.
cusparseDnnz_compress^⚠: This function is the step one to convert from csr format to compressed csr format.
cusparseDpruneCsr2csr^⚠
cusparseDpruneCsr2csrByPercentage^⚠
cusparseDpruneCsr2csrByPercentage_bufferSizeExt^⚠
cusparseDpruneCsr2csrNnz^⚠
cusparseDpruneCsr2csrNnzByPercentage^⚠
cusparseDpruneCsr2csr_bufferSizeExt^⚠
cusparseDpruneDense2csr^⚠
cusparseDpruneDense2csrByPercentage^⚠
cusparseDpruneDense2csrByPercentage_bufferSizeExt^⚠
cusparseDpruneDense2csrNnz^⚠
cusparseDpruneDense2csrNnzByPercentage^⚠
cusparseDpruneDense2csr_bufferSizeExt^⚠
cusparseGather^⚠: The function gathers the elements of the dense vector vecY into the sparse vector vecX
cusparseGetErrorName^⚠: The function returns the string representation of an error code enum name. If the error code is not recognized, “unrecognized error code” is returned.
cusparseGetErrorString^⚠: Parameters
cusparseGetMatDiagType^⚠: This function returns the DiagType field of the matrix descriptor descrA.
cusparseGetMatFillMode^⚠: This function returns the FillMode field of the matrix descriptor descrA.
cusparseGetMatIndexBase^⚠: This function returns the IndexBase field of the matrix descriptor descrA.
cusparseGetMatType^⚠: This function returns the MatrixType field of the matrix descriptor descrA.
cusparseGetPointerMode^⚠: This function obtains the pointer mode used by the cuSPARSE library. Please see the section on the cusparsePointerMode_t type for more details.
cusparseGetProperty^⚠: The function returns the value of the requested property. Refer to libraryPropertyType for supported types.
cusparseGetStream^⚠: This function gets the cuSPARSE library stream, which is being used to to execute all calls to the cuSPARSE library functions. If the cuSPARSE library stream is not set, all kernels use the default NULL stream.
cusparseGetVersion^⚠: This function returns the version number of the cuSPARSE library.
cusparseLoggerForceDisable^⚠
cusparseLoggerOpenFile^⚠: Experimental: The function opens a logging output file in the given path.
cusparseLoggerSetCallback^⚠: Experimental: The function sets the logging callback function.
cusparseLoggerSetFile^⚠: Experimental: The function sets the logging output file. Note: once registered using this function call, the provided file handle must not be closed unless the function is called again to switch to a different file handle.
cusparseLoggerSetLevel^⚠: Experimental: The function sets the value of the logging level. path.
cusparseLoggerSetMask^⚠: Experimental: The function sets the value of the logging mask.
cusparseRot^⚠Deprecated: The function computes the Givens rotation matrix
cusparseSDDMM^⚠: This function performs the multiplication of matA and matB, followed by an element-wise multiplication with the sparsity pattern of matC. Formally, it performs the following operation:
cusparseSDDMM_bufferSize^⚠
cusparseSDDMM_preprocess^⚠
cusparseSbsr2csr^⚠: This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA) into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.
cusparseSbsric02^⚠: This function performs the solve phase of the incomplete-Cholesky factorization with 0 fill-in and no pivoting.
cusparseSbsric02_analysis^⚠: This function performs the analysis phase of the incomplete-Cholesky factorization with 0 fill-in and no pivoting
cusparseSbsric02_bufferSize^⚠: This function returns the size of a buffer used in computing the incomplete-Cholesky factorization with 0 fill-in and no pivoting
cusparseSbsric02_bufferSizeExt^⚠
cusparseSbsrilu02^⚠: This function performs the solve phase of the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseSbsrilu02_analysis^⚠: This function performs the analysis phase of the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseSbsrilu02_bufferSize^⚠: This function returns the size of the buffer used in computing the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseSbsrilu02_bufferSizeExt^⚠
cusparseSbsrilu02_numericBoost^⚠: The user can use a boost value to replace a numerical value in incomplete LU factorization. Parameter tol is used to determine a numerical zero, and boost_val is used to replace a numerical zero. The behavior is as follows:
cusparseSbsrmm^⚠: This function performs one of the following matrix-matrix operations:
cusparseSbsrmv^⚠: This function performs the matrix-vector operation
cusparseSbsrsm2_analysis^⚠: This function performs the analysis phase of bsrsm2(), a new sparse triangular linear system op(A)*op(X) =$\alpha$op(B).
cusparseSbsrsm2_bufferSize^⚠: This function returns size of buffer used in bsrsm2(), a new sparse triangular linear system op(A)*op(X)=$\alpha$op(B).
cusparseSbsrsm2_bufferSizeExt^⚠
cusparseSbsrsm2_solve^⚠: This function performs the solve phase of the solution of a sparse triangular linear system:
cusparseSbsrsv2_analysis^⚠: This function performs the analysis phase of bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseSbsrsv2_bufferSize^⚠: This function returns size of the buffer used in bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseSbsrsv2_bufferSizeExt^⚠
cusparseSbsrsv2_solve^⚠: This function performs the solve phase of bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseSbsrxmv^⚠: This function performs a bsrmv and a mask operation
cusparseScatter^⚠: The function scatters the elements of the sparse vector vecX into the dense vector vecY
cusparseScsr2bsr^⚠
cusparseScsr2csr_compress^⚠
cusparseScsr2csru^⚠
cusparseScsr2gebsr^⚠: This function converts a sparse matrix A in CSR format (that is defined by arrays csrValA, csrRowPtrA, and csrColIndA) into a sparse matrix C in general BSR format (that is defined by the three arrays bsrValC, bsrRowPtrC, and bsrColIndC).
cusparseScsr2gebsr_bufferSize^⚠
cusparseScsr2gebsr_bufferSizeExt^⚠
cusparseScsrcolor^⚠: This function performs the coloring of the adjacency graph associated with the matrix A stored in CSR format. The coloring is an assignment of colors (integer numbers) to nodes, such that neighboring nodes have distinct colors. An approximate coloring algorithm is used in this routine, and is stopped when a certain percentage of nodes has been colored. The rest of the nodes are assigned distinct colors (an increasing sequence of integers numbers, starting from the last integer used previously). The last two auxiliary routines can be used to extract the resulting number of colors, their assignment and the associated reordering. The reordering is such that nodes that have been assigned the same color are reordered to be next to each other.
cusparseScsrgeam2^⚠: This function performs following matrix-matrix operation
cusparseScsrgeam2_bufferSizeExt^⚠
cusparseScsric02^⚠: This function performs the solve phase of the computing the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseScsric02_analysis^⚠: This function performs the analysis phase of the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseScsric02_bufferSize^⚠: This function returns size of buffer used in computing the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseScsric02_bufferSizeExt^⚠
cusparseScsrilu02^⚠: This function performs the solve phase of the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseScsrilu02_analysis^⚠: This function performs the analysis phase of the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseScsrilu02_bufferSize^⚠: This function returns size of the buffer used in computing the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseScsrilu02_bufferSizeExt^⚠
cusparseScsrilu02_numericBoost^⚠: The user can use a boost value to replace a numerical value in incomplete LU factorization. The tol is used to determine a numerical zero, and the boost_val is used to replace a numerical zero. The behavior is
cusparseScsru2csr^⚠
cusparseScsru2csr_bufferSizeExt^⚠
cusparseSetMatDiagType^⚠: This function sets the DiagType field of the matrix descriptor descrA.
cusparseSetMatFillMode^⚠: This function sets the FillMode field of the matrix descriptor descrA.
cusparseSetMatIndexBase^⚠: This function sets the IndexBase field of the matrix descriptor descrA.
cusparseSetMatType^⚠: This function sets the MatrixType field of the matrix descriptor descrA.
cusparseSetPointerMode^⚠: This function sets the pointer mode used by the cuSPARSE library. The default is for the values to be passed by reference on the host. Please see the section on the cublasPointerMode_t type for more details.
cusparseSetStream^⚠: This function sets the stream to be used by the cuSPARSE library to execute its routines.
cusparseSgebsr2csr^⚠: This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA) into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.
cusparseSgebsr2gebsc^⚠: This function can be seen as the same as csr2csc() when each block of size rowBlockDim*colBlockDim is regarded as a scalar.
cusparseSgebsr2gebsc_bufferSize^⚠
cusparseSgebsr2gebsc_bufferSizeExt^⚠
cusparseSgebsr2gebsr^⚠: This function converts a sparse matrix in general BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in another general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.
cusparseSgebsr2gebsr_bufferSize^⚠
cusparseSgebsr2gebsr_bufferSizeExt^⚠
cusparseSgemvi^⚠: This function performs the matrix-vector operation
cusparseSgemvi_bufferSize^⚠
cusparseSgpsvInterleavedBatch^⚠: This function computes the solution of multiple penta-diagonal linear systems for i=0,…,batchCount:
cusparseSgpsvInterleavedBatch_bufferSizeExt^⚠
cusparseSgtsv2^⚠: This function computes the solution of a tridiagonal linear system with multiple right-hand sides:
cusparseSgtsv2StridedBatch^⚠: This function computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseSgtsv2StridedBatch_bufferSizeExt^⚠: This function returns the size of the buffer used in gtsv2StridedBatch which computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseSgtsv2_bufferSizeExt^⚠
cusparseSgtsv2_nopivot^⚠: This function computes the solution of a tridiagonal linear system with multiple right-hand sides:
cusparseSgtsv2_nopivot_bufferSizeExt^⚠: This function returns the size of the buffer used in gtsv2_nopivot which computes the solution of a tridiagonal linear system with multiple right-hand sides.
cusparseSgtsvInterleavedBatch^⚠: This function computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseSgtsvInterleavedBatch_bufferSizeExt^⚠
cusparseSnnz^⚠: This function computes the number of nonzero elements per row or column and the total number of nonzero elements in a dense matrix.
cusparseSnnz_compress^⚠: This function is the step one to convert from csr format to compressed csr format.
cusparseSpGEMM_compute^⚠
cusparseSpGEMM_copy^⚠
cusparseSpGEMM_createDescr^⚠
cusparseSpGEMM_destroyDescr^⚠
cusparseSpGEMM_estimateMemory^⚠
cusparseSpGEMM_getNumProducts^⚠
cusparseSpGEMM_workEstimation^⚠
cusparseSpGEMMreuse_compute^⚠
cusparseSpGEMMreuse_copy^⚠
cusparseSpGEMMreuse_nnz^⚠: This function computes the number of nonzero elements per row or column and the total number of nonzero elements in a dense matrix.
cusparseSpGEMMreuse_workEstimation^⚠
cusparseSpMM^⚠: The function performs the multiplication of a sparse matrix matA and a dense matrix matB.
cusparseSpMMOp^⚠: NOTE 1: NVRTC and nvJitLink are not currently available on Arm64 Android platforms.
cusparseSpMMOp_createPlan^⚠
cusparseSpMMOp_destroyPlan^⚠
cusparseSpMM_bufferSize^⚠
cusparseSpMM_preprocess^⚠
cusparseSpMV^⚠: This function performs the multiplication of a sparse matrix matA and a dense vector vecX
cusparseSpMV_bufferSize^⚠
cusparseSpMV_preprocess^⚠
cusparseSpMatGetAttribute^⚠: The function gets the attributes of the sparse matrix descriptor spMatDescr.
cusparseSpMatGetFormat^⚠: This function returns the format field of the sparse matrix descriptor spMatDescr.
cusparseSpMatGetIndexBase^⚠: This function returns the idxBase field of the sparse matrix descriptor spMatDescr.
cusparseSpMatGetSize^⚠: This function returns the sizes of the sparse matrix spMatDescr.
cusparseSpMatGetStridedBatch^⚠: This function returns the batchCount field of the sparse matrix descriptor spMatDescr.
cusparseSpMatGetValues^⚠: This function returns the values field of the sparse matrix descriptor spMatDescr.
cusparseSpMatSetAttribute^⚠: The function sets the attributes of the sparse matrix descriptor spMatDescr
cusparseSpMatSetValues^⚠: This function sets the values field of the sparse matrix descriptor spMatDescr.
cusparseSpSM_analysis^⚠
cusparseSpSM_bufferSize^⚠
cusparseSpSM_createDescr^⚠
cusparseSpSM_destroyDescr^⚠
cusparseSpSM_solve^⚠
cusparseSpSM_updateMatrix^⚠
cusparseSpSV_analysis^⚠
cusparseSpSV_bufferSize^⚠
cusparseSpSV_createDescr^⚠
cusparseSpSV_destroyDescr^⚠
cusparseSpSV_solve^⚠
cusparseSpSV_updateMatrix^⚠
cusparseSpVV^⚠Deprecated: The function computes the inner dot product of a sparse vector vecX and a dense vector vecY
cusparseSpVV_bufferSize^⚠
cusparseSpVecGet^⚠: This function returns the fields of the sparse vector descriptor spVecDescr.
cusparseSpVecGetIndexBase^⚠: This function returns the idxBase field of the sparse vector descriptor spVecDescr.
cusparseSpVecGetValues^⚠: This function returns the values field of the sparse vector descriptor spVecDescr.
cusparseSpVecSetValues^⚠: This function sets the values field of the sparse vector descriptor spVecDescr.
cusparseSparseToDense^⚠: The function converts the sparse matrix matA in CSR, CSC, or COO format into its dense representation matB. Blocked-ELL is not currently supported.
cusparseSparseToDense_bufferSize^⚠
cusparseSpruneCsr2csr^⚠
cusparseSpruneCsr2csrByPercentage^⚠
cusparseSpruneCsr2csrByPercentage_bufferSizeExt^⚠
cusparseSpruneCsr2csrNnz^⚠
cusparseSpruneCsr2csrNnzByPercentage^⚠
cusparseSpruneCsr2csr_bufferSizeExt^⚠
cusparseSpruneDense2csr^⚠
cusparseSpruneDense2csrByPercentage^⚠
cusparseSpruneDense2csrByPercentage_bufferSizeExt^⚠
cusparseSpruneDense2csrNnz^⚠
cusparseSpruneDense2csrNnzByPercentage^⚠
cusparseSpruneDense2csr_bufferSizeExt^⚠
cusparseXbsric02_zeroPivot^⚠Deprecated: If the returned error code is cusparseStatus_t::CUSPARSE_STATUS_ZERO_PIVOT, position=j means A(j,j) has either a structural zero or a numerical zero (the block is not positive definite). Otherwise position=-1.
cusparseXbsrilu02_zeroPivot^⚠Deprecated: If the returned error code is cusparseStatus_t::CUSPARSE_STATUS_ZERO_PIVOT, position=j means A(j,j) has either a structural zero or a numerical zero (the block is not invertible). Otherwise position=-1.
cusparseXbsrsm2_zeroPivot^⚠Deprecated: If the returned error code is cusparseStatus_t::CUSPARSE_STATUS_ZERO_PIVOT, position=j means A(j,j) is either a structural zero or a numerical zero (singular block). Otherwise position=-1.
cusparseXbsrsv2_zeroPivot^⚠Deprecated: If the returned error code is cusparseStatus_t::CUSPARSE_STATUS_ZERO_PIVOT, position=j means A(j,j) is either structural zero or numerical zero (singular block). Otherwise position=-1.
cusparseXcoo2csr^⚠: This function converts the array containing the uncompressed row indices (corresponding to COO format) into an array of compressed row pointers (corresponding to CSR format).
cusparseXcoosortByColumn^⚠
cusparseXcoosortByRow^⚠
cusparseXcoosort_bufferSizeExt^⚠
cusparseXcscsort^⚠: This function sorts CSC format. The stable sorting is in-place.
cusparseXcscsort_bufferSizeExt^⚠
cusparseXcsr2bsrNnz^⚠
cusparseXcsr2coo^⚠: This function converts the array containing the compressed row pointers (corresponding to CSR format) into an array of uncompressed row indices (corresponding to COO format).
cusparseXcsr2gebsrNnz^⚠
cusparseXcsrgeam2Nnz^⚠
cusparseXcsric02_zeroPivot^⚠Deprecated: If the returned error code is cusparseStatus_t::CUSPARSE_STATUS_ZERO_PIVOT, position=j means A(j,j) has either a structural zero or a numerical zero; otherwise, position=-1.
cusparseXcsrilu02_zeroPivot^⚠Deprecated: If the returned error code is cusparseStatus_t::CUSPARSE_STATUS_ZERO_PIVOT, position=j means A(j,j) has either a structural zero or a numerical zero; otherwise, position=-1.
cusparseXcsrsort^⚠: This function sorts CSR format. The stable sorting is in-place.
cusparseXcsrsort_bufferSizeExt^⚠
cusparseXgebsr2csr^⚠: This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA) into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.
cusparseXgebsr2gebsrNnz^⚠
cusparseZbsr2csr^⚠: This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA) into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.
cusparseZbsric02^⚠: This function performs the solve phase of the incomplete-Cholesky factorization with 0 fill-in and no pivoting.
cusparseZbsric02_analysis^⚠: This function performs the analysis phase of the incomplete-Cholesky factorization with 0 fill-in and no pivoting
cusparseZbsric02_bufferSize^⚠: This function returns the size of a buffer used in computing the incomplete-Cholesky factorization with 0 fill-in and no pivoting
cusparseZbsric02_bufferSizeExt^⚠
cusparseZbsrilu02^⚠: This function performs the solve phase of the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseZbsrilu02_analysis^⚠: This function performs the analysis phase of the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseZbsrilu02_bufferSize^⚠: This function returns the size of the buffer used in computing the incomplete-LU factorization with 0 fill-in and no pivoting.
cusparseZbsrilu02_bufferSizeExt^⚠
cusparseZbsrilu02_numericBoost^⚠: The user can use a boost value to replace a numerical value in incomplete LU factorization. Parameter tol is used to determine a numerical zero, and boost_val is used to replace a numerical zero. The behavior is as follows:
cusparseZbsrmm^⚠: This function performs one of the following matrix-matrix operations:
cusparseZbsrmv^⚠: This function performs the matrix-vector operation
cusparseZbsrsm2_analysis^⚠: This function performs the analysis phase of bsrsm2(), a new sparse triangular linear system op(A)*op(X) =$\alpha$op(B).
cusparseZbsrsm2_bufferSize^⚠: This function returns size of buffer used in bsrsm2(), a new sparse triangular linear system op(A)*op(X)=$\alpha$op(B).
cusparseZbsrsm2_bufferSizeExt^⚠
cusparseZbsrsm2_solve^⚠: This function performs the solve phase of the solution of a sparse triangular linear system:
cusparseZbsrsv2_analysis^⚠: This function performs the analysis phase of bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseZbsrsv2_bufferSize^⚠: This function returns size of the buffer used in bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseZbsrsv2_bufferSizeExt^⚠
cusparseZbsrsv2_solve^⚠: This function performs the solve phase of bsrsv2, a new sparse triangular linear system op(A)*y =$\alpha$x.
cusparseZbsrxmv^⚠: This function performs a bsrmv and a mask operation
cusparseZcsr2bsr^⚠
cusparseZcsr2csr_compress^⚠
cusparseZcsr2csru^⚠
cusparseZcsr2gebsr^⚠: This function converts a sparse matrix A in CSR format (that is defined by arrays csrValA, csrRowPtrA, and csrColIndA) into a sparse matrix C in general BSR format (that is defined by the three arrays bsrValC, bsrRowPtrC, and bsrColIndC).
cusparseZcsr2gebsr_bufferSize^⚠
cusparseZcsr2gebsr_bufferSizeExt^⚠
cusparseZcsrcolor^⚠: This function performs the coloring of the adjacency graph associated with the matrix A stored in CSR format. The coloring is an assignment of colors (integer numbers) to nodes, such that neighboring nodes have distinct colors. An approximate coloring algorithm is used in this routine, and is stopped when a certain percentage of nodes has been colored. The rest of the nodes are assigned distinct colors (an increasing sequence of integers numbers, starting from the last integer used previously). The last two auxiliary routines can be used to extract the resulting number of colors, their assignment and the associated reordering. The reordering is such that nodes that have been assigned the same color are reordered to be next to each other.
cusparseZcsrgeam2^⚠: This function performs following matrix-matrix operation
cusparseZcsrgeam2_bufferSizeExt^⚠
cusparseZcsric02^⚠: This function performs the solve phase of the computing the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseZcsric02_analysis^⚠: This function performs the analysis phase of the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseZcsric02_bufferSize^⚠: This function returns size of buffer used in computing the incomplete-Cholesky factorization with $0$ fill-in and no pivoting:
cusparseZcsric02_bufferSizeExt^⚠
cusparseZcsrilu02^⚠: This function performs the solve phase of the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseZcsrilu02_analysis^⚠: This function performs the analysis phase of the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseZcsrilu02_bufferSize^⚠: This function returns size of the buffer used in computing the incomplete-LU factorization with $0$ fill-in and no pivoting:
cusparseZcsrilu02_bufferSizeExt^⚠
cusparseZcsrilu02_numericBoost^⚠: The user can use a boost value to replace a numerical value in incomplete LU factorization. The tol is used to determine a numerical zero, and the boost_val is used to replace a numerical zero. The behavior is
cusparseZcsru2csr^⚠
cusparseZcsru2csr_bufferSizeExt^⚠
cusparseZgebsr2csr^⚠: This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA) into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.
cusparseZgebsr2gebsc^⚠: This function can be seen as the same as csr2csc() when each block of size rowBlockDim*colBlockDim is regarded as a scalar.
cusparseZgebsr2gebsc_bufferSize^⚠
cusparseZgebsr2gebsc_bufferSizeExt^⚠
cusparseZgebsr2gebsr^⚠: This function converts a sparse matrix in general BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in another general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.
cusparseZgebsr2gebsr_bufferSize^⚠
cusparseZgebsr2gebsr_bufferSizeExt^⚠
cusparseZgemvi^⚠: This function performs the matrix-vector operation
cusparseZgemvi_bufferSize^⚠
cusparseZgpsvInterleavedBatch^⚠: This function computes the solution of multiple penta-diagonal linear systems for i=0,…,batchCount:
cusparseZgpsvInterleavedBatch_bufferSizeExt^⚠
cusparseZgtsv2^⚠: This function computes the solution of a tridiagonal linear system with multiple right-hand sides:
cusparseZgtsv2StridedBatch^⚠: This function computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseZgtsv2StridedBatch_bufferSizeExt^⚠: This function returns the size of the buffer used in gtsv2StridedBatch which computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseZgtsv2_bufferSizeExt^⚠
cusparseZgtsv2_nopivot^⚠: This function computes the solution of a tridiagonal linear system with multiple right-hand sides:
cusparseZgtsv2_nopivot_bufferSizeExt^⚠: This function returns the size of the buffer used in gtsv2_nopivot which computes the solution of a tridiagonal linear system with multiple right-hand sides.
cusparseZgtsvInterleavedBatch^⚠: This function computes the solution of multiple tridiagonal linear systems for i=0,…,batchCount:
cusparseZgtsvInterleavedBatch_bufferSizeExt^⚠
cusparseZnnz^⚠: This function computes the number of nonzero elements per row or column and the total number of nonzero elements in a dense matrix.
cusparseZnnz_compress^⚠: This function is the step one to convert from csr format to compressed csr format.

Type Aliases§

FILE
_IO_lock_t
__off64_t
__off_t
__uint64_t
bsric02Info_t
bsrilu02Info_t
bsrsm2Info_t
bsrsv2Info_t
csric02Info_t
csrilu02Info_t
csru2csrInfo_t
cuComplex
cuDoubleComplex
cuFloatComplex
cusparseColorInfo_tDeprecated: This is a pointer type to an opaque structure holding the information used in csrcolor().
cusparseConstDnMatDescr_t
cusparseConstDnVecDescr_t
cusparseConstSpMatDescr_t
cusparseConstSpVecDescr_t
cusparseDnMatDescr_t
cusparseDnVecDescr_t
cusparseHandle_t: This is a pointer type to an opaque cuSPARSE context, which the user must initialize by calling prior to calling cusparseCreate any other library function. The handle created and returned by cusparseCreate must be passed to every cuSPARSE function.
cusparseLoggerCallback_t
cusparseMatDescr_t: This structure is used to describe the shape and properties of a matrix.
cusparseSpGEMMDescr_t
cusparseSpMMOpPlan_t
cusparseSpMatDescr_t
cusparseSpSMDescr_t
cusparseSpSVDescr_t
cusparseSpVecDescr_t
pruneInfo_t
size_t

Crate singe_cusparse_sys

Crate singe_cusparse_sys Copy item path

Structs§

Enums§

Constants§

Functions§

Type Aliases§

Crate singe_cusparse_sys