 |
clSPARSE
v0.10.0.0
a software library containing Sparse functions written in OpenCL
|
|
clSPARSE
v0.10.0.0
a software library containing Sparse functions written in OpenCL
|
clSPARSE.h defines 'C' compatible callable functions and types that call into the library More...
Go to the source code of this file.
Classes | |
| struct | clsparseCreateResult |
| A structure returned by value from the clsparseCreateControl function. This serves as result/status pair for the creation operation. More... | |
| struct | clsparseEventResult |
| A structure returned by value from the clsparseGetEvent function. This serves as result/status pair for the creation operation. More... | |
| struct | clsparseCreateSolverResult |
| A structure returned by value from the clsparseCreateSolverControl function. This serves as result/status pair for the creation operation. More... | |
| struct | clsparseMetaSizeResult |
| A structure returned by value from the clsparseCsrMetaSize function. This serves as a result/status pair for the size of the meta data associated with a sparse matrix. More... | |
Typedefs | |
| typedef struct _clsparseControl * | clsparseControl |
| clsparseControl keeps OpenCL state like kernel execution, memory allocation and synchronization behavior More... | |
Enumerations | |
| enum | clsparseStatus { clsparseSuccess = CL_SUCCESS, clsparseInvalidValue = CL_INVALID_VALUE, clsparseInvalidCommandQueue = CL_INVALID_COMMAND_QUEUE, clsparseInvalidContext = CL_INVALID_CONTEXT, clsparseInvalidMemObject = CL_INVALID_MEM_OBJECT, clsparseInvalidDevice = CL_INVALID_DEVICE, clsparseInvalidEventWaitList = CL_INVALID_EVENT_WAIT_LIST, clsparseInvalidEvent = CL_INVALID_EVENT, clsparseOutOfResources = CL_OUT_OF_RESOURCES, clsparseOutOfHostMemory = CL_OUT_OF_HOST_MEMORY, clsparseInvalidOperation = CL_INVALID_OPERATION, clsparseCompilerNotAvailable = CL_COMPILER_NOT_AVAILABLE, clsparseBuildProgramFailure = CL_BUILD_PROGRAM_FAILURE, clsparseInvalidKernelArgs = CL_INVALID_KERNEL_ARGS, clsparseNotImplemented = -1024, clsparseNotInitialized, clsparseStructInvalid, clsparseInvalidSize, clsparseInvalidMemObj, clsparseInsufficientMemory, clsparseInvalidControlObject, clsparseInvalidFile, clsparseInvalidFileFormat, clsparseInvalidKernelExecution, clsparseInvalidType, clsparseInvalidSolverControlObject = -2048, clsparseInvalidSystemSize, clsparseIterationsExceeded, clsparseToleranceNotReached, clsparseSolverError } |
| Building for OpenCL version is a compile time decision. More... | |
Functions | |
| CLSPARSE_EXPORT clsparseStatus | clsparseInitScalar (clsparseScalar *scalar) |
| Initialize a scalar structure to be used in the clsparse library. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseInitVector (cldenseVector *vec) |
| Initialize a dense vector structure to be used in the clsparse library. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseInitCooMatrix (clsparseCooMatrix *cooMatx) |
| Initialize a sparse matrix COO structure to be used in the clsparse library. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseInitCsrMatrix (clsparseCsrMatrix *csrMatx) |
| Initialize a sparse matrix CSR structure to be used in the clsparse library. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseInitMatrix (cldenseMatrix *denseMatx) |
| Initialize a dense matrix structure to be used in the clsparse library. More... | |
| CLSPARSE_EXPORT clsparseCreateResult | clsparseCreateControl (cl_command_queue queue) |
| Setup the clsparse control object from external OpenCL queue. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseEnableAsync (clsparseControl control, cl_bool async) |
| Enable/Disable asynchronous behavior for clSPARSE. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseEnableExtendedPrecision (clsparseControl control, cl_bool extPrecision) |
| Enable/Disable the use of compensated summation. More... | |
| CLSPARSE_EXPORT clsparseEventResult | clsparseGetEvent (clsparseControl control) |
| Return an event from the last kernel execution. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseReleaseControl (clsparseControl control) |
| Sets internal control fields to 0 or Null and frees allocated structures. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseHeaderfromFile (clsparseIdx_t *nnz, clsparseIdx_t *row, clsparseIdx_t *col, const char *filePath) |
| Read the sparse matrix header from file. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseSCooMatrixfromFile (clsparseCooMatrix *cooMatx, const char *filePath, clsparseControl control, cl_bool read_explicit_zeroes) |
| Read sparse matrix data from file in single precision COO format. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseDCooMatrixfromFile (clsparseCooMatrix *cooMatx, const char *filePath, clsparseControl control, cl_bool read_explicit_zeroes) |
| Read sparse matrix data from file in double precision COO format. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseSCsrMatrixfromFile (clsparseCsrMatrix *csrMatx, const char *filePath, clsparseControl control, cl_bool read_explicit_zeroes) |
| Read sparse matrix data from file in single precision CSR format. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseDCsrMatrixfromFile (clsparseCsrMatrix *csrMatx, const char *filePath, clsparseControl control, cl_bool read_explicit_zeroes) |
| Read sparse matrix data from file in double precision CSR format. More... | |
| CLSPARSE_EXPORT clsparseMetaSizeResult | clsparseCsrMetaSize (clsparseCsrMatrix *csrMatx, clsparseControl control) |
| Calculate the amount of device memory required to hold meta-data for csr-adaptive SpM-dV algorithm. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseCsrMetaCreate (clsparseCsrMatrix *csrMatx, clsparseControl control) |
| Allocate memory and calculate the meta-data for csr-adaptive SpM-dV algorithm. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseCsrMetaDelete (clsparseCsrMatrix *csrMatx) |
| Delete meta data associated with a CSR encoded matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseScsrmm (const clsparseScalar *alpha, const clsparseCsrMatrix *sparseMatA, const cldenseMatrix *denseMatB, const clsparseScalar *beta, cldenseMatrix *denseMatC, const clsparseControl control) |
| Single precision CSR sparse matrix times dense matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseDcsrmm (const clsparseScalar *alpha, const clsparseCsrMatrix *sparseMatA, const cldenseMatrix *denseMatB, const clsparseScalar *beta, cldenseMatrix *denseMatC, const clsparseControl control) |
| Double precision CSR sparse matrix times dense matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseScsrSpGemm (const clsparseCsrMatrix *sparseMatA, const clsparseCsrMatrix *sparseMatB, clsparseCsrMatrix *sparseMatC, const clsparseControl control) |
| Single Precision CSR Sparse Matrix times Sparse Matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseScsr2coo (const clsparseCsrMatrix *csr, clsparseCooMatrix *coo, const clsparseControl control) |
| Convert a single precision CSR encoded sparse matrix into a COO encoded sparse matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseDcsr2coo (const clsparseCsrMatrix *csr, clsparseCooMatrix *coo, const clsparseControl control) |
| Convert a double precision CSR encoded sparse matrix into a COO encoded sparse matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseScoo2csr (const clsparseCooMatrix *coo, clsparseCsrMatrix *csr, const clsparseControl control) |
| Convert a single precision COO encoded sparse matrix into a CSR encoded sparse matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseDcoo2csr (const clsparseCooMatrix *coo, clsparseCsrMatrix *csr, const clsparseControl control) |
| Convert a double precision COO encoded sparse matrix into a CSR encoded sparse matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseScsr2dense (const clsparseCsrMatrix *csr, cldenseMatrix *A, const clsparseControl control) |
| Convert a single precision CSR encoded sparse matrix into a dense matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseDcsr2dense (const clsparseCsrMatrix *csr, cldenseMatrix *A, clsparseControl control) |
| Convert a double precision CSR encoded sparse matrix into a dense matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseSdense2csr (const cldenseMatrix *A, clsparseCsrMatrix *csr, const clsparseControl control) |
| Convert a single precision dense matrix into a CSR encoded sparse matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseDdense2csr (const cldenseMatrix *A, clsparseCsrMatrix *csr, const clsparseControl control) |
| Convert a double precision dense matrix into a CSR encoded sparse matrix. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseSetup (void) |
| Initialize the clsparse library. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseTeardown (void) |
| Finalize the usage of the clsparse library Frees all state allocated by the clsparse runtime and other internal data. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseGetVersion (cl_uint *major, cl_uint *minor, cl_uint *patch, cl_uint *tweak) |
| Query for the runtime clsparse library version info. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseSscale (cldenseVector *r, const clsparseScalar *alpha, const cldenseVector *y, const clsparseControl control) |
| Single precision scale dense vector by a scalar. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseDscale (cldenseVector *r, const clsparseScalar *alpha, const cldenseVector *y, const clsparseControl control) |
| Double precision scale dense vector by a scalar. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseSaxpy (cldenseVector *r, const clsparseScalar *alpha, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Single precision scale dense vector and add dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseDaxpy (cldenseVector *r, const clsparseScalar *alpha, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Double precision scale dense vector and add dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseSaxpby (cldenseVector *r, const clsparseScalar *alpha, const cldenseVector *x, const clsparseScalar *beta, const cldenseVector *y, const clsparseControl control) |
| Single precision scale dense vector and add scaled dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseDaxpby (cldenseVector *r, const clsparseScalar *alpha, const cldenseVector *x, const clsparseScalar *beta, const cldenseVector *y, const clsparseControl control) |
| Double precision scale dense vector and add scaled dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseIreduce (clsparseScalar *s, const cldenseVector *x, const clsparseControl control) |
| Reduce integer elements of a dense vector into a scalar value. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseSreduce (clsparseScalar *s, const cldenseVector *x, const clsparseControl control) |
| Reduce single precision elements of a dense vector into a scalar value. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseDreduce (clsparseScalar *s, const cldenseVector *x, const clsparseControl control) |
| Reduce double precision elements of a dense vector into a scalar value. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseSnrm1 (clsparseScalar *s, const cldenseVector *x, const clsparseControl control) |
| Calculate the single precision L1 norm of a dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseDnrm1 (clsparseScalar *s, const cldenseVector *x, const clsparseControl control) |
| Calculate the double precision L1 norm of a dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseSnrm2 (clsparseScalar *s, const cldenseVector *x, const clsparseControl control) |
| Calculate the single precision L2 norm of a dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseDnrm2 (clsparseScalar *s, const cldenseVector *x, const clsparseControl control) |
| Calculate the double precision L2 norm of a dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseSdot (clsparseScalar *r, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Calculates the single precision dot-product of a dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseDdot (clsparseScalar *r, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Calculates the double precision dot-product of a dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseSadd (cldenseVector *r, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Element-wise single precision addition of two dense vectors. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseDadd (cldenseVector *r, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Element-wise double precision addition of two dense vectors. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseSsub (cldenseVector *r, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Element-wise single precision subtraction of two dense vectors. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseDsub (cldenseVector *r, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Element-wise double precision subtraction of two dense vectors. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseSmul (cldenseVector *r, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Element-wise single precision multiplication of two dense vectors. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseDmul (cldenseVector *r, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Element-wise double precision multiplication of two dense vectors. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseSdiv (cldenseVector *r, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Element-wise single precision division of two dense vectors. More... | |
| CLSPARSE_EXPORT clsparseStatus | cldenseDdiv (cldenseVector *r, const cldenseVector *x, const cldenseVector *y, const clsparseControl control) |
| Element-wise double precision division of two dense vectors. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseScsrmv (const clsparseScalar *alpha, const clsparseCsrMatrix *matx, const cldenseVector *x, const clsparseScalar *beta, cldenseVector *y, const clsparseControl control) |
| Single precision CSR sparse matrix times dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseDcsrmv (const clsparseScalar *alpha, const clsparseCsrMatrix *matx, const cldenseVector *x, const clsparseScalar *beta, cldenseVector *y, const clsparseControl control) |
| Double precision CSR sparse matrix times dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseScoomv (const clsparseScalar *alpha, const clsparseCooMatrix *matx, const cldenseVector *x, const clsparseScalar *beta, cldenseVector *y, const clsparseControl control) |
| Single precision COO sparse matrix times dense vector. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseDcoomv (const clsparseScalar *alpha, const clsparseCooMatrix *matx, const cldenseVector *x, const clsparseScalar *beta, cldenseVector *y, const clsparseControl control) |
| Double precision COO sparse matrix times dense vector. More... | |
| enum | PRINT_MODE { QUIET = 0, NORMAL, VERBOSE } |
| Enumeration to control the verbosity of the sparse iterative solver routines. VERBOSE will print helpful diagnostic messages to console. | |
| enum | PRECONDITIONER { NOPRECOND = 0, DIAGONAL } |
| Enumeration to select the preconditioning algorithm used to precondition the sparse data before the iterative solver execution phase. | |
| typedef struct _solverControl * | clSParseSolverControl |
| clSParseSolverControl keeps state relevant for OpenCL operations like kernel execution, memory allocation and synchronization behavior, specifically for sparse iterative solvers | |
| CLSPARSE_EXPORT clsparseCreateSolverResult | clsparseCreateSolverControl (PRECONDITIONER precond, cl_int maxIters, cl_double relTol, cl_double absTol) |
| Create a clSParseSolverControl object to control clsparse iterative solver operations. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseReleaseSolverControl (clSParseSolverControl solverControl) |
| Release a clSParseSolverControl object created with clsparseCreateSolverControl. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseSetSolverParams (clSParseSolverControl solverControl, PRECONDITIONER precond, cl_int maxIters, cl_double relTol, cl_double absTol) |
| Set clSParseSolverControl state. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseSolverPrintMode (clSParseSolverControl solverControl, PRINT_MODE mode) |
| Set the verbosity level of the clSParseSolverControl object. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseScsrcg (cldenseVector *x, const clsparseCsrMatrix *A, const cldenseVector *b, clSParseSolverControl solverControl, clsparseControl control) |
| Execute a single precision Conjugate Gradients solver. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseDcsrcg (cldenseVector *x, const clsparseCsrMatrix *A, const cldenseVector *b, clSParseSolverControl solverControl, clsparseControl control) |
| Execute a double precision Conjugate Gradients solver. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseScsrbicgStab (cldenseVector *x, const clsparseCsrMatrix *A, const cldenseVector *b, clSParseSolverControl solverControl, clsparseControl control) |
| Execute a single precision Bi-Conjugate Gradients Stabilized solver. More... | |
| CLSPARSE_EXPORT clsparseStatus | clsparseDcsrbicgStab (cldenseVector *x, const clsparseCsrMatrix *A, const cldenseVector *b, clSParseSolverControl solverControl, clsparseControl control) |
| Execute a double precision Bi-Conjugate Gradients Stabilized solver. More... | |
clSPARSE.h defines 'C' compatible callable functions and types that call into the library
| enum clsparseStatus |
Building for OpenCL version is a compile time decision.
Possible error code values that can be returned from clSPARSE API's
1.8.10
