GBMV - General banded matrix-vector multiplication

Functions
clblasStatus	clblasSgbmv (clblasOrder order, clblasTranspose trans, size_t M, size_t N, size_t KL, size_t KU, cl_float alpha, const cl_mem A, size_t offa, size_t lda, const cl_mem X, size_t offx, int incx, cl_float beta, cl_mem Y, size_t offy, int incy, cl_uint numCommandQueues, cl_command_queue *commandQueues, cl_uint numEventsInWaitList, const cl_event *eventWaitList, cl_event *events)
	Matrix-vector product with a general rectangular banded matrix and float elements. More...
clblasStatus	clblasDgbmv (clblasOrder order, clblasTranspose trans, size_t M, size_t N, size_t KL, size_t KU, cl_double alpha, const cl_mem A, size_t offa, size_t lda, const cl_mem X, size_t offx, int incx, cl_double beta, cl_mem Y, size_t offy, int incy, cl_uint numCommandQueues, cl_command_queue *commandQueues, cl_uint numEventsInWaitList, const cl_event *eventWaitList, cl_event *events)
	Matrix-vector product with a general rectangular banded matrix and double elements. More...
clblasStatus	clblasCgbmv (clblasOrder order, clblasTranspose trans, size_t M, size_t N, size_t KL, size_t KU, cl_float2 alpha, const cl_mem A, size_t offa, size_t lda, const cl_mem X, size_t offx, int incx, cl_float2 beta, cl_mem Y, size_t offy, int incy, cl_uint numCommandQueues, cl_command_queue *commandQueues, cl_uint numEventsInWaitList, const cl_event *eventWaitList, cl_event *events)
	Matrix-vector product with a general rectangular banded matrix and float-complex elements. More...
clblasStatus	clblasZgbmv (clblasOrder order, clblasTranspose trans, size_t M, size_t N, size_t KL, size_t KU, cl_double2 alpha, const cl_mem A, size_t offa, size_t lda, const cl_mem X, size_t offx, int incx, cl_double2 beta, cl_mem Y, size_t offy, int incy, cl_uint numCommandQueues, cl_command_queue *commandQueues, cl_uint numEventsInWaitList, const cl_event *eventWaitList, cl_event *events)
	Matrix-vector product with a general rectangular banded matrix and double-complex elements. More...

Detailed Description

Function Documentation

clblasStatus clblasCgbmv	(	clblasOrder	order,
		clblasTranspose	trans,
		size_t	M,
		size_t	N,
		size_t	KL,
		size_t	KU,
		cl_float2	alpha,
		const cl_mem	A,
		size_t	offa,
		size_t	lda,
		const cl_mem	X,
		size_t	offx,
		int	incx,
		cl_float2	beta,
		cl_mem	Y,
		size_t	offy,
		int	incy,
		cl_uint	numCommandQueues,
		cl_command_queue *	commandQueues,
		cl_uint	numEventsInWaitList,
		const cl_event *	eventWaitList,
		cl_event *	events
	)

Matrix-vector product with a general rectangular banded matrix and float-complex elements.

Matrix-vector products:

• \( Y \leftarrow \alpha A X + \beta Y \)
• \( Y \leftarrow \alpha A^T X + \beta Y \)

Parameters

[in]	order	Row/column order.
[in]	trans	How matrix A is to be transposed.
[in]	M	Number of rows in banded matrix A.
[in]	N	Number of columns in banded matrix A.
[in]	KL	Number of sub-diagonals in banded matrix A.
[in]	KU	Number of super-diagonals in banded matrix A.
[in]	alpha	The factor of banded matrix A.
[in]	A	Buffer object storing banded matrix A.
[in]	offa	Offset in number of elements for the first element in banded matrix A.
[in]	lda	Leading dimension of banded matrix A. It cannot be less than ( KL + KU + 1 )
[in]	X	Buffer object storing vector X.
[in]	offx	Offset of first element of vector X in buffer object. Counted in elements.
[in]	incx	Increment for the elements of X. Must not be zero.
[in]	beta	The factor of the vector Y.
[out]	Y	Buffer object storing the vector y.
[in]	offy	Offset of first element of vector Y in buffer object. Counted in elements.
[in]	incy	Increment for the elements of Y. Must not be zero.
[in]	numCommandQueues	Number of OpenCL command queues in which the task is to be performed.
[in]	commandQueues	OpenCL command queues.
[in]	numEventsInWaitList	Number of events in the event wait list.
[in]	eventWaitList	Event wait list.
[in]	events	Event objects per each command queue that identify a particular kernel execution instance.

Returns

The same result as the clblasSgbmv() function.

clblasStatus clblasDgbmv	(	clblasOrder	order,
		clblasTranspose	trans,
		size_t	M,
		size_t	N,
		size_t	KL,
		size_t	KU,
		cl_double	alpha,
		const cl_mem	A,
		size_t	offa,
		size_t	lda,
		const cl_mem	X,
		size_t	offx,
		int	incx,
		cl_double	beta,
		cl_mem	Y,
		size_t	offy,
		int	incy,
		cl_uint	numCommandQueues,
		cl_command_queue *	commandQueues,
		cl_uint	numEventsInWaitList,
		const cl_event *	eventWaitList,
		cl_event *	events
	)

Matrix-vector product with a general rectangular banded matrix and double elements.

Matrix-vector products:

• \( Y \leftarrow \alpha A X + \beta Y \)
• \( Y \leftarrow \alpha A^T X + \beta Y \)

Parameters

[in]	order	Row/column order.
[in]	trans	How matrix A is to be transposed.
[in]	M	Number of rows in banded matrix A.
[in]	N	Number of columns in banded matrix A.
[in]	KL	Number of sub-diagonals in banded matrix A.
[in]	KU	Number of super-diagonals in banded matrix A.
[in]	alpha	The factor of banded matrix A.
[in]	A	Buffer object storing banded matrix A.
[in]	offa	Offset in number of elements for the first element in banded matrix A.
[in]	lda	Leading dimension of banded matrix A. It cannot be less than ( KL + KU + 1 )
[in]	X	Buffer object storing vector X.
[in]	offx	Offset of first element of vector X in buffer object. Counted in elements.
[in]	incx	Increment for the elements of X. Must not be zero.
[in]	beta	The factor of the vector Y.
[out]	Y	Buffer object storing the vector y.
[in]	offy	Offset of first element of vector Y in buffer object. Counted in elements.
[in]	incy	Increment for the elements of Y. Must not be zero.
[in]	numCommandQueues	Number of OpenCL command queues in which the task is to be performed.
[in]	commandQueues	OpenCL command queues.
[in]	numEventsInWaitList	Number of events in the event wait list.
[in]	eventWaitList	Event wait list.
[in]	events	Event objects per each command queue that identify a particular kernel execution instance.

Returns

• clblasSuccess on success;
• clblasInvalidDevice if a target device does not support floating point arithmetic with double precision;
• the same error codes as the clblasSgbmv() function otherwise.

clblasStatus clblasSgbmv	(	clblasOrder	order,
		clblasTranspose	trans,
		size_t	M,
		size_t	N,
		size_t	KL,
		size_t	KU,
		cl_float	alpha,
		const cl_mem	A,
		size_t	offa,
		size_t	lda,
		const cl_mem	X,
		size_t	offx,
		int	incx,
		cl_float	beta,
		cl_mem	Y,
		size_t	offy,
		int	incy,
		cl_uint	numCommandQueues,
		cl_command_queue *	commandQueues,
		cl_uint	numEventsInWaitList,
		const cl_event *	eventWaitList,
		cl_event *	events
	)

Matrix-vector product with a general rectangular banded matrix and float elements.

Matrix-vector products:

• \( Y \leftarrow \alpha A X + \beta Y \)
• \( Y \leftarrow \alpha A^T X + \beta Y \)

Parameters

[in]	order	Row/column order.
[in]	trans	How matrix A is to be transposed.
[in]	M	Number of rows in banded matrix A.
[in]	N	Number of columns in banded matrix A.
[in]	KL	Number of sub-diagonals in banded matrix A.
[in]	KU	Number of super-diagonals in banded matrix A.
[in]	alpha	The factor of banded matrix A.
[in]	A	Buffer object storing banded matrix A.
[in]	offa	Offset in number of elements for the first element in banded matrix A.
[in]	lda	Leading dimension of banded matrix A. It cannot be less than ( KL + KU + 1 )
[in]	X	Buffer object storing vector X.
[in]	offx	Offset of first element of vector X in buffer object. Counted in elements.
[in]	incx	Increment for the elements of X. Must not be zero.
[in]	beta	The factor of the vector Y.
[out]	Y	Buffer object storing the vector y.
[in]	offy	Offset of first element of vector Y in buffer object. Counted in elements.
[in]	incy	Increment for the elements of Y. Must not be zero.
[in]	numCommandQueues	Number of OpenCL command queues in which the task is to be performed.
[in]	commandQueues	OpenCL command queues.
[in]	numEventsInWaitList	Number of events in the event wait list.
[in]	eventWaitList	Event wait list.
[in]	events	Event objects per each command queue that identify a particular kernel execution instance.

Returns

• clblasSuccess on success;
• clblasNotInitialized if clblasSetup() was not called;
• clblasInvalidValue if invalid parameters are passed:
  • either M or N is zero, or
  • KL is greater than M - 1, or
  • KU is greater than N - 1, or
  • either incx or incy is zero, or
  • any of the leading dimensions is invalid;
  • the matrix size or the vector sizes along with the increments lead to accessing outside of any of the buffers;
• clblasInvalidMemObject if either A, X, or Y object is Invalid, or an image object rather than the buffer one;
• clblasOutOfHostMemory if the library can't allocate memory for internal structures;
• clblasInvalidCommandQueue if the passed command queue is invalid;
• clblasInvalidContext if a context a passed command queue belongs to was released;
• clblasInvalidOperation if kernel compilation relating to a previous call has not completed for any of the target devices;
• clblasCompilerNotAvailable if a compiler is not available;
• clblasBuildProgramFailure if there is a failure to build a program executable.

Examples:

example_sgbmv.c.

clblasStatus clblasZgbmv	(	clblasOrder	order,
		clblasTranspose	trans,
		size_t	M,
		size_t	N,
		size_t	KL,
		size_t	KU,
		cl_double2	alpha,
		const cl_mem	A,
		size_t	offa,
		size_t	lda,
		const cl_mem	X,
		size_t	offx,
		int	incx,
		cl_double2	beta,
		cl_mem	Y,
		size_t	offy,
		int	incy,
		cl_uint	numCommandQueues,
		cl_command_queue *	commandQueues,
		cl_uint	numEventsInWaitList,
		const cl_event *	eventWaitList,
		cl_event *	events
	)

Matrix-vector product with a general rectangular banded matrix and double-complex elements.

Matrix-vector products:

• \( Y \leftarrow \alpha A X + \beta Y \)
• \( Y \leftarrow \alpha A^T X + \beta Y \)

Parameters

[in]	order	Row/column order.
[in]	trans	How matrix A is to be transposed.
[in]	M	Number of rows in banded matrix A.
[in]	N	Number of columns in banded matrix A.
[in]	KL	Number of sub-diagonals in banded matrix A.
[in]	KU	Number of super-diagonals in banded matrix A.
[in]	alpha	The factor of banded matrix A.
[in]	A	Buffer object storing banded matrix A.
[in]	offa	Offset in number of elements for the first element in banded matrix A.
[in]	lda	Leading dimension of banded matrix A. It cannot be less than ( KL + KU + 1 )
[in]	X	Buffer object storing vector X.
[in]	offx	Offset of first element of vector X in buffer object. Counted in elements.
[in]	incx	Increment for the elements of X. Must not be zero.
[in]	beta	The factor of the vector Y.
[out]	Y	Buffer object storing the vector y.
[in]	offy	Offset of first element of vector Y in buffer object. Counted in elements.
[in]	incy	Increment for the elements of Y. Must not be zero.
[in]	numCommandQueues	Number of OpenCL command queues in which the task is to be performed.
[in]	commandQueues	OpenCL command queues.
[in]	numEventsInWaitList	Number of events in the event wait list.
[in]	eventWaitList	Event wait list.
[in]	events	Event objects per each command queue that identify a particular kernel execution instance.

Returns

The same result as the clblasDgbmv() function.