Functions
int	plasma_cgeqrf (int m, int n, plasma_complex32_t pA, int lda, plasma_desc_t T)

void	plasma_omp_cgeqrf (plasma_desc_t A, plasma_desc_t T, plasma_workspace_t work, plasma_sequence_t sequence, plasma_request_t request)

int	plasma_dgeqrf (int m, int n, double pA, int lda, plasma_desc_t T)

void	plasma_omp_dgeqrf (plasma_desc_t A, plasma_desc_t T, plasma_workspace_t work, plasma_sequence_t sequence, plasma_request_t request)

int	plasma_sgeqrf (int m, int n, float pA, int lda, plasma_desc_t T)

void	plasma_omp_sgeqrf (plasma_desc_t A, plasma_desc_t T, plasma_workspace_t work, plasma_sequence_t sequence, plasma_request_t request)

int	plasma_zgeqrf (int m, int n, plasma_complex64_t pA, int lda, plasma_desc_t T)

void	plasma_omp_zgeqrf (plasma_desc_t A, plasma_desc_t T, plasma_workspace_t work, plasma_sequence_t sequence, plasma_request_t request)

Detailed Description

Function Documentation

int plasma_cgeqrf	(	int	m,
		int	n,
		plasma_complex32_t *	pA,
		int	lda,
		plasma_desc_t *	T
	)

Computes a tile QR factorization of a real or complex m-by-n matrix A. The factorization has the form

\[ A = Q \times R \]

, where Q is a matrix with orthonormal columns and R is an upper triangular with positive diagonal.

Parameters

[in]	m	The number of rows of the matrix A. m >= 0.
[in]	n	The number of columns of the matrix A. n >= 0.
[in,out]	pA	On entry, pointer to the m-by-n matrix A. On exit, the elements on and above the diagonal of the array contain the min(m,n)-by-n upper trapezoidal matrix R (R is upper triangular if m >= n); the elements below the diagonal represent the unitary matrix Q as a product of elementary reflectors stored by tiles.
[in]	lda	The leading dimension of the array A. lda >= max(1,m).
[out]	T	On exit, auxiliary factorization data, required by plasma_cgeqrs to solve the system of equations. Matrix in T is allocated inside this function and needs to be destroyed by plasma_desc_destroy.

Return values

PlasmaSuccess	successful exit
<	0 if -i, the i-th argument had an illegal value

See also: plasma_omp_cgeqrf; plasma_cgeqrf; plasma_dgeqrf; plasma_sgeqrf; plasma_cgeqrs; plasma_cgels

void plasma_omp_cgeqrf	(	plasma_desc_t	A,
		plasma_desc_t	T,
		plasma_workspace_t	work,
		plasma_sequence_t *	sequence,
		plasma_request_t *	request
	)

Computes a tile QR factorization of a matrix. Non-blocking tile version of plasma_cgeqrf(). May return before the computation is finished. Operates on matrices stored by tiles. All matrices are passed through descriptors. All dimensions are taken from the descriptors. Allows for pipelining of operations at runtime.

Parameters

[in,out]	A	Descriptor of matrix A. A is stored in the tile layout.
[out]	T	Descriptor of matrix T. On exit, auxiliary factorization data, required by plasma_cgeqrs to solve the system of equations.
[in]	work	Workspace for the auxiliary arrays needed by some coreblas kernels. For QR factorization, contains preallocated space for tau and work arrays. Allocated by the plasma_workspace_create function.
[in]	sequence	Identifies the sequence of function calls that this call belongs to (for completion checks and exception handling purposes).
[out]	request	Identifies this function call (for exception handling purposes).

Return values

void	Errors are returned by setting sequence->status and request->status to error values. The sequence->status and request->status should never be set to PlasmaSuccess (the initial values) since another async call may be setting a failure value at the same time.

See also: plasma_cgeqrf; plasma_omp_cgeqrf; plasma_omp_dgeqrf; plasma_omp_sgeqrf; plasma_omp_cgeqrs; plasma_omp_cgeqrs; plasma_omp_cgels

int plasma_dgeqrf	(	int	m,
		int	n,
		double *	pA,
		int	lda,
		plasma_desc_t *	T
	)

Computes a tile QR factorization of a real or complex m-by-n matrix A. The factorization has the form

\[ A = Q \times R \]

, where Q is a matrix with orthonormal columns and R is an upper triangular with positive diagonal.

Parameters

[in]	m	The number of rows of the matrix A. m >= 0.
[in]	n	The number of columns of the matrix A. n >= 0.
[in,out]	pA	On entry, pointer to the m-by-n matrix A. On exit, the elements on and above the diagonal of the array contain the min(m,n)-by-n upper trapezoidal matrix R (R is upper triangular if m >= n); the elements below the diagonal represent the orthogonal matrix Q as a product of elementary reflectors stored by tiles.
[in]	lda	The leading dimension of the array A. lda >= max(1,m).
[out]	T	On exit, auxiliary factorization data, required by plasma_dgeqrs to solve the system of equations. Matrix in T is allocated inside this function and needs to be destroyed by plasma_desc_destroy.

Return values

PlasmaSuccess	successful exit
<	0 if -i, the i-th argument had an illegal value

See also: plasma_omp_dgeqrf; plasma_cgeqrf; plasma_dgeqrf; plasma_sgeqrf; plasma_dgeqrs; plasma_dgels

void plasma_omp_dgeqrf	(	plasma_desc_t	A,
		plasma_desc_t	T,
		plasma_workspace_t	work,
		plasma_sequence_t *	sequence,
		plasma_request_t *	request
	)

Computes a tile QR factorization of a matrix. Non-blocking tile version of plasma_dgeqrf(). May return before the computation is finished. Operates on matrices stored by tiles. All matrices are passed through descriptors. All dimensions are taken from the descriptors. Allows for pipelining of operations at runtime.

Parameters

[in,out]	A	Descriptor of matrix A. A is stored in the tile layout.
[out]	T	Descriptor of matrix T. On exit, auxiliary factorization data, required by plasma_dgeqrs to solve the system of equations.
[in]	work	Workspace for the auxiliary arrays needed by some coreblas kernels. For QR factorization, contains preallocated space for tau and work arrays. Allocated by the plasma_workspace_create function.
[in]	sequence	Identifies the sequence of function calls that this call belongs to (for completion checks and exception handling purposes).
[out]	request	Identifies this function call (for exception handling purposes).

Return values

void	Errors are returned by setting sequence->status and request->status to error values. The sequence->status and request->status should never be set to PlasmaSuccess (the initial values) since another async call may be setting a failure value at the same time.

See also: plasma_dgeqrf; plasma_omp_cgeqrf; plasma_omp_dgeqrf; plasma_omp_sgeqrf; plasma_omp_dgeqrs; plasma_omp_dgeqrs; plasma_omp_dgels

int plasma_sgeqrf	(	int	m,
		int	n,
		float *	pA,
		int	lda,
		plasma_desc_t *	T
	)

Computes a tile QR factorization of a real or complex m-by-n matrix A. The factorization has the form

\[ A = Q \times R \]

, where Q is a matrix with orthonormal columns and R is an upper triangular with positive diagonal.

Parameters

[in]	m	The number of rows of the matrix A. m >= 0.
[in]	n	The number of columns of the matrix A. n >= 0.
[in,out]	pA	On entry, pointer to the m-by-n matrix A. On exit, the elements on and above the diagonal of the array contain the min(m,n)-by-n upper trapezoidal matrix R (R is upper triangular if m >= n); the elements below the diagonal represent the orthogonal matrix Q as a product of elementary reflectors stored by tiles.
[in]	lda	The leading dimension of the array A. lda >= max(1,m).
[out]	T	On exit, auxiliary factorization data, required by plasma_sgeqrs to solve the system of equations. Matrix in T is allocated inside this function and needs to be destroyed by plasma_desc_destroy.

Return values

PlasmaSuccess	successful exit
<	0 if -i, the i-th argument had an illegal value

See also: plasma_omp_sgeqrf; plasma_cgeqrf; plasma_dgeqrf; plasma_sgeqrf; plasma_sgeqrs; plasma_sgels

void plasma_omp_sgeqrf	(	plasma_desc_t	A,
		plasma_desc_t	T,
		plasma_workspace_t	work,
		plasma_sequence_t *	sequence,
		plasma_request_t *	request
	)

Computes a tile QR factorization of a matrix. Non-blocking tile version of plasma_sgeqrf(). May return before the computation is finished. Operates on matrices stored by tiles. All matrices are passed through descriptors. All dimensions are taken from the descriptors. Allows for pipelining of operations at runtime.

Parameters

[in,out]	A	Descriptor of matrix A. A is stored in the tile layout.
[out]	T	Descriptor of matrix T. On exit, auxiliary factorization data, required by plasma_sgeqrs to solve the system of equations.
[in]	work	Workspace for the auxiliary arrays needed by some coreblas kernels. For QR factorization, contains preallocated space for tau and work arrays. Allocated by the plasma_workspace_create function.
[in]	sequence	Identifies the sequence of function calls that this call belongs to (for completion checks and exception handling purposes).
[out]	request	Identifies this function call (for exception handling purposes).

Return values

void	Errors are returned by setting sequence->status and request->status to error values. The sequence->status and request->status should never be set to PlasmaSuccess (the initial values) since another async call may be setting a failure value at the same time.

See also: plasma_sgeqrf; plasma_omp_cgeqrf; plasma_omp_dgeqrf; plasma_omp_sgeqrf; plasma_omp_sgeqrs; plasma_omp_sgeqrs; plasma_omp_sgels

int plasma_zgeqrf	(	int	m,
		int	n,
		plasma_complex64_t *	pA,
		int	lda,
		plasma_desc_t *	T
	)

Computes a tile QR factorization of a real or complex m-by-n matrix A. The factorization has the form

\[ A = Q \times R \]

, where Q is a matrix with orthonormal columns and R is an upper triangular with positive diagonal.

Parameters

[in]	m	The number of rows of the matrix A. m >= 0.
[in]	n	The number of columns of the matrix A. n >= 0.
[in,out]	pA	On entry, pointer to the m-by-n matrix A. On exit, the elements on and above the diagonal of the array contain the min(m,n)-by-n upper trapezoidal matrix R (R is upper triangular if m >= n); the elements below the diagonal represent the unitary matrix Q as a product of elementary reflectors stored by tiles.
[in]	lda	The leading dimension of the array A. lda >= max(1,m).
[out]	T	On exit, auxiliary factorization data, required by plasma_zgeqrs to solve the system of equations. Matrix in T is allocated inside this function and needs to be destroyed by plasma_desc_destroy.

Return values

PlasmaSuccess	successful exit
<	0 if -i, the i-th argument had an illegal value

See also: plasma_omp_zgeqrf; plasma_cgeqrf; plasma_dgeqrf; plasma_sgeqrf; plasma_zgeqrs; plasma_zgels

void plasma_omp_zgeqrf	(	plasma_desc_t	A,
		plasma_desc_t	T,
		plasma_workspace_t	work,
		plasma_sequence_t *	sequence,
		plasma_request_t *	request
	)

Computes a tile QR factorization of a matrix. Non-blocking tile version of plasma_zgeqrf(). May return before the computation is finished. Operates on matrices stored by tiles. All matrices are passed through descriptors. All dimensions are taken from the descriptors. Allows for pipelining of operations at runtime.

Parameters

[in,out]	A	Descriptor of matrix A. A is stored in the tile layout.
[out]	T	Descriptor of matrix T. On exit, auxiliary factorization data, required by plasma_zgeqrs to solve the system of equations.
[in]	work	Workspace for the auxiliary arrays needed by some coreblas kernels. For QR factorization, contains preallocated space for tau and work arrays. Allocated by the plasma_workspace_create function.
[in]	sequence	Identifies the sequence of function calls that this call belongs to (for completion checks and exception handling purposes).
[out]	request	Identifies this function call (for exception handling purposes).

Return values

void	Errors are returned by setting sequence->status and request->status to error values. The sequence->status and request->status should never be set to PlasmaSuccess (the initial values) since another async call may be setting a failure value at the same time.

See also: plasma_zgeqrf; plasma_omp_cgeqrf; plasma_omp_dgeqrf; plasma_omp_sgeqrf; plasma_omp_zgeqrs; plasma_omp_zgeqrs; plasma_omp_zgels

Functions

Detailed Description

Function Documentation