PLASMA
Parallel Linear Algebra Software for Multicore Architectures
|
\( C = \alpha A A^T + \beta C \) where \( C \) is Hermitian More...
Functions | |
int | plasma_cherk (plasma_enum_t uplo, plasma_enum_t trans, int n, int k, float alpha, plasma_complex32_t *pA, int lda, float beta, plasma_complex32_t *pC, int ldc) |
void | plasma_omp_cherk (plasma_enum_t uplo, plasma_enum_t trans, float alpha, plasma_desc_t A, float beta, plasma_desc_t C, plasma_sequence_t *sequence, plasma_request_t *request) |
int | plasma_zherk (plasma_enum_t uplo, plasma_enum_t trans, int n, int k, double alpha, plasma_complex64_t *pA, int lda, double beta, plasma_complex64_t *pC, int ldc) |
void | plasma_omp_zherk (plasma_enum_t uplo, plasma_enum_t trans, double alpha, plasma_desc_t A, double beta, plasma_desc_t C, plasma_sequence_t *sequence, plasma_request_t *request) |
\( C = \alpha A A^T + \beta C \) where \( C \) is Hermitian
int plasma_cherk | ( | plasma_enum_t | uplo, |
plasma_enum_t | trans, | ||
int | n, | ||
int | k, | ||
float | alpha, | ||
plasma_complex32_t * | pA, | ||
int | lda, | ||
float | beta, | ||
plasma_complex32_t * | pC, | ||
int | ldc | ||
) |
Performs one of the Hermitian rank k operations
\[ C = \alpha A \times A^H + \beta C, \]
or
\[ C = \alpha A^H \times A + \beta C, \]
where alpha and beta are real scalars, C is an n-by-n Hermitian matrix, and A is an n-by-k matrix in the first case and a k-by-n matrix in the second case.
[in] | uplo |
|
[in] | trans |
|
[in] | n | The order of the matrix C. n >= 0. |
[in] | k | If trans = PlasmaNoTrans, number of columns of the A matrix; if trans = PlasmaConjTrans, number of rows of the A matrix. |
[in] | alpha | The scalar alpha. |
[in] | pA | A is an lda-by-ka matrix. If trans = PlasmaNoTrans, ka = k; if trans = PlasmaConjTrans, ka = n. |
[in] | lda | The leading dimension of the array A. If trans = PlasmaNoTrans, lda >= max(1, n); if trans = PlasmaConjTrans, lda >= max(1, k). |
[in] | beta | The scalar beta. |
[in,out] | pC | C is an ldc-by-n matrix. On exit, the uplo part of the matrix is overwritten by the uplo part of the updated matrix. |
[in] | ldc | The leading dimension of the array C. ldc >= max(1, n). |
PlasmaSuccess | successful exit |
void plasma_omp_cherk | ( | plasma_enum_t | uplo, |
plasma_enum_t | trans, | ||
float | alpha, | ||
plasma_desc_t | A, | ||
float | beta, | ||
plasma_desc_t | C, | ||
plasma_sequence_t * | sequence, | ||
plasma_request_t * | request | ||
) |
Performs rank k update. Non-blocking tile version of plasma_cherk(). 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.
[in] | uplo |
|
[in] | trans |
|
[in] | alpha | The scalar alpha. |
[in] | A | Descriptor of matrix A. |
[in] | beta | The scalar beta. |
[in,out] | C | Descriptor of matrix C. |
[in] | sequence | Identifies the sequence of function calls that this call belongs to (for completion checks and exception handling purposes). Check the sequence->status for errors. |
[out] | request | Identifies this function call (for exception handling purposes). |
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. |
int plasma_zherk | ( | plasma_enum_t | uplo, |
plasma_enum_t | trans, | ||
int | n, | ||
int | k, | ||
double | alpha, | ||
plasma_complex64_t * | pA, | ||
int | lda, | ||
double | beta, | ||
plasma_complex64_t * | pC, | ||
int | ldc | ||
) |
Performs one of the Hermitian rank k operations
\[ C = \alpha A \times A^H + \beta C, \]
or
\[ C = \alpha A^H \times A + \beta C, \]
where alpha and beta are real scalars, C is an n-by-n Hermitian matrix, and A is an n-by-k matrix in the first case and a k-by-n matrix in the second case.
[in] | uplo |
|
[in] | trans |
|
[in] | n | The order of the matrix C. n >= 0. |
[in] | k | If trans = PlasmaNoTrans, number of columns of the A matrix; if trans = PlasmaConjTrans, number of rows of the A matrix. |
[in] | alpha | The scalar alpha. |
[in] | pA | A is an lda-by-ka matrix. If trans = PlasmaNoTrans, ka = k; if trans = PlasmaConjTrans, ka = n. |
[in] | lda | The leading dimension of the array A. If trans = PlasmaNoTrans, lda >= max(1, n); if trans = PlasmaConjTrans, lda >= max(1, k). |
[in] | beta | The scalar beta. |
[in,out] | pC | C is an ldc-by-n matrix. On exit, the uplo part of the matrix is overwritten by the uplo part of the updated matrix. |
[in] | ldc | The leading dimension of the array C. ldc >= max(1, n). |
PlasmaSuccess | successful exit |
void plasma_omp_zherk | ( | plasma_enum_t | uplo, |
plasma_enum_t | trans, | ||
double | alpha, | ||
plasma_desc_t | A, | ||
double | beta, | ||
plasma_desc_t | C, | ||
plasma_sequence_t * | sequence, | ||
plasma_request_t * | request | ||
) |
Performs rank k update. Non-blocking tile version of plasma_zherk(). 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.
[in] | uplo |
|
[in] | trans |
|
[in] | alpha | The scalar alpha. |
[in] | A | Descriptor of matrix A. |
[in] | beta | The scalar beta. |
[in,out] | C | Descriptor of matrix C. |
[in] | sequence | Identifies the sequence of function calls that this call belongs to (for completion checks and exception handling purposes). Check the sequence->status for errors. |
[out] | request | Identifies this function call (for exception handling purposes). |
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. |