Implementations of methods for lama::BLAS3Interface with OpenMP. More...

#include <OpenMPBLAS3.hpp>

Public Member Functions
template<>
void	gemm (const enum CBLAS_ORDER order, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_TRANSPOSE TransB, const IndexType m, const IndexType n, const IndexType k, const float alpha, const float A, const IndexType lda, const float B, const IndexType ldb, const float beta, float C, const IndexType ldc, SyncToken syncToken)
template<>
void	gemm (const enum CBLAS_ORDER order, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_TRANSPOSE TransB, const IndexType m, const IndexType n, const IndexType k, const double alpha, const double A, const IndexType lda, const double B, const IndexType ldb, const double beta, double C, const IndexType ldc, SyncToken syncToken)
template<>
void	symm (const enum CBLAS_ORDER order, const enum CBLAS_SIDE Side, const enum CBLAS_UPLO Uplo, const IndexType m, const IndexType n, const float alpha, const float A, const IndexType lda, const float B, const IndexType ldb, const float beta, float C, const IndexType ldc, SyncToken syncToken)
	symm
template<>
void	symm (const enum CBLAS_ORDER order, const enum CBLAS_SIDE Side, const enum CBLAS_UPLO Uplo, const IndexType m, const IndexType n, const double alpha, const double A, const IndexType lda, const double B, const IndexType ldb, const double beta, double C, const IndexType ldc, SyncToken syncToken)
template<>
void	trmm (const enum CBLAS_ORDER order, const enum CBLAS_SIDE Side, const enum CBLAS_UPLO Uplo, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_DIAG Diag, const IndexType m, const IndexType n, const float alpha, const float A, const IndexType lda, float B, const IndexType ldb, SyncToken *syncToken)
	trmm
template<>
void	trmm (const enum CBLAS_ORDER order, const enum CBLAS_SIDE Side, const enum CBLAS_UPLO Uplo, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_DIAG Diag, const IndexType m, const IndexType n, const double alpha, const double A, const IndexType lda, double B, const IndexType ldb, SyncToken *syncToken)
template<>
void	trsm (const enum CBLAS_ORDER order, const enum CBLAS_SIDE Side, const enum CBLAS_UPLO Uplo, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_DIAG Diag, const IndexType m, const IndexType n, const float alpha, const float A, const IndexType lda, float B, const IndexType ldb, SyncToken *syncToken)
	trsm
template<>
void	trsm (const enum CBLAS_ORDER order, const enum CBLAS_SIDE Side, const enum CBLAS_UPLO Uplo, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_DIAG Diag, const IndexType m, const IndexType n, const double alpha, const double A, const IndexType lda, double B, const IndexType ldb, SyncToken *syncToken)
template<>
void	syrk (const enum CBLAS_ORDER order, const enum CBLAS_UPLO Uplo, const enum CBLAS_TRANSPOSE Trans, const IndexType n, const IndexType k, const float alpha, const float A, const IndexType lda, const float beta, float C, const IndexType ldc, SyncToken *syncToken)
	syrk
template<>
void	syrk (const enum CBLAS_ORDER order, const enum CBLAS_UPLO Uplo, const enum CBLAS_TRANSPOSE Trans, const IndexType n, const IndexType k, const double alpha, const double A, const IndexType lda, const double beta, double C, const IndexType ldc, SyncToken *syncToken)
template<>
void	syrk2 (const enum CBLAS_ORDER order, const enum CBLAS_UPLO Uplo, const enum CBLAS_TRANSPOSE Trans, const IndexType n, const IndexType k, const float alpha, const float A, const IndexType lda, const float B, const IndexType ldb, const float beta, float C, const IndexType ldc, SyncToken syncToken)
	syrk2
template<>
void	syrk2 (const enum CBLAS_ORDER order, const enum CBLAS_UPLO Uplo, const enum CBLAS_TRANSPOSE Trans, const IndexType n, const IndexType k, const double alpha, const double A, const IndexType lda, const double B, const IndexType ldb, const double beta, double C, const IndexType ldc, SyncToken syncToken)
Static Public Member Functions
template<typename T >
static void	gemm (const enum CBLAS_ORDER order, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_TRANSPOSE TransB, const IndexType M, const IndexType N, const IndexType K, const T alpha, const T A, const IndexType lda, const T B, const IndexType ldb, const T beta, T C, const IndexType ldc, SyncToken syncToken)
	OpenMP implementation for BLAS3Interface<T>::gemm.
template<typename T >
static void	symm (const enum CBLAS_ORDER order, const enum CBLAS_SIDE side, const enum CBLAS_UPLO uplo, const IndexType m, const IndexType n, const T alpha, const T A, const IndexType lda, const T B, const IndexType ldb, const T beta, T C, const IndexType ldc, SyncToken syncToken)
	symm performs one of the matrix-matrix operations
template<typename T >
static void	trmm (const enum CBLAS_ORDER order, const enum CBLAS_SIDE Side, const enum CBLAS_UPLO Uplo, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_DIAG Diag, const IndexType M, const IndexType N, const T alpha, const T A, const IndexType lda, T B, const IndexType ldb, SyncToken *syncToken)
	trmm performs one of the matrix-matrix operations
template<typename T >
static void	trsm (const enum CBLAS_ORDER order, const enum CBLAS_SIDE Side, const enum CBLAS_UPLO Uplo, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_DIAG Diag, const IndexType M, const IndexType N, const T alpha, const T A, const IndexType lda, T B, const IndexType ldb, SyncToken *syncToken)
	trsm solves one of the matrix equations
template<typename T >
static void	syrk (const enum CBLAS_ORDER order, const enum CBLAS_UPLO uplo, const enum CBLAS_TRANSPOSE trans, const IndexType n, const IndexType k, const T alpha, const T A, const IndexType lda, const T beta, T C, const IndexType ldc, SyncToken *syncToken)
	syrk performs one of the symmetric rank k operations
template<typename T >
static void	syrk2 (const enum CBLAS_ORDER order, const enum CBLAS_UPLO uplo, const enum CBLAS_TRANSPOSE trans, const IndexType n, const IndexType k, const T alpha, const T A, const IndexType lda, const T B, const IndexType ldb, const T beta, T C, const IndexType ldc, SyncToken syncToken)
	syrk2 performs one of the symmetric rank 2k operations
Private Member Functions
	LAMA_LOG_DECL_STATIC_LOGGER (logger)

Detailed Description

Implementations of methods for lama::BLAS3Interface with OpenMP.

Todo:

Move all method documentations to LAMAInterface and make references here

Add information here about use of native BLAS1 libraries

Member Function Documentation

template<>

void lama::OpenMPBLAS3::gemm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_TRANSPOSE	TransA,
		const enum CBLAS_TRANSPOSE	TransB,
		const IndexType	m,
		const IndexType	n,
		const IndexType	k,
		const float	alpha,
		const float *	A,
		const IndexType	lda,
		const float *	B,
		const IndexType	ldb,
		const float	beta,
		float *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)

References lama::CblasColMajor, lama::CblasConjTrans, lama::CblasNoTrans, lama::CblasRowMajor, lama::CblasTrans, F77_K, F77_lda, F77_ldb, F77_ldc, F77_M, F77_N, F77_sgemm(), F77_TA, F77_TB, and lama::BLASHelper::XERBLA_cpu().

template<typename T >

static void lama::OpenMPBLAS3::gemm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_TRANSPOSE	TransA,
		const enum CBLAS_TRANSPOSE	TransB,
		const IndexType	M,
		const IndexType	N,
		const IndexType	K,
		const T	alpha,
		const T *	A,
		const IndexType	lda,
		const T *	B,
		const IndexType	ldb,
		const T	beta,
		T *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)		`[static]`

OpenMP implementation for BLAS3Interface<T>::gemm.

Referenced by lama::LUSolver::lama_gemm< T >::__gemm(), and lama::LUSolver::computeLUFactorization().

template<>

void lama::OpenMPBLAS3::gemm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_TRANSPOSE	TransA,
		const enum CBLAS_TRANSPOSE	TransB,
		const IndexType	m,
		const IndexType	n,
		const IndexType	k,
		const double	alpha,
		const double *	A,
		const IndexType	lda,
		const double *	B,
		const IndexType	ldb,
		const double	beta,
		double *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)

References lama::CblasColMajor, lama::CblasConjTrans, lama::CblasNoTrans, lama::CblasRowMajor, lama::CblasTrans, F77_dgemm(), F77_K, F77_lda, F77_ldb, F77_ldc, F77_M, F77_N, F77_TA, F77_TB, and lama::BLASHelper::XERBLA_cpu().

lama::OpenMPBLAS3::LAMA_LOG_DECL_STATIC_LOGGER ( logger ) [private]

template<typename T >

static void lama::OpenMPBLAS3::symm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_SIDE	side,
		const enum CBLAS_UPLO	uplo,
		const IndexType	m,
		const IndexType	n,
		const T	alpha,
		const T *	A,
		const IndexType	lda,
		const T *	B,
		const IndexType	ldb,
		const T	beta,
		T *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)		`[static]`

symm performs one of the matrix-matrix operations

C = alpha * A * B + beta * C or C = alpha * B * A + beta * C,

where alpha and beta are scalars, A is a symmetric matrix consisting of single‐precision elements and is stored in either lower or upper storage mode. B and C are m×n matrices consisting of elements.

Parameters:

[in]	side	specifies whether the symmetric matrix A appears on the left-hand side or right-hand side of Matrix B. If side == 'L' or 'l', C = alpha * A * B + beta * C. If side == 'R' or 'R', C = alpha * B * A + beta * C.
[in]	uplo	specifies whether the symmetric matrix A is stored in upper or lower storage mode. If uplo == 'U' or 'u', only the upper triangular part of the symmetric matrix is referenced, and the elements of the strictly lower triangular part are inferred from those in the upper triangular part. If uplo == 'L' or 'l', only the lower triangular part of the symmetric matrix is referenced, and the elements of the strictly upper triangular part are inferred from those in the lower triangular part.
[in]	m	specifies the number of rows of matrix C, and the number of rows of matrix B. It also specifies the dimensions of symmetric matrix A when side == 'L' or 'l'; m must be at least zero.
[in]	n	specifies the number of columns of matrix C, and the number of columns of matrix B. It also specifies the dimensions of symmetric matrix A when side == 'R' or 'r''; n must be at least zero.
[in]	alpha	scalar multiplier applied to A * B or B * A
[in]	A	array of dimensions (lda, ka), where ka is m when side == 'L' or 'l' and is n otherwise. If side == 'L' or 'l', the leading m×m part of array A must contain the symmetric matrix such that when uplo == 'U' or 'u', the leading m×m part stores the upper triangular part of the symmetric matrix, and the strictly lower triangular part of A is not referenced; and when uplo == 'L' or 'l', the leading m×m part stores the lower triangular part of the symmetric matrix, and the strictly upper triangular part is not referenced. If side == 'R' or 'r', the leading n×n part of array A must contain the symmetric matrix such that when uplo == 'U' or 'u', the leading n×n part stores the upper triangular part of the symmetric matrix, and the strictly lower triangular part of A is not referenced; and when uplo == 'L' or 'l', the leading n×n part stores the lower triangular part of the symmetric matrix, and the strictly upper triangular part is not referenced.
[in]	lda	leading dimension of A. When side == 'L' or 'l', it must be at least max(1, m) and at least max(1, n) otherwise.
[in]	B	array of dimensions (ldb, n). On entry, the leading m×n part of the array contains the matrix B.
[in]	ldb	leading dimension of B; ldb must be at least max(1,m).
[in]	beta	scalar multiplier applied to C. If beta is zero, C does not have to be a valid input
[in]	C	array of dimensions (ldc,n);
[in]	ldc	leading dimension of C. ldc must be at least max(1,m)
[out]	C	updated according to C = alpha * A * B + beta * C or C = alpha * B * A + beta * C

template<>

void lama::OpenMPBLAS3::symm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_SIDE	Side,
		const enum CBLAS_UPLO	Uplo,
		const IndexType	m,
		const IndexType	n,
		const float	alpha,
		const float *	A,
		const IndexType	lda,
		const float *	B,
		const IndexType	ldb,
		const float	beta,
		float *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)

symm

References lama::CblasColMajor, lama::CblasLeft, lama::CblasLower, lama::CblasRight, lama::CblasRowMajor, lama::CblasUpper, F77_lda, F77_ldb, F77_ldc, F77_M, F77_N, F77_SD, F77_ssymm(), F77_UL, and lama::BLASHelper::XERBLA_cpu().

template<>

void lama::OpenMPBLAS3::symm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_SIDE	Side,
		const enum CBLAS_UPLO	Uplo,
		const IndexType	m,
		const IndexType	n,
		const double	alpha,
		const double *	A,
		const IndexType	lda,
		const double *	B,
		const IndexType	ldb,
		const double	beta,
		double *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)

References lama::CblasColMajor, lama::CblasLeft, lama::CblasLower, lama::CblasRight, lama::CblasRowMajor, lama::CblasUpper, F77_dsymm(), F77_lda, F77_ldb, F77_ldc, F77_M, F77_N, F77_SD, F77_UL, and lama::BLASHelper::XERBLA_cpu().

template<typename T >

static void lama::OpenMPBLAS3::syrk	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_UPLO	uplo,
		const enum CBLAS_TRANSPOSE	trans,
		const IndexType	n,
		const IndexType	k,
		const T	alpha,
		const T *	A,
		const IndexType	lda,
		const T	beta,
		T *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)		`[static]`

syrk performs one of the symmetric rank k operations

C = alpha * A * AT + beta * C or C = alpha * AT * A + beta * C

where alpha and beta are scalars. C is an n×n symmetric matrix consisting of elements and is stored in either lower or upper storage mode. A is a matrix consisting of elements with dimensions of n×k in the first case and k×n in the second case.

Parameters:

[in]	uplo	specifies whether the symmetric matrix C is stored in upper or lower storage mode. If uplo == 'U' or 'u', only the upper triangular part of the symmetric matrix is referenced, and the elements of the strictly lower triangular part are inferred from those in the upper triangular part. If uplo == 'L' or 'l', only the lower triangular part of the symmetric matrix is referenced, and the elements of the strictly upper triangular part are inferred from those in the lower triangular part.
[in]	trans	specifies the operation to be performed. If trans == 'N', or 'n' C = alpha * A * AT + beta * C. If trans == 'T','t','C','c' C = alpha * AT * A + beta * C.
[in]	n	specifies the number of rows and the number columns of matrix C. If trans == 'N' or 'n', n specifies the number of rows of matrix A. If trans == 'T', 't', 'C', or 'c', n specifies the number of columns of matrix A; n must be at least zero.
[in]	k	If trans == 'N' or 'n', k specifies the number of columns of matrix A. If trans == 'T', 't', 'C', or 'c', k specifies the number of rows of matrix A; k must be at least zero.
[in]	alpha	scalar multiplier applied to A * AT or AT * A
[in]	A	array of dimensions (lda, ka), where ka is k when trans == 'N' or 'n' and is n otherwise. When trans == 'N' or 'n', the leading n×k part of array A contains the matrix A; otherwise, the leading k×n part of the array contains the matrix A.
[in]	lda	leading dimension of A. When trans == 'N' or 'n', lda must be at least max(1, n). Otherwise lda must be at least max(1, k).
[in]	beta	scalar multiplier applied to C. If beta is zero, C is not read.
[in]	C	array of dimensions (ldc, n). If uplo == 'U' or 'u', the leading n×n triangular part of the array C must contain the upper triangular part of the symmetric matrix C, and the strictly lower triangular part of C is not referenced. On exit, the upper triangular part of C is overwritten by the upper triangular part of the updated matrix. If uplo == 'L' or 'l', the leading n×n triangular part of the array C must contain the lower triangular part of the symmetric matrix C, and the strictly upper triangular part of C is not referenced. On exit, the lower triangular part of C is overwritten by the lower triangular part of the updated matrix.
[in]	ldc	leading dimension of C. ldc must be at least max(1,n)
[out]	C	updated according to C = alpha * A * AT + beta * C or C = alpha * AT * A + beta * C

template<>

void lama::OpenMPBLAS3::syrk	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_UPLO	Uplo,
		const enum CBLAS_TRANSPOSE	Trans,
		const IndexType	n,
		const IndexType	k,
		const float	alpha,
		const float *	A,
		const IndexType	lda,
		const float	beta,
		float *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)

syrk

References lama::CblasColMajor, lama::CblasConjTrans, lama::CblasLower, lama::CblasNoTrans, lama::CblasRowMajor, lama::CblasTrans, lama::CblasUpper, F77_K, F77_lda, F77_ldc, F77_N, F77_ssyrk(), F77_TR, F77_UL, and lama::BLASHelper::XERBLA_cpu().

template<>

void lama::OpenMPBLAS3::syrk	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_UPLO	Uplo,
		const enum CBLAS_TRANSPOSE	Trans,
		const IndexType	n,
		const IndexType	k,
		const double	alpha,
		const double *	A,
		const IndexType	lda,
		const double	beta,
		double *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)

References lama::CblasColMajor, lama::CblasConjTrans, lama::CblasLower, lama::CblasNoTrans, lama::CblasRowMajor, lama::CblasTrans, lama::CblasUpper, F77_dsyrk(), F77_K, F77_lda, F77_ldc, F77_N, F77_TR, F77_UL, and lama::BLASHelper::XERBLA_cpu().

template<typename T >

static void lama::OpenMPBLAS3::syrk2	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_UPLO	uplo,
		const enum CBLAS_TRANSPOSE	trans,
		const IndexType	n,
		const IndexType	k,
		const T	alpha,
		const T *	A,
		const IndexType	lda,
		const T *	B,
		const IndexType	ldb,
		const T	beta,
		T *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)		`[static]`

syrk2 performs one of the symmetric rank 2k operations

C = alpha * A * BT + alpha * B * AT + beta * C or C = alpha * AT * B + alpha * BT * A + beta * C

where alpha and beta are sscalars. C is an n×n symmetric matrix consisting of elements and is stored in either lower or upper storage mode. A and B are matrices consisting of elements with dimension of n×k in the first case and k×n in the second case.

Parameters:

[in]	uplo	specifies whether the symmetric matrix C is stored in upper or lower storage mode. If uplo == 'U' or 'u', only the upper triangular part of the symmetric matrix is referenced, and the elements of the strictly lower triangular part are inferred from those in the upper triangular part. If uplo == 'L' or 'l', only the lower triangular part of the symmetric matrix is referenced, and the elements of the strictly upper triangular part are inferred from those in the lower triangular part.
[in]	trans	specifies the operation to be performed. If trans = 'N' or 'n' C = alpha * A * BT + alpha * B * AT + beta * C If trans == 'T','t','C','c' alpha * AT * B + alpha * BT * A + beta * C
[in]	n	specifies the number of rows and the number columns of matrix C. If trans == 'N', or 'n' n specifies the number of rows of matrix A. If trans == 'T','t','C','c' n specifies the number of columns of matrix A; n must be at least zero.
[in]	k	If trans == 'N', or 'n' k specifies the number of columns of matrix A. If trans == 'T','t','C','c' k specifies the number of rows of matrix A; k must be at least zero.
[in]	alpha	scalar multiplier applied to A * AT or AT * A
[in]	A	array of dimensions (lda, ka), where ka is k when trans == 'N' or 'n' and is n otherwise. When trans == 'N' or 'n', the leading n×k part of array A must contain the matrix A, otherwise, the leading k×n part of the array must contain the matrix A.
[in]	lda	leading dimension of A. When trans == 'N' or 'n', lda must be at least max(1, n). Otherwise lda must be at least max(1, k).
[in]	beta	scalar multiplier applied to C. If beta is zero, C does not have to be a valid input.
[in]	C	array of dimensions (ldc, n). If uplo == 'U' or 'u', the leading n×n triangular part of the array C must contain the upper triangular part of the symmetric matrix C, and the strictly lower triangular part of C is not referenced. On exit, the upper triangular part of C is overwritten by the upper triangular part of the updated matrix. If uplo == 'L' or 'l', the leading n×n triangular part of the array C must contain the lower triangular part of the symmetric matrix C, and the strictly upper triangular part of C is not referenced. On exit, the lower triangular part of C is overwritten by the lower triangular part of the updated matrix.
[in]	ldc	leading dimension of C. ldc must be at least max(1,n)
[out]	C	updated according to alpha * A * BT + alpha * B * AT + beta * C or C = alpha * AT * B + alpha * BT * A + beta * C

template<>

void lama::OpenMPBLAS3::syrk2	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_UPLO	Uplo,
		const enum CBLAS_TRANSPOSE	Trans,
		const IndexType	n,
		const IndexType	k,
		const float	alpha,
		const float *	A,
		const IndexType	lda,
		const float *	B,
		const IndexType	ldb,
		const float	beta,
		float *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)

syrk2

References lama::CblasColMajor, lama::CblasConjTrans, lama::CblasLower, lama::CblasNoTrans, lama::CblasRowMajor, lama::CblasTrans, lama::CblasUpper, F77_K, F77_lda, F77_ldb, F77_ldc, F77_N, F77_ssyr2k(), F77_TA, F77_TR, F77_UL, and lama::BLASHelper::XERBLA_cpu().

template<>

void lama::OpenMPBLAS3::syrk2	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_UPLO	Uplo,
		const enum CBLAS_TRANSPOSE	Trans,
		const IndexType	n,
		const IndexType	k,
		const double	alpha,
		const double *	A,
		const IndexType	lda,
		const double *	B,
		const IndexType	ldb,
		const double	beta,
		double *	C,
		const IndexType	ldc,
		SyncToken *	syncToken
	)

References lama::CblasColMajor, lama::CblasConjTrans, lama::CblasLower, lama::CblasNoTrans, lama::CblasRowMajor, lama::CblasTrans, lama::CblasUpper, F77_dsyr2k(), F77_K, F77_lda, F77_ldb, F77_ldc, F77_N, F77_TA, F77_TR, F77_UL, and lama::BLASHelper::XERBLA_cpu().

template<typename T >

static void lama::OpenMPBLAS3::trmm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_SIDE	Side,
		const enum CBLAS_UPLO	Uplo,
		const enum CBLAS_TRANSPOSE	TransA,
		const enum CBLAS_DIAG	Diag,
		const IndexType	M,
		const IndexType	N,
		const T	alpha,
		const T *	A,
		const IndexType	lda,
		T *	B,
		const IndexType	ldb,
		SyncToken *	syncToken
	)		`[static]`

trmm performs one of the matrix-matrix operations

B = alpha * op(A) * B or B = alpha * B * op(A) where op(A) = A or op(A) = AT

alpha is a scalar, B is an m×n matrix consisting of double‐precision elements, A is a unit or non‐unit, upper or lower triangular matrix consisting of double‐precision elements. matrix A and B are stored in column‐major format, lda and ldb are the leading dimensions of the two‐dimensional arrays that contain A and B, respectively.

Parameters:

[in]	side	specifies whether op(A) multiplies B from the left or right. If side == 'L' or 'l', C = alpha * op(A) * B If side == 'R' or 'r', C = alpha * B * op(A)
[in]	uplo	specifies whether the matrix A is an upper or lower triangular matrix. If uplo == 'U' or 'u', A is an upper triangular matrix. If uplo == 'L' or 'l', A is a lower triangular matrix.
[in]	transa	specifies the form of op(A) to be used in the matrix multiplication. If transa == 'N' or 'n', op(A) = A. If transa == 'T','t','C','c', op(A) = AT.
[in]	diag	specifies whether or not A is a unit triangular matrix. If diag == 'U' or 'u', A is assumed to be unit triangular. If diag == 'N' or 'n', A is not assumed to be unit triangular.
[in]	m	the number of rows of matrix B; m must be at least zero.
[in]	n	the number of columns of matrix B; n must be at least zero.
[in]	alpha	scalar multiplier applied to op(A) * B or B * op(A), respectively. If alpha is zero, no accesses are made to matrix A and no read accesses are made to matrix B.
[in]	A	array of dimensions (lda, k). If side == 'L' or 'l', k = m. If side == 'R' or 'r', k = n. If uplo == 'U' or 'u', the leading k×k upper triangular part of the array A must contain the upper triangular matrix, and the strictly lower triangular part of A is not referenced. If uplo == 'L' or 'l', the leading k×k lower triangular part of the array A must contain the lower triangular matrix, and the strictly upper triangular part of A is not referenced. When diag == 'U' or 'u', the diagonal elements of A are not referenced and are assumed to be unity.
[in]	lda	leading dimension of A. When side == 'L' or 'l', it must be at least max(1, m) and at least max(1, n) otherwise.
[in]	B	array of dimensions (ldb, n). On entry, the leading m×n part of the array contains the matrix B. It is overwritten with the transformed matrix on exit
[in]	ldb	leading dimension of B; ldb must be at least max(1,m).
[out]	B	updated according to B = alpha * op(A) * B or B = alpha * B * op(A)

template<>

void lama::OpenMPBLAS3::trmm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_SIDE	Side,
		const enum CBLAS_UPLO	Uplo,
		const enum CBLAS_TRANSPOSE	TransA,
		const enum CBLAS_DIAG	Diag,
		const IndexType	m,
		const IndexType	n,
		const float	alpha,
		const float *	A,
		const IndexType	lda,
		float *	B,
		const IndexType	ldb,
		SyncToken *	syncToken
	)

template<>

void lama::OpenMPBLAS3::trmm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_SIDE	Side,
		const enum CBLAS_UPLO	Uplo,
		const enum CBLAS_TRANSPOSE	TransA,
		const enum CBLAS_DIAG	Diag,
		const IndexType	m,
		const IndexType	n,
		const double	alpha,
		const double *	A,
		const IndexType	lda,
		double *	B,
		const IndexType	ldb,
		SyncToken *	syncToken
	)

template<typename T >

static void lama::OpenMPBLAS3::trsm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_SIDE	Side,
		const enum CBLAS_UPLO	Uplo,
		const enum CBLAS_TRANSPOSE	TransA,
		const enum CBLAS_DIAG	Diag,
		const IndexType	M,
		const IndexType	N,
		const T	alpha,
		const T *	A,
		const IndexType	lda,
		T *	B,
		const IndexType	ldb,
		SyncToken *	syncToken
	)		`[static]`

trsm solves one of the matrix equations

op(A) * X = alpha * B or X * op(A) = alpha * B where op(A) = A or op(A) = AT

alpha is a scalar, X and B are m×n matrices that consist of elements. A is a unit or non‐unit, upper or lower, triangular matrix. The result matrix X overwrites input matrix B; that is, on exit the result is stored in B. matrix A and B are stored in column‐major format, lda and ldb are the leading dimensions of the two‐dimensional arrays that contain A and B, respectively.

Parameters:

[in]	side	specifies whether op(A) appears on the left or right of X: If side == 'L' or 'l', op(A) * X = alpha * B If side == 'R' or 'R', X * op(A) = alpha * B
[in]	uplo	specifies whether the matrix A is an upper or lower triangular matrix. If uplo == 'U' or 'u', A is an upper triangular matrix. If uplo == 'L' or 'l', A is a lower triangular matrix.
[in]	transa	specifies the form of op(A) to be used in the matrix multiplication. If transa == 'N' or 'n', op(A) = A. If transa == 'T','t','C','c', op(A) = AT.
[in]	diag	specifies whether or not A is a unit triangular matrix. If diag == 'U' or 'u', A is assumed to be unit triangular. If diag == 'N' or 'n', A is not assumed to be unit triangular.
[in]	m	the number of rows of matrix B; m must be at least zero.
[in]	n	the number of columns of matrix B; n must be at least zero.
[in]	alpha	scalar multiplier applied to B. When alpha is zero, A is not referenced and B does not have to be a valid input.
[in]	A	array of dimensions (lda, k), where k is m when side == 'L' or 'l' and is n when side == 'R' or 'r'. If uplo == 'U' or 'u', the leading k×k upper triangular part of the array A must contain the upper triangular matrix, and the strictly lower triangular matrix of A is not referenced. When uplo == 'L' or 'l', the leading k×k lower triangular part of the array A must contain the lower triangular matrix, and the strictly upper triangular part of A is not referenced. If diag == 'U' or 'u', the diagonal elements of A are not referenced and are assumed to be unity.
[in]	lda	leading dimension of the two-dimensional array containing A. When side == 'L' or 'l', lda must be at least max(1, m). When side == 'R' or 'r', lda must be at least max(1, n).
[in]	B	array of dimensions (ldb, n); ldb must be at least max(1, m). T he leading m×n part of the array B must contain the righthand side matrix B. On exit B is overwritten by the solution matrix X.
[in]	ldb	leading dimension of the two-dimensional array containing B; ldb must be at least max(1, m).
[out]	B	contains the solution matrix X satisfying op(A) * X = alpha * B or X * op(A) = alpha * B

Referenced by lama::LUSolver::computeLUFactorization(), and lama::LUSolver::ptrsm().

template<>

void lama::OpenMPBLAS3::trsm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_SIDE	Side,
		const enum CBLAS_UPLO	Uplo,
		const enum CBLAS_TRANSPOSE	TransA,
		const enum CBLAS_DIAG	Diag,
		const IndexType	m,
		const IndexType	n,
		const float	alpha,
		const float *	A,
		const IndexType	lda,
		float *	B,
		const IndexType	ldb,
		SyncToken *	syncToken
	)

template<>

void lama::OpenMPBLAS3::trsm	(	const enum CBLAS_ORDER	order,
		const enum CBLAS_SIDE	Side,
		const enum CBLAS_UPLO	Uplo,
		const enum CBLAS_TRANSPOSE	TransA,
		const enum CBLAS_DIAG	Diag,
		const IndexType	m,
		const IndexType	n,
		const double	alpha,
		const double *	A,
		const IndexType	lda,
		double *	B,
		const IndexType	ldb,
		SyncToken *	syncToken
	)

The documentation for this class was generated from the following files:

/home/brandes/workspace/LAMA/src/lama/openmp/OpenMPBLAS3.hpp
/home/brandes/workspace/LAMA/src/lama/openmp/OpenMPBLAS3.cpp

Public Member Functions

Static Public Member Functions

Private Member Functions

Detailed Description

Member Function Documentation