symm
Computes a matrix-matrix product where one input matrix is symmetric and
one matrix is general.
Description
The
symm
routines compute a scalar-matrix-matrix product and add the
result to a scalar-matrix product, where one of the matrices in the
multiplication is symmetric. The argument left_right
determines if the symmetric matrix
A
is on the left of the multiplication (left_right
= side::left
)
or on the right (left_right
= side::right
). The operation is defined as:If (
left_right
= side::left
),
If (
left_right
= side::right
),
where:
- alphaandbetaare scalars
- Ais eithermxmornxnsymmetric matrix
- BandCaremxnmatrices
symm
supports the following precisions:T |
---|
float |
double |
std::complex<float> |
std::complex<double> |
symm (Buffer Version)
Syntax
namespace oneapi::mkl::blas::column_major {
void symm(sycl::queue &queue,
oneapi::mkl::side left_right,
oneapi::mkl::uplo upper_lower,
std::int64_t m,
std::int64_t n,
T alpha,
sycl::buffer<T,1> &a,
std::int64_t lda,
sycl::buffer<T,1> &b,
std::int64_t ldb,
T beta,
sycl::buffer<T,1> &c,
std::int64_t ldc)
}
namespace oneapi::mkl::blas::row_major {
void symm(sycl::queue &queue,
oneapi::mkl::side left_right,
oneapi::mkl::uplo upper_lower,
std::int64_t m,
std::int64_t n,
T alpha,
sycl::buffer<T,1> &a,
std::int64_t lda,
sycl::buffer<T,1> &b,
std::int64_t ldb,
T beta,
sycl::buffer<T,1> &c,
std::int64_t ldc)
}
Input Parameters
- queue
- The queue where the routine should be executed.
- left_right
- Specifies whether matrixAis on the left side or right side of the multiplication. See Data Types for more details.
- upper_lower
- Specifies whether matrixAis upper or lower triangular. See Data Types for more details.
- m
- Number of rows of matrixBand matrixC. Must be at least zero.
- n
- Number of columns of matrixBand matrixC. Must be at least zero.
- alpha
- Scaling factor for matrix-matrix product.
- a
- Buffer holding input matrixA. Size of the buffer must be at leastlda*mifleft_right=side::leftorlda*nifleft_right=side::right. See Matrix Storage for more details.
- lda
- Leading dimension of matrixA. Must be at leastmifleft_right=side::leftor at leastnifleft_right=side::right. Must be positive.
- b
- Buffer holding input matrixB. Size of the buffer must be at leastldb*nif column major layout or at leastldb*mif row major layout is used. See Matrix Storage for more details.
- ldb
- Leading dimension of matrixB. Must be at leastmif column major layout or at leastnif row major layout is used. Must be positive.
- beta
- Scaling factor for matrixC.
- c
- Buffer holding input/output matrixC. Size of the buffer must be at leastldc*nif column major layout or at leastldc*mif row major layout is used. See Matrix Storage for more details.
- ldc
- Leading dimension of matrixC. Must be at leastmif column major layout or at leastnif row major layout is used. Must be positive.
Output Parameters
- c
- Output buffer overwritten byalpha*A*B+beta*Cifleft_right=side::leftoralpha*B*A+beta*Cifleft_right=side::right.Ifbeta= 0, matrixCdoes not need to be initialized before callingsymm.
symm (USM Version)
Syntax
namespace oneapi::mkl::blas::column_major {
sycl::event symm(sycl::queue &queue,
oneapi::mkl::side left_right,
oneapi::mkl::uplo upper_lower,
std::int64_t m,
std::int64_t n,
T alpha,
const T* a,
std::int64_t lda,
const T* b,
std::int64_t ldb,
T beta,
T* c,
std::int64_t ldc,
const std::vector<sycl::event> &dependencies = {})
}
namespace oneapi::mkl::blas::row_major {
sycl::event symm(sycl::queue &queue,
oneapi::mkl::side left_right,
oneapi::mkl::uplo upper_lower,
std::int64_t m,
std::int64_t n,
T alpha,
const T* a,
std::int64_t lda,
const T* b,
std::int64_t ldb,
T beta,
T* c,
std::int64_t ldc,
const std::vector<sycl::event> &dependencies = {})
}
Input Parameters
- queue
- The queue where the routine should be executed.
- left_right
- Specifies whether matrixAis on the left side or right side of the multiplication. See Data Types for more details.
- upper_lower
- Specifies whether matrixAis upper or lower triangular. See Data Types for more details.
- m
- Number of rows of matrixBand matrixC. Must be at least zero.
- n
- Number of columns of matrixBand matrixC. Must be at least zero.
- alpha
- Scaling factor for matrix-matrix product.
- a
- Pointer to input matrixA. Size of the array must be at leastlda*mifleft_right=side::leftorlda*nifleft_right=side::right. See Matrix Storage for more details.
- lda
- Leading dimension of matrixA. Must be at leastmifleft_right=side::leftor at leastnifleft_right=side::right. Must be positive.
- b
- Pointer to input matrixB. Size of the array must be at leastldb*nif column major layout or at leastldb*mif row major layout is used. See Matrix Storage for more details.
- ldb
- Leading dimension of matrixB. Must be at leastmif column major layout or at leastnif row major layout is used. Must be positive.
- beta
- Scaling factor for matrixC.
- c
- Pointer to input/output matrixC. Size of the array must be at leastldc*nif column major layout or at leastldc*mif row major layout is used. See Matrix Storage for more details.
- ldc
- Leading dimension of matrixC. Must be at leastmif column major layout or at leastnif row major layout is used. Must be positive.
- dependencies
- List of events to wait for before starting computation, if any. If omitted, defaults to no dependencies.
Output Parameters
- c
- Pointer to output matrix overwritten byalpha*A*B+beta*Cifleft_right=side::leftoralpha*B*A+beta*Cifleft_right=side::right.Ifbeta= 0, matrixCdoes not need to be initialized before callingsymm.
Return Values
Output event to wait on to ensure computation is complete.