syrk#
Performs a symmetric rank-k update.
Description
The syrk
routines perform a rank-k update of a symmetric matrix C
by a general matrix A
. The operation is defined as:
where:
op(X
) is one of op(X
) = X
or op(X
) = X
T
,
alpha
and beta
are scalars,
C
is a symmetric matrix and A
is a general matrix.
Here op(A
) is n
-by-k
, and C
is n
-by-n
.
syrk
supports the following precisions.
T
float
double
std::complex<float>
std::complex<double>
syrk (Buffer Version)#
Syntax
namespace oneapi::mkl::blas::column_major {
void syrk(sycl::queue &queue,
onemkl::uplo upper_lower,
onemkl::transpose trans,
std::int64_t n,
std::int64_t k,
T alpha,
sycl::buffer<T,1> &a,
std::int64_t lda,
T beta,
sycl::buffer<T,1> &c,
std::int64_t ldc)
}
namespace oneapi::mkl::blas::row_major {
void syrk(sycl::queue &queue,
onemkl::uplo upper_lower,
onemkl::transpose trans,
std::int64_t n,
std::int64_t k,
T alpha,
sycl::buffer<T,1> &a,
std::int64_t lda,
T beta,
sycl::buffer<T,1> &c,
std::int64_t ldc)
}
Input Parameters
- queue
The queue where the routine should be executed.
- upper_lower
Specifies whether
A
’s data is stored in its upper or lower triangle. See oneMKL Defined Datatypes for more details.- trans
Specifies op(
A
), the transposition operation applied toA
(See oneMKL Defined Datatypes for more details). Conjugation is never performed, even iftrans
=transpose::conjtrans
.- n
Number of rows and columns in
C
. The value ofn
must be at least zero.- k
Number of columns in op(
A
).The value ofk
must be at least zero.- alpha
Scaling factor for the rank-k update.
- a
Buffer holding input matrix
A
.trans
=transpose::nontrans
trans
=transpose::trans
ortranspose::conjtrans
Column major
A
is ann
-by-k
matrix so the arraya
must have size at leastlda
*k
.A
is ank
-by-n
matrix so the arraya
must have size at leastlda
*n
Row major
A
is ann
-by-k
matrix so the arraya
must have size at leastlda
*n
.A
is ank
-by-n
matrix so the arraya
must have size at leastlda
*k
.See Matrix Storage for more details.
- lda
The leading dimension of
A
. It must be positive.trans
=transpose::nontrans
trans
=transpose::trans
ortranspose::conjtrans
Column major
lda
must be at leastn
.lda
must be at leastk
.Row major
lda
must be at leastk
.lda
must be at leastn
.- beta
Scaling factor for matrix
C
.- c
Buffer holding input/output matrix
C
. Must have size at leastldc
*n
. See Matrix Storage for more details.- ldc
Leading dimension of
C
. Must be positive and at leastn
.
Output Parameters
- c
Output buffer, overwritten by
alpha
*op(A
)*op(A
)T +beta
*C
.
syrk (USM Version)#
Syntax
namespace oneapi::mkl::blas::column_major {
sycl::event syrk(sycl::queue &queue,
onemkl::uplo upper_lower,
onemkl::transpose trans,
std::int64_t n,
std::int64_t k,
T alpha,
const T* a,
std::int64_t lda,
T beta,
T* c,
std::int64_t ldc,
const std::vector<sycl::event> &dependencies = {})
}
namespace oneapi::mkl::blas::row_major {
sycl::event syrk(sycl::queue &queue,
onemkl::uplo upper_lower,
onemkl::transpose trans,
std::int64_t n,
std::int64_t k,
T alpha,
const T* a,
std::int64_t lda,
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.
- upper_lower
Specifies whether
A
’s data is stored in its upper or lower triangle. See oneMKL Defined Datatypes for more details.- trans
Specifies op(
A
), the transposition operation applied toA
(See oneMKL Defined Datatypes for more details). Conjugation is never performed, even iftrans
=transpose::conjtrans
.- n
Number of rows and columns in
C
. The value ofn
must be at least zero.- k
Number of columns in op(
A
). The value ofk
must be at least zero.- alpha
Scaling factor for the rank-k update.
- a
Pointer to input matrix
A
.trans
=transpose::nontrans
trans
=transpose::trans
ortranspose::conjtrans
Column major
A
is ann
-by-k
matrix so the arraya
must have size at leastlda
*k
.A
is ank
-by-n
matrix so the arraya
must have size at leastlda
*n
Row major
A
is ann
-by-k
matrix so the arraya
must have size at leastlda
*n
.A
is ank
-by-n
matrix so the arraya
must have size at leastlda
*k
.See Matrix Storage for more details.
- lda
The leading dimension of
A
. It must be positive.trans
=transpose::nontrans
trans
=transpose::trans
ortranspose::conjtrans
Column major
lda
must be at leastn
.lda
must be at leastk
.Row major
lda
must be at leastk
.lda
must be at leastn
.- beta
Scaling factor for matrix
C
.- c
Pointer to input/output matrix
C
. Must have size at leastldc
*n
. See Matrix Storage for more details.- ldc
Leading dimension of
C
. Must be positive and at leastn
.
Output Parameters
- c
Pointer to the output matrix, overwritten by
alpha
*op(A
)*op(A
)T +beta
*C
.
Return Values
Output event to wait on to ensure computation is complete.
Parent topic: BLAS Level 3 Routines