omatcopy2#
Computes two-strided scaling and out-of-place transposition or copying of general dense matrices.
Description
The omatcopy2
routine performs a two-strided scaling and out-of-place
transposition or copy of matrices. For complex matrices the transpose operation can
be a conjugate transpose.
Normally, matrices in the BLAS or LAPACK are specified by a single
stride index. For instance, in the column-major order, A(2,1)
is
stored in memory one element away from A(1,1)
, but A(1,2)
is a leading
dimension away. The leading dimension in this case is at least the
number of rows of the source matrix. If a matrix has two strides, then
both A(2,1)
and A(1,2)
may be an arbitrary distance from A(1,1)
.
The operation is defined as:
where:
op(X
) is one of op(X
) = X
, or op(X
) = X
T, or op(X
) = X
H,
alpha
is a scalar,
A
and B
are matrices,
A
is m
x n
matrix,
B
is m
x n
matrix if op
is non-transpose and an n
x m
matrix otherwise.,
omatcopy2
supports the following precisions:
T
float
double
std::complex<float>
std::complex<double>
omatcopy2 (Buffer Version)#
Syntax
namespace oneapi::mkl::blas::column_major {
void omatcopy2(sycl::queue &queue,
oneapi::mkl::transpose trans,
std::int64_t m,
std::int64_t n,
T alpha,
sycl::buffer<T, 1> &a,
std::int64_t lda,
std::int64_t stridea,
sycl::buffer<T, 1> &b,
std::int64_t ldb,
std::int64_t strideb);
}
namespace oneapi::mkl::blas::row_major {
void omatcopy2(sycl::queue &queue,
oneapi::mkl::transpose trans,
std::int64_t m,
std::int64_t n,
T alpha,
sycl::buffer<T, 1> &a,
std::int64_t lda,
std::int64_t stridea,
sycl::buffer<T, 1> &b,
std::int64_t ldb,
std::int64_t strideb);
}
Input Parameters
- queue
The queue where the routine should be executed.
- trans
Specifies op(
A
), the transposition operation applied to the matrixA
. See oneMKL defined datatypes for more details.- m
Number of rows for the matrix
A
. Must be at least zero.- n
Number of columns for the matrix
A
. Must be at least zero.- alpha
Scaling factor for the matrix transposition or copy.
- a
Buffer holding the input matrix
A
. Must have size at leastlda
*n
for column major ordering and at leastlda
*m
for row major ordering.- lda
Leading dimension of the matrix
A
. If matrices are stored using column major layout,lda
is the number of elements in the array between adjacent columns of the matrix, and must be at leaststridea
* (m
-1) + 1. If using row major layout,lda
is the number of elements between adjacent rows of the matrix and must be at leaststridea
* (n
-1) + 1.- stridea
The second stride of the matrix
A
. For column major layout,stridea
is the number of elements in the array between adjacent rows of the matrix. For row major layoutstridea
is the number of elements between adjacent columns of the matrix. In both casesstridea
must be at least 1.- b
Buffer holding the output matrix
B
.trans
=transpose::nontrans
trans
=transpose::trans
ortrans
=transpose::conjtrans
Column major
B
ism
xn
matrix. Size of bufferb
must be at leastldb
*n
B
isn
xm
matrix. Size of bufferb
must be at leastldb
*m
Row major
B
ism
xn
matrix. Size of bufferb
must be at leastldb
*m
B
isn
xm
matrix. Size of bufferb
must be at leastldb
*n
- ldb
The leading dimension of the matrix
B
. Must be positive.trans
=transpose::nontrans
trans
=transpose::trans
ortrans
=transpose::conjtrans
Column major
ldb
must be at leaststrideb
* (m
-1) + 1.ldb
must be at leaststrideb
* (n
-1) + 1.Row major
ldb
must be at leaststrideb
* (n
-1) + 1.ldb
must be at leaststrideb
* (m
-1) + 1.- strideb
The second stride of the matrix
B
. For column major layout,strideb
is the number of elements in the array between adjacent rows of the matrix. For row major layout,strideb
is the number of elements between adjacent columns of the matrix. In both casesstrideb
must be at least 1.
Output Parameters
- b
Output buffer, overwritten by
alpha
* op(A
).
Throws
This routine shall throw the following exceptions if the associated condition is detected. An implementation may throw additional implementation-specific exception(s) in case of error conditions not covered here.
omatcopy2 (USM Version)#
Syntax
namespace oneapi::mkl::blas::column_major {
sycl::event omatcopy2(sycl::queue &queue,
oneapi::mkl::transpose trans,
std::int64_t m,
std::int64_t n,
T alpha,
const T *a,
std::int64_t lda,
std::int64_t stridea,
T *b,
std::int64_t ldb,
std::int64_t strideb,
const std::vector<sycl::event> &dependencies = {});
}
namespace oneapi::mkl::blas::row_major {
sycl::event omatcopy2(sycl::queue &queue,
oneapi::mkl::transpose trans,
std::int64_t m,
std::int64_t n,
T alpha,
const T *a,
std::int64_t lda,
std::int64_t stridea,
T *b,
std::int64_t ldb,
std::int64_t strideb,
const std::vector<sycl::event> &dependencies = {});
}
Input Parameters
- queue
The queue where the routine will be executed.
- trans
Specifies op(
A
), the transposition operation applied to matrixA
. See oneMKL defined datatypes for more details.- m
Number of rows for the matrix
A
. Must be at least zero.- n
Number of columns for the matrix
A
. Must be at least zero.- alpha
Scaling factor for the matrix transposition or copy.
- a
Pointer to input matrix
A
. Must have size at leastlda
*n
for column-major and at leastlda
*m
for row-major.- lda
Leading dimension of the matrix
A
. If matrices are stored using column major layout,lda
is the number of elements in the array between adjacent columns of the matrix, and must be at leaststridea
* (m
-1) + 1. If using row major layout,lda
is the number of elements between adjacent rows of the matrix and must be at leaststridea
* (n
-1) + 1.- stridea
The second stride of the matrix
A
. For column major layout,stridea
is the number of elements in the array between adjacent rows of the matrix. For row major layoutstridea
is the number of elements between adjacent columns of the matrix. In both casesstridea
must be at least 1.- b
Pointer to output matrix
B
.trans
=transpose::nontrans
trans
=transpose::trans
ortrans
=transpose::conjtrans
Column major
B
ism
xn
matrix. Size of arrayb
must be at leastldb
*n
B
isn
xm
matrix. Size of arrayb
must be at leastldb
*m
Row major
B
ism
xn
matrix. Size of arrayb
must be at leastldb
*m
B
isn
xm
matrix. Size of arrayb
must be at leastldb
*n
- ldb
The leading dimension of the matrix
B
. Must be positive.trans
=transpose::nontrans
trans
=transpose::trans
ortrans
=transpose::conjtrans
Column major
ldb
must be at leaststrideb
* (m
-1) + 1.ldb
must be at leaststrideb
* (n
-1) + 1.Row major
ldb
must be at leaststrideb
* (n
-1) + 1.ldb
must be at leaststrideb
* (m
-1) + 1.- strideb
The second stride of the matrix
B
. For column major layout,strideb
is the number of elements in the array between adjacent rows of the matrix. For row major layout,strideb
is the number of elements between adjacent columns of the matrix. In both casesstrideb
must be at least 1.- dependencies
List of events to wait for before starting computation, if any. If omitted, defaults to no dependencies.
Output Parameters
- b
Pointer to output matrix
B
overwritten byalpha
* op(A
).
Return Values
Output event to wait on to ensure computation is complete.
Throws
This routine shall throw the following exceptions if the associated condition is detected. An implementation may throw additional implementation-specific exception(s) in case of error conditions not covered here.
oneapi::mkl::unsupported_device
Parent topic: BLAS-like Extensions