gemm#
Computes a matrix-matrix product with general matrices.
Description#
The gemm
routines compute a scalar-matrix-matrix product and add the result to a scalar-matrix product, with general matrices.
The operation is defined as:
where:
op(
X
) is one of op(X
) =X
, or op(X
) =X
T, or op(X
) =X
Halpha
andbeta
are scalarsA
,B
andC
are matricesop(
A
) ism
xk
matrixop(
B
) isk
xn
matrixC
ism
xn
matrix
gemm
supports the following precisions:
Ta
(A matrix)
|
Tb
(B matrix)
|
Tc
(C matrix)
|
Ts
(alpha/beta)
|
---|---|---|---|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gemm (Buffer Version)#
Syntax#
namespace oneapi::mkl::blas::column_major {
void gemm(sycl::queue &queue,
oneapi::mkl::transpose transa,
oneapi::mkl::transpose transb,
std::int64_t m,
std::int64_t n,
std::int64_t k,
Ts alpha,
sycl::buffer<Ta,1> &a,
std::int64_t lda,
sycl::buffer<Tb,1> &b,
std::int64_t ldb,
Ts beta,
sycl::buffer<Tc,1> &c,
std::int64_t ldc,
compute_mode mode = compute_mode::unset)
}
namespace oneapi::mkl::blas::row_major {
void gemm(sycl::queue &queue,
oneapi::mkl::transpose transa,
oneapi::mkl::transpose transb,
std::int64_t m,
std::int64_t n,
std::int64_t k,
Ts alpha,
sycl::buffer<Ta,1> &a,
std::int64_t lda,
sycl::buffer<Tb,1> &b,
std::int64_t ldb,
Ts beta,
sycl::buffer<Tc,1> &c,
std::int64_t ldc,
compute_mode mode = compute_mode::unset)
}
Input Parameters#
- queue
The queue where the routine should be executed.
- transa
Specifies op(
A
), the transposition operation applied to matrixA
. See Data Types for more details.- transb
Specifies op(
B
), the transposition operation applied to matrixB
. See Data Types for more details.- m
Number of rows of matrix op(
A
) and matrixC
. Must be at least zero.- n
Number of columns of matrix op(
B
) and matrixC
. Must be at least zero.- k
Number of columns of matrix op(
A
) and rows of matrix op(B
). Must be at least zero.- alpha
Scaling factor for matrix-matrix product.
- a
Buffer holding input matrix
A
. See Matrix Storage for more details.transa
=transpose::nontrans
transa
=transpose::trans
ortrans
=transpose::conjtrans
Column major
A
ism
xk
matrix. Size of arraya
must be at leastlda
*k
A
isk
xm
matrix. Size of arraya
must be at leastlda
*m
Row major
A
ism
xk
matrix. Size of arraya
must be at leastlda
*m
A
isk
xm
matrix. Size of arraya
must be at leastlda
*k
- lda
Leading dimension of matrix
A
. Must be positive.transa
=transpose::nontrans
transa
=transpose::trans
ortrans
=transpose::conjtrans
Column major
Must be at least
m
Must be at least
k
Row major
Must be at least
k
Must be at least
m
- b
Buffer holding input matrix
B
. See Matrix Storage for more details.transb
=transpose::nontrans
transb
=transpose::trans
ortrans
=transpose::conjtrans
Column major
B
isk
xn
matrix. Size of arrayb
must be at leastldb
*n
B
isn
xk
matrix. Size of arrayb
must be at leastldb
*k
Row major
B
isk
xn
matrix. Size of arrayb
must be at leastldb
*k
B
isn
xk
matrix. Size of arrayb
must be at leastldb
*n
- ldb
Leading dimension of matrix
B
. Must be positive.transb
=transpose::nontrans
transb
=transpose::trans
ortrans
=transpose::conjtrans
Column major
Must be at least
k
Must be at least
n
Row major
Must be at least
n
Must be at least
k
- beta
Scaling factor for matrix
C
.- c
Buffer holding input/output matrix
C
. See Matrix Storage for more details.Column major
C
ism
xn
matrix. Size of arrayc
must be at leastldc
*n
Row major
C
ism
xn
matrix. Size of arrayc
must be at leastldc
*m
- ldc
Leading dimension of matrix
C
. Must be positive.Column major
Must be at least
m
Row major
Must be at least
n
- mode
Optional. Compute mode settings. See Compute Modes for more details.
Output Parameters#
- c
Output buffer overwritten by
alpha
* op(A
)*op(B
) +beta
*C
.
Note
If beta
= 0, matrix C
does not need to be initialized before calling gemm
.
Examples#
An example of how to use buffer version of gemm
can be found in oneMKL installation directory, under:
share/doc/mkl/examples/sycl/blas/source/gemm.cpp
gemm (USM Version)#
Syntax#
namespace oneapi::mkl::blas::column_major {
sycl::event gemm(sycl::queue &queue,
oneapi::mkl::transpose transa,
oneapi::mkl::transpose transb,
std::int64_t m,
std::int64_t n,
std::int64_t k,
oneapi::mkl::value_or_pointer<Ts> alpha,
const Ta *a,
std::int64_t lda,
const Tb *b,
std::int64_t ldb,
oneapi::mkl::value_or_pointer<Ts> beta,
Tc *c,
std::int64_t ldc,
compute_mode mode = compute_mode::unset,
const std::vector<sycl::event> &dependencies = {})
}
namespace oneapi::mkl::blas::row_major {
sycl::event gemm(sycl::queue &queue,
oneapi::mkl::transpose transa,
oneapi::mkl::transpose transb,
std::int64_t m,
std::int64_t n,
std::int64_t k,
oneapi::mkl::value_or_pointer<Ts> alpha,
const Ta *a,
std::int64_t lda,
const Tb *b,
std::int64_t ldb,
oneapi::mkl::value_or_pointer<Ts> beta,
Tc *c,
std::int64_t ldc,
compute_mode mode = compute_mode::unset,
const std::vector<sycl::event> &dependencies = {})
}
Input Parameters#
- queue
The queue where the routine should be executed.
- transa
Specifies op(
A
), the transposition operation applied to matrixA
. See Data Types for more details.- transb
Specifies op(
B
), the transposition operation applied to matrixB
. See Data Types for more details.- m
Number of rows of matrix op(
A
) and matrixC
. Must be at least zero.- n
Number of columns of matrix op(
B
) and matrixC
. Must be at least zero.- k
Number of columns of matrix op(
A
) and rows of matrix op(B
). Must be at least zero.- alpha
Scaling factor for matrix-matrix product. See Scalar Arguments for more information on the
value_or_pointer
data type.- a
Pointer to input matrix
A
. See Matrix Storage for more details.A
not transposedA
transposedColumn major
A
ism
xk
matrix. Size of arraya
must be at leastlda
*k
A
isk
xm
matrix. Size of arraya
must be at leastlda
*m
Row major
A
ism
xk
matrix. Size of arraya
must be at leastlda
*m
A
isk
xm
matrix. Size of arraya
must be at leastlda
*k
- lda
Leading dimension of matrix
A
. Must be positive.A
not transposedA
transposedColumn major
Must be at least
m
Must be at least
k
Row major
Must be at least
k
Must be at least
m
- b
Pointer to input matrix
B
. See Matrix Storage for more details.B
not transposedB
transposedColumn major
B
isk
xn
matrix. Size of arrayb
must be at leastldb
*n
B
isn
xk
matrix. Size of arrayb
must be at leastldb
*k
Row major
B
isk
xn
matrix. Size of arrayb
must be at leastldb
*k
B
isn
xk
matrix. Size of arrayb
must be at leastldb
*n
- ldb
Leading dimension of matrix
B
. Must be positive.B
not transposedB
transposedColumn major
Must be at least
k
Must be at least
n
Row major
Must be at least
n
Must be at least
k
- beta
Scaling factor for matrix
C
. See Scalar Arguments for more information on thevalue_or_pointer
data type.- c
Pointer to input/output matrix
C
. See Matrix Storage for more details.Column major
C
ism
xn
matrix. Size of arrayc
must be at leastldc
*n
Row major
C
ism
xn
matrix. Size of arrayc
must be at leastldc
*m
- ldc
Leading dimension of matrix
C
. Must be positive.Column major
Must be at least
m
Row major
Must be at least
n
- mode
Optional. Compute mode settings. See Compute Modes for more details.
- dependencies
Optional. List of events to wait for before starting computation, if any. If omitted, defaults to no dependencies.
mode
anddependencies
may be omitted independently; it is not necessary to specifymode
in order to provide dependencies.
Output Parameters#
- c
Pointer to output matrix overwritten by
alpha
* op(A
)*op(B
) +beta
*C
.
Note
If beta
= 0, matrix C
does not need to be initialized before calling gemm
.
Return Values#
Output event to wait on to ensure computation is complete.
Examples#
An example of how to use USM version of gemm
can be found in oneMKL installation directory, under:
share/doc/mkl/examples/sycl/blas/source/gemm_usm.cpp