gemm_bias#
Computes a matrix-matrix product using general integer matrices with bias.
Description
The gemm_bias routines compute a scalar-matrix-matrix product and add the result to a scalar-matrix product, using general integer matrices with biases/offsets. 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
and beta
are scalars,
A_offset
is an m
-by-k
matrix with every element equal to the value ao,
B_offset
is a k
-by-n
matrix with every element equal to the value bo,
C_offset
is an m
-by-n
matrix defined by the
co buffer as described below,
A
, B
, and C
are matrices,
op(A
) is m
x k
, op(B
) is k
x n
, and
C
is m
x n
.
gemm_bias
supports the following precisions.
Ts
Ta
Tb
Tc
float
std::uint8_t
std::uint8_t
std::int32_t
float
std::int8_t
std::uint8_t
std::int32_t
float
std::uint8_t
std::int8_t
std::int32_t
float
std::int8_t
std::int8_t
std::int32_t
gemm_bias (Buffer Version)#
Syntax
namespace oneapi::mkl::blas::column_major {
void gemm_bias(sycl::queue &queue,
onemkl::transpose transa,
onemkl::transpose transb,
onemkl::offset offset_type,
std::int64_t m,
std::int64_t n,
std::int64_t k,
Ts alpha,
sycl::buffer<Ta,1> &a,
std::int64_t lda,
Ta ao,
sycl::buffer<Tb,1> &b,
std::int64_t ldb,
Tb bo,
Ts beta,
sycl::buffer<Tc,1> &c,
std::int64_t ldc,
sycl::buffer<Tc,1> &co)
}
namespace oneapi::mkl::blas::row_major {
void gemm_bias(sycl::queue &queue,
onemkl::transpose transa,
onemkl::transpose transb,
onemkl::offset offset_type,
std::int64_t m,
std::int64_t n,
std::int64_t k,
Ts alpha,
sycl::buffer<Ta,1> &a,
std::int64_t lda,
Ta ao,
sycl::buffer<Tb,1> &b,
std::int64_t ldb,
Tb bo,
Ts beta,
sycl::buffer<Tc,1> &c,
std::int64_t ldc,
sycl::buffer<Tc,1> &co)
}
Input Parameters
- queue
The queue where the routine should be executed.
- transa
Specifies op(
A
), the transposition operation applied toA
. See oneMKL Defined Datatypes for more details.- transb
Specifies op(
B
), the transposition operation applied toB
. See oneMKL Defined Datatypes for more details.- offset_type
Specifies the form of
C_offset
used in the matrix multiplication. See oneMKL Defined Datatypes for more details.- m
Number of rows of op(
A
) andC
. Must be at least zero.- n
Number of columns of op(
B
) andC
. Must be at least zero.- k
Number of columns of op(
A
) and rows of op(B
). Must be at least zero.- alpha
Scaling factor for the matrix-matrix product.
- a
The buffer holding the input matrix
A
.A
not transposedA
transposedColumn major
A
is anm
-by-k
matrix so the arraya
must have size at leastlda
*k
.A
is ank
-by-m
matrix so the arraya
must have size at leastlda
*m
Row major
A
is anm
-by-k
matrix so the arraya
must have size at leastlda
*m
.A
is ank
-by-m
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.A
not transposedA
transposedColumn major
lda
must be at leastm
.lda
must be at leastk
.Row major
lda
must be at leastk
.lda
must be at leastm
.- ao
Specifies the scalar offset value for matrix
A
.- b
Buffer holding the input matrix
B
.B
not transposedB
transposedColumn major
B
is ank
-by-n
matrix so the arrayb
must have size at leastldb
*n
.B
is ann
-by-k
matrix so the arrayb
must have size at leastldb
*k
Row major
B
is ank
-by-n
matrix so the arrayb
must have size at leastldb
*k
.B
is ann
-by-k
matrix so the arrayb
must have size at leastldb
*n
See Matrix Storage for more details.
- ldb
The leading dimension of
B
. It must be positive.B
not transposedB
transposedColumn major
ldb
must be at leastk
.ldb
must be at leastn
.Row major
ldb
must be at leastn
.ldb
must be at leastk
.- bo
Specifies the scalar offset value for matrix
B
.- beta
Scaling factor for matrix
C
.- c
Buffer holding the input/output matrix
C
. It must have a size of at leastldc
*n
if column major layout is used to store matrices or at leastldc
*m
if row major layout is used to store matrices . See Matrix Storage for more details.- ldc
The leading dimension of
C
. It must be positive and at leastm
if column major layout is used to store matrices or at leastn
if row major layout is used to store matrices.- co
Buffer holding the offset values for matrix
C
.If
offset_type
=offset::fix
, theco
array must have size at least 1.If
offset_type
=offset::col
, theco
array must have size at leastmax(1,m)
.If
offset_type
=offset::row
, theco
array must have size at leastmax(1,n)
.
Output Parameters
- c
Output buffer, overwritten by
alpha
* (op(A
) -A_offset
)*(op(B
) -B_offset
) +beta
*C
+C_offset
.
Notes
If beta
= 0, matrix C
does not need to be initialized
before calling gemm_bias
.
gemm_bias (USM Version)#
Syntax
namespace oneapi::mkl::blas::column_major {
sycl::event gemm_bias(sycl::queue &queue,
onemkl::transpose transa,
onemkl::transpose transb,
onemkl::offset offset_type,
std::int64_t m,
std::int64_t n,
std::int64_t k,
Ts alpha,
const Ta *a,
std::int64_t lda,
Ta ao,
const Tb *b,
std::int64_t ldb,
Tb bo,
Ts beta,
Tc *c,
std::int64_t ldc,
const Tc *co,
const std::vector<sycl::event> &dependencies = {})
}
namespace oneapi::mkl::blas::row_major {
sycl::event gemm_bias(sycl::queue &queue,
onemkl::transpose transa,
onemkl::transpose transb,
onemkl::offset offset_type,
std::int64_t m,
std::int64_t n,
std::int64_t k,
Ts alpha,
const Ta *a,
std::int64_t lda,
Ta ao,
const Tb *b,
std::int64_t ldb,
Tb bo,
Ts beta,
Tc *c,
std::int64_t ldc,
const Tc *co,
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 toA
. See oneMKL Defined Datatypes for more details.- transb
Specifies op(
B
), the transposition operation applied toB
. See oneMKL Defined Datatypes for more details.- offset_type
Specifies the form of
C_offset
used in the matrix multiplication. See oneMKL Defined Datatypes for more details.- m
Number of rows of op(
A
) andC
. Must be at least zero.- n
Number of columns of op(
B
) andC
. Must be at least zero.- k
Number of columns of op(
A
) and rows of op(B
). Must be at least zero.- alpha
Scaling factor for the matrix-matrix product.
- a
Pointer to input matrix
A
.A
not transposedA
transposedColumn major
A
is anm
-by-k
matrix so the arraya
must have size at leastlda
*k
.A
is ank
-by-m
matrix so the arraya
must have size at leastlda
*m
Row major
A
is anm
-by-k
matrix so the arraya
must have size at leastlda
*m
.A
is ank
-by-m
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.A
not transposedA
transposedColumn major
lda
must be at leastm
.lda
must be at leastk
.Row major
lda
must be at leastk
.lda
must be at leastm
.- ao
Specifies the scalar offset value for matrix
A
.- b
Pointer to input matrix
B
.B
not transposedB
transposedColumn major
B
is ank
-by-n
matrix so the arrayb
must have size at leastldb
*n
.B
is ann
-by-k
matrix so the arrayb
must have size at leastldb
*k
Row major
B
is ank
-by-n
matrix so the arrayb
must have size at leastldb
*k
.B
is ann
-by-k
matrix so the arrayb
must have size at leastldb
*n
See Matrix Storage for more details.
- ldb
The leading dimension of
B
. It must be positive.B
not transposedB
transposedColumn major
ldb
must be at leastk
.ldb
must be at leastn
.Row major
ldb
must be at leastn
.ldb
must be at leastk
.- bo
Specifies the scalar offset value for matrix
B
.- beta
Scaling factor for matrix
C
.- c
Pointer to input/output matrix
C
. It must have a size of at leastldc
*n
if column major layout is used to store matrices or at leastldc
*m
if row major layout is used to store matrices . See Matrix Storage for more details.- ldc
The leading dimension of
C
. It must be positive and at leastm
if column major layout is used to store matrices or at leastn
if row major layout is used to store matrices.- co
Pointer to offset values for matrix
C
.If
offset_type
=offset::fix
, theco
array must have size at least 1.If
offset_type
=offset::col
, theco
array must have size at leastmax(1,m)
.If
offset_type
=offset::row
, theco
array must have size at leastmax(1,n)
.- dependencies
List of events to wait for before starting computation, if any. If omitted, defaults to no dependencies.
Output Parameters
- c
Pointer to the output matrix, overwritten by
alpha
* (op(A
) -A_offset
)*(op(B
) -B_offset
) +beta
*C
+C_offset
.
Notes
If beta
= 0, matrix C
does not need to be initialized
before calling gemm_bias
.
Return Values
Output event to wait on to ensure computation is complete.
Parent topic: BLAS-like Extensions