copy_batch#
Computes a group of copy operations.
Description#
The copy_batch routines are batched versions of copy, performing
multiple copy operations in a single call. Each copy
operation copies one vector to another.
copy_batch supports the following precisions:
T |
|---|
|
|
|
|
copy_batch (Buffer Version)#
Buffer version of copy_batch supports only strided API.
Strided API#
Strided API operation is defined as:
for i = 0 … batch_size – 1
X and Y are vectors at offset i * stridex and i * stridey in x and y
Y = X
end for
where:
XandYare vectors
For strided API, all vectors x (y) have same parameters (size, increments) and are stored at constant stridex (stridey) from each other.
The x and y arrays contain all the input vectors. Total number of vectors in x and y are given by batch_size parameter.
Syntax#
namespace oneapi::mkl::blas::column_major {
void copy_batch(sycl::queue &queue,
std::int64_t n,
sycl::buffer<T, 1> &x,
std::int64_t incx,
std::int64_t stridex,
sycl::buffer<T, 1> &y,
std::int64_t incy,
std::int64_t stridey,
std::int64_t batch_size)
}
namespace oneapi::mkl::blas::row_major {
void copy_batch(sycl::queue &queue,
std::int64_t n,
sycl::buffer<T, 1> &x,
std::int64_t incx,
std::int64_t stridex,
sycl::buffer<T, 1> &y,
std::int64_t incy,
std::int64_t stridey,
std::int64_t batch_size)
}
Input Parameters#
- queue
The queue where the routine should be executed.
- n
Number of elements in vectors
XandY.- x
Buffer holding input vectors
X. Size of the buffer must be at leastbatch_size*stridex.- incx
Stride between two consecutive elements of
Xvectors. Must not be zero.- stridex
Stride between two consecutive
Xvectors. Must be at least zero.- y
Buffer holding input/output vectors
Y. Size of the buffer must be at leastbatch_size*stridey.- incy
Stride between two consecutive elements of
Yvectors. Must not be zero.- stridey
Stride between two consecutive
Yvectors. Must be at least (1 + (n-1)*abs(incy)). See Matrix Storage for more details.- batch_size
Number of
copycomputations to perform. Must be at least zero.
Output Parameters#
- y
Output buffer overwritten by
batch_sizecopyoperations.
copy_batch (USM Version)#
USM version of copy_batch supports group API and strided API.
Group API#
The type Ti of integer pointers in the group API may be either std::int64_t or std::int32_t.
Group API operation is defined as:
idx = 0
for i = 0 … group_count – 1
for j = 0 … group_size – 1
X and Y are vectors at x[idx] and y[idx]
Y = X
idx = idx + 1
end for
end for
where:
XandYare vectors
For group API, each group contains vectors with the same parameters (size and increment).
The x and y arrays contain the pointers for all the input vectors. Total number of vectors in x and y are given by:
Syntax#
namespace oneapi::mkl::blas::column_major {
sycl::event copy_batch(sycl::queue &queue,
const Ti *n,
const T **x,
const Ti *incx,
T **y,
const Ti *incy,
std::int64_t group_count,
const Ti *group_size,
const std::vector<sycl::event> &dependencies = {})
}
namespace oneapi::mkl::blas::row_major {
sycl::event copy_batch(sycl::queue &queue,
const Ti *n,
const T **x,
const Ti *incx,
T **y,
const Ti *incy,
std::int64_t group_count,
const Ti *group_size,
const std::vector<sycl::event> &dependencies = {})
}
Input Parameters#
- queue
The queue where the routine should be executed.
- n
Array of
group_countintegers.n[i]specifies number of elements in vectorsXandYfor every vector in groupi.- x
Array of pointers to input vectors
Xwith sizetotal_batch_count. Size of the array allocated for theXvector of the groupimust be at least (1 + (n[i]– 1)*abs(incx[i])). See Matrix Storage for more details.- incx
Array of
group_countintegers.incx[i]specifies stride of vectorXin groupi. Must not be zero.- y
Array of pointers to input/output vectors
Ywith sizetotal_batch_count. Size of the array allocated for theYvector of the groupimust be at least (1 + (n[i]– 1)*abs(incy[i])). See Matrix Storage for more details.- incy
Array of
group_countintegers.incy[i]specifies the stride of vectorYin groupi. Must not be zero.- group_count
Number of groups. Must be at least zero.
- group_size
Array of
group_countintegers.group_size[i]specifies the number ofcopyoperations in groupi. Each element ingroup_sizemust be at least zero.- dependencies
List of events to wait for before starting computation, if any. If omitted, defaults to no dependencies.
Output Parameters#
- y
Array of pointers holding
Yvectors, overwritten bytotal_batch_countcopyoperations.
Return Values#
Output event to wait on to ensure computation is complete.
Examples#
An example of how to use USM version of copy_batch can be found in oneMKL installation directory, under:
share/doc/mkl/examples/sycl/blas/source/copy_batch_usm.cpp
Strided API#
Strided API operation is defined as:
for i = 0 … batch_size – 1
X and Y are vectors at offset i * stridex and i * stridey in x and y
Y = X
end for
where:
XandYare vectors
For strided API, all vectors x (y) have same parameters (size, increments) and are stored at constant stridex (stridey) from each other.
The x and y arrays contain all the input vectors. Total number of vectors in x and y are given by batch_size parameter.
Syntax#
namespace oneapi::mkl::blas::column_major {
sycl::event copy_batch(sycl::queue &queue,
std::int64_t n,
const T *x,
std::int64_t incx,
std::int64_t stridex,
T *y,
std::int64_t incy,
std::int64_t stridey,
std::int64_t batch_size,
const std::vector<sycl::event> &dependencies = {})
}
namespace oneapi::mkl::blas::row_major {
sycl::event copy_batch(sycl::queue &queue,
std::int64_t n,
const T *x,
std::int64_t incx,
std::int64_t stridex,
T *y,
std::int64_t incy,
std::int64_t stridey,
std::int64_t batch_size,
const std::vector<sycl::event> &dependencies = {})
}
Input Parameters#
- queue
The queue where the routine should be executed.
- n
Number of elements in vectors
XandY.- x
Pointer to input vectors
X. Size of the array must be at leastbatch_size*stridex.- incx
Stride between two consecutive elements of
Xvectors. Must not be zero.- stridex
Stride between two consecutive
Xvectors. Must be at least zero.- y
Pointer to input/output vectors
Y. Size of the array must be at leastbatch_size*stridey.- incy
Stride between two consecutive elements of
Yvectors. Must not be zero.- stridey
Stride between two consecutive
Yvectors. Must be at least (1 + (n-1)*abs(incy)). See Matrix Storage for more details.- batch_size
Number of
copycomputations to perform. Must be at least zero.- dependencies
List of events to wait for before starting computation, if any. If omitted, defaults to no dependencies.
Output Parameters#
- y
Output vectors overwritten by
batch_sizecopyoperations.
Return Values#
Output event to wait on to ensure computation is complete.