Eigen-unsupported  5.0.1-dev+284dcc12
 
Loading...
Searching...
No Matches
Eigen::TensorSycl::internal::GeneralVectorTensor< OutScalar, OutAccessor, VectorMapper, TensorMapper, StorageIndex, Properties, KFactor, Vectorizable, is_lhs_vec, IsFinal > Struct Template Reference

#include <unsupported/Eigen/CXX11/src/Tensor/TensorContractionSycl.h>

Detailed Description

template<typename OutScalar, typename OutAccessor, typename VectorMapper, typename TensorMapper, typename StorageIndex, typename Properties, StorageIndex KFactor, bool Vectorizable, bool is_lhs_vec, bool IsFinal>
struct Eigen::TensorSycl::internal::GeneralVectorTensor< OutScalar, OutAccessor, VectorMapper, TensorMapper, StorageIndex, Properties, KFactor, Vectorizable, is_lhs_vec, IsFinal >

GeneralVectorTensor is a template class that provides Tensor -vector contraction operation, which is a special case of Tensor Tensor contraction.

Template Parameters
OutScalardetermines the output scalar type
OutAccessordetermines the sycl accessor type for out put (please see the sycl-1.2.1 specification (https://www.khronos.org/registry/SYCL/specs/sycl-1.2.1.pdf) for accessor definition)
VectorMapperdetermines the tensor contraction mapper for the vector input (can be lhs or rhs)
TensorMapperdetermines the tensor contraction mapper for the tensor input (can be lhs or rhs)
StorageIndexdetermines the StorageIndex Type
Propertiesdetermines the Contraction Panel properties
KFactordetermines the number of elements in K dimension in a Tile
Vectorizabledetermines whether or not the vectorization is enabled for the Eigen expression.
is_lhs_vecdetermines whether lhs is a vector or rhs is a vector
IsFinaldetermine if this is the final kernel. If so, the result will be written in a final output. Otherwise, the result of contraction will be written iin a temporary buffer.
Parameters
scratchdetermines the local memory containing the vector block for each work-group
vecdetermines the vector input (tensor mapper)
matdetermines the tensor input (tensor mapper)
out_resdetermines the output vector containing the contraction result
nonContractGroupSizea logical number determining the number of work-group for non-contracting dimension
nonContractDimdetermines the size of non contracting dimension for the flattened tensor
contractDimdetermines the size of non contracting dimension for the flattened tensor

The documentation for this struct was generated from the following file: