44 T operator()(
const T &lhs,
const T &rhs)
const 46 return (lhs + rhs * rhs);
70 const int reduce_elems = src.
shape()[axis];
71 const int upper_dims = src.
shape().total_size_upper(axis + 1);
73 for(
int du = 0; du < upper_dims; ++du)
77 const T *src_row_ptr = src.
data() + du * reduce_elems;
78 dst[du] = reduce_operation(src_row_ptr, reduce_elems, op);
#define ARM_COMPUTE_ERROR(...)
Print the given message then throw an std::runtime_error.
ReductionOperation
Available reduction operations.
DataType data_type() const override
Data type of the tensor.
TensorShape shape() const override
Shape of the tensor.
SimpleTensor< T > reduction_operation(const SimpleTensor< T > &src, const TensorShape &dst_shape, unsigned int axis, ReductionOperation op)
This file contains all available output stages for GEMMLowp on OpenCL.
const T * data() const
Constant pointer to the underlying buffer.
Simple tensor object that stores elements in a consecutive chunk of memory.
__kernel void accumulate(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_offset_first_element_in_bytes, __global uchar *accu_ptr, uint accu_stride_x, uint accu_step_x, uint accu_stride_y, uint accu_step_y, uint accu_offset_first_element_in_bytes)
This function accumulates an input image into output image.
convolution configure & src