24.02.1
|
Go to the documentation of this file.
54 if (
dst->total_size() != 0)
58 if (dst_window ==
nullptr)
100 if (dst_window !=
nullptr)
102 _has_dst_window =
true;
103 _dst_window =
Window(*dst_window);
105 const int vec_size_x_leftover = width_x % vec_size_x;
106 const bool multi_access_x = width_x >=
static_cast<int32_t
>(vec_size_x);
119 const int width_x =
src->tensor_shape().x();
120 const int vec_size_x_leftover = width_x % vec_size_x;
128 _kernel =
create_kernel(compile_context,
"copy_tensor", build_opts.options());
131 ICLKernel::configure_internal(win_config);
161 unsigned int idx = 0;
173 unsigned int idx = 0;
Class to describe a number of elements in each dimension.
std::string to_string(T &&value)
Convert integer and float values to string.
constexpr int start() const
Return the start of the dimension.
SimpleTensor< float > src
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
Status validate_arguments(const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *dst, const PadStrideInfo &conv_info)
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
Window collapse_if_possible(const Window &full_window, size_t first, size_t last, bool *has_collapsed=nullptr) const
Collapse the dimensions between first and last if possible.
constexpr size_t num_iterations(size_t dimension) const
Return the number of iterations needed to iterate through a given dimension.
void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst, Window *dst_window=nullptr)
Initialize the kernel's src, dst.
ITensor * get_tensor(int id)
Get tensor of a given id from the pac.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Manages all the OpenCL kernels compilation and caching, provides accessors for the OpenCL Context.
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
#define ARM_COMPUTE_ERROR_ON(cond)
If the condition is true then an error message is printed and an exception thrown.
const ITensor * get_const_tensor(int id) const
Get constant tensor of a given id.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
void add_option(std::string option)
Adds option to the existing build option list.
bool auto_init_if_empty(ITensorInfo &info, const TensorShape &shape, int num_channels, DataType data_type, QuantizationInfo quantization_info=QuantizationInfo())
Auto initialize the tensor info (shape, number of channels and data type) if the current assignment i...
cl::Kernel create_kernel(const CLCompileContext &ctx, const std::string &kernel_name, const std::set< std::string > &build_opts=std::set< std::string >())
Creates an opencl kernel using a compile context.
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
bool slide_window_slice_3D(Window &slice) const
Slide the passed 3D window slice.
Describe one of the image's dimensions with a start, end and step.
void set(size_t dimension, const Dimension &dim)
Set the values of a given dimension.
auto ceil_to_multiple(S value, T divisor) -> decltype(((value+divisor - 1)/divisor) *divisor)
Computes the smallest number larger or equal to value that is a multiple of divisor.
Window first_slice_window_3D() const
First 3D slice of the window.
const Window & window() const
The maximum window the kernel can be executed on.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_QUANTIZATION_INFO(...)
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
void add_3D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 3D tensor's parameters to the object's kernel's arguments starting from the index idx.
Describe a multidimensional execution window.
@ ELEMENTWISE
Elementwise CL kernel type.
static Status validate(const ITensorInfo *src, const ITensorInfo *dst, Window *dst_window=nullptr)
Static function to check if given info will lead to a valid configuration.
Copyright (c) 2017-2024 Arm Limited.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DIMENSIONS(...)
unsigned int adjust_vec_size(unsigned int vec_size, size_t dim0)
Returns the adjusted vector size in case it is less than the input's first dimension,...
bool has_padding_changed(const std::unordered_map< const ITensorInfo *, PaddingSize > &padding_map)
Check if the previously stored padding info has changed after configuring a kernel.
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
Store the tensor's metadata.
constexpr int end() const
Return the end of the dimension.
constexpr const Dimension & x() const
Alias to access the first dimension of the window.
std::unordered_map< const ITensorInfo *, PaddingSize > get_padding_info(std::initializer_list< const ITensorInfo * > infos)
Stores padding information before configuring a kernel.
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)
void enqueue(cl::CommandQueue &queue, ICLKernel &kernel, const Window &window, const cl::NDRange &lws_hint=CLKernelLibrary::get().default_ndrange(), bool use_dummy_work_items=false)
Add the kernel to the command queue with the given window.