45 Status validate_arguments(
const ITensorInfo *
input,
unsigned int axis,
unsigned int idx_input,
unsigned int num_tensors,
const ITensorInfo *output)
54 if(output->total_size() != 0)
64 std::pair<Status, Window> validate_and_configure_window(ITensorInfo *input,
unsigned int axis,
unsigned int num_tensors, ITensorInfo *output)
72 return std::make_pair(Status{}, win);
77 : _input(nullptr), _output(nullptr)
96 auto win_config = validate_and_configure_window(input->
info(), axis, num_tensors, output->
info());
106 _kernel =
create_kernel(compile_context,
"stack_layer", build_opts.options());
109 ICLKernel::configure_internal(win_config.second);
112 _kernel.setArg<cl_uint>(idx, idx_input);
135 unsigned int idx = 0;
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
#define ARM_COMPUTE_RETURN_ERROR_ON_F16_UNSUPPORTED(tensor)
const Window & window() const
The maximum window the kernel can be executed on.
static Status validate(const ITensorInfo *input, unsigned int axis, unsigned int idx_input, unsigned int num_tensors, const ITensorInfo *output)
Static function to check if given info will lead to a valid configuration of CLStackLayerKernel.
TensorShape compute_stack_shape(const ITensorInfo &a, unsigned int axis, unsigned int num_tensors)
Calculate the stack output shape of a tensor.
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_QUANTIZATION_INFO(...)
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.
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
std::string to_string(T &&value)
Convert integer and float values to string.
virtual DataType data_type() const =0
Data type used for each element of the tensor.
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
Store the tensor's metadata.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Manages all the OpenCL kernels compilation and caching, provides accessors for the OpenCL Context...
#define ARM_COMPUTE_RETURN_ERROR_ON(cond)
If the condition is true, an error is returned.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DIMENSIONS(...)
void use_tensor_dimensions(const TensorShape &shape, size_t first_dimension=Window::DimX)
Use the tensor's dimensions to fill the window dimensions.
Copyright (c) 2017-2021 Arm Limited.
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
void add_option(std::string option)
Adds option to the existing build option list.
Window collapse(const Window &full_window, size_t first, size_t last=Coordinates::num_max_dimensions) const
Collapse the dimensions between first and last.
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.
void run(const Window &window, cl::CommandQueue &queue) override
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue...
virtual const TensorShape & tensor_shape() const =0
Size for each dimension of the tensor.
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
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...
virtual std::unique_ptr< T > clone() const =0
Provide a clone of the current object of class T.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
CLStackLayerKernel()
Default constructor.
static constexpr unsigned int num_arguments_per_4D_tensor()
Returns the number of arguments enqueued per 4D tensor object.
Elementeise CL kernel type.
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Interface for OpenCL tensor.
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
void configure(const ICLTensor *input, unsigned int axis, unsigned int idx_input, unsigned int num_tensors, ICLTensor *output)
Initialise the kernel's inputs and output.
Window first_slice_window_4D() const
First 4D slice of the window.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
void add_4D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 4D tensor's parameters to the object's kernel's arguments starting from the index idx...
Describe a multidimensional execution window.
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)