NESpaceToBatchLayerKernel Class Reference

Interface for the space to batch kernel. More...

#include <NESpaceToBatchLayerKernel.h>

Collaboration diagram for NESpaceToBatchLayerKernel:

Public Member Functions
const char *	name () const override
	Name of the kernel. More...
	NESpaceToBatchLayerKernel ()
	Default constructor. More...
	NESpaceToBatchLayerKernel (const NESpaceToBatchLayerKernel &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
NESpaceToBatchLayerKernel &	operator= (const NESpaceToBatchLayerKernel &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
	NESpaceToBatchLayerKernel (NESpaceToBatchLayerKernel &&)=default
	Allow instances of this class to be moved. More...
NESpaceToBatchLayerKernel &	operator= (NESpaceToBatchLayerKernel &&)=default
	Allow instances of this class to be moved. More...
	~NESpaceToBatchLayerKernel ()=default
	Default destructor. More...
void	configure (const ITensor *input, const ITensor *block_shape, const ITensor *paddings, ITensor *output)
	Initialise the kernel's inputs and output. More...
void	configure (const ITensor *input, const int block_shape_x, const int block_shape_y, const Size2D &padding_left, const Size2D &padding_right, ITensor *output)
	Initialise the kernel's input and output. More...
void	run (const Window &window, const ThreadInfo &info) override
	Execute the kernel on the passed window. More...
Public Member Functions inherited from ICPPKernel
virtual	~ICPPKernel ()=default
	Default destructor. More...
virtual void	run_nd (const Window &window, const ThreadInfo &info, const Window &thread_locator)
	legacy compatibility layer for implemantions which do not support thread_locator In these cases we simply narrow the interface down the legacy version More...
virtual void	run_op (ITensorPack &tensors, const Window &window, const ThreadInfo &info)
	Execute the kernel on the passed window. More...
virtual size_t	get_mws (const CPUInfo &platform, size_t thread_count) const
	Return minimum workload size of the relevant kernel. More...
Public Member Functions inherited from IKernel
	IKernel ()
	Constructor. More...
virtual	~IKernel ()=default
	Destructor. More...
virtual bool	is_parallelisable () const
	Indicates whether or not the kernel is parallelisable. More...
virtual BorderSize	border_size () const
	The size of the border for that kernel. More...
const Window &	window () const
	The maximum window the kernel can be executed on. More...
bool	is_window_configured () const
	Function to check if the embedded window of this kernel has been configured. More...

Static Public Member Functions
static Status	validate (const ITensorInfo *input, const ITensorInfo *block_shape, const ITensorInfo *paddings, const ITensorInfo *output)
	Static function to check if given info will lead to a valid configuration of NESpaceToBatchLayerKernel. More...
static Status	validate (const ITensorInfo *input, const int block_shape_x, const int block_shape_y, const Size2D &padding_left, const Size2D &padding_right, const ITensorInfo *output)
	Static function to check if given info will lead to a valid configuration of NESpaceToBatchLayerKernel (Static block shape and paddings) More...

Additional Inherited Members
Static Public Attributes inherited from ICPPKernel
static constexpr size_t	default_mws = 1

Detailed Description

Interface for the space to batch kernel.

Definition at line 37 of file NESpaceToBatchLayerKernel.h.

Constructor & Destructor Documentation

NESpaceToBatchLayerKernel() [1/3]

NESpaceToBatchLayerKernel

(

)

Default constructor.

Definition at line 97 of file NESpaceToBatchLayerKernel.cpp.

    : _input(nullptr),
      _block_shape(nullptr),
      _paddings(nullptr),
      _output(nullptr),
      _data_layout(DataLayout::UNKNOWN),
      _padding_left(),
      _block_shape_x(),
      _block_shape_y()
{
}

References arm_compute::UNKNOWN.

NESpaceToBatchLayerKernel() [2/3]

NESpaceToBatchLayerKernel ( const NESpaceToBatchLayerKernel &  )

delete

Prevent instances of this class from being copied (As this class contains pointers)

NESpaceToBatchLayerKernel() [3/3]

NESpaceToBatchLayerKernel ( NESpaceToBatchLayerKernel &&  )

default

Allow instances of this class to be moved.

~NESpaceToBatchLayerKernel()

~NESpaceToBatchLayerKernel ( )

default

Default destructor.

Member Function Documentation

configure() [1/2]

void configure	(	const ITensor *	input,
		const int	block_shape_x,
		const int	block_shape_y,
		const Size2D &	padding_left,
		const Size2D &	padding_right,
		ITensor *	output
	)

Initialise the kernel's input and output.

(Static block shape and paddings)

Parameters

[in]	input	Tensor input. Supported tensor rank: 4. Data types supported: All.
[in]	block_shape_x	Block shape x value.
[in]	block_shape_y	Block shape y value.
[in]	padding_left	The padding at the beginning of every dimension of the output tensor.
[in]	padding_right	The padding at the end of every dimension of the output tensor.
[out]	output	Tensor output. Data types supported: same as input

Definition at line 129 of file NESpaceToBatchLayerKernel.cpp.

{
    ARM_COMPUTE_ERROR_ON_NULLPTR(input, output);
 
    TensorShape output_shape = misc::shape_calculator::compute_space_to_batch_shape(
        input->info(), block_shape_x, block_shape_y, padding_left, padding_right);
    auto_init_if_empty(*output->info(), output_shape, 1, input->info()->data_type(),
                       input->info()->quantization_info());
 
    ARM_COMPUTE_ERROR_THROW_ON(validate_arguments_static(input->info(), block_shape_x, block_shape_y, padding_left,
                                                         padding_right, output->info()));
 
    _input         = input;
    _output        = output;
    _block_shape_x = block_shape_x;
    _block_shape_y = block_shape_y;
    _padding_left  = padding_left;
    _data_layout   = input->info()->data_layout();
 
    // Configure kernel window
    Window win = calculate_max_window(*output->info(), Steps());
    INEKernel::configure(win);
}

References ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), arm_compute::calculate_max_window(), arm_compute::misc::shape_calculator::compute_space_to_batch_shape(), ITensor::info(), arm_compute::test::validation::input, and arm_compute::test::validation::output_shape.

configure() [2/2]

void configure	(	const ITensor *	input,
		const ITensor *	block_shape,
		const ITensor *	paddings,
		ITensor *	output
	)

Initialise the kernel's inputs and output.

Parameters

[in]	input	Tensor input. Supported tensor rank: 4. Data types supported: All.
[in]	block_shape	1-D tensor with shape [M]. Supported M: 2. Data types supported: S32
[in]	paddings	2-D tensor with shape [2, M] (First dimension is the fastest-changing dimension). Supported M: 2. Data types supported: S32
[out]	output	Tensor output. Data types supported: same as input

Definition at line 109 of file NESpaceToBatchLayerKernel.cpp.

{
    ARM_COMPUTE_ERROR_ON_NULLPTR(input, block_shape, paddings, output);
    ARM_COMPUTE_ERROR_THROW_ON(
        validate_arguments(input->info(), block_shape->info(), paddings->info(), output->info()));
 
    _input       = input;
    _block_shape = block_shape;
    _paddings    = paddings;
    _output      = output;
    _data_layout = input->info()->data_layout();
 
    // Configure kernel window
    Window win = calculate_max_window(*output->info(), Steps());
    ICPPKernel::configure(win);
}

References ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::calculate_max_window(), ITensor::info(), arm_compute::test::validation::input, and arm_compute::cpu::kernels::validate_arguments().

name()

const char* name ( ) const

inlineoverridevirtual

Name of the kernel.

Returns

Kernel name

Implements ICPPKernel.

Definition at line 40 of file NESpaceToBatchLayerKernel.h.

    {
        return "NESpaceToBatchLayerKernel";
    }

operator=() [1/2]

NESpaceToBatchLayerKernel& operator= ( const NESpaceToBatchLayerKernel &  )

delete

Prevent instances of this class from being copied (As this class contains pointers)

operator=() [2/2]

NESpaceToBatchLayerKernel& operator= ( NESpaceToBatchLayerKernel &&  )

default

Allow instances of this class to be moved.

run()

void run ( const Window &  window, const ThreadInfo &  info  )

overridevirtual

Execute the kernel on the passed window.

Warning

If is_parallelisable() returns false then the passed window must be equal to window()

Note

The window has to be a region within the window returned by the window() method

The width of the window has to be a multiple of num_elems_processed_per_iteration().

Parameters

[in]	window	Region on which to execute the kernel. (Must be a region of the window returned by window())
[in]	info	Info about executing thread and CPU.

Reimplemented from ICPPKernel.

Definition at line 178 of file NESpaceToBatchLayerKernel.cpp.

{
    ARM_COMPUTE_UNUSED(info);
    ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(this);
    ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(ICPPKernel::window(), window);
 
    if (_block_shape != nullptr)
    {
        // Retrieve the block shapes dynamically
        _block_shape_x = *(reinterpret_cast<const int *>(_block_shape->ptr_to_element(0)));
        _block_shape_y = *(reinterpret_cast<const int *>(_block_shape->ptr_to_element(1)));
    }
 
    if (_paddings != nullptr)
    {
        const size_t pad_left_x = *reinterpret_cast<const size_t *>(_paddings->ptr_to_element({0, 0}));
        const size_t pad_left_y = *reinterpret_cast<const size_t *>(_paddings->ptr_to_element({1, 0}));
        _padding_left           = Size2D(pad_left_x, pad_left_y);
    }
    const int height_idx   = get_data_layout_dimension_index(_data_layout, DataLayoutDimension::HEIGHT);
    const int width_idx    = get_data_layout_dimension_index(_data_layout, DataLayoutDimension::WIDTH);
    const int batch_idx    = get_data_layout_dimension_index(_data_layout, DataLayoutDimension::BATCHES);
    const int element_size = _input->info()->element_size();
 
    const size_t height     = _input->info()->dimension(height_idx);
    const size_t width      = _input->info()->dimension(width_idx);
    const size_t batch_size = _input->info()->dimension(batch_idx);
 
    Window slice_out = window.first_slice_window_3D();
 
    int batch_id = 0;
 
    // Main loop for NCHW and NHWC
    if (_data_layout == DataLayout::NCHW)
    {
        do
        {
            Iterator out(_output, slice_out);
            execute_window_loop(
                slice_out,
                [&](const Coordinates &id)
                {
                    const size_t out_x = id.x();
                    const size_t out_y = id.y();
                    const size_t z     = id.z();
                    const size_t pos_x = out_x * _block_shape_x + (batch_id / batch_size) % _block_shape_x;
                    const size_t pos_y = out_y * _block_shape_y + (batch_id / batch_size) / _block_shape_x;
                    if (pos_y >= _padding_left.y() && pos_y < _padding_left.y() + height &&
                        pos_x >= _padding_left.x() && pos_x < _padding_left.x() + width)
                    {
                        const int   w    = batch_id % batch_size;
                        const int   in_x = pos_x - _padding_left.x();
                        const int   in_y = pos_y - _padding_left.y();
                        Coordinates input_coords{in_x, in_y, z, w};
                        memcpy(out.ptr(), _input->ptr_to_element(input_coords), element_size);
                    }
                },
                out);
            ++batch_id;
        } while (window.slide_window_slice_3D(slice_out));
    }
    else
    {
        do
        {
            Iterator out(_output, slice_out);
            execute_window_loop(
                slice_out,
                [&](const Coordinates &id)
                {
                    const size_t out_x = id.y();
                    const size_t out_y = id.z();
                    const size_t z     = id.x();
                    const size_t pos_x = out_x * _block_shape_x + (batch_id / batch_size) % _block_shape_x;
                    const size_t pos_y = out_y * _block_shape_y + (batch_id / batch_size) / _block_shape_x;
                    if (pos_y >= _padding_left.y() && pos_y < _padding_left.y() + height &&
                        pos_x >= _padding_left.x() && pos_x < _padding_left.x() + width)
                    {
                        const int   w    = batch_id % batch_size;
                        const int   in_x = pos_x - _padding_left.x();
                        const int   in_y = pos_y - _padding_left.y();
                        Coordinates input_coords{z, in_x, in_y, w};
                        memcpy(out.ptr(), _input->ptr_to_element(input_coords), element_size);
                    }
                },
                out);
            ++batch_id;
        } while (window.slide_window_slice_3D(slice_out));
    }
}

References ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ARM_COMPUTE_UNUSED, arm_compute::BATCHES, ITensorInfo::dimension(), ITensorInfo::element_size(), arm_compute::execute_window_loop(), Window::first_slice_window_3D(), arm_compute::get_data_layout_dimension_index(), arm_compute::HEIGHT, arm_compute::cpu::height_idx, ITensor::info(), arm_compute::test::validation::info, arm_compute::NCHW, Iterator::ptr(), ITensor::ptr_to_element(), Window::slide_window_slice_3D(), arm_compute::test::validation::w, arm_compute::WIDTH, arm_compute::cpu::width_idx, IKernel::window(), Size2D::x(), Window::x(), Size2D::y(), and Window::y().

validate() [1/2]

Status validate ( const ITensorInfo *  input, const int  block_shape_x, const int  block_shape_y, const Size2D &  padding_left, const Size2D &  padding_right, const ITensorInfo *  output  )

static

Static function to check if given info will lead to a valid configuration of NESpaceToBatchLayerKernel (Static block shape and paddings)

Parameters

[in]	input	Tensor input. Supported tensor rank: 4. Data types supported: All.
[in]	block_shape_x	Block shape x value.
[in]	block_shape_y	Block shape y value.
[in]	padding_left	The padding at the beginning of every dimension of the output tensor.
[in]	padding_right	The padding at the end of every dimension of the output tensor.
[in]	output	Tensor output. Data types supported: same as input

Returns

a status

Definition at line 166 of file NESpaceToBatchLayerKernel.cpp.

{
    ARM_COMPUTE_RETURN_ON_ERROR(
        validate_arguments_static(input, block_shape_x, block_shape_y, padding_left, padding_right, output));
    return Status{};
}

References ARM_COMPUTE_RETURN_ON_ERROR, and arm_compute::test::validation::input.

validate() [2/2]

Status validate ( const ITensorInfo *  input, const ITensorInfo *  block_shape, const ITensorInfo *  paddings, const ITensorInfo *  output  )

static

Static function to check if given info will lead to a valid configuration of NESpaceToBatchLayerKernel.

Parameters

[in]	input	Tensor input. Supported tensor rank: 4. Data types supported: All.
[in]	block_shape	1-D tensor with shape [M]. Supported M: 2. Data types supported: S32
[in]	paddings	2-D tensor with shape [2, M] (First dimension is the fastest-changing dimension). Supported M: 2. Data types supported: S32
[in]	output	Tensor output. Data types supported: same as input

Returns

a status

Definition at line 158 of file NESpaceToBatchLayerKernel.cpp.

{
    ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input, block_shape, paddings, output));
    return Status{};
}

References ARM_COMPUTE_RETURN_ON_ERROR, arm_compute::test::validation::input, and arm_compute::cpu::kernels::validate_arguments().

Referenced by NESpaceToBatchLayer::validate().

---

The documentation for this class was generated from the following files:

• src/core/NEON/kernels/NESpaceToBatchLayerKernel.h
• src/core/NEON/kernels/NESpaceToBatchLayerKernel.cpp