CLPadLayerKernel Class Reference

Interface for the PadLayer function. More...

#include <CLPadLayerKernel.h>

Collaboration diagram for CLPadLayerKernel:

Public Member Functions
	CLPadLayerKernel ()
	Default constructor. More...
	CLPadLayerKernel (const CLPadLayerKernel &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
CLPadLayerKernel &	operator= (const CLPadLayerKernel &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
	CLPadLayerKernel (CLPadLayerKernel &&)=default
	Allow instances of this class to be moved. More...
CLPadLayerKernel &	operator= (CLPadLayerKernel &&)=default
	Allow instances of this class to be moved. More...
	~CLPadLayerKernel ()=default
	Default destructor. More...
void	configure (const ICLTensor *input, ICLTensor *output, const PaddingList &padding, PixelValue constant_value=PixelValue(), PaddingMode mode=PaddingMode::CONSTANT)
	Set the input and output tensor. More...
void	configure (const CLCompileContext &compile_context, const ICLTensor *input, ICLTensor *output, const PaddingList &padding, PixelValue constant_value=PixelValue(), PaddingMode mode=PaddingMode::CONSTANT)
	Set the input and output tensor. More...
void	run (const Window &window, cl::CommandQueue &queue) override
	Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. More...
Public Member Functions inherited from ICLKernel
	ICLKernel ()
	Constructor. More...
cl::Kernel &	kernel ()
	Returns a reference to the OpenCL kernel of this object. More...
CLKernelType	type () const
	Returns the CL kernel type. More...
template<typename T >
void	add_1D_array_argument (unsigned int &idx, const ICLArray< T > *array, const Strides &strides, unsigned int num_dimensions, const Window &window)
	Add the passed 1D array's parameters to the object's kernel's arguments starting from the index idx. More...
void	add_1D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
	Add the passed 1D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
void	add_1D_tensor_argument_if (bool cond, unsigned int &idx, const ICLTensor *tensor, const Window &window)
	Add the passed 1D tensor's parameters to the object's kernel's arguments starting from the index idx if the condition is true. More...
void	add_2D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
	Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
void	add_2D_tensor_argument_if (bool cond, unsigned int &idx, const ICLTensor *tensor, const Window &window)
	Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx if the condition is true. More...
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. More...
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. More...
void	add_5D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
	Add the passed 5D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
void	add_3d_tensor_nhw_argument (unsigned int &idx, const ICLTensor *tensor)
	Add the passed NHW 3D tensor's parameters to the object's kernel's arguments by passing strides, dimensions and the offset to the first valid element in bytes. More...
void	add_4d_tensor_nhwc_argument (unsigned int &idx, const ICLTensor *tensor)
	Add the passed NHWC 4D tensor's parameters to the object's kernel's arguments by passing strides, dimensions and the offset to the first valid element in bytes. More...
virtual void	run_op (ITensorPack &tensors, const Window &window, cl::CommandQueue &queue)
	Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. More...
template<typename T >
void	add_argument (unsigned int &idx, T value)
	Add the passed parameters to the object's kernel's arguments starting from the index idx. More...
void	set_lws_hint (const cl::NDRange &lws_hint)
	Set the Local-Workgroup-Size hint. More...
cl::NDRange	lws_hint () const
	Return the Local-Workgroup-Size hint. More...
void	set_wbsm_hint (const cl_int &wbsm_hint)
	Set the workgroup batch size modifier hint. More...
cl_int	wbsm_hint () const
	Return the workgroup batch size modifier hint. More...
const std::string &	config_id () const
	Get the configuration ID. More...
void	set_target (GPUTarget target)
	Set the targeted GPU architecture. More...
void	set_target (cl::Device &device)
	Set the targeted GPU architecture according to the CL device. More...
GPUTarget	get_target () const
	Get the targeted GPU architecture. More...
size_t	get_max_workgroup_size ()
	Get the maximum workgroup size for the device the CLKernelLibrary uses. More...
cl::NDRange	get_cached_gws () const
	Get the cached gws used to enqueue this kernel. More...
void	cache_gws (const cl::NDRange &gws)
	Cache the latest gws used to enqueue this kernel. More...
template<unsigned int dimension_size>
void	add_tensor_argument (unsigned &idx, const ICLTensor *tensor, const Window &window)
template<typename T , unsigned int dimension_size>
void	add_array_argument (unsigned &idx, const ICLArray< T > *array, const Strides &strides, unsigned int num_dimensions, const Window &window)
	Add the passed array's parameters to the object's kernel's arguments starting from the index idx. 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 *output, const PaddingList &padding, PixelValue constant_value=PixelValue(), PaddingMode mode=PaddingMode::CONSTANT)
	Static function to check if given info will lead to a valid configuration of CLPadLayerKernel. More...
Static Public Member Functions inherited from ICLKernel
constexpr static unsigned int	num_arguments_per_3d_tensor_nhw ()
	Returns the number of arguments enqueued per NHW 3D Tensor object. More...
constexpr static unsigned int	num_arguments_per_4d_tensor_nhwc ()
	Returns the number of arguments enqueued per NHWC 4D Tensor object. More...
constexpr static unsigned int	num_arguments_per_1D_array ()
	Returns the number of arguments enqueued per 1D array object. More...
constexpr static unsigned int	num_arguments_per_1D_tensor ()
	Returns the number of arguments enqueued per 1D tensor object. More...
constexpr static unsigned int	num_arguments_per_2D_tensor ()
	Returns the number of arguments enqueued per 2D tensor object. More...
constexpr static unsigned int	num_arguments_per_3D_tensor ()
	Returns the number of arguments enqueued per 3D tensor object. More...
constexpr static unsigned int	num_arguments_per_4D_tensor ()
	Returns the number of arguments enqueued per 4D tensor object. More...
static cl::NDRange	gws_from_window (const Window &window, bool use_dummy_work_items)
	Get the global work size given an execution window. More...

Detailed Description

Interface for the PadLayer function.

Definition at line 34 of file CLPadLayerKernel.h.

Constructor & Destructor Documentation

CLPadLayerKernel() [1/3]

CLPadLayerKernel

(

)

Default constructor.

Definition at line 73 of file CLPadLayerKernel.cpp.

                                   : _input(nullptr), _output(nullptr), _4d_enabled(false)
{
    _type = CLKernelType::ELEMENTWISE;
}

References arm_compute::ELEMENTWISE.

CLPadLayerKernel() [2/3]

CLPadLayerKernel ( const CLPadLayerKernel &  )

delete

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

CLPadLayerKernel() [3/3]

CLPadLayerKernel ( CLPadLayerKernel &&  )

default

Allow instances of this class to be moved.

~CLPadLayerKernel()

~CLPadLayerKernel ( )

default

Default destructor.

Member Function Documentation

configure() [1/2]

void configure	(	const CLCompileContext &	compile_context,
		const ICLTensor *	input,
		ICLTensor *	output,
		const PaddingList &	padding,
		PixelValue	constant_value = PixelValue(),
		PaddingMode	mode = PaddingMode::CONSTANT
	)

Set the input and output tensor.

Parameters

[in]	compile_context	The compile context to be used.
[in]	input	Source tensor. Data types supported: All.
[out]	output	Output tensor. Data type supported: same as input
[in]	padding	The padding for each spatial dimension of the input tensor. The pair padding[i] specifies the front and the end padding in the i-th dimension.
[in]	constant_value	(Optional) Constant value to be used for the padding.
[in]	mode	(Optional) Controls whether the padding should be filled with constant_value using CONSTANT, or reflect the input, either including the border values (SYMMETRIC) or not (REFLECT).

Definition at line 84 of file CLPadLayerKernel.cpp.

{
    ARM_COMPUTE_ERROR_ON_NULLPTR(input, output);
    auto_init_if_empty(*output->info(),
                       input->info()->clone()->set_tensor_shape(
                           misc::shape_calculator::compute_padded_shape(input->info()->tensor_shape(), padding)));
    ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input->info(), output->info(), padding, constant_value, mode));
 
    auto padding_info = get_padding_info({input, output});
 
    _input      = input;
    _output     = output;
    _4d_enabled = (mode == PaddingMode::CONSTANT) && (padding.size() > 3);
 
    // Set build options
    const DataType    &data_type    = input->info()->data_type();
    const unsigned int input_width  = input->info()->dimension(0);
    const unsigned int input_height = input->info()->dimension(1);
    const unsigned int input_depth  = input->info()->dimension(2);
    const unsigned int pad_x_before = padding.at(0).first;
    const unsigned int pad_y_before = padding.size() > 1 ? padding.at(1).first : 0;
    const unsigned int pad_z_before = padding.size() > 2 ? padding.at(2).first : 0;
    const unsigned int vec_size     = adjust_vec_size(
            std::min(16U, 32U / static_cast<unsigned int>(element_size_from_data_type(input->info()->data_type()))),
            input_width);
    const unsigned int pad_right_start        = input_width + pad_x_before;
    const unsigned int pad_x_before_remainder = pad_x_before % vec_size;
    const unsigned int vec_size_leftover_write =
        vec_size - (ceil_to_multiple(output->info()->dimension(0), vec_size) - output->info()->dimension(0));
 
    CLBuildOptions build_opts;
    build_opts.add_option("-DDATA_TYPE=" + get_cl_type_from_data_type(data_type));
    build_opts.add_option("-DVEC_SIZE=" + support::cpp11::to_string(vec_size));
    build_opts.add_option("-DPAD_X_BEFORE=" + support::cpp11::to_string(pad_x_before));
    build_opts.add_option("-DSRC_WIDTH=" + support::cpp11::to_string(input_width));
    build_opts.add_option("-DPAD_X_BEFORE_REMAINDER=" + support::cpp11::to_string(pad_x_before_remainder));
    build_opts.add_option("-DVEC_SIZE_LEFTOVER_WRITE=" + support::cpp11::to_string(vec_size_leftover_write));
    if (padding.size() > 1)
    {
        build_opts.add_option("-DPAD_Y_BEFORE=" + support::cpp11::to_string(pad_y_before));
        build_opts.add_option("-DSRC_HEIGHT=" + support::cpp11::to_string(input_height));
 
        if (padding.size() > 2)
        {
            build_opts.add_option("-DPAD_Z_BEFORE=" + support::cpp11::to_string(pad_z_before));
            build_opts.add_option("-DSRC_DEPTH=" + support::cpp11::to_string(input_depth));
        }
    }
 
    std::string kernel_name = "pad_layer_";
    switch (mode)
    {
        case PaddingMode::CONSTANT:
        {
            kernel_name += "constant";
 
            const unsigned int vec_size_leftover_read =
                vec_size - (ceil_to_multiple(pad_right_start, vec_size) - pad_right_start);
 
            build_opts.add_option("-DCONST_VAL=" + string_from_pixel_value(constant_value, data_type));
            build_opts.add_option("-DVEC_SIZE_LEFTOVER_READ=" + support::cpp11::to_string(vec_size_leftover_read));
 
            if (pad_x_before >= vec_size)
            {
                build_opts.add_option("-DTHREADS_TO_SKIP_BEFORE=" + support::cpp11::to_string(pad_x_before / vec_size));
                build_opts.add_option("-DTHREADS_TO_SKIP_AFTER=" +
                                      support::cpp11::to_string(pad_right_start / vec_size));
            }
            if (_4d_enabled)
            {
                build_opts.add_option("-DPAD_W_BEFORE=" + support::cpp11::to_string(padding.at(3).first));
                build_opts.add_option("-DSRC_BATCH=" + support::cpp11::to_string(input->info()->dimension(3)));
            }
 
            break;
        }
        case PaddingMode::SYMMETRIC:
        case PaddingMode::REFLECT:
        {
            kernel_name += "symmetric_reflect";
 
            const auto is_reflect = static_cast<unsigned int>(mode == PaddingMode::REFLECT);
 
            const unsigned int pad_x_after_remainder = pad_right_start % vec_size;
            const unsigned int after_pad_fact_x      = (2 * input_width + pad_x_before) - is_reflect;
            const unsigned int output_last_x = ceil_to_multiple(pad_right_start + padding.at(0).second, vec_size);
 
            build_opts.add_option("-DIS_REFLECT=" + support::cpp11::to_string(is_reflect));
            build_opts.add_option("-DPAD_X_AFTER_REMAINDER=" + support::cpp11::to_string(pad_x_after_remainder));
            build_opts.add_option("-DPAD_X_BEFORE_REMAINDER_REFL=" +
                                  support::cpp11::to_string((pad_x_before_remainder + is_reflect) % vec_size));
            build_opts.add_option("-DPAD_X_AFTER_REMAINDER_REFL=" +
                                  support::cpp11::to_string((pad_x_after_remainder - is_reflect) % vec_size));
            build_opts.add_option("-DAFTER_PAD_FACT_X=" + support::cpp11::to_string(after_pad_fact_x));
            build_opts.add_option_if(after_pad_fact_x < output_last_x,
                                     "-DAFTER_PAD_REM=" + support::cpp11::to_string(after_pad_fact_x % vec_size));
 
            break;
        }
        default:
            ARM_COMPUTE_ERROR("Padding mode not supported.");
    }
 
    // Create kernel
    _kernel = create_kernel(compile_context, kernel_name, build_opts.options());
 
    // Configure window
    Window win = calculate_max_window(*output->info(), Steps(vec_size));
    ICLKernel::configure_internal(win);
 
    ARM_COMPUTE_ERROR_ON(has_padding_changed(padding_info));
}

References CLBuildOptions::add_option(), arm_compute::adjust_vec_size(), ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), arm_compute::calculate_max_window(), arm_compute::ceil_to_multiple(), arm_compute::misc::shape_calculator::compute_padded_shape(), arm_compute::CONSTANT, arm_compute::create_kernel(), arm_compute::test::validation::data_type, ITensorInfo::dimension(), arm_compute::element_size_from_data_type(), arm_compute::get_cl_type_from_data_type(), arm_compute::get_padding_info(), arm_compute::has_padding_changed(), ITensor::info(), arm_compute::test::validation::input, kernel_name, clang_tidy_rules::mode, arm_compute::REFLECT, arm_compute::string_from_pixel_value(), arm_compute::SYMMETRIC, arm_compute::support::cpp11::to_string(), arm_compute::utils::cast::U, and arm_compute::cpu::kernels::validate_arguments().

configure() [2/2]

void configure	(	const ICLTensor *	input,
		ICLTensor *	output,
		const PaddingList &	padding,
		PixelValue	constant_value = PixelValue(),
		PaddingMode	mode = PaddingMode::CONSTANT
	)

Set the input and output tensor.

Parameters

[in]	input	Source tensor. Data types supported: All.
[out]	output	Output tensor. Data type supported: same as input
[in]	padding	The padding for each spatial dimension of the input tensor. The pair padding[i] specifies the front and the end padding in the i-th dimension.
[in]	constant_value	(Optional) Constant value to be used for the padding.
[in]	mode	(Optional) Controls whether the padding should be filled with constant_value using CONSTANT, or reflect the input, either including the border values (SYMMETRIC) or not (REFLECT).

Definition at line 78 of file CLPadLayerKernel.cpp.

{
    configure(CLKernelLibrary::get().get_compile_context(), input, output, padding, constant_value, mode);
}

References CLKernelLibrary::get(), arm_compute::test::validation::input, and clang_tidy_rules::mode.

operator=() [1/2]

CLPadLayerKernel& operator= ( CLPadLayerKernel &&  )

default

Allow instances of this class to be moved.

operator=() [2/2]

CLPadLayerKernel& operator= ( const CLPadLayerKernel &  )

delete

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

run()

void run ( const Window &  window, cl::CommandQueue &  queue  )

overridevirtual

Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.

Note

The queue is not flushed by this method, and therefore the kernel will not have been executed by the time this method returns.

Parameters

[in]	window	Region on which to execute the kernel. (Must be a valid region of the window returned by window()).
[in,out]	queue	Command queue on which to enqueue the kernel.

Reimplemented from ICLKernel.

Definition at line 212 of file CLPadLayerKernel.cpp.

{
    ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(this);
    ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(ICLKernel::window(), window);
 
    Window       slice = window.first_slice_window_3D();
    unsigned int batch = 0;
    do
    {
        unsigned int idx = 0;
        add_3D_tensor_argument(idx, _input, slice);
        add_3D_tensor_argument(idx, _output, slice);
        if (_4d_enabled)
        {
            add_argument<unsigned int>(idx, batch++);
        }
 
        enqueue(queue, *this, slice, lws_hint());
    } while (window.slide_window_slice_3D(slice));
}

References ICLKernel::add_3D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::enqueue(), Window::first_slice_window_3D(), ICLKernel::lws_hint(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), and IKernel::window().

validate()

Status validate ( const ITensorInfo *  input, const ITensorInfo *  output, const PaddingList &  padding, PixelValue  constant_value = PixelValue(), PaddingMode  mode = PaddingMode::CONSTANT  )

static

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

Parameters

[in]	input	Source tensor info. Data types supported: All.
[in]	output	Output tensor info. Data type supported: same as input
[in]	padding	The padding for each spatial dimension of the input tensor. The pair padding[i] specifies the front and the end padding in the i-th dimension.
[in]	constant_value	(Optional) Constant value to be used for the padding.
[in]	mode	(Optional) Controls whether the padding should be filled with constant_value using CONSTANT, or reflect the input, either including the border values (SYMMETRIC) or not (REFLECT).

Definition at line 202 of file CLPadLayerKernel.cpp.

{
    ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input, output, padding, constant_value, mode));
    return Status{};
}

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

Referenced by CLPadLayer::validate(), and CLGenerateProposalsLayer::validate().

---

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

• src/core/CL/kernels/CLPadLayerKernel.h
• src/core/CL/kernels/CLPadLayerKernel.cpp