CLChannelShuffleLayerKernel Class Reference

Interface for the channel shuffle kernel. More...

#include <CLChannelShuffleLayerKernel.h>

Collaboration diagram for CLChannelShuffleLayerKernel:

Public Member Functions
	CLChannelShuffleLayerKernel ()
	Default constructor. More...
	CLChannelShuffleLayerKernel (const CLChannelShuffleLayerKernel &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
CLChannelShuffleLayerKernel &	operator= (const CLChannelShuffleLayerKernel &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
	CLChannelShuffleLayerKernel (CLChannelShuffleLayerKernel &&)=default
	Allow instances of this class to be moved. More...
CLChannelShuffleLayerKernel &	operator= (CLChannelShuffleLayerKernel &&)=default
	Allow instances of this class to be moved. More...
	~CLChannelShuffleLayerKernel ()=default
	Default destructor. More...
void	configure (const ICLTensor *input, ICLTensor *output, unsigned int num_groups)
	Configure function's inputs and outputs. More...
void	configure (const CLCompileContext &compile_context, const ICLTensor *input, ICLTensor *output, unsigned int num_groups)
	Configure function's inputs and outputs. 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...
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, unsigned int num_groups)
	Static function to check if given info will lead to a valid configuration of CLChannelShuffleLayerKernel. More...
Static Public Member Functions inherited from ICLKernel
static constexpr unsigned int	num_arguments_per_3d_tensor_nhw ()
	Returns the number of arguments enqueued per NHW 3D Tensor object. More...
static constexpr unsigned int	num_arguments_per_4d_tensor_nhwc ()
	Returns the number of arguments enqueued per NHWC 4D Tensor object. More...
static constexpr unsigned int	num_arguments_per_1D_array ()
	Returns the number of arguments enqueued per 1D array object. More...
static constexpr unsigned int	num_arguments_per_1D_tensor ()
	Returns the number of arguments enqueued per 1D tensor object. More...
static constexpr unsigned int	num_arguments_per_2D_tensor ()
	Returns the number of arguments enqueued per 2D tensor object. More...
static constexpr unsigned int	num_arguments_per_3D_tensor ()
	Returns the number of arguments enqueued per 3D tensor object. More...
static constexpr 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)
	Get the global work size given an execution window. More...

Detailed Description

Interface for the channel shuffle kernel.

Definition at line 34 of file CLChannelShuffleLayerKernel.h.

Constructor & Destructor Documentation

CLChannelShuffleLayerKernel() [1/3]

CLChannelShuffleLayerKernel

(

)

Default constructor.

Definition at line 97 of file CLChannelShuffleLayerKernel.cpp.

References arm_compute::ELEMENTWISE.

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

CLChannelShuffleLayerKernel() [2/3]

CLChannelShuffleLayerKernel ( const CLChannelShuffleLayerKernel &  )

delete

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

CLChannelShuffleLayerKernel() [3/3]

CLChannelShuffleLayerKernel ( CLChannelShuffleLayerKernel &&  )

default

Allow instances of this class to be moved.

~CLChannelShuffleLayerKernel()

~CLChannelShuffleLayerKernel ( )

default

Default destructor.

Member Function Documentation

configure() [1/2]

void configure	(	const ICLTensor *	input,
		ICLTensor *	output,
		unsigned int	num_groups
	)

Configure function's inputs and outputs.

Parameters

[in]	input	Input tensor. Data types supported: All.
[out]	output	Output tensor. Data type supported: Same as input
[in]	num_groups	Number of groups. Must be greater than 1 and the number of channels of the tensors must be a multiple of the number of groups.

Definition at line 103 of file CLChannelShuffleLayerKernel.cpp.

References CLKernelLibrary::get().

{
    configure(CLKernelLibrary::get().get_compile_context(), input, output, num_groups);
}

configure() [2/2]

void configure	(	const CLCompileContext &	compile_context,
		const ICLTensor *	input,
		ICLTensor *	output,
		unsigned int	num_groups
	)

Configure function's inputs and outputs.

Parameters

[in]	compile_context	The compile context to be used.
[in]	input	Input tensor. Data types supported: All.
[out]	output	Output tensor. Data type supported: Same as input
[in]	num_groups	Number of groups. Must be greater than 1 and the number of channels of the tensors must be a multiple of the number of groups.

Definition at line 108 of file CLChannelShuffleLayerKernel.cpp.

References CLBuildOptions::add_option(), CLBuildOptions::add_option_if(), arm_compute::adjust_vec_size(), ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::CHANNEL, arm_compute::create_kernel(), ITensorInfo::data_layout(), arm_compute::test::validation::data_layout, ITensorInfo::data_type(), ITensorInfo::dimension(), ITensorInfo::element_size(), arm_compute::get_cl_unsigned_type_from_element_size(), arm_compute::get_data_layout_dimension_index(), arm_compute::get_padding_info(), arm_compute::has_padding_changed(), ITensor::info(), arm_compute::test::validation::input, kernel_name, arm_compute::lower_string(), arm_compute::NHWC, arm_compute::test::validation::num_groups, CLBuildOptions::options(), arm_compute::string_from_data_layout(), arm_compute::string_from_data_type(), arm_compute::support::cpp11::to_string(), arm_compute::cpu::kernels::validate_and_configure_window(), and arm_compute::cpu::kernels::validate_arguments().

{
    ARM_COMPUTE_ERROR_ON_NULLPTR(input, output);
    ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input->info(), output->info(), num_groups));
    auto padding_info = get_padding_info({ input, output });

    _input  = input;
    _output = output;

    const DataLayout   data_layout          = input->info()->data_layout();
    const bool         is_nhwc              = data_layout == DataLayout::NHWC;
    const unsigned int channels             = input->info()->dimension(get_data_layout_dimension_index(data_layout, DataLayoutDimension::CHANNEL));
    unsigned int       vec_size_x           = 0;
    unsigned int       vec_size_x_leftovers = 0;
    if(is_nhwc)
    {
        vec_size_x           = adjust_vec_size(max_cl_vector_width / input->info()->element_size(), input->info()->dimension(0));
        vec_size_x_leftovers = input->info()->dimension(0) % vec_size_x;
    }
    else
    {
        vec_size_x = max_cl_vector_width / input->info()->element_size();
    }

    // Set kernel build options
    CLBuildOptions build_opts;
    build_opts.add_option("-DNUM_GROUPS=" + support::cpp11::to_string(num_groups));
    build_opts.add_option("-DK=" + support::cpp11::to_string(channels / num_groups));
    build_opts.add_option("-DVEC_SIZE=" + support::cpp11::to_string(vec_size_x));
    build_opts.add_option_if(is_nhwc, "-DVEC_SIZE_LEFTOVER=" + support::cpp11::to_string(vec_size_x_leftovers));
    build_opts.add_option_if(is_nhwc, "-DSRC_DIM_X=" + support::cpp11::to_string(input->info()->dimension(0)));
    build_opts.add_option("-DSRC_DIM_Z=" + support::cpp11::to_string(input->info()->dimension(2)));
    build_opts.add_option("-DDATA_TYPE=" + get_cl_unsigned_type_from_element_size(input->info()->element_size()));

    // Create kernel
    std::string kernel_name = "channel_shuffle_" + lower_string(string_from_data_layout(data_layout));

    _kernel = create_kernel(compile_context, kernel_name, build_opts.options());

    // Configure kernel window
    auto win_config = validate_and_configure_window(input->info(), output->info());
    ARM_COMPUTE_ERROR_THROW_ON(win_config.first);
    ICLKernel::configure_internal(win_config.second);

    // Set config_id for enabling LWS tuning
    _config_id = kernel_name;
    _config_id += "_";
    _config_id += lower_string(string_from_data_type(input->info()->data_type()));
    _config_id += "_";
    _config_id += support::cpp11::to_string(num_groups);
    _config_id += "_";
    _config_id += support::cpp11::to_string(input->info()->dimension(0));
    _config_id += "_";
    _config_id += support::cpp11::to_string(input->info()->dimension(1));
    _config_id += "_";
    _config_id += support::cpp11::to_string(input->info()->dimension(2));
    _config_id += "_";
    _config_id += support::cpp11::to_string(output->info()->dimension(0));
    _config_id += "_";
    _config_id += support::cpp11::to_string(output->info()->dimension(1));
    _config_id += "_";
    _config_id += support::cpp11::to_string(output->info()->dimension(2));
    if(data_layout == DataLayout::NHWC)
    {
        ARM_COMPUTE_ERROR_ON(has_padding_changed(padding_info));
    }
}

operator=() [1/2]

CLChannelShuffleLayerKernel& operator= ( const CLChannelShuffleLayerKernel &  )

delete

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

operator=() [2/2]

CLChannelShuffleLayerKernel& operator= ( CLChannelShuffleLayerKernel &&  )

default

Allow instances of this class to be moved.

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 184 of file CLChannelShuffleLayerKernel.cpp.

References ICLKernel::add_4D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::enqueue(), ICLKernel::lws_hint(), and IKernel::window().

{
    ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(this);
    ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(ICLKernel::window(), window);

    unsigned int idx = 0;
    add_4D_tensor_argument(idx, _input, window);
    add_4D_tensor_argument(idx, _output, window);
    enqueue(queue, *this, window, lws_hint());
}

validate()

Status validate ( const ITensorInfo *  input, const ITensorInfo *  output, unsigned int  num_groups  )

static

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

Parameters

[in]	input	Input tensor info. Data types supported: All.
[in]	output	Output tensor info. Data type supported: Same as input
[in]	num_groups	Number of groups. Must be greater than 1 and the number of channels of the tensors must be a multiple of the number of groups.

Returns

a status

Definition at line 176 of file CLChannelShuffleLayerKernel.cpp.

References ARM_COMPUTE_RETURN_ON_ERROR, ICloneable< T >::clone(), arm_compute::cpu::kernels::validate_and_configure_window(), and arm_compute::cpu::kernels::validate_arguments().

Referenced by CLChannelShuffleLayer::validate().

{
    ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input, output, num_groups));
    ARM_COMPUTE_RETURN_ON_ERROR(validate_and_configure_window(input->clone().get(), output->clone().get()).first);

    return Status{};
}

---

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

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