Interface for the height concatenate kernel. More...

#include <ClHeightConcatenateKernel.h>

Collaboration diagram for ClHeightConcatenateKernel:

Public Member Functions
	ClHeightConcatenateKernel ()

	ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE (ClHeightConcatenateKernel)

void	configure (const CLCompileContext &compile_context, ITensorInfo src, unsigned int height_offset, ITensorInfo dst)
	Initialise the kernel's source and destination. More...

void	run_op (ITensorPack &tensors, const Window &window, ::cl::CommandQueue &queue) override

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 (const Window &window, cl::CommandQueue &queue)
	Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. 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 src, unsigned int height_offset, const ITensorInfo dst)
	Static function to check if given info will lead to a valid configuration. 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 height concatenate kernel.

The source tensor will be concatenated into the destination tensor.

Definition at line 40 of file ClHeightConcatenateKernel.h.

Constructor & Destructor Documentation

◆ ClHeightConcatenateKernel()

ClHeightConcatenateKernel ( )

Definition at line 65 of file ClHeightConcatenateKernel.cpp.

                                                      : _height_offset(0)
 {
     _type = CLKernelType::ELEMENTWISE;
 }

References arm_compute::ELEMENTWISE.

Member Function Documentation

◆ ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE()

ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE ( ClHeightConcatenateKernel )

◆ configure()

void configure	(	const CLCompileContext &	compile_context,
		ITensorInfo *	src,
		unsigned int	height_offset,
		ITensorInfo *	dst
	)

Initialise the kernel's source and destination.

Parameters

[in]	compile_context	The compile context to be used.
[in]	src	Source tensor info. Data types supported: All.
[in]	height_offset	The starting offset on the Y axis for the dst tensor.
[out]	dst	Destination tensor info. Data types supported: same as `src`.

Definition at line 76 of file ClHeightConcatenateKernel.cpp.

 {
     ARM_COMPUTE_ERROR_ON_NULLPTR(src, dst);
     ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(src, height_offset, dst));
  
     auto padding_info = get_padding_info({src, dst});
  
     _height_offset = height_offset;
  
     // Add build options
     const unsigned int num_elems_processed_per_iteration = adjust_vec_size(4, src->dimension(0));
  
     CLBuildOptions build_opts;
     build_opts.add_option("-DDATA_TYPE=" + get_cl_unsigned_type_from_element_size(src->element_size()));
     build_opts.add_option("-DVEC_SIZE=" + support::cpp11::to_string(num_elems_processed_per_iteration));
     build_opts.add_option("-DHEIGHT_OFFSET=" + support::cpp11::to_string(_height_offset));
     build_opts.add_option("-DVEC_SIZE_LEFTOVER=" +
                           support::cpp11::to_string(src->dimension(0) % num_elems_processed_per_iteration));
  
     if (is_data_type_quantized_asymmetric(src->data_type()) && src->quantization_info() != dst->quantization_info())
     {
         const UniformQuantizationInfo iq_info = src->quantization_info().uniform();
         const UniformQuantizationInfo oq_info = dst->quantization_info().uniform();
  
         build_opts.add_option("-DOFFSET_IN1=" + float_to_string_with_full_precision(iq_info.offset));
         build_opts.add_option("-DOFFSET_OUT=" + float_to_string_with_full_precision(oq_info.offset));
         build_opts.add_option("-DSCALE_IN1=" + float_to_string_with_full_precision(iq_info.scale));
         build_opts.add_option("-DSCALE_OUT=" + float_to_string_with_full_precision(oq_info.scale));
     }
     _depth = src->dimension(2);
  
     std::string kernel_name = "concatenate_height";
  
     // A macro guard to compile ONLY the kernel of interest
     build_opts.add_option("-D" + upper_string(kernel_name));
  
     // Create kernel
     _kernel = create_kernel(compile_context, kernel_name, build_opts.options());
     // Configure kernel window
  
     // The window needs to be based on src as we copy all the heights of src
     Window win = calculate_max_window(*src, Steps(num_elems_processed_per_iteration));
     ICLKernel::configure_internal(win.collapse(win, Window::DimZ));
  
     ARM_COMPUTE_ERROR_ON(has_padding_changed(padding_info));
 }

References CLBuildOptions::add_option(), arm_compute::adjust_vec_size(), ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::calculate_max_window(), Window::collapse(), arm_compute::create_kernel(), Window::DimZ, arm_compute::test::validation::dst, arm_compute::float_to_string_with_full_precision(), arm_compute::get_cl_unsigned_type_from_element_size(), arm_compute::get_padding_info(), arm_compute::has_padding_changed(), arm_compute::is_data_type_quantized_asymmetric(), kernel_name, num_elems_processed_per_iteration, UniformQuantizationInfo::offset, CLBuildOptions::options(), UniformQuantizationInfo::scale, arm_compute::test::validation::src, arm_compute::support::cpp11::to_string(), arm_compute::upper_string(), and arm_compute::validate_arguments().

◆ run_op()

void run_op	(	ITensorPack &	tensors,
		const Window &	window,
		::cl::CommandQueue &	queue
	)

override

Definition at line 126 of file ClHeightConcatenateKernel.cpp.

 {
     ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(this);
     ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(ICLKernel::window(), window);
  
     const auto src =
         utils::cast::polymorphic_downcast<const ICLTensor *>(tensors.get_const_tensor(TensorType::ACL_SRC));
     auto dst = utils::cast::polymorphic_downcast<ICLTensor *>(tensors.get_tensor(TensorType::ACL_DST));
  
     unsigned int idx = 0;
     add_4D_tensor_argument(idx, src, window);
     add_4D_tensor_argument(idx, dst, window);
     _kernel.setArg<cl_uint>(idx++, _depth);
     enqueue(queue, *this, window, lws_hint());
 }

References arm_compute::ACL_DST, arm_compute::ACL_SRC, ICLKernel::add_4D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::test::validation::dst, arm_compute::enqueue(), ITensorPack::get_const_tensor(), ITensorPack::get_tensor(), ICLKernel::lws_hint(), arm_compute::test::validation::src, and IKernel::window().

◆ validate()

Status validate	(	const ITensorInfo *	src,
		unsigned int	height_offset,
		const ITensorInfo *	dst
	)

static

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

Returns: a status

Definition at line 70 of file ClHeightConcatenateKernel.cpp.

 {
     ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(src, height_offset, dst));
     return Status{};
 }

References ARM_COMPUTE_RETURN_ON_ERROR, arm_compute::test::validation::dst, arm_compute::test::validation::src, and arm_compute::validate_arguments().

Referenced by ClConcatenate::validate().

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

src/gpu/cl/kernels/ClHeightConcatenateKernel.h
src/gpu/cl/kernels/ClHeightConcatenateKernel.cpp

Public Member Functions

Static Public Member Functions