Compute Library
 21.02
CLSobel5x5VertKernel Class Reference

Interface for the kernel to run the vertical pass of 5x5 Sobel filter on a tensor. More...

#include <CLSobel5x5Kernel.h>

Collaboration diagram for CLSobel5x5VertKernel:
[legend]

Public Member Functions

 CLSobel5x5VertKernel ()
 Default constructor: initialize all the pointers to nullptr and parameters to zero. More...
 
 CLSobel5x5VertKernel (const CLSobel5x5VertKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLSobel5x5VertKerneloperator= (const CLSobel5x5VertKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLSobel5x5VertKernel (CLSobel5x5VertKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLSobel5x5VertKerneloperator= (CLSobel5x5VertKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~CLSobel5x5VertKernel ()=default
 Default destructor. More...
 
void configure (const ICLTensor *input_x, const ICLTensor *input_y, ICLTensor *output_x, ICLTensor *output_y, bool border_undefined)
 Initialise the kernel's source, destination and border. More...
 
void configure (const CLCompileContext &compile_context, const ICLTensor *input_x, const ICLTensor *input_y, ICLTensor *output_x, ICLTensor *output_y, bool border_undefined)
 Initialise the kernel's source, destination and border. 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...
 
BorderSize border_size () const override
 The size of the border for that kernel. More...
 
- Public Member Functions inherited from ICLKernel
 ICLKernel ()
 Constructor. More...
 
cl::Kernel & kernel ()
 Returns a reference to the OpenCL kernel of this object. 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...
 
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...
 
const Windowwindow () const
 The maximum window the kernel can be executed on. More...
 

Additional Inherited Members

- Static Public Member Functions inherited from ICLKernel
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 kernel to run the vertical pass of 5x5 Sobel filter on a tensor.

Definition at line 86 of file CLSobel5x5Kernel.h.

Constructor & Destructor Documentation

◆ CLSobel5x5VertKernel() [1/3]

Default constructor: initialize all the pointers to nullptr and parameters to zero.

Definition at line 142 of file CLSobel5x5Kernel.cpp.

143  : _input_x(nullptr), _input_y(nullptr), _output_x(nullptr), _output_y(nullptr), _run_sobel_x(false), _run_sobel_y(false)
144 {
145 }

◆ CLSobel5x5VertKernel() [2/3]

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

◆ CLSobel5x5VertKernel() [3/3]

Allow instances of this class to be moved.

◆ ~CLSobel5x5VertKernel()

~CLSobel5x5VertKernel ( )
default

Default destructor.

Member Function Documentation

◆ border_size()

BorderSize border_size ( ) const
overridevirtual

The size of the border for that kernel.

Returns
The width in number of elements of the border.

Reimplemented from IKernel.

Definition at line 147 of file CLSobel5x5Kernel.cpp.

Referenced by CLSobel5x5VertKernel::configure().

148 {
149  return BorderSize{ 2, 0 };
150 }
Container for 2D border size.
Definition: Types.h:273

◆ configure() [1/2]

void configure ( const ICLTensor input_x,
const ICLTensor input_y,
ICLTensor output_x,
ICLTensor output_y,
bool  border_undefined 
)

Initialise the kernel's source, destination and border.

Note
At least one of output_x or output_y must be set and the corresponding input.
Parameters
[in]input_x(Optional) Input for X (X output of horizontal pass). Data types supported: S16.
[in]input_y(Optional) Input for Y (Y output of horizontal pass). Data types supported: S16.
[out]output_x(Optional) Destination tensor for the X gradient, Data types supported: S16.
[out]output_y(Optional) Destination tensor for the Y gradient, Data types supported: S16.
[in]border_undefinedTrue if the border mode is undefined. False if it's replicate or constant.

Definition at line 152 of file CLSobel5x5Kernel.cpp.

References CLKernelLibrary::get().

153 {
154  configure(CLKernelLibrary::get().get_compile_context(), input_x, input_y, output_x, output_y, border_undefined);
155 }
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
void configure(const ICLTensor *input_x, const ICLTensor *input_y, ICLTensor *output_x, ICLTensor *output_y, bool border_undefined)
Initialise the kernel&#39;s source, destination and border.

◆ configure() [2/2]

void configure ( const CLCompileContext compile_context,
const ICLTensor input_x,
const ICLTensor input_y,
ICLTensor output_x,
ICLTensor output_y,
bool  border_undefined 
)

Initialise the kernel's source, destination and border.

Note
At least one of output_x or output_y must be set and the corresponding input.
Parameters
[in]compile_contextThe compile context to be used.
[in]input_x(Optional) Input for X (X output of horizontal pass). Data types supported: S16.
[in]input_y(Optional) Input for Y (Y output of horizontal pass). Data types supported: S16.
[out]output_x(Optional) Destination tensor for the X gradient, Data types supported: S16.
[out]output_y(Optional) Destination tensor for the Y gradient, Data types supported: S16.
[in]border_undefinedTrue if the border mode is undefined. False if it's replicate or constant.

Definition at line 157 of file CLSobel5x5Kernel.cpp.

References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, CLSobel5x5VertKernel::border_size(), arm_compute::calculate_max_window(), arm_compute::create_kernel(), ITensorInfo::data_type(), ITensorInfo::dimension(), ITensor::info(), arm_compute::test::validation::input, kernel_name, arm_compute::lower_string(), num_elems_processed_per_iteration, arm_compute::S16, arm_compute::string_from_data_type(), arm_compute::support::cpp11::to_string(), BorderSize::top, arm_compute::update_window_and_padding(), and ITensorInfo::valid_region().

158 {
159  ARM_COMPUTE_ERROR_ON((output_x == nullptr) && (output_y == nullptr));
160 
161  _run_sobel_x = output_x != nullptr;
162  _run_sobel_y = output_y != nullptr;
163 
164  if(_run_sobel_x)
165  {
168  }
169 
170  if(_run_sobel_y)
171  {
174  }
175 
176  _input_x = input_x;
177  _input_y = input_y;
178  _output_x = output_x;
179  _output_y = output_y;
180 
181  // Set build options
182  std::set<std::string> build_opts;
183 
184  if(_run_sobel_x)
185  {
186  build_opts.insert("-DGRAD_X");
187  }
188 
189  if(_run_sobel_y)
190  {
191  build_opts.insert("-DGRAD_Y");
192  }
193 
194  // Create kernel
195  const std::string kernel_name = std::string("sobel_separable5x1");
196  _kernel = create_kernel(compile_context, kernel_name, build_opts);
197 
198  const ICLTensor *input = _run_sobel_x ? _input_x : _input_y;
199 
200  // Configure kernel window
201  constexpr unsigned int num_elems_processed_per_iteration = 8;
202  constexpr unsigned int num_elems_written_per_iteration = 8;
203  constexpr unsigned int num_elems_read_per_iteration = 8;
204  constexpr unsigned int num_rows_read_per_iteration = 5;
205 
206  Window win = calculate_max_window(*input->info(), Steps(num_elems_processed_per_iteration), border_undefined, border_size());
207 
208  AccessWindowRectangle input_x_access(input_x == nullptr ? nullptr : input_x->info(), 0, -border_size().top, num_elems_read_per_iteration, num_rows_read_per_iteration);
209  AccessWindowRectangle input_y_access(input_y == nullptr ? nullptr : input_y->info(), 0, -border_size().top, num_elems_read_per_iteration, num_rows_read_per_iteration);
210  AccessWindowHorizontal output_x_access(output_x == nullptr ? nullptr : output_x->info(), 0, num_elems_written_per_iteration);
211  AccessWindowHorizontal output_y_access(output_y == nullptr ? nullptr : output_y->info(), 0, num_elems_written_per_iteration);
212 
213  update_window_and_padding(win, input_x_access, input_y_access, output_x_access, output_y_access);
214 
215  output_x_access.set_valid_region(win, input->info()->valid_region(), border_undefined, border_size());
216  output_y_access.set_valid_region(win, input->info()->valid_region(), border_undefined, border_size());
217 
218  ICLKernel::configure_internal(win);
219 
220  // Set config_id for enabling LWS tuning
221  _config_id = kernel_name;
222  _config_id += "_";
223  _config_id += lower_string(string_from_data_type(input->info()->data_type()));
224  _config_id += "_";
225  _config_id += support::cpp11::to_string(input->info()->dimension(0));
226  _config_id += "_";
227  _config_id += support::cpp11::to_string(input->info()->dimension(1));
228  _config_id += "_";
229  _config_id += support::cpp11::to_string(border_undefined);
230 }
unsigned int top
top of the border
Definition: Types.h:375
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
BorderSize border_size() const override
The size of the border for that kernel.
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
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.
#define ARM_COMPUTE_ERROR_ON(cond)
If the condition is true then an error message is printed and an exception thrown.
Definition: Error.h:466
std::string lower_string(const std::string &val)
Lower a given string.
Definition: Utils.cpp:350
virtual ValidRegion valid_region() const =0
Valid region of the tensor.
Implementation of a rectangular access pattern.
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.
Definition: CLHelpers.cpp:403
const std::string & string_from_data_type(DataType dt)
Convert a data type identity into a string.
Definition: Utils.cpp:135
bool update_window_and_padding(Window &win, Ts &&... patterns)
Update window and padding size for each of the access patterns.
Definition: WindowHelpers.h:46
Class to describe a number of elements in each dimension.
Definition: Steps.h:40
Implementation of a row access pattern.
std::string kernel_name
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor&#39;s metadata.
1 channel, 1 S16 per channel
#define ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
Definition: Validate.h:790
Interface for OpenCL tensor.
Definition: ICLTensor.h:42
unsigned int num_elems_processed_per_iteration
Describe a multidimensional execution window.
Definition: Window.h:39

◆ operator=() [1/2]

CLSobel5x5VertKernel& operator= ( const CLSobel5x5VertKernel )
delete

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

◆ operator=() [2/2]

CLSobel5x5VertKernel& operator= ( CLSobel5x5VertKernel &&  )
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]windowRegion on which to execute the kernel. (Must be a valid region of the window returned by window()).
[in,out]queueCommand queue on which to enqueue the kernel.

Reimplemented from ICLKernel.

Definition at line 232 of file CLSobel5x5Kernel.cpp.

References ICLKernel::add_2D_tensor_argument_if(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::enqueue(), Window::first_slice_window_2D(), ICLKernel::lws_hint(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_2D(), and IKernel::window().

233 {
236 
238  do
239  {
240  unsigned int idx = 0;
241  add_2D_tensor_argument_if((_run_sobel_x), idx, _input_x, slice);
242  add_2D_tensor_argument_if((_run_sobel_x), idx, _output_x, slice);
243  add_2D_tensor_argument_if((_run_sobel_y), idx, _input_y, slice);
244  add_2D_tensor_argument_if((_run_sobel_y), idx, _output_y, slice);
245 
246  _kernel.setArg(idx++, 0 /*dummy*/);
247 
248  enqueue(queue, *this, slice, lws_hint());
249  }
250  while(window.slide_window_slice_2D(slice));
251 }
Window first_slice_window_2D() const
First 2D slice of the window.
Definition: Window.h:283
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
void add_2D_tensor_argument_if(bool cond, unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 2D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx ...
Definition: ICLKernel.h:159
void enqueue(IGCKernel &kernel, const Window &window, const gles::NDRange &lws=gles::NDRange(1U, 1U, 1U))
Add the kernel to the command queue with the given window.
Definition: IGCKernel.cpp:41
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
Definition: ICLKernel.h:276
bool slide_window_slice_2D(Window &slice) const
Slide the passed 2D window slice.
Definition: Window.h:323
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941
Describe a multidimensional execution window.
Definition: Window.h:39
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

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