Compute Library
 21.02
CLLKTrackerStage0Kernel Class Reference

Interface to run the first stage of LKTracker, where A11, A12, A22, min_eig, ival, ixval and iyval are computed. More...

#include <CLLKTrackerKernel.h>

Collaboration diagram for CLLKTrackerStage0Kernel:
[legend]

Public Member Functions

 CLLKTrackerStage0Kernel ()
 Default constructor. More...
 
 CLLKTrackerStage0Kernel (const CLLKTrackerStage0Kernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLLKTrackerStage0Kerneloperator= (const CLLKTrackerStage0Kernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLLKTrackerStage0Kernel (CLLKTrackerStage0Kernel &&)=default
 Allow instances of this class to be moved. More...
 
CLLKTrackerStage0Kerneloperator= (CLLKTrackerStage0Kernel &&)=default
 Allow instances of this class to be moved. More...
 
void configure (const ICLTensor *old_input, const ICLTensor *old_scharr_gx, const ICLTensor *old_scharr_gy, ICLLKInternalKeypointArray *old_points_internal, ICLLKInternalKeypointArray *new_points_internal, ICLCoefficientTableArray *coeff_table, ICLOldValArray *old_ival, size_t window_dimension, size_t level)
 Initialise the kernel input and output. More...
 
void configure (const CLCompileContext &compile_context, const ICLTensor *old_input, const ICLTensor *old_scharr_gx, const ICLTensor *old_scharr_gy, ICLLKInternalKeypointArray *old_points_internal, ICLLKInternalKeypointArray *new_points_internal, ICLCoefficientTableArray *coeff_table, ICLOldValArray *old_ival, size_t window_dimension, size_t level)
 Initialise the kernel input and output. 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...
 
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...
 
virtual BorderSize border_size () const
 The size of the border for that kernel. 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 to run the first stage of LKTracker, where A11, A12, A22, min_eig, ival, ixval and iyval are computed.

Definition at line 99 of file CLLKTrackerKernel.h.

Constructor & Destructor Documentation

◆ CLLKTrackerStage0Kernel() [1/3]

Default constructor.

Definition at line 129 of file CLLKTrackerKernel.cpp.

130  : _old_input(nullptr), _old_scharr_gx(nullptr), _old_scharr_gy(nullptr)
131 {
132 }

◆ CLLKTrackerStage0Kernel() [2/3]

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

◆ CLLKTrackerStage0Kernel() [3/3]

Allow instances of this class to be moved.

Member Function Documentation

◆ configure() [1/2]

void configure ( const ICLTensor old_input,
const ICLTensor old_scharr_gx,
const ICLTensor old_scharr_gy,
ICLLKInternalKeypointArray old_points_internal,
ICLLKInternalKeypointArray new_points_internal,
ICLCoefficientTableArray coeff_table,
ICLOldValArray old_ival,
size_t  window_dimension,
size_t  level 
)

Initialise the kernel input and output.

Parameters
[in]old_inputPointer to the input old tensor. Data types supported: U8
[in]old_scharr_gxPointer to the input scharr X tensor. Data types supported: S16
[in]old_scharr_gyPointer to the input scharr Y tensor. Data types supported: S16
[in]old_points_internalPointer to the array of CLLKInternalKeypoint old points
[in,out]new_points_internalPointer to the array of CLLKInternalKeypoint new points
[out]coeff_tablePointer to the array holding the Spatial Gradient coefficients
[out]old_ivalPointer to the array holding internal values
[in]window_dimensionThe size of the window on which to perform the algorithm
[in]levelThe pyramid level

Definition at line 134 of file CLLKTrackerKernel.cpp.

References CLKernelLibrary::get().

138 {
139  configure(CLKernelLibrary::get().get_compile_context(), old_input, old_scharr_gx, old_scharr_gy, old_points_internal, new_points_internal, coeff_table, old_ival, window_dimension, level);
140 }
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
void configure(const ICLTensor *old_input, const ICLTensor *old_scharr_gx, const ICLTensor *old_scharr_gy, ICLLKInternalKeypointArray *old_points_internal, ICLLKInternalKeypointArray *new_points_internal, ICLCoefficientTableArray *coeff_table, ICLOldValArray *old_ival, size_t window_dimension, size_t level)
Initialise the kernel input and output.

◆ configure() [2/2]

void configure ( const CLCompileContext compile_context,
const ICLTensor old_input,
const ICLTensor old_scharr_gx,
const ICLTensor old_scharr_gy,
ICLLKInternalKeypointArray old_points_internal,
ICLLKInternalKeypointArray new_points_internal,
ICLCoefficientTableArray coeff_table,
ICLOldValArray old_ival,
size_t  window_dimension,
size_t  level 
)

Initialise the kernel input and output.

Parameters
[in]compile_contextThe compile context to be used.
[in]old_inputPointer to the input old tensor. Data types supported: U8
[in]old_scharr_gxPointer to the input scharr X tensor. Data types supported: S16
[in]old_scharr_gyPointer to the input scharr Y tensor. Data types supported: S16
[in]old_points_internalPointer to the array of CLLKInternalKeypoint old points
[in,out]new_points_internalPointer to the array of CLLKInternalKeypoint new points
[out]coeff_tablePointer to the array holding the Spatial Gradient coefficients
[out]old_ivalPointer to the array holding internal values
[in]window_dimensionThe size of the window on which to perform the algorithm
[in]levelThe pyramid level

Definition at line 142 of file CLLKTrackerKernel.cpp.

References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ICLArray< T >::cl_buffer(), arm_compute::create_kernel(), Window::DimX, Window::DimY, ValidRegion::end(), ITensor::info(), arm_compute::intersect_valid_regions(), ICLKernel::num_arguments_per_2D_tensor(), IArray< T >::num_values(), arm_compute::S16, Window::set(), ValidRegion::start(), arm_compute::U8, arm_compute::update_window_and_padding(), arm_compute::test::validation::valid_region, ITensorInfo::valid_region(), and IKernel::window().

147 {
151  ARM_COMPUTE_ERROR_ON(old_points_internal == nullptr);
152  ARM_COMPUTE_ERROR_ON(new_points_internal == nullptr);
153  ARM_COMPUTE_ERROR_ON(coeff_table == nullptr);
154  ARM_COMPUTE_ERROR_ON(old_ival == nullptr);
155 
156  _old_input = old_input;
157  _old_scharr_gx = old_scharr_gx;
158  _old_scharr_gy = old_scharr_gy;
159 
160  // Configure kernel window
161  Window window;
162  window.set(Window::DimX, Window::Dimension(0, new_points_internal->num_values(), 1));
163  window.set(Window::DimY, Window::Dimension(0, 1, 1));
164 
166  old_input->info()->valid_region(),
167  old_scharr_gx->info()->valid_region(),
168  old_scharr_gy->info()->valid_region());
169 
171  AccessWindowStatic(old_input->info(), valid_region.start(0), valid_region.start(1),
172  valid_region.end(0), valid_region.end(1)),
173  AccessWindowStatic(old_scharr_gx->info(), valid_region.start(0), valid_region.start(1),
174  valid_region.end(0), valid_region.end(1)),
175  AccessWindowStatic(old_scharr_gy->info(), valid_region.start(0), valid_region.start(1),
176  valid_region.end(0), valid_region.end(1)));
177 
178  ICLKernel::configure_internal(window);
179 
180  // Initialize required variables
181  const int level0 = (level == 0) ? 1 : 0;
182  const int window_size = window_dimension;
183  const int window_size_squared = window_dimension * window_dimension;
184  const int window_size_half = window_dimension / 2;
185  const float eig_const = 1.0f / (2.0f * window_size_squared);
186  const cl_float3 border_limits =
187  {
188  {
189  // -1 because we load 2 values at once for bilinear interpolation
190  static_cast<cl_float>(valid_region.end(0) - window_size - 1),
191  static_cast<cl_float>(valid_region.end(1) - window_size - 1),
192  static_cast<cl_float>(valid_region.start(0))
193  }
194  };
195 
196  // Create kernel
197  _kernel = create_kernel(compile_context, "lktracker_stage0");
198 
199  // Set arguments
200  unsigned int idx = 3 * num_arguments_per_2D_tensor();
201  _kernel.setArg(idx++, old_points_internal->cl_buffer());
202  _kernel.setArg(idx++, new_points_internal->cl_buffer());
203  _kernel.setArg(idx++, coeff_table->cl_buffer());
204  _kernel.setArg(idx++, old_ival->cl_buffer());
205  _kernel.setArg<cl_int>(idx++, window_size);
206  _kernel.setArg<cl_int>(idx++, window_size_squared);
207  _kernel.setArg<cl_int>(idx++, window_size_half);
208  _kernel.setArg<cl_float3>(idx++, border_limits);
209  _kernel.setArg<cl_float>(idx++, eig_const);
210  _kernel.setArg<cl_int>(idx++, level0);
211 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
1 channel, 1 U8 per channel
#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
Describe one of the image&#39;s dimensions with a start, end and step.
Definition: Window.h:77
const ValidRegion valid_region
Definition: Scale.cpp:221
virtual ValidRegion valid_region() const =0
Valid region of the tensor.
Implementation of a static 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
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
Definition: Window.h:43
bool update_window_and_padding(Window &win, Ts &&... patterns)
Update window and padding size for each of the access patterns.
Definition: WindowHelpers.h:46
size_t num_values() const
Number of values currently stored in the array.
Definition: IArray.h:68
int start(unsigned int d) const
Return the start of the valid region for the given dimension d.
Definition: Types.h:234
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor&#39;s metadata.
ValidRegion intersect_valid_regions(const Ts &... regions)
Intersect multiple valid regions.
Definition: WindowHelpers.h:74
void set(size_t dimension, const Dimension &dim)
Set the values of a given dimension.
Definition: Window.inl:49
static constexpr unsigned int num_arguments_per_2D_tensor()
Returns the number of arguments enqueued per 2D tensor object.
Definition: ICLKernel.h:206
1 channel, 1 S16 per channel
#define ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
Definition: Validate.h:790
static constexpr size_t DimY
Alias for dimension 1 also known as Y dimension.
Definition: Window.h:45
int end(unsigned int d) const
Return the end of the valid region for the given dimension d.
Definition: Types.h:240
Container for valid region of a window.
Definition: Types.h:188
virtual const cl::Buffer & cl_buffer() const =0
Interface to be implemented by the child class to return a reference to the OpenCL buffer containing ...
Describe a multidimensional execution window.
Definition: Window.h:39

◆ operator=() [1/2]

CLLKTrackerStage0Kernel& operator= ( const CLLKTrackerStage0Kernel )
delete

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

◆ operator=() [2/2]

CLLKTrackerStage0Kernel& operator= ( CLLKTrackerStage0Kernel &&  )
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 213 of file CLLKTrackerKernel.cpp.

References ICLKernel::add_2D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::enqueue(), ICLKernel::lws_hint(), and IKernel::window().

214 {
217 
218  // Set static tensor arguments. Setting here as allocation might be deferred.
219  unsigned int idx = 0;
220  add_2D_tensor_argument(idx, _old_input, window);
221  add_2D_tensor_argument(idx, _old_scharr_gx, window);
222  add_2D_tensor_argument(idx, _old_scharr_gy, window);
223 
224  enqueue(queue, *this, window, lws_hint());
225 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
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
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941
void add_2D_tensor_argument(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:148
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205

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