Compute Library
 21.02
CLGaussianPyramidHorKernel Class Reference

OpenCL kernel to perform a Gaussian filter and half scaling across width (horizontal pass) More...

#include <CLGaussianPyramidKernel.h>

Collaboration diagram for CLGaussianPyramidHorKernel:
[legend]

Public Member Functions

 CLGaussianPyramidHorKernel ()
 Default constructor. More...
 
 CLGaussianPyramidHorKernel (const CLGaussianPyramidHorKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLGaussianPyramidHorKerneloperator= (const CLGaussianPyramidHorKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLGaussianPyramidHorKernel (CLGaussianPyramidHorKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLGaussianPyramidHorKerneloperator= (CLGaussianPyramidHorKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~CLGaussianPyramidHorKernel ()=default
 Default destructor. More...
 
void configure (const ICLTensor *input, ICLTensor *output)
 Initialise the kernel's source, destination and border mode. More...
 
void configure (const CLCompileContext &compile_context, const ICLTensor *input, ICLTensor *output)
 Initialise the kernel's source, destination and border mode. 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 ICLSimpleKernel
 ICLSimpleKernel ()
 Constructor. More...
 
 ICLSimpleKernel (const ICLSimpleKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
ICLSimpleKerneloperator= (const ICLSimpleKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 ICLSimpleKernel (ICLSimpleKernel &&)=default
 Allow instances of this class to be moved. More...
 
ICLSimpleKerneloperator= (ICLSimpleKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~ICLSimpleKernel ()=default
 Default destructor. More...
 
void configure (const ICLTensor *input, ICLTensor *output, unsigned int num_elems_processed_per_iteration, bool border_undefined=false, const BorderSize &border_size=BorderSize())
 Configure the 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

OpenCL kernel to perform a Gaussian filter and half scaling across width (horizontal pass)

Definition at line 34 of file CLGaussianPyramidKernel.h.

Constructor & Destructor Documentation

◆ CLGaussianPyramidHorKernel() [1/3]

Default constructor.

Definition at line 36 of file CLGaussianPyramidKernel.cpp.

37  : _l2_load_offset(0)
38 {
39 }

◆ CLGaussianPyramidHorKernel() [2/3]

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

◆ CLGaussianPyramidHorKernel() [3/3]

Allow instances of this class to be moved.

◆ ~CLGaussianPyramidHorKernel()

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 41 of file CLGaussianPyramidKernel.cpp.

Referenced by CLGaussianPyramidHorKernel::configure().

42 {
43  return BorderSize{ 0, 2 };
44 }
Container for 2D border size.
Definition: Types.h:273

◆ configure() [1/2]

void configure ( const ICLTensor input,
ICLTensor output 
)

Initialise the kernel's source, destination and border mode.

Parameters
[in]inputSource tensor. Data types supported: U8.
[out]outputDestination tensor. Output should have half the input width. Data types supported: U16.

Definition at line 46 of file CLGaussianPyramidKernel.cpp.

References CLKernelLibrary::get().

47 {
48  configure(CLKernelLibrary::get().get_compile_context(), input, output);
49 }
void configure(const ICLTensor *input, ICLTensor *output)
Initialise the kernel&#39;s source, destination and border mode.
static CLKernelLibrary & get()
Access the KernelLibrary singleton.

◆ configure() [2/2]

void configure ( const CLCompileContext compile_context,
const ICLTensor input,
ICLTensor output 
)

Initialise the kernel's source, destination and border mode.

Parameters
[in]compile_contextThe compile context to be used.
[in]inputSource tensor. Data types supported: U8.
[out]outputDestination tensor. Output should have half the input width. Data types supported: U16.

Definition at line 51 of file CLGaussianPyramidKernel.cpp.

References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, CLGaussianPyramidHorKernel::border_size(), arm_compute::calculate_max_window_horizontal(), arm_compute::create_kernel(), ITensorInfo::data_type(), ITensorInfo::dimension(), ITensor::info(), arm_compute::test::validation::input, kernel_name, BorderSize::left, arm_compute::lower_string(), num_elems_processed_per_iteration, Dimensions< int >::num_max_dimensions, arm_compute::test::validation::scale_x, ITensorInfo::set_valid_region(), arm_compute::string_from_data_type(), ITensorInfo::tensor_shape(), arm_compute::support::cpp11::to_string(), arm_compute::U16, arm_compute::U8, and arm_compute::update_window_and_padding().

52 {
55  ARM_COMPUTE_ERROR_ON(input->info()->dimension(1) != output->info()->dimension(1));
56 
57  for(size_t i = 2; i < Coordinates::num_max_dimensions; ++i)
58  {
59  ARM_COMPUTE_ERROR_ON(input->info()->dimension(i) != output->info()->dimension(i));
60  }
61 
62  _input = input;
63  _output = output;
64 
65  // Create kernel
66  const std::string kernel_name = std::string("gaussian1x5_sub_x");
67  _kernel = create_kernel(compile_context, kernel_name);
68 
69  // Configure kernel window
70  constexpr unsigned int num_elems_processed_per_iteration = 16;
71  constexpr unsigned int num_elems_read_per_iteration = 20;
72  constexpr unsigned int num_elems_written_per_iteration = 8;
73  const float scale_x = static_cast<float>(output->info()->dimension(0)) / input->info()->dimension(0);
74 
75  Window win = calculate_max_window_horizontal(*input->info(), Steps(num_elems_processed_per_iteration));
76  AccessWindowHorizontal output_access(output->info(), 0, num_elems_written_per_iteration, scale_x);
77 
78  // Sub sampling selects odd pixels (1, 3, 5, ...) for images with even
79  // width and even pixels (0, 2, 4, ...) for images with odd width. (Whether
80  // a pixel is even or odd is determined based on the tensor shape not the
81  // valid region!)
82  // Thus the offset from which the first pixel (L2) for the convolution is
83  // loaded depends on the anchor and shape of the valid region.
84  // In the case of an even shape (= even image width) we need to load L2
85  // from -2 if the anchor is odd and from -1 if the anchor is even. That
86  // makes sure that L2 is always loaded from an odd pixel.
87  // On the other hand, for an odd shape (= odd image width) we need to load
88  // L2 from -1 if the anchor is odd and from -2 if the anchor is even to
89  // achieve the opposite effect.
90  // The condition can be simplified to checking whether anchor + shape is
91  // odd (-2) or even (-1) as only adding an odd and an even number will have
92  // an odd result.
93  _l2_load_offset = -border_size().left;
94 
95  if((_input->info()->valid_region().anchor[0] + _input->info()->valid_region().shape[0]) % 2 == 0)
96  {
97  _l2_load_offset += 1;
98  }
99 
101  AccessWindowHorizontal(input->info(), _l2_load_offset, num_elems_read_per_iteration),
102  output_access);
103 
104  output->info()->set_valid_region(ValidRegion(Coordinates(), output->info()->tensor_shape()));
105 
106  ICLKernel::configure_internal(win);
107 
108  // Set config_id for enabling LWS tuning
109  _config_id = kernel_name;
110  _config_id += "_";
111  _config_id += lower_string(string_from_data_type(input->info()->data_type()));
112  _config_id += "_";
113  _config_id += support::cpp11::to_string(input->info()->dimension(0));
114  _config_id += "_";
115  _config_id += support::cpp11::to_string(input->info()->dimension(1));
116  _config_id += "_";
117  _config_id += support::cpp11::to_string(output->info()->dimension(0));
118  _config_id += "_";
119  _config_id += support::cpp11::to_string(output->info()->dimension(1));
120 }
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
1 channel, 1 U8 per channel
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
1 channel, 1 U16 per channel
std::string lower_string(const std::string &val)
Lower a given string.
Definition: Utils.cpp:350
Window calculate_max_window_horizontal(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
virtual void set_valid_region(const ValidRegion &valid_region)=0
Set the valid region of the tensor.
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
virtual const TensorShape & tensor_shape() const =0
Size for each dimension of the tensor.
Class to describe a number of elements in each dimension.
Definition: Steps.h:40
Coordinates of an item.
Definition: Coordinates.h:37
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.
unsigned int left
left of the border
Definition: Types.h:378
#define ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
Definition: Validate.h:790
BorderSize border_size() const override
The size of the border for that kernel.
unsigned int num_elems_processed_per_iteration
Container for valid region of a window.
Definition: Types.h:188
static constexpr size_t num_max_dimensions
Number of dimensions the tensor has.
Definition: Dimensions.h:46
Describe a multidimensional execution window.
Definition: Window.h:39

◆ operator=() [1/2]

CLGaussianPyramidHorKernel& operator= ( const CLGaussianPyramidHorKernel )
delete

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

◆ operator=() [2/2]

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 122 of file CLGaussianPyramidKernel.cpp.

References ICLKernel::add_2D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, Window::DimX, arm_compute::enqueue(), Window::first_slice_window_2D(), ICLKernel::lws_hint(), Window::scale(), Window::shift(), Window::slide_window_slice_2D(), and IKernel::window().

123 {
126 
127  Window win_in(window);
128  win_in.shift(Window::DimX, _l2_load_offset);
129 
130  //The output is half the width of the input:
131  Window win_out(window);
132  win_out.scale(Window::DimX, 0.5f);
133 
134  Window slice_in = win_in.first_slice_window_2D();
135  Window slice_out = win_out.first_slice_window_2D();
136 
137  do
138  {
139  unsigned int idx = 0;
140  add_2D_tensor_argument(idx, _input, slice_in);
141  add_2D_tensor_argument(idx, _output, slice_out);
142  enqueue(queue, *this, slice_out, lws_hint());
143  }
144  while(win_in.slide_window_slice_2D(slice_in) && win_out.slide_window_slice_2D(slice_out));
145 }
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 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
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
Definition: Window.h:43
#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
Describe a multidimensional execution window.
Definition: Window.h:39
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205

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