Compute Library
 21.02
CLComparisonKernel Class Reference

Interface for the comparison kernel. More...

#include <CLComparisonKernel.h>

Collaboration diagram for CLComparisonKernel:
[legend]

Public Member Functions

 CLComparisonKernel ()
 Default constructor. More...
 
 CLComparisonKernel (const CLComparisonKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLComparisonKerneloperator= (const CLComparisonKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLComparisonKernel (CLComparisonKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLComparisonKerneloperator= (CLComparisonKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~CLComparisonKernel ()=default
 Default destructor. More...
 
void configure (const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, ComparisonOperation operation)
 Set the inputs and output tensors. More...
 
void configure (const CLCompileContext &compile_context, const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, ComparisonOperation operation)
 Set the inputs and output tensors. 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...
 

Static Public Member Functions

static Status validate (const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *output, ComparisonOperation operation)
 Static function to check if given info will lead to a valid configuration of CLComparisonKernel. More...
 
- 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 comparison kernel.

Definition at line 36 of file CLComparisonKernel.h.

Constructor & Destructor Documentation

◆ CLComparisonKernel() [1/3]

Default constructor.

Definition at line 106 of file CLComparisonKernel.cpp.

107  : _input1(nullptr), _input2(nullptr), _output(nullptr)
108 {
109 }

◆ CLComparisonKernel() [2/3]

CLComparisonKernel ( const CLComparisonKernel )
delete

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

◆ CLComparisonKernel() [3/3]

Allow instances of this class to be moved.

◆ ~CLComparisonKernel()

~CLComparisonKernel ( )
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 222 of file CLComparisonKernel.cpp.

References ITensorInfo::dimension(), ITensor::info(), and arm_compute::U.

223 {
224  const int num_elems_processed_per_iteration = calculate_num_elems_processed_per_iteration(*_input1->info());
225 
226  const unsigned int replicateSize = _output->info()->dimension(0) - std::min(_input1->info()->dimension(0), _input2->info()->dimension(0));
227  const unsigned int border = std::min<unsigned int>(num_elems_processed_per_iteration - 1U, replicateSize);
228  return BorderSize{ 0, border, 0, 0 };
229 }
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor&#39;s metadata.
unsigned int num_elems_processed_per_iteration

◆ configure() [1/2]

void configure ( const ICLTensor input1,
const ICLTensor input2,
ICLTensor output,
ComparisonOperation  operation 
)

Set the inputs and output tensors.

Parameters
[in]input1Source tensor. Data types supported: All.
[in]input2Source tensor. Data types supported: Same as input1.
[out]outputDestination tensor. Data types supported: U8.
[in]operationComparison operation to use.

Definition at line 111 of file CLComparisonKernel.cpp.

References CLKernelLibrary::get().

112 {
113  configure(CLKernelLibrary::get().get_compile_context(), input1, input2, output, operation);
114 }
void configure(const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, ComparisonOperation operation)
Set the inputs and output tensors.
static CLKernelLibrary & get()
Access the KernelLibrary singleton.

◆ configure() [2/2]

void configure ( const CLCompileContext compile_context,
const ICLTensor input1,
const ICLTensor input2,
ICLTensor output,
ComparisonOperation  operation 
)

Set the inputs and output tensors.

Parameters
[in]compile_contextThe compile context to be used.
[in]input1Source tensor. Data types supported: All.
[in]input2Source tensor. Data types supported: Same as input1.
[out]outputDestination tensor. Data types supported: U8.
[in]operationComparison operation to use.

Definition at line 116 of file CLComparisonKernel.cpp.

References ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::create_kernel(), ITensorInfo::data_layout(), ITensorInfo::data_type(), ITensorInfo::dimension(), arm_compute::float_to_string_with_full_precision(), arm_compute::get_cl_type_from_data_type(), ITensor::info(), arm_compute::is_data_type_quantized(), kernel_name, arm_compute::lower_string(), UniformQuantizationInfo::offset, ITensorInfo::quantization_info(), UniformQuantizationInfo::scale, arm_compute::string_from_data_layout(), arm_compute::string_from_data_type(), arm_compute::support::cpp11::to_string(), QuantizationInfo::uniform(), and arm_compute::validate_arguments().

117 {
118  ARM_COMPUTE_ERROR_ON_NULLPTR(input1, input2, output);
119  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(*input1->info(), *input2->info(), *output->info(), operation));
120 
121  // Configure kernel window
122  auto win_config = validate_and_configure_window(*input1->info(), *input2->info(), *output->info());
123  ARM_COMPUTE_ERROR_THROW_ON(win_config.first);
124 
125  _input1 = input1;
126  _input2 = input2;
127  _output = output;
128 
129  const std::string &operation_name = supported_comparison_ops.at(operation);
130  std::string kernel_name = "compare_" + lower_string(operation_name);
131 
132  // Set kernel build options
133  std::set<std::string> build_opts;
134  build_opts.emplace("-DDATA_TYPE=" + get_cl_type_from_data_type(input1->info()->data_type()));
135  build_opts.emplace("-DVEC_SIZE=" + support::cpp11::to_string(calculate_num_elems_processed_per_iteration(*input1->info())));
136  build_opts.emplace("-DOP=" + operation_name);
137  build_opts.emplace("-DOP_NAME=" + lower_string(operation_name));
138  if(is_data_type_quantized(input1->info()->data_type()))
139  {
140  const UniformQuantizationInfo iq1_info = input1->info()->quantization_info().uniform();
141  const UniformQuantizationInfo iq2_info = input2->info()->quantization_info().uniform();
142 
143  build_opts.emplace("-DOFFSET_IN1=" + support::cpp11::to_string(iq1_info.offset));
144  build_opts.emplace("-DOFFSET_IN2=" + support::cpp11::to_string(iq2_info.offset));
145  build_opts.emplace("-DSCALE_IN1=" + float_to_string_with_full_precision(iq1_info.scale));
146  build_opts.emplace("-DSCALE_IN2=" + float_to_string_with_full_precision(iq2_info.scale));
147  kernel_name += "_quantized";
148  }
149 
150  // Create kernel
151  _kernel = create_kernel(compile_context, kernel_name, build_opts);
152 
153  ICLKernel::configure_internal(win_config.second);
154 
155  // Set config_id for enabling LWS tuning
156  _config_id = kernel_name;
157  _config_id += "_";
158  _config_id += lower_string(string_from_data_type(input1->info()->data_type()));
159  _config_id += "_";
160  _config_id += support::cpp11::to_string(output->info()->dimension(0));
161  _config_id += "_";
162  _config_id += support::cpp11::to_string(output->info()->dimension(1));
163  _config_id += lower_string(string_from_data_layout(input1->info()->data_layout()));
164 }
bool is_data_type_quantized(DataType dt)
Check if a given data type is of quantized type.
Definition: Utils.h:1168
std::string to_string(T &&value)
Convert integer and float values to string.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
std::string lower_string(const std::string &val)
Lower a given string.
Definition: Utils.cpp:350
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
std::string float_to_string_with_full_precision(float val)
Create a string with the float in full precision.
Definition: Utils.h:1262
std::string kernel_name
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
Definition: CLHelpers.cpp:37
const std::string & string_from_data_layout(DataLayout dl)
Convert a data layout identity into a string.
Definition: Utils.cpp:123
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161

◆ operator=() [1/2]

CLComparisonKernel& operator= ( const CLComparisonKernel )
delete

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

◆ operator=() [2/2]

CLComparisonKernel& operator= ( CLComparisonKernel &&  )
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 176 of file CLComparisonKernel.cpp.

References ICLKernel::add_3D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ARM_COMPUTE_UNUSED, Window::broadcast_if_dimension_le_one(), Window::collapse_if_possible(), TensorShape::collapsed_from(), Window::DimZ, arm_compute::enqueue(), Window::first_slice_window_3D(), ITensor::info(), ICLKernel::lws_hint(), Dimensions< T >::num_dimensions(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), ITensorInfo::tensor_shape(), TensorShape::total_size(), and IKernel::window().

177 {
180 
181  const TensorShape &in_shape1 = _input1->info()->tensor_shape();
182  const TensorShape &in_shape2 = _input2->info()->tensor_shape();
183  const TensorShape &out_shape = _output->info()->tensor_shape();
184 
185  bool can_collapse = true;
186  const bool is_vector = in_shape1.num_dimensions() == 1 || in_shape2.num_dimensions() == 1;
187  if(std::min(in_shape1.total_size(), in_shape2.total_size()) > 1 && !is_vector)
188  {
189  can_collapse = (std::min(in_shape1.num_dimensions(), in_shape2.num_dimensions()) > Window::DimZ);
190  for(size_t d = Window::DimZ; can_collapse && (d < out_shape.num_dimensions()); d++)
191  {
192  can_collapse = (in_shape1[d] == in_shape2[d]);
193  }
194  }
195 
196  bool has_collapsed = false;
197  Window collapsed = can_collapse ? window.collapse_if_possible(ICLKernel::window(), Window::DimZ, &has_collapsed) : window;
198 
199  const TensorShape &in_shape1_collapsed = has_collapsed ? in_shape1.collapsed_from(Window::DimZ) : in_shape1;
200  const TensorShape &in_shape2_collapsed = has_collapsed ? in_shape2.collapsed_from(Window::DimZ) : in_shape2;
201 
202  Window slice = collapsed.first_slice_window_3D();
203  Window slice_input1 = slice.broadcast_if_dimension_le_one(in_shape1_collapsed);
204  Window slice_input2 = slice.broadcast_if_dimension_le_one(in_shape2_collapsed);
205 
206  do
207  {
208  unsigned int idx = 0;
209 
210  add_3D_tensor_argument(idx, _input1, slice_input1);
211  add_3D_tensor_argument(idx, _input2, slice_input2);
212  add_3D_tensor_argument(idx, _output, slice);
213 
214  enqueue(queue, *this, slice, lws_hint());
215 
216  ARM_COMPUTE_UNUSED(collapsed.slide_window_slice_3D(slice_input1));
217  ARM_COMPUTE_UNUSED(collapsed.slide_window_slice_3D(slice_input2));
218  }
219  while(collapsed.slide_window_slice_3D(slice));
220 }
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
void add_3D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 3D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx...
Definition: ICLKernel.h:172
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
Definition: Error.h:152
Window collapse_if_possible(const Window &full_window, size_t first, size_t last, bool *has_collapsed=nullptr) const
Collapse the dimensions between first and last if possible.
Definition: Window.inl:68
virtual const TensorShape & tensor_shape() const =0
Size for each dimension of the tensor.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor&#39;s metadata.
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
Definition: Window.h:47
unsigned int num_dimensions() const
Returns the effective dimensionality of the tensor.
Definition: Dimensions.h:143
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

◆ validate()

Status validate ( const ITensorInfo input1,
const ITensorInfo input2,
const ITensorInfo output,
ComparisonOperation  operation 
)
static

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

Parameters
[in]input1Source tensor. Data types supported: All.
[in]input2Source tensor. Data types supported: Same as input1.
[in]outputDestination tensor. Data types supported: U8.
[in]operationComparison operation to use.
Returns
a status

Definition at line 166 of file CLComparisonKernel.cpp.

References ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR, ARM_COMPUTE_RETURN_ON_ERROR, ICloneable< T >::clone(), and arm_compute::validate_arguments().

Referenced by CLComparison::validate(), and CLComparisonStatic< COP >::validate().

167 {
168  ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(input1, input2, output);
169 
170  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(*input1, *input2, *output, operation));
171  ARM_COMPUTE_RETURN_ON_ERROR(validate_and_configure_window(*input1->clone(), *input2->clone(), *output->clone()).first);
172 
173  return Status{};
174 }
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
Definition: Validate.h:163
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)

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