Compute Library
 19.08
CLActivationLayerKernel Class Reference

Interface for the activation layer kernel. More...

#include <CLActivationLayerKernel.h>

Collaboration diagram for CLActivationLayerKernel:
[legend]

Public Member Functions

 CLActivationLayerKernel ()
 Default constructor. More...
 
 CLActivationLayerKernel (const CLActivationLayerKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLActivationLayerKerneloperator= (const CLActivationLayerKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLActivationLayerKernel (CLActivationLayerKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLActivationLayerKerneloperator= (CLActivationLayerKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~CLActivationLayerKernel ()=default
 Default destructor. More...
 
void configure (ICLTensor *input, ICLTensor *output, ActivationLayerInfo act_info)
 Set the input and output tensor. 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...
 
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...
 
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<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...
 
template<unsigned int dimension_size>
void add_tensor_argument (unsigned &idx, const ICLTensor *tensor, const Window &window)
 
- 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...
 

Static Public Member Functions

static Status validate (const ITensorInfo *input, const ITensorInfo *output, const ActivationLayerInfo &act_info)
 Static function to check if given info will lead to a valid configuration of CLActivationLayerKernel. 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 activation layer kernel.

Definition at line 34 of file CLActivationLayerKernel.h.

Constructor & Destructor Documentation

◆ CLActivationLayerKernel() [1/3]

Default constructor.

Definition at line 114 of file CLActivationLayerKernel.cpp.

115  : _input(nullptr), _output(nullptr), _run_in_place(false)
116 {
117 }

◆ CLActivationLayerKernel() [2/3]

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

◆ CLActivationLayerKernel() [3/3]

Allow instances of this class to be moved.

◆ ~CLActivationLayerKernel()

Default destructor.

Member Function Documentation

◆ configure()

void configure ( ICLTensor input,
ICLTensor output,
ActivationLayerInfo  act_info 
)

Set the input and output tensor.

Note
If the output tensor is a nullptr, the activation function will be performed in-place
Parameters
[in,out]inputSource tensor. In case of output tensor = nullptr, this tensor will store the result of the activation function. Data types supported: QASYMM8/QSYMM16/F16/F32.
[out]outputDestination tensor. Data type supported: same as input
[in]act_infoActivation layer information.

Definition at line 119 of file CLActivationLayerKernel.cpp.

120 {
122 
123  _run_in_place = (output == nullptr) || (output == input);
124 
125  if(output != nullptr)
126  {
127  // Output auto inizialitation if not yet initialized
128  auto_init_if_empty(*output->info(),
129  *input->info()->clone());
130  }
131 
132  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input->info(), (output != nullptr) ? output->info() : nullptr, act_info));
133 
134  const unsigned int num_elems_processed_per_iteration = 16 / input->info()->element_size();
135  const DataType dt = input->info()->data_type();
136  float a_const = act_info.a();
137  float b_const = act_info.b();
138  int a_const_int = 0;
139  int b_const_int = 0;
140 
141  const ActivationLayerInfo::ActivationFunction f_act = act_info.activation();
142  const bool is_quantized = is_data_type_quantized(dt);
143  const bool perform_activation_in_float = (f_act == ActivationLayerInfo::ActivationFunction::LOGISTIC) || (f_act == ActivationLayerInfo::ActivationFunction::TANH);
144 
145  // Create quantized version of constants a, b if needed
146  if(dt == DataType::QASYMM8)
147  {
148  const UniformQuantizationInfo iq_info = input->info()->quantization_info().uniform();
149  a_const_int = quantize_qasymm8(a_const, iq_info);
150  b_const_int = quantize_qasymm8(b_const, iq_info);
151  }
152  else if(dt == DataType::QSYMM16)
153  {
154  const UniformQuantizationInfo iq_info = input->info()->quantization_info().uniform();
155  a_const_int = quantize_qsymm16(a_const, iq_info);
156  b_const_int = quantize_qsymm16(b_const, iq_info);
157  }
158 
159  // Set build options
160  CLBuildOptions build_opts;
161  build_opts.add_option_if(perform_activation_in_float, "-DFLOAT_DOMAIN");
162  build_opts.add_option_if(_run_in_place, "-DIN_PLACE");
163  build_opts.add_option(("-DACT=" + lower_string(string_from_activation_func(f_act))));
164  build_opts.add_option(("-DDATA_TYPE=" + get_cl_type_from_data_type(dt)));
165  build_opts.add_option(("-DVEC_SIZE=" + support::cpp11::to_string(num_elems_processed_per_iteration)));
166 
167  // Set A, B constants in build options
168  if(is_quantized && !perform_activation_in_float)
169  {
170  build_opts.add_option(("-DA_VAL=" + support::cpp11::to_string(a_const_int)));
171  build_opts.add_option(("-DB_VAL=" + support::cpp11::to_string(b_const_int)));
172  }
173  else
174  {
175  build_opts.add_option(("-DA_VAL=" + float_to_string_with_full_precision(a_const)));
176  build_opts.add_option(("-DB_VAL=" + float_to_string_with_full_precision(b_const)));
177  }
178 
179  // Set quantization info build options
180  if(is_quantized)
181  {
182  const UniformQuantizationInfo iq_info = input->info()->quantization_info().uniform();
183 
184  // Quantized value of 0 corresponds to the offset o1
185  build_opts.add_option(("-DCONST_0=" + (is_data_type_quantized_asymmetric(dt) ? support::cpp11::to_string(iq_info.offset) : "0")));
186  build_opts.add_option(("-DS1_VAL=" + float_to_string_with_full_precision(iq_info.scale)));
188 
189  // Set scale and offset of the input and output if they have different quantization info
190  if(output != nullptr)
191  {
192  const UniformQuantizationInfo oq_info = output->info()->quantization_info().uniform();
193 
194  if(iq_info != oq_info)
195  {
196  build_opts.add_option(("-DS2_VAL=" + float_to_string_with_full_precision(oq_info.scale)));
198  }
199  }
200  }
201 
202  // Create kernel
203  std::string kernel_name = std::string("activation_layer");
204  if(is_quantized)
205  {
206  kernel_name += perform_activation_in_float ? std::string("_quant_f32") : std::string("_quant");
207  }
208  _kernel = static_cast<cl::Kernel>(CLKernelLibrary::get().create_kernel(kernel_name, build_opts.options()));
209 
210  // Make sure _kernel is initialized before calling the parent's configure
211  _input = input;
212  _output = output;
213 
214  // Configure kernel window
215  auto win_config = validate_and_configure_window(input->info(), (_run_in_place) ? nullptr : output->info());
216  ARM_COMPUTE_ERROR_THROW_ON(win_config.first);
217  ICLKernel::configure_internal(win_config.second);
218 
219  // Set config_id for enabling LWS tuning
220  _config_id = "activation_layer_";
221  _config_id += lower_string(string_from_data_type(dt));
222  _config_id += "_";
223  _config_id += support::cpp11::to_string(input->info()->dimension(0));
224  _config_id += "_";
225  _config_id += support::cpp11::to_string(input->info()->dimension(1));
226 }
bool is_data_type_quantized(DataType dt)
Check if a given data type is of quantized type.
Definition: Utils.h:1010
int16_t quantize_qsymm16(float value, const UniformQuantizationInfo &qinfo, RoundingPolicy rounding_policy=RoundingPolicy::TO_NEAREST_UP)
Quantize a value given a 16-bit symmetric quantization scheme.
quantized, symmetric fixed-point 16-bit number
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
const StringSet & options() const
Gets the current options list set.
std::pair< Status, Window > validate_and_configure_window(ITensorInfo *input, ITensorInfo *weights, ITensorInfo *biases, ITensorInfo *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier, const Size2D &dilation)
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.
const std::string & string_from_activation_func(ActivationLayerInfo::ActivationFunction act)
Translates a given activation function to a string.
Definition: Utils.cpp:170
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:327
Quantization info when assuming per layer quantization.
std::string lower_string(const std::string &val)
Lower a given string.
Definition: Utils.cpp:327
bool auto_init_if_empty(ITensorInfo &info, const TensorShape &shape, int num_channels, DataType data_type, QuantizationInfo quantization_info=QuantizationInfo())
Auto initialize the tensor info (shape, number of channels and data type) if the current assignment i...
Definition: Helpers.inl:201
ActivationFunction
Available activation functions.
Definition: Types.h:1521
void add_option(std::string option)
Adds option to the existing build option list.
const std::string & string_from_data_type(DataType dt)
Convert a data type identity into a string.
Definition: Utils.cpp:144
std::string float_to_string_with_full_precision(float val)
Create a string with the float in full precision.
Definition: Utils.h:1066
quantized, asymmetric fixed-point 8-bit number
UniformQuantizationInfo uniform() const
Return per layer quantization info.
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
Definition: CLHelpers.cpp:35
virtual std::unique_ptr< T > clone() const =0
Provide a clone of the current object of class T.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
void add_option_if(bool cond, std::string option)
Adds option if a given condition is true;.
virtual size_t element_size() const =0
Element size in bytes calculated as data_size() * num_channels()
std::unique_ptr< Kernel > create_kernel()
Helper function to create and return a unique_ptr pointed to a CL/GLES kernel object.
Definition: Helpers.h:86
virtual QuantizationInfo quantization_info() const =0
Get the quantization settings (scale and offset) of the tensor.
bool is_data_type_quantized_asymmetric(DataType dt)
Check if a given data type is of asymmetric quantized type.
Definition: Utils.h:1030
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161
DataType
Available data types.
Definition: Types.h:74
uint8_t quantize_qasymm8(float value, const UniformQuantizationInfo &qinfo, RoundingPolicy rounding_policy=RoundingPolicy::TO_NEAREST_UP)
Quantize a value given a asymmetric quantization scheme.

References arm_compute::test::validation::act_info, CLBuildOptions::add_option(), CLBuildOptions::add_option_if(), ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), ICloneable< T >::clone(), arm_compute::create_kernel(), ITensorInfo::data_type(), ITensorInfo::dimension(), ITensorInfo::element_size(), arm_compute::float_to_string_with_full_precision(), CLKernelLibrary::get(), arm_compute::get_cl_type_from_data_type(), ITensor::info(), arm_compute::is_data_type_quantized(), arm_compute::is_data_type_quantized_asymmetric(), ActivationLayerInfo::LOGISTIC, arm_compute::lower_string(), UniformQuantizationInfo::offset, CLBuildOptions::options(), arm_compute::QASYMM8, arm_compute::QSYMM16, ITensorInfo::quantization_info(), arm_compute::quantize_qasymm8(), arm_compute::quantize_qsymm16(), UniformQuantizationInfo::scale, arm_compute::string_from_activation_func(), arm_compute::string_from_data_type(), ActivationLayerInfo::TANH, arm_compute::support::cpp11::to_string(), QuantizationInfo::uniform(), and arm_compute::validate_and_configure_window().

Referenced by CLRNNLayer::configure(), and CLLSTMLayer::configure().

◆ operator=() [1/2]

CLActivationLayerKernel& operator= ( const CLActivationLayerKernel )
delete

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

◆ operator=() [2/2]

CLActivationLayerKernel& operator= ( CLActivationLayerKernel &&  )
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.

Implements ICLKernel.

Definition at line 237 of file CLActivationLayerKernel.cpp.

238 {
241 
243  Window slice = collapsed.first_slice_window_3D();
244 
245  do
246  {
247  unsigned int idx = 0;
248  add_3D_tensor_argument(idx, _input, slice);
249  if(!_run_in_place)
250  {
251  add_3D_tensor_argument(idx, _output, slice);
252  }
253  enqueue(queue, *this, slice, lws_hint());
254  }
255  while(collapsed.slide_window_slice_3D(slice));
256 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
void enqueue(cl::CommandQueue &queue, ICLKernel &kernel, const Window &window, const cl::NDRange &lws_hint=CLKernelLibrary::get().default_ndrange(), bool use_dummy_work_items=false)
Add the kernel to the command queue with the given window.
Definition: ICLKernel.cpp:39
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
Definition: ICLKernel.h:247
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.
Definition: ICLKernel.h:158
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:54
bool slide_window_slice_3D(Window &slice) const
Slide the passed 3D window slice.
Definition: Window.h:319
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
Definition: Window.h:47
Window first_slice_window_3D() const
First 3D slice of the window.
Definition: Window.h:275
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
Describe a multidimensional execution window.
Definition: Window.h:39
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:940
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

References ICLKernel::add_3D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, Window::collapse_if_possible(), Window::DimZ, arm_compute::enqueue(), Window::first_slice_window_3D(), ICLKernel::lws_hint(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), and IKernel::window().

◆ validate()

Status validate ( const ITensorInfo input,
const ITensorInfo output,
const ActivationLayerInfo act_info 
)
static

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

Parameters
[in]inputSource tensor info. In case of output tensor info = nullptr, this tensor will store the result of the activation function. Data types supported: QASYMM8/QSYMM16/F16/F32.
[in]outputDestination tensor info. Data type supported: same as input
[in]act_infoActivation layer information.
Returns
a status

Definition at line 228 of file CLActivationLayerKernel.cpp.

229 {
230  const bool run_in_place = (output == nullptr) || (output == input);
231  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input, output, act_info));
232  ARM_COMPUTE_RETURN_ON_ERROR(validate_and_configure_window(input->clone().get(), (run_in_place) ? nullptr : output->clone().get()).first);
233 
234  return Status{};
235 }
std::pair< Status, Window > validate_and_configure_window(ITensorInfo *input, ITensorInfo *weights, ITensorInfo *biases, ITensorInfo *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier, const Size2D &dilation)
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:193
Status class.
Definition: Error.h:52
virtual std::unique_ptr< T > clone() const =0
Provide a clone of the current object of class T.

References arm_compute::test::validation::act_info, ARM_COMPUTE_RETURN_ON_ERROR, ICloneable< T >::clone(), and arm_compute::validate_and_configure_window().

Referenced by CLActivationLayer::validate(), CLRNNLayer::validate(), and CLLSTMLayer::validate().


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