Compute Library
 21.05
ClActivationKernel Class Reference

Interface for the activation kernel. More...

#include <ClActivationKernel.h>

Collaboration diagram for ClActivationKernel:
[legend]

Public Member Functions

 ClActivationKernel ()
 
 ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE (ClActivationKernel)
 
void configure (const ClCompileContext &compile_context, ITensorInfo *src, ITensorInfo *dst, ActivationLayerInfo act_info)
 Configure kernel for a given list of arguments. More...
 
void run_op (ITensorPack &tensors, const Window &window, ::cl::CommandQueue &queue) override
 
- 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 (const Window &window, cl::CommandQueue &queue)
 Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. 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...
 
bool is_window_configured () const
 Function to check if the embedded window of this kernel has been configured. More...
 

Static Public Member Functions

static Status validate (const ITensorInfo *src, const ITensorInfo *dst, const ActivationLayerInfo &act_info)
 Static function to check if given info will lead to a valid configuration of ClActivationKernel. 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 kernel.

Definition at line 38 of file ClActivationKernel.h.

Constructor & Destructor Documentation

◆ ClActivationKernel()

Definition at line 90 of file ClActivationKernel.cpp.

91  : _run_in_place(false)
92 {
93 }

Member Function Documentation

◆ ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE()

ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE ( ClActivationKernel  )

◆ configure()

void configure ( const ClCompileContext compile_context,
ITensorInfo src,
ITensorInfo dst,
ActivationLayerInfo  act_info 
)

Configure kernel for a given list of arguments.

Note
If the output tensor is a nullptr, the activation function will be performed in-place
Parameters
[in]compile_contextThe compile context to be used.
[in,out]srcSource tensor info. In case of dst tensor = nullptr, this tensor will store the result of the activation function. Data types supported: QASYMM8/QASYMM8_SIGNED/QSYMM16/F16/F32.
[out]dstDestination tensor info. Data type supported: same as src
[in]act_infoActivation layer information.

Definition at line 95 of file ClActivationKernel.cpp.

96 {
98 
99  auto padding_info = get_padding_info({ src, dst });
100 
101  _run_in_place = (dst == nullptr) || (dst == src);
102 
103  if(dst != nullptr)
104  {
105  // Destination auto inizialitation if not yet initialized
106  auto_init_if_empty(*dst, *src->clone());
107  }
108 
109  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(src, (dst != nullptr) ? dst : nullptr, act_info));
110 
111  const unsigned int num_elems_processed_per_iteration = adjust_vec_size(16 / src->element_size(), src->dimension(0));
112 
113  const DataType dt = src->data_type();
114  float a_const = act_info.a();
115  float b_const = act_info.b();
116 
117  const ActivationLayerInfo::ActivationFunction f_act = act_info.activation();
118  const bool is_quantized = is_data_type_quantized(dt);
119  const bool perform_activation_in_float =
124 
125  // Set build options
126  CLBuildOptions build_opts;
127  build_opts.add_option_if(perform_activation_in_float, "-DFLOAT_DOMAIN");
128  build_opts.add_option_if(_run_in_place, "-DIN_PLACE");
129  build_opts.add_option("-DACT=" + lower_string(string_from_activation_func(f_act)));
130  build_opts.add_option("-DDATA_TYPE=" + get_cl_type_from_data_type(dt));
131  build_opts.add_option("-DVEC_SIZE=" + support::cpp11::to_string(num_elems_processed_per_iteration));
132  build_opts.add_option("-DVEC_SIZE_LEFTOVER=" + support::cpp11::to_string(src->dimension(0) % num_elems_processed_per_iteration));
133 
134  std::string kernel_name = std::string("activation_layer");
135 
136  // Set quantization info build options
137  if(is_quantized)
138  {
139  const UniformQuantizationInfo iq_info = src->quantization_info().uniform();
140 
141  if(!perform_activation_in_float)
142  {
143  int a_const_int = 0;
144  int b_const_int = 0;
145 
146  // Create quantized version of constants a, b if needed
147  switch(dt)
148  {
149  case DataType::QASYMM8:
150  {
151  a_const_int = quantize_qasymm8(a_const, iq_info);
152  b_const_int = quantize_qasymm8(b_const, iq_info);
153  }
154  break;
156  {
157  a_const_int = quantize_qasymm8_signed(a_const, iq_info);
158  b_const_int = quantize_qasymm8_signed(b_const, iq_info);
159  }
160  break;
161  case DataType::QSYMM16:
162  {
163  a_const_int = quantize_qsymm16(a_const, iq_info);
164  b_const_int = quantize_qsymm16(b_const, iq_info);
165  }
166  break;
167  default:
168  break;
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  // Quantized value of 0 corresponds to the offset o1
180  build_opts.add_option(("-DCONST_0=" + (is_data_type_quantized_asymmetric(dt) ? support::cpp11::to_string(iq_info.offset) : "0")));
181  build_opts.add_option(("-DS1_VAL=" + float_to_string_with_full_precision(iq_info.scale)));
182  build_opts.add_option_if(is_data_type_quantized_asymmetric(dt), "-DO1_VAL=" + support::cpp11::to_string(iq_info.offset));
183 
184  // Set correct kernel name
185  kernel_name += perform_activation_in_float ? std::string("_quant_f32") : std::string("_quant");
186 
187  // Set scale and offset of the source and destination if they have different quantization info
188  if(dst != nullptr)
189  {
190  const UniformQuantizationInfo oq_info = dst->quantization_info().uniform();
191 
192  if(iq_info != oq_info)
193  {
194  build_opts.add_option(("-DS2_VAL=" + float_to_string_with_full_precision(oq_info.scale)));
195  build_opts.add_option_if(is_data_type_quantized_asymmetric(dt), "-DO2_VAL=" + support::cpp11::to_string(oq_info.offset));
196  }
197  }
198  }
199  else
200  {
201  // Set A, B constants in build options for float types
202  build_opts.add_option(("-DA_VAL=" + float_to_string_with_full_precision(a_const)));
203  build_opts.add_option(("-DB_VAL=" + float_to_string_with_full_precision(b_const)));
204  }
205 
206  // Create kernel
207  _kernel = create_kernel(compile_context, kernel_name, build_opts.options());
208 
209  // Configure kernel window
211  ICLKernel::configure_internal(win);
212 
213  // Set config_id for enabling LWS tuning
214  _config_id = "activation_layer_";
215  _config_id += lower_string(string_from_data_type(dt));
216  _config_id += "_";
217  _config_id += support::cpp11::to_string(src->dimension(0));
218  _config_id += "_";
219  _config_id += support::cpp11::to_string(src->dimension(1));
220 
222 }
bool is_data_type_quantized(DataType dt)
Check if a given data type is of quantized type.
Definition: Utils.h:967
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
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
std::unordered_map< const ITensorInfo *, PaddingSize > get_padding_info(std::initializer_list< const ITensorInfo * > infos)
Stores padding information before configuring a kernel.
Definition: Utils.cpp:489
uint8_t quantize_qasymm8(float value, const INFO_TYPE &qinfo, RoundingPolicy rounding_policy=RoundingPolicy::TO_NEAREST_UP)
Quantize a value given an unsigned 8-bit asymmetric quantization scheme.
std::string to_string(T &&value)
Convert integer and float values to string.
#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
const std::string & string_from_activation_func(ActivationLayerInfo::ActivationFunction act)
Translates a given activation function to a string.
Definition: Utils.cpp:163
#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:326
SimpleTensor< float > src
Definition: DFT.cpp:155
ActivationFunction
Available activation functions.
Definition: Types.h:1482
DataType dt
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:1061
int8_t quantize_qasymm8_signed(float value, const INFO_TYPE &qinfo, RoundingPolicy rounding_policy=RoundingPolicy::TO_NEAREST_UP)
Quantize a value given a signed 8-bit asymmetric quantization scheme.
quantized, asymmetric fixed-point 8-bit number unsigned
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
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...
bool has_padding_changed(const std::unordered_map< const ITensorInfo *, PaddingSize > &padding_map)
Check if the previously stored padding info has changed after configuring a kernel.
Definition: Utils.cpp:504
bool is_data_type_quantized_asymmetric(DataType dt)
Check if a given data type is of asymmetric quantized type.
Definition: Utils.h:989
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)
unsigned int num_elems_processed_per_iteration
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:157
unsigned int adjust_vec_size(unsigned int vec_size, size_t dim0)
Returns the adjusted vector size in case it is less than the input's first dimension,...
Definition: Utils.h:1157
quantized, asymmetric fixed-point 8-bit number signed
DataType
Available data types.
Definition: Types.h:77

References ActivationLayerInfo::a(), ActivationLayerInfo::activation(), CLBuildOptions::add_option(), CLBuildOptions::add_option_if(), arm_compute::adjust_vec_size(), ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), ActivationLayerInfo::b(), arm_compute::calculate_max_window(), arm_compute::create_kernel(), arm_compute::test::validation::dst, dt, arm_compute::float_to_string_with_full_precision(), arm_compute::get_cl_type_from_data_type(), arm_compute::get_padding_info(), ActivationLayerInfo::HARD_SWISH, arm_compute::has_padding_changed(), arm_compute::is_data_type_quantized(), arm_compute::is_data_type_quantized_asymmetric(), kernel_name, ActivationLayerInfo::LEAKY_RELU, ActivationLayerInfo::LOGISTIC, arm_compute::lower_string(), num_elems_processed_per_iteration, UniformQuantizationInfo::offset, CLBuildOptions::options(), arm_compute::QASYMM8, arm_compute::QASYMM8_SIGNED, arm_compute::QSYMM16, arm_compute::quantize_qasymm8(), arm_compute::quantize_qasymm8_signed(), arm_compute::quantize_qsymm16(), UniformQuantizationInfo::scale, arm_compute::test::validation::src, arm_compute::string_from_activation_func(), arm_compute::string_from_data_type(), ActivationLayerInfo::TANH, arm_compute::support::cpp11::to_string(), and arm_compute::validate_arguments().

◆ run_op()

void run_op ( ITensorPack tensors,
const Window window,
::cl::CommandQueue &  queue 
)
override

Definition at line 230 of file ClActivationKernel.cpp.

231 {
234 
235  const auto src = utils::cast::polymorphic_downcast<const ICLTensor *>(tensors.get_const_tensor(TensorType::ACL_SRC));
236  auto dst = utils::cast::polymorphic_downcast<ICLTensor *>(tensors.get_tensor(TensorType::ACL_DST));
237  ARM_COMPUTE_ERROR_ON(_run_in_place && src != dst);
238 
240  Window slice = collapsed.first_slice_window_3D();
241 
242  do
243  {
244  unsigned int idx = 0;
246  if(!_run_in_place)
247  {
249  }
250  enqueue(queue, *this, slice, lws_hint());
251  }
252  while(collapsed.slide_window_slice_3D(slice));
253 }
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:32
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
Definition: ICLKernel.h:276
#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
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:172
SimpleTensor< float > src
Definition: DFT.cpp:155
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
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:915
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
Definition: Window.h:47
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:201
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

References arm_compute::ACL_DST, arm_compute::ACL_SRC, ICLKernel::add_3D_tensor_argument(), ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, Window::collapse_if_possible(), Window::DimZ, arm_compute::test::validation::dst, arm_compute::enqueue(), Window::first_slice_window_3D(), ITensorPack::get_const_tensor(), ITensorPack::get_tensor(), ICLKernel::lws_hint(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), arm_compute::test::validation::src, and IKernel::window().

◆ validate()

Status validate ( const ITensorInfo src,
const ITensorInfo dst,
const ActivationLayerInfo act_info 
)
static

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

Parameters
[in]srcSource tensor info. In case of dst tensor info = nullptr, this tensor will store the result of the activation function. Data types supported: QASYMM8/QASYMM8_SIGNED/QSYMM16/F16/F32.
[in]dstDestination tensor info. Data type supported: same as src
[in]act_infoActivation layer information.
Returns
a status

Definition at line 224 of file ClActivationKernel.cpp.

225 {
227  return Status{};
228 }
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204
SimpleTensor< float > src
Definition: DFT.cpp:155
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)

References ARM_COMPUTE_RETURN_ON_ERROR, arm_compute::test::validation::dst, arm_compute::test::validation::src, and arm_compute::validate_arguments().

Referenced by ClActivation::validate(), and ClDirectConvolution::validate().


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