Compute Library
 21.08
NERangeKernel Class Reference

Kernel class for Range. More...

#include <NERangeKernel.h>

Collaboration diagram for NERangeKernel:
[legend]

Public Member Functions

const char * name () const override
 Name of the kernel. More...
 
 NERangeKernel ()
 Default constructor. More...
 
 NERangeKernel (const NERangeKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
NERangeKerneloperator= (const NERangeKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 NERangeKernel (NERangeKernel &&)=default
 Allow instances of this class to be moved. More...
 
NERangeKerneloperator= (NERangeKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~NERangeKernel ()=default
 Default destructor. More...
 
void configure (ITensor *output, float start, float end, float step)
 Initialize the kernel's output tensor, start, end and step of the sequence. More...
 
void run (const Window &window, const ThreadInfo &info) override
 Execute the kernel on the passed window. More...
 
- Public Member Functions inherited from ICPPKernel
virtual ~ICPPKernel ()=default
 Default destructor. More...
 
virtual void run_nd (const Window &window, const ThreadInfo &info, const Window &thread_locator)
 legacy compatibility layer for implemantions which do not support thread_locator In these cases we simply narrow the interface down the legacy version More...
 
virtual void run_op (ITensorPack &tensors, const Window &window, const ThreadInfo &info)
 Execute the kernel on the passed window. 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 *output, float start, float end, float step)
 Static function to check if given info will lead to a valid configuration of NERangeKernel. More...
 

Detailed Description

Kernel class for Range.

range generates a 1-D tensor containing a sequence of numbers that begins at 'start' and extends by increments of 'step' up to but not including 'end'.

Definition at line 39 of file NERangeKernel.h.

Constructor & Destructor Documentation

◆ NERangeKernel() [1/3]

Default constructor.

Definition at line 113 of file NERangeKernel.cpp.

Referenced by NERangeKernel::name().

114  : _func(nullptr), _start(0), _end(1), _step(1), _output(nullptr)
115 {
116 }

◆ NERangeKernel() [2/3]

NERangeKernel ( const NERangeKernel )
delete

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

◆ NERangeKernel() [3/3]

NERangeKernel ( NERangeKernel &&  )
default

Allow instances of this class to be moved.

◆ ~NERangeKernel()

~NERangeKernel ( )
default

Default destructor.

Referenced by NERangeKernel::name().

Member Function Documentation

◆ configure()

void configure ( ITensor output,
float  start,
float  end,
float  step 
)

Initialize the kernel's output tensor, start, end and step of the sequence.

Parameters
[out]outputOutput tensor. Data types supported: U8/S8/U16/S16/U32/S32/F16/F32.
[in]startThe starting value of the sequence.
[in]endThe ending (not including) value of the sequence.
[in]stepThe gap between each pair of values in the sequence.

Definition at line 118 of file NERangeKernel.cpp.

References ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), arm_compute::calculate_max_window(), ITensorInfo::data_type(), arm_compute::mlgo::parser::end(), arm_compute::F16, arm_compute::F32, ITensor::info(), arm_compute::num_of_elements_in_range(), ITensorInfo::quantization_info(), arm_compute::S16, arm_compute::S32, arm_compute::S8, arm_compute::cpu::step, arm_compute::U16, arm_compute::U32, and arm_compute::U8.

Referenced by NERangeKernel::name().

119 {
121 
122  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(*(output->info()), start, end, step));
123 
124  // Auto initialize output if not initialized
125  auto_init_if_empty(*output->info(), TensorShape(num_of_elements_in_range(start, end, step)), 1, output->info()->data_type(), output->info()->quantization_info());
126 
127  // Configure kernel window
128  Window win = calculate_max_window(*output->info(), Steps());
129 
130  _start = start;
131  _end = end;
132  _step = step;
133  _output = output;
134  switch(_output->info()->data_type())
135  {
136  case DataType::U8:
137  _func = &range_function<uint8_t>;
138  break;
139  case DataType::U16:
140  _func = &range_function<uint16_t>;
141  break;
142  case DataType::U32:
143  _func = &range_function<uint32_t>;
144  break;
145  case DataType::S8:
146  _func = &range_function<int8_t>;
147  break;
148  case DataType::S16:
149  _func = &range_function<int16_t>;
150  break;
151  case DataType::S32:
152  _func = &range_function<int32_t>;
153  break;
154  case DataType::F32:
155  _func = &range_function<float>;
156  break;
157 #ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
158  case DataType::F16:
159  _func = &range_function<float16_t>;
160  break;
161 #endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
162  default:
163  ARM_COMPUTE_ERROR("Unsupported data type.");
164  break;
165  }
166 
167  INEKernel::configure(win);
168 }
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
#define ARM_COMPUTE_ERROR(msg)
Print the given message then throw an std::runtime_error.
Definition: Error.h:352
1 channel, 1 U8 per channel
virtual DataType data_type() const =0
Data type used for each element of the tensor.
1 channel, 1 F32 per channel
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
1 channel, 1 U16 per channel
1 channel, 1 F16 per channel
1 channel, 1 S32 per channel
1 channel, 1 U32 per channel
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...
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor&#39;s metadata.
void end(TokenStream &in, bool &valid)
Definition: MLGOParser.cpp:290
size_t num_of_elements_in_range(const float start, const float end, const float step)
Returns the number of elements required to go from start to end with the wanted step.
Definition: Utils.h:1097
1 channel, 1 S16 per channel
constexpr int step
Definition: fp32.cpp:35
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:157
signed 8-bit number

◆ name()

const char* name ( ) const
inlineoverridevirtual

◆ operator=() [1/2]

NERangeKernel& operator= ( const NERangeKernel )
delete

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

Referenced by NERangeKernel::name().

◆ operator=() [2/2]

NERangeKernel& operator= ( NERangeKernel &&  )
default

Allow instances of this class to be moved.

◆ run()

void run ( const Window window,
const ThreadInfo info 
)
overridevirtual

Execute the kernel on the passed window.

Warning
If is_parallelisable() returns false then the passed window must be equal to window()
Note
The window has to be a region within the window returned by the window() method
The width of the window has to be a multiple of num_elems_processed_per_iteration().
Parameters
[in]windowRegion on which to execute the kernel. (Must be a region of the window returned by window())
[in]infoInfo about executing thread and CPU.

Reimplemented from ICPPKernel.

Definition at line 179 of file NERangeKernel.cpp.

References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ARM_COMPUTE_UNUSED, and IKernel::window().

Referenced by NERangeKernel::name().

180 {
184  ARM_COMPUTE_ERROR_ON(_func == nullptr);
185 
186  (*_func)(_output, _start, _step, window);
187 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
#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
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
Definition: Error.h:152
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:915
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:201

◆ validate()

Status validate ( const ITensorInfo output,
float  start,
float  end,
float  step 
)
static

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

Parameters
[in]outputOutput tensor info. Data types supported: U8/S8/U16/S16/U32/S32/F16/F32.
[in]startThe starting value of the sequence.
[in]endThe ending (not including) value of the sequence.
[in]stepThe gap between each pair of values in the sequence.
Returns
a status

Definition at line 170 of file NERangeKernel.cpp.

References ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR, and ARM_COMPUTE_RETURN_ON_ERROR.

Referenced by NERangeKernel::name(), and NERange::validate().

171 {
173 
174  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(*output, start, end, step));
175 
176  return Status{};
177 }
#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:159
void end(TokenStream &in, bool &valid)
Definition: MLGOParser.cpp:290
constexpr int step
Definition: fp32.cpp:35

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