Compute Library
 21.02
NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel Class Reference

Neon kernel used to quantize down the int32 accumulator values of GEMMLowp to QASYMM8. More...

#include <NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h>

Collaboration diagram for NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel:
[legend]

Public Member Functions

const char * name () const override
 Name of the kernel. More...
 
 NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel ()
 Constructor. More...
 
 NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel (const NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKerneloperator= (const NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel (NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel &&)=default
 Allow instances of this class to be moved. More...
 
NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKerneloperator= (NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel ()=default
 Default destructor. More...
 
void configure (const ITensor *input, const ITensor *bias, ITensor *output, int result_fixedpoint_multiplier, int result_shift, int result_offset_after_shift, int min=0, int max=0)
 Initialise the kernel's input and output. 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...
 

Static Public Member Functions

static Status validate (const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, int min=0, int max=0)
 Static function to check if given info will lead to a valid configuration of NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel. More...
 

Detailed Description

Neon kernel used to quantize down the int32 accumulator values of GEMMLowp to QASYMM8.

This kernel takes a final int32 accumulator value (the output of NEGEMMLowpMatrixMultiplyKernel), and processes it to obtain the final QASYMM8 value. The following computations will be performed by the kernel:

  1. Compute fixed point multiplication between each entry of input by result_fixedpoint_multiplier
  2. Add bias to final result if bias tensor is not a nullptr
  3. Round to nearest division by a power-of-two using result_shift
  4. Add offset to each result
  5. Clamp the value between the specified min and max bounds
  6. Clamp the resulting int32 values to the [0..255] range and cast to QASYMM8.

Definition at line 46 of file NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h.

Constructor & Destructor Documentation

◆ NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel() [1/3]

Constructor.

Definition at line 201 of file NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.cpp.

Referenced by NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::name().

202  : _func(nullptr), _input(nullptr), _bias(nullptr), _output(nullptr), _result_fixedpoint_multiplier(0), _result_shift(0), _result_offset_after_shift(0), _min(0), _max(0)
203 {
204 }

◆ NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel() [2/3]

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

◆ NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel() [3/3]

◆ ~NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel()

Member Function Documentation

◆ configure()

void configure ( const ITensor input,
const ITensor bias,
ITensor output,
int  result_fixedpoint_multiplier,
int  result_shift,
int  result_offset_after_shift,
int  min = 0,
int  max = 0 
)

Initialise the kernel's input and output.

Parameters
[in]inputInput tensor. Data type supported: S32
[in]biasBiases tensor. Only shared biases supported and it can be a nullptr if the biases addition is not required. Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as input.
[out]outputOutput tensor. Data type supported: Data type supported: QASYMM8
[in]result_fixedpoint_multiplierFixed point value to be multiplied to each element of the input matrix when once the result_offset has been add
[in]result_shiftInteger value used to round to nearest division by a power-of-two the result after the fixed point multiplication
[in]result_offset_after_shiftOffset to be applied to result before converting it back to QASYMM8
[in]min(Optional) Min value used to saturate down the output result before converting back to QASYMM8
[in]max(Optional) Max value used to saturate up the output result before converting back to QASYMM8, Along with min, this value can be used to implement "rectified linear unit" activation functions

Definition at line 206 of file NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.cpp.

References ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, ITensor::info(), arm_compute::test::validation::input, and arm_compute::validate_arguments().

Referenced by NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::name().

208 {
209  // Perform validate step
211  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input->info(), (bias != nullptr) ? bias->info() : nullptr, output->info(), min, max));
212 
213  _input = input;
214  _bias = bias;
215  _output = output;
216  _result_fixedpoint_multiplier = result_fixedpoint_multiplier;
217  _result_shift = result_shift;
218  _result_offset_after_shift = result_offset_after_shift;
219  _min = min;
220  _max = max;
221 
222  // Configure kernel window
223  auto win_config = validate_and_configure_window(input->info(), output->info());
224  ARM_COMPUTE_ERROR_THROW_ON(win_config.first);
225  INEKernel::configure(win_config.second);
226 
227  // Check if we need to clamp the result using min and max
228  const bool is_bounded_relu = !(min <= 0 && max >= 255);
229  _func = is_bounded_relu ? &NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::run<true> : &NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::run<false>;
230 }
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
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

◆ name()

◆ operator=() [1/2]

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

Referenced by NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::name().

◆ operator=() [2/2]

◆ 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 241 of file NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.cpp.

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

Referenced by NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::name().

242 {
246 
247  (this->*_func)(window);
248 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
Definition: Error.h:152
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205

◆ validate()

Status validate ( const ITensorInfo input,
const ITensorInfo bias,
const ITensorInfo output,
int  min = 0,
int  max = 0 
)
static

Static function to check if given info will lead to a valid configuration of NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.

Parameters
[in]inputInput tensor. Data type supported: S32
[in]biasBiases tensor. Only shared biases supported and it can be a nullptr if the biases addition is not required. Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as input.
[in]outputOutput tensor. Data type supported: Data type supported: QASYMM8
[in]min(Optional) Min value used to saturate down the output result before converting back to QASYMM8
[in]max(Optional) Max value used to saturate up the output result before converting back to QASYMM8, Along with min, this value can be used to implement "rectified linear unit" activation functions
Returns
a status

Definition at line 232 of file NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.cpp.

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

Referenced by NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::name(), NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint::validate(), and NEGEMMLowpOutputStage::validate().

233 {
235  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input, bias, output, min, max));
236  ARM_COMPUTE_RETURN_ON_ERROR(validate_and_configure_window(input->clone().get(), output->clone().get()).first);
237 
238  return Status{};
239 }
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204
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

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