ArmNN
 21.05
Public Member Functions | List of all members
Float16Encoder Class Reference

#include <BaseIterator.hpp>

Inheritance diagram for Float16Encoder:
TypedIterator< Half, Encoder< float > > Encoder< float > BaseIterator

Public Member Functions

 Float16Encoder (Half *data)
 
 Float16Encoder ()
 
void Set (float right) override
 
float Get () const override
 
- Public Member Functions inherited from TypedIterator< Half, Encoder< float > >
 TypedIterator (Half *data=nullptr)
 
void Reset (void *data) override
 
TypedIterator & operator++ () override
 
TypedIterator & operator+= (const unsigned int increment) override
 
TypedIterator & operator-= (const unsigned int increment) override
 
TypedIterator & operator[] (const unsigned int index) override
 
TypedIterator & SetIndex (unsigned int index, unsigned int axisIndex=0) override
 
- Public Member Functions inherited from Encoder< float >
 Encoder ()
 
virtual ~Encoder ()
 
- Public Member Functions inherited from BaseIterator
 BaseIterator ()
 
virtual ~BaseIterator ()
 

Additional Inherited Members

- Protected Attributes inherited from TypedIterator< Half, Encoder< float > >
Half * m_Iterator
 
Half * m_Start
 

Detailed Description

Definition at line 670 of file BaseIterator.hpp.

Constructor & Destructor Documentation

◆ Float16Encoder() [1/2]

Float16Encoder ( Half *  data)
inline

Definition at line 673 of file BaseIterator.hpp.

674  : TypedIterator(data) {}

◆ Float16Encoder() [2/2]

Float16Encoder ( )
inline

Definition at line 676 of file BaseIterator.hpp.

677  : Float16Encoder(nullptr) {}

Member Function Documentation

◆ Get()

float Get ( ) const
inlineoverridevirtual

Implements Encoder< float >.

Definition at line 684 of file BaseIterator.hpp.

References FloatingPointConverter::ConvertFloat16To32().

685  {
686  float val = 0.f;
687  armnnUtils::FloatingPointConverter::ConvertFloat16To32(m_Iterator, 1, &val);
688  return val;
689  }
armnnUtils::FloatingPointConverter::ConvertFloat16To32
static void ConvertFloat16To32(const void *srcFloat16Buffer, size_t numElements, float *dstFloat32Buffer)
Definition: FloatingPointConverter.cpp:31

◆ Set()

void Set ( float  right)
inlineoverridevirtual

Implements Encoder< float >.

Definition at line 679 of file BaseIterator.hpp.

References FloatingPointConverter::ConvertFloat32To16().

680  {
681  armnnUtils::FloatingPointConverter::ConvertFloat32To16(&right, 1, m_Iterator);
682  }
armnnUtils::FloatingPointConverter::ConvertFloat32To16
static void ConvertFloat32To16(const float *srcFloat32Buffer, size_t numElements, void *dstFloat16Buffer)
Converts a buffer of FP32 values to FP16, and stores in the given dstFloat16Buffer.
Definition: FloatingPointConverter.cpp:16
The documentation for this class was generated from the following file: