mlir::quant::UniformQuantizedValueConverter Class Reference

#include <UniformSupport.h>

Public Member Functions
	UniformQuantizedValueConverter (UniformQuantizedType uniformType)
	UniformQuantizedValueConverter (double scale, double zeroPoint, double clampMin, double clampMax, uint32_t storageBitWidth, bool isSigned)
	UniformQuantizedValueConverter (double scale, double zeroPoint, APFloat clampMin, APFloat clampMax, uint32_t storageBitWidth, bool isSigned)
virtual APInt	quantizeFloatToInt (APFloat expressedValue) const
int64_t	quantizeFloatToInt64 (APFloat expressedValue) const
virtual	~UniformQuantizedValueConverter ()

Detailed Description

Reference implementation of converting between real numbers and values represented by a UniformQuantizedType. Note that this is not expected to be speedy and may be superseded eventually by a more optimal implementation. Also, the interface assumes that quantization is done per-layer and will need to be wider for various per-channel schemes. As such, this is a placeholder.

Constructor & Destructor Documentation

UniformQuantizedValueConverter() [1/3]

mlir::quant::UniformQuantizedValueConverter::UniformQuantizedValueConverter ( UniformQuantizedType  uniformType )

inlineexplicit

UniformQuantizedValueConverter() [2/3]

mlir::quant::UniformQuantizedValueConverter::UniformQuantizedValueConverter ( double  scale, double  zeroPoint, double  clampMin, double  clampMax, uint32_t  storageBitWidth, bool  isSigned  )

inline

UniformQuantizedValueConverter() [3/3]

mlir::quant::UniformQuantizedValueConverter::UniformQuantizedValueConverter ( double  scale, double  zeroPoint, APFloat  clampMin, APFloat  clampMax, uint32_t  storageBitWidth, bool  isSigned  )

inline

~UniformQuantizedValueConverter()

virtual mlir::quant::UniformQuantizedValueConverter::~UniformQuantizedValueConverter ( )

inlinevirtual

Member Function Documentation

quantizeFloatToInt()

virtual APInt mlir::quant::UniformQuantizedValueConverter::quantizeFloatToInt ( APFloat  expressedValue ) const

inlinevirtual

quantizeFloatToInt64()

int64_t mlir::quant::UniformQuantizedValueConverter::quantizeFloatToInt64 ( APFloat  expressedValue ) const

inline

---

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

• include/mlir/Dialect/QuantOps/UniformSupport.h