#include "mlir/Dialect/Tosa/Utils/QuantUtils.h"

Macros
#define	GET_UQTYPE(inputType) (llvm::dyn_cast<quant::UniformQuantizedType>((inputType).getElementType()))

#define	GET_QTYPE(inputType) (llvm::dyn_cast<quant::QuantizedType>((inputType).getElementType()))

Functions
static void	computeMultiplierAndShiftTosaScale16 (double scale, int32_t &multiplier, int32_t &shift)
	From a scale value, generates multiplier and shift values where mantissa is in [-1.0,-0.5] or [0.5, 1.0] such that multiplier = mantissa*2^shift for 16-bit scaling. More...

static void	computeMultiplierAndShiftTosaScale32 (double scale, int32_t &multiplier, int32_t &shift)
	From a scale value, generates multiplier and shift values where mantissa is in [-1.0,-0.5] or [0.5, 1.0] such that multiplier = mantissa*2^shift for 32-bit scaling. More...

Macro Definition Documentation

◆ GET_QTYPE

#define GET_QTYPE ( inputType ) (llvm::dyn_cast<quant::QuantizedType>((inputType).getElementType()))

Definition at line 112 of file QuantUtils.cpp.

◆ GET_UQTYPE

#define GET_UQTYPE ( inputType ) (llvm::dyn_cast<quant::UniformQuantizedType>((inputType).getElementType()))

Definition at line 110 of file QuantUtils.cpp.

Function Documentation

◆ computeMultiplierAndShiftTosaScale16()

static void computeMultiplierAndShiftTosaScale16	(	double	scale,
		int32_t &	multiplier,
		int32_t &	shift
	)

static

From a scale value, generates multiplier and shift values where mantissa is in [-1.0,-0.5] or [0.5, 1.0] such that multiplier = mantissa*2^shift for 16-bit scaling.

Definition at line 22 of file QuantUtils.cpp.

References frexp(), max(), and mlir::presburger::round().

Referenced by mlir::tosa::computeMultiplierAndShift().

◆ computeMultiplierAndShiftTosaScale32()

static void computeMultiplierAndShiftTosaScale32	(	double	scale,
		int32_t &	multiplier,
		int32_t &	shift
	)

static

From a scale value, generates multiplier and shift values where mantissa is in [-1.0,-0.5] or [0.5, 1.0] such that multiplier = mantissa*2^shift for 32-bit scaling.

Definition at line 60 of file QuantUtils.cpp.