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

Include dependency graph for QuantUtils.cpp:

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

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

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 ( input_type ) ((input_type).getElementType().dyn_cast<quant::QuantizedType>())

Definition at line 108 of file QuantUtils.cpp.

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

◆ GET_UQTYPE

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

Definition at line 106 of file QuantUtils.cpp.

Referenced by mlir::tosa::buildConvOpQuantizationAttr(), mlir::tosa::buildMatMulOpQuantizationAttr(), mlir::tosa::buildPadOpQuantizationAttr(), and mlir::tosa::buildUnaryOpQuantizationAttr().

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(), and max().

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 58 of file QuantUtils.cpp.