QuantUtils.cpp File Reference

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

Go to the source code of this file.

Macros
#define	GET_UQTYPE(inputType)
#define	GET_QTYPE(inputType)

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.
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.
static std::optional< std::pair< std::int64_t, std::int64_t > >	getConvZeroPoints (Value input, Value weight)

Macro Definition Documentation

GET_QTYPE

#define GET_QTYPE

(

inputType

)

Value:

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

Definition at line 119 of file QuantUtils.cpp.

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

GET_UQTYPE

#define GET_UQTYPE

(

inputType

)

Value:

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

Definition at line 117 of file QuantUtils.cpp.

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

Function Documentation

computeMultiplierAndShiftTosaScale16()

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.

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

computeMultiplierAndShiftTosaScale32()

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.

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

getConvZeroPoints()

std::optional< std::pair< std::int64_t, std::int64_t > > getConvZeroPoints ( Value input, Value weight )

static

Definition at line 123 of file QuantUtils.cpp.

References GET_UQTYPE, and mlir::Value::getType().

Referenced by mlir::tosa::buildConvOpQuantizationAttr(), and mlir::tosa::createZPsAsConst().