mlir::quant Namespace Reference

Namespaces
	detail
	QuantizationFlags
	Enumeration of bit-mapped flags related to quantized types.

Classes
class	QuantizedType
	Base class for all quantized types known to this dialect. More...
class	AnyQuantizedType
	A quantized type that maps storage to/from expressed types in an unspecified way. More...
class	UniformQuantizedType
	Represents a family of uniform, quantized types. More...
class	UniformQuantizedPerAxisType
	Represents per-axis (also known as per-channel quantization). More...
class	CalibratedQuantizedType
	A quantized type that infers its range from given min/max values. More...
struct	ExpressedToQuantizedConverter
	Performs type conversion from an arbitrary input type to a type that is expressed by a QuantizedType. More...
class	UniformQuantizedValueConverter
	Reference implementation of converting between real numbers and values represented by a UniformQuantizedType. More...
class	UniformQuantizedPerAxisValueConverter
	An utility class to quantize an attribute by the per-axis quantization parameters. More...

Functions
void	populateLowerQuantOpsPatterns (RewritePatternSet &patterns)
UniformQuantizedType	fakeQuantAttrsToType (Location loc, unsigned numBits, double rmin, double rmax, bool narrowRange, Type expressedType, bool isSigned=false)
	Converts per-layer FakeQuant attributes to the corresponding type. More...
UniformQuantizedPerAxisType	fakeQuantAttrsToType (Location loc, unsigned numBits, int32_t quantizedDimension, ArrayRef< double > rmins, ArrayRef< double > rmax, bool narrowRange, Type expressedType, bool isSigned=false)
	Converts per-channel FakeQuant attributes to the corresponding type. More...

Function Documentation

fakeQuantAttrsToType() [1/2]

UniformQuantizedType mlir::quant::fakeQuantAttrsToType	(	Location	loc,
		unsigned	numBits,
		double	rmin,
		double	rmax,
		bool	narrowRange,
		Type	expressedType,
		bool	isSigned = false
	)

Converts per-layer FakeQuant attributes to the corresponding type.

In the event that the parameters cannot be converted, returns a nullptr convertible Type and issues an appropriate error. Note that there are multiple variants of a per-layer FakeQuant op, so this function takes the attributes discretely vs taking a reference to the originating op.

Definition at line 108 of file FakeQuantSupport.cpp.

References mlir::emitError(), mlir::quant::UniformQuantizedType::getChecked(), mlir::Type::getContext(), getDefaultStorageParams(), getNudgedScaleAndZeroPoint(), and mlir::quant::QuantizationFlags::Signed.

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

fakeQuantAttrsToType() [2/2]

UniformQuantizedPerAxisType mlir::quant::fakeQuantAttrsToType	(	Location	loc,
		unsigned	numBits,
		int32_t	quantizedDimension,
		ArrayRef< double >	rmins,
		ArrayRef< double >	rmax,
		bool	narrowRange,
		Type	expressedType,
		bool	isSigned = false
	)

Converts per-channel FakeQuant attributes to the corresponding type.

In the event that the parameters cannot be converted, returns a nullptr convertible Type and issues an appropriate error.

Definition at line 139 of file FakeQuantSupport.cpp.

References mlir::emitError(), mlir::quant::UniformQuantizedPerAxisType::getChecked(), mlir::Type::getContext(), getDefaultStorageParams(), getNudgedScaleAndZeroPoint(), and mlir::quant::QuantizationFlags::Signed.

populateLowerQuantOpsPatterns()

void mlir::quant::populateLowerQuantOpsPatterns

(

RewritePatternSet &

patterns

)

Definition at line 668 of file LowerQuantOps.cpp.

References mlir::patterns.