mlir::quant Namespace Reference

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

Classes
class	AnyQuantizedType
	A quantized type that maps storage to/from expressed types in an unspecified way. 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	QuantizedType
	Base class for all quantized types known to this dialect. More...
class	UniformQuantizedPerAxisType
	Represents per-axis (also known as per-channel quantization). More...
class	UniformQuantizedPerAxisValueConverter
	An utility class to quantize an attribute by the per-axis quantization parameters. More...
class	UniformQuantizedSubChannelType
	Represents sub-channel (also known as blockwise quantization). More...
class	UniformQuantizedType
	Represents a family of uniform, quantized types. More...
class	UniformQuantizedValueConverter
	Reference implementation of converting between real numbers and values represented by a UniformQuantizedType. More...

Functions
std::unique_ptr<::mlir::Pass >	createLowerQuantOps ()
std::unique_ptr<::mlir::Pass >	createNormalizeQuantTypes ()
std::unique_ptr<::mlir::Pass >	createStripFuncQuantTypes ()
void	registerLowerQuantOps ()
void	registerLowerQuantOpsPass ()
void	registerNormalizeQuantTypes ()
void	registerNormalizeQuantTypesPass ()
void	registerStripFuncQuantTypes ()
void	registerStripFuncQuantTypesPass ()
void	registerQuantPasses ()
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.
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.

Function Documentation

createLowerQuantOps()

std::unique_ptr<::mlir::Pass > mlir::quant::createLowerQuantOps

(

)

We declare an explicit private instantiation because Pass classes should only be visible by the current library.

Definition at line 85 of file LowerQuantOps.cpp.

References mlir::Builder::getContext(), mlir::shape::getExtentTensorType(), mlir::Builder::getIndexType(), and mlir::Value::getType().

createNormalizeQuantTypes()

std::unique_ptr<::mlir::Pass > mlir::quant::createNormalizeQuantTypes

(

)

We declare an explicit private instantiation because Pass classes should only be visible by the current library.

Definition at line 161 of file NormalizeQuantTypes.cpp.

References mlir::patterns, and target.

createStripFuncQuantTypes()

std::unique_ptr<::mlir::Pass > mlir::quant::createStripFuncQuantTypes

(

)

We declare an explicit private instantiation because Pass classes should only be visible by the current library.

Definition at line 237 of file StripFuncQuantTypes.cpp.

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 781 of file LowerQuantOps.cpp.

References mlir::patterns, and populateLowerQuantOpsPatterns().

Referenced by populateLowerQuantOpsPatterns().

registerLowerQuantOps()

void mlir::quant::registerLowerQuantOps ( )

inline

Definition at line 254 of file Passes.h.

registerLowerQuantOpsPass()

void mlir::quant::registerLowerQuantOpsPass ( )

inline

Definition at line 261 of file Passes.h.

registerNormalizeQuantTypes()

void mlir::quant::registerNormalizeQuantTypes ( )

inline

Definition at line 275 of file Passes.h.

registerNormalizeQuantTypesPass()

void mlir::quant::registerNormalizeQuantTypesPass ( )

inline

Definition at line 282 of file Passes.h.

registerQuantPasses()

void mlir::quant::registerQuantPasses ( )

inline

Definition at line 317 of file Passes.h.

Referenced by mlir::registerAllPasses().

registerStripFuncQuantTypes()

void mlir::quant::registerStripFuncQuantTypes ( )

inline

Definition at line 296 of file Passes.h.

registerStripFuncQuantTypesPass()

void mlir::quant::registerStripFuncQuantTypesPass ( )

inline

Definition at line 303 of file Passes.h.