MLIR  15.0.0git
Public Member Functions | Static Public Member Functions | List of all members
mlir::quant::UniformQuantizedPerAxisType Class Reference

Represents per-axis (also known as per-channel quantization). More...

#include "mlir/Dialect/Quant/QuantTypes.h"

+ Inheritance diagram for mlir::quant::UniformQuantizedPerAxisType:
+ Collaboration diagram for mlir::quant::UniformQuantizedPerAxisType:

Public Member Functions

ArrayRef< double > getScales () const
 Gets the quantization scales. More...
 
ArrayRef< int64_t > getZeroPoints () const
 Gets the storage values corresponding to the real value 0 in the affine equation. More...
 
int32_t getQuantizedDimension () const
 Specifies the dimension of the Tensor's shape that the scales and zero_points correspond to. More...
 
bool isFixedPoint () const
 Fixed point values are real numbers divided by a scale. More...
 

Static Public Member Functions

static UniformQuantizedPerAxisType get (unsigned flags, Type storageType, Type expressedType, ArrayRef< double > scales, ArrayRef< int64_t > zeroPoints, int32_t quantizedDimension, int64_t storageTypeMin, int64_t storageTypeMax)
 Gets an instance of the type with all parameters specified but not checked. More...
 
static UniformQuantizedPerAxisType getChecked (function_ref< InFlightDiagnostic()> emitError, unsigned flags, Type storageType, Type expressedType, ArrayRef< double > scales, ArrayRef< int64_t > zeroPoints, int32_t quantizedDimension, int64_t storageTypeMin, int64_t storageTypeMax)
 Gets an instance of the type with all specified parameters checked. More...
 
static LogicalResult verify (function_ref< InFlightDiagnostic()> emitError, unsigned flags, Type storageType, Type expressedType, ArrayRef< double > scales, ArrayRef< int64_t > zeroPoints, int32_t quantizedDimension, int64_t storageTypeMin, int64_t storageTypeMax)
 Verifies construction invariants and issues errors/warnings. More...
 
- Static Public Member Functions inherited from mlir::detail::StorageUserBase< ConcreteT, BaseT, StorageT, UniquerT, Traits >
static TypeID getTypeID ()
 Return a unique identifier for the concrete type. More...
 
template<typename T >
static bool classof (T val)
 Provide an implementation of 'classof' that compares the type id of the provided value with that of the concrete type. More...
 
static detail::InterfaceMap getInterfaceMap ()
 Returns an interface map for the interfaces registered to this storage user. More...
 
static HasTraitFn getHasTraitFn ()
 Returns the function that returns true if the given Trait ID matches the IDs of any of the traits defined by the storage user. More...
 
template<typename... IfaceModels>
static void attachInterface (MLIRContext &context)
 Attach the given models as implementations of the corresponding interfaces for the concrete storage user class. More...
 
template<typename... Args>
static ConcreteT get (MLIRContext *ctx, Args... args)
 Get or create a new ConcreteT instance within the ctx. More...
 
template<typename... Args>
static ConcreteT getChecked (const Location &loc, Args... args)
 Get or create a new ConcreteT instance within the ctx, defined at the given, potentially unknown, location. More...
 
template<typename... Args>
static ConcreteT getChecked (function_ref< InFlightDiagnostic()> emitErrorFn, MLIRContext *ctx, Args... args)
 Get or create a new ConcreteT instance within the ctx. More...
 
static ConcreteT getFromOpaquePointer (const void *ptr)
 Get an instance of the concrete type from a void pointer. More...
 

Additional Inherited Members

- Public Types inherited from mlir::detail::StorageUserBase< ConcreteT, BaseT, StorageT, UniquerT, Traits >
using Base = StorageUserBase< ConcreteT, BaseT, StorageT, UniquerT, Traits... >
 Utility declarations for the concrete attribute class. More...
 
using ImplType = StorageT
 
using HasTraitFn = bool(*)(TypeID)
 
- Protected Member Functions inherited from mlir::detail::StorageUserBase< ConcreteT, BaseT, StorageT, UniquerT, Traits >
template<typename... Args>
LogicalResult mutate (Args &&...args)
 Mutate the current storage instance. More...
 
ImplTypegetImpl () const
 Utility for easy access to the storage instance. More...
 
- Static Protected Member Functions inherited from mlir::detail::StorageUserBase< ConcreteT, BaseT, StorageT, UniquerT, Traits >
template<typename... Args>
static LogicalResult verify (Args... args)
 Default implementation that just returns success. More...
 

Detailed Description

Represents per-axis (also known as per-channel quantization).

Syntax synopsis: Per-axis, all parameters expressed: !quant<uniform[StorageType:ExpressedType:QuantizedDim]{QuantParams}> Per-axis, optional parameters omitted: !quant<uniform[StorageType]{Scale}>

StorageType: 'i'|'u' NumBits ExpressedType: 'f16', 'f32', 'bf16', 'f64' QuantizedDim: An integer value QuantParams: (Scale ':' ZeroPoint)+ Scale: A legal double value ZeroPoint: An integer value

Definition at line 314 of file QuantTypes.h.

Member Function Documentation

◆ get()

UniformQuantizedPerAxisType UniformQuantizedPerAxisType::get ( unsigned  flags,
Type  storageType,
Type  expressedType,
ArrayRef< double >  scales,
ArrayRef< int64_t >  zeroPoints,
int32_t  quantizedDimension,
int64_t  storageTypeMin,
int64_t  storageTypeMax 
)
static

Gets an instance of the type with all parameters specified but not checked.

Definition at line 303 of file QuantTypes.cpp.

References mlir::Type::getContext().

Referenced by mlirUniformQuantizedPerAxisTypeGet().

◆ getChecked()

UniformQuantizedPerAxisType UniformQuantizedPerAxisType::getChecked ( function_ref< InFlightDiagnostic()>  emitError,
unsigned  flags,
Type  storageType,
Type  expressedType,
ArrayRef< double >  scales,
ArrayRef< int64_t >  zeroPoints,
int32_t  quantizedDimension,
int64_t  storageTypeMin,
int64_t  storageTypeMax 
)
static

Gets an instance of the type with all specified parameters checked.

Returns a nullptr convertible type on failure.

Definition at line 313 of file QuantTypes.cpp.

References mlir::emitError(), and mlir::Type::getContext().

Referenced by mlir::quant::fakeQuantAttrsToType().

◆ getQuantizedDimension()

int32_t UniformQuantizedPerAxisType::getQuantizedDimension ( ) const

Specifies the dimension of the Tensor's shape that the scales and zero_points correspond to.

For example, a tensor t, with dims=[4, 3, 2, 1] with quantization params: scales=[1.0, 2.0, 3.0], zeroPoints=[1, 2, 3], quantizedDimension=1 will be quantized across the second dimension of t. t[:, 0, :, :] will have scale[0]=1.0, zero_point[0]=1 t[:, 1, :, :] will have scale[1]=2.0, zero_point[0]=2 t[:, 2, :, :] will have scale[2]=3.0, zero_point[0]=3

Definition at line 366 of file QuantTypes.cpp.

Referenced by printUniformQuantizedPerAxisType().

◆ getScales()

ArrayRef< double > UniformQuantizedPerAxisType::getScales ( ) const

Gets the quantization scales.

The scales designate the difference between the real values corresponding to consecutive quantized values differing by 1. The ith scale corresponds to the ith slice in the quantized_dimension.

Definition at line 358 of file QuantTypes.cpp.

Referenced by printUniformQuantizedPerAxisType().

◆ getZeroPoints()

ArrayRef< int64_t > UniformQuantizedPerAxisType::getZeroPoints ( ) const

Gets the storage values corresponding to the real value 0 in the affine equation.

The ith zero point corresponds to the ith slice in the quantized_dimension.

Definition at line 362 of file QuantTypes.cpp.

Referenced by printUniformQuantizedPerAxisType().

◆ isFixedPoint()

bool mlir::quant::UniformQuantizedPerAxisType::isFixedPoint ( ) const
inline

Fixed point values are real numbers divided by a scale.

Currently, only signed storage types are treated as fixed point. A fixed point value can be obtained from an affine value by subtracting the zeroPoint. In the future, this may be explicit versus implied by type and zeroPoint.

Definition at line 371 of file QuantTypes.h.

◆ verify()

LogicalResult UniformQuantizedPerAxisType::verify ( function_ref< InFlightDiagnostic()>  emitError,
unsigned  flags,
Type  storageType,
Type  expressedType,
ArrayRef< double >  scales,
ArrayRef< int64_t >  zeroPoints,
int32_t  quantizedDimension,
int64_t  storageTypeMin,
int64_t  storageTypeMax 
)
static

Verifies construction invariants and issues errors/warnings.

Definition at line 323 of file QuantTypes.cpp.

References mlir::emitError(), mlir::failed(), mlir::failure(), mlir::Type::isa(), mlir::success(), and mlir::quant::QuantizedType::verify().


The documentation for this class was generated from the following files: