#include <QuantTypes.h>
Public Member Functions | |
| ArrayRef< double > | getScales () const |
| ArrayRef< int64_t > | getZeroPoints () const |
| int32_t | getQuantizedDimension () const |
| bool | isFixedPoint () const |
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) |
| static UniformQuantizedPerAxisType | getChecked (unsigned flags, Type storageType, Type expressedType, ArrayRef< double > scales, ArrayRef< int64_t > zeroPoints, int32_t quantizedDimension, int64_t storageTypeMin, int64_t storageTypeMax, Location location) |
| static LogicalResult | verifyConstructionInvariants (Optional< Location > loc, MLIRContext *context, 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 bool | kindof (unsigned kind) |
| Support method to enable LLVM-style type casting. More... | |
 Static Public Member Functions inherited from mlir::detail::StorageUserBase< ConcreteT, BaseT, StorageT, UniquerT > | |
| static ClassID * | getClassID () |
| Return a unique identifier for the concrete type. More... | |
| template<typename T > | |
| static bool | classof (T val) |
Additional Inherited Members | |
| Public Types inherited from mlir::detail::StorageUserBase< ConcreteT, BaseT, StorageT, UniquerT > | |
| using | Base = StorageUserBase< ConcreteT, BaseT, StorageT, UniquerT > |
| Utility declarations for the concrete attribute class. More... | |
| using | ImplType = StorageT |
| Protected Member Functions inherited from mlir::detail::StorageUserBase< ConcreteT, BaseT, StorageT, UniquerT > | |
| ImplType * | getImpl () const |
| Utility for easy access to the storage instance. More... | |
| Static Protected Member Functions inherited from mlir::detail::StorageUserBase< ConcreteT, BaseT, StorageT, UniquerT > | |
| template<typename... Args> | |
| static ConcreteT | get (MLIRContext *ctx, unsigned kind, Args... args) |
| template<typename... Args> | |
| static ConcreteT | getChecked (const Location &loc, MLIRContext *ctx, unsigned kind, Args... args) |
| template<typename... Args> | |
| static LogicalResult | verifyConstructionInvariants (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
Member Function Documentation
◆ get()
|
static |
Gets an instance of the type with all parameters specified but not checked.
◆ getChecked()
|
static |
Gets an instance of the type with all specified parameters checked. Returns a nullptr convertible type on failure.
◆ 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
◆ 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.
◆ 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.
◆ isFixedPoint()
|
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.
◆ kindof()
|
inlinestatic |
Support method to enable LLVM-style type casting.
◆ verifyConstructionInvariants()
|
static |
Verifies construction invariants and issues errors/warnings.
The documentation for this class was generated from the following files:
- include/mlir/Dialect/QuantOps/QuantTypes.h
- lib/Dialect/QuantOps/IR/QuantTypes.cpp
