tvm::meta_schedule::Mutator Class Reference

Managed reference to MutatorNode. More...

#include <mutator.h>

Inheritance diagram for tvm::meta_schedule::Mutator:

Collaboration diagram for tvm::meta_schedule::Mutator:

Public Types
using	FInitializeWithTuneContext = ffi::TypedFunction< void(const TuneContext &)>
	The function type of InitializeWithTuneContext method. More...
using	FApply = ffi::TypedFunction< ffi::Optional< tir::Trace >(const tir::Trace &, support::LinearCongruentialEngine::TRandState rand_state)>
	Apply the mutator function to the given trace. More...
using	FClone = ffi::TypedFunction< Mutator()>
	Clone the mutator. More...
using	FAsString = ffi::TypedFunction< ffi::String()>
	Get the mutator as string with name. More...

Public Member Functions
	TVM_FFI_DEFINE_OBJECT_REF_METHODS_NULLABLE (Mutator, ObjectRef, MutatorNode)

Static Public Member Functions
static Mutator	MutateTileSize ()
	Create a Mutator that mutates the decision of instruction Sample-Perfect-Tile. More...
static Mutator	MutateParallel (int64_t max_jobs_per_core)
	Create a Mutator that mutates the parallel extent. More...
static Mutator	MutateUnroll ()
	Create a Mutator that mutates auto unroll step. More...
static Mutator	MutateComputeLocation ()
	Create a Mutator that mutates the outcome of SampleComputeLocation. More...
static Mutator	MutateThreadBinding ()
	Create a Mutator that mutates auto thread binding. More...
static Mutator	PyMutator (FInitializeWithTuneContext f_initialize_with_tune_context, FApply f_apply, FClone f_clone, FAsString f_as_string)
	Create a mutator with customized methods on the python-side. More...
static ffi::Map< Mutator, FloatImm, void >	DefaultLLVM ()
	Create default mutators for LLVM. More...
static ffi::Map< Mutator, FloatImm, void >	DefaultCUDA ()
	Create default mutators for CUDA. More...
static ffi::Map< Mutator, FloatImm, void >	DefaultCUDATensorCore ()
	Create default mutators for CUDA with TensorCore. More...
static ffi::Map< Mutator, FloatImm, void >	DefaultHexagon ()
	Create default mutators for Hexagon. More...

Detailed Description

Managed reference to MutatorNode.

See also

MutatorNode

Member Typedef Documentation

FApply

using tvm::meta_schedule::Mutator::FApply = ffi::TypedFunction<ffi::Optional<tir::Trace>( const tir::Trace&, support::LinearCongruentialEngine::TRandState rand_state)>

Apply the mutator function to the given trace.

Parameters

trace

The given trace for mutation.

Returns

None if mutator failed, otherwise return the mutated trace.

FAsString

using tvm::meta_schedule::Mutator::FAsString = ffi::TypedFunction<ffi::String()>

Get the mutator as string with name.

Returns

The string of the mutator.

FClone

using tvm::meta_schedule::Mutator::FClone = ffi::TypedFunction<Mutator()>

Clone the mutator.

Returns

The cloned mutator.

FInitializeWithTuneContext

using tvm::meta_schedule::Mutator::FInitializeWithTuneContext = ffi::TypedFunction<void(const TuneContext&)>

The function type of InitializeWithTuneContext method.

Parameters

context

The tuning context for initialization.

Member Function Documentation

DefaultCUDA()

static ffi::Map<Mutator, FloatImm, void> tvm::meta_schedule::Mutator::DefaultCUDA ( )

static

Create default mutators for CUDA.

DefaultCUDATensorCore()

static ffi::Map<Mutator, FloatImm, void> tvm::meta_schedule::Mutator::DefaultCUDATensorCore ( )

static

Create default mutators for CUDA with TensorCore.

DefaultHexagon()

static ffi::Map<Mutator, FloatImm, void> tvm::meta_schedule::Mutator::DefaultHexagon ( )

static

Create default mutators for Hexagon.

DefaultLLVM()

static ffi::Map<Mutator, FloatImm, void> tvm::meta_schedule::Mutator::DefaultLLVM ( )

static

Create default mutators for LLVM.

MutateComputeLocation()

static Mutator tvm::meta_schedule::Mutator::MutateComputeLocation ( )

static

Create a Mutator that mutates the outcome of SampleComputeLocation.

Returns

The mutator created

MutateParallel()

static Mutator tvm::meta_schedule::Mutator::MutateParallel ( int64_t  max_jobs_per_core )

static

Create a Mutator that mutates the parallel extent.

Parameters

max_jobs_per_core

The maximum number of parallel jobs per core.

Returns

The created mutator.

MutateThreadBinding()

static Mutator tvm::meta_schedule::Mutator::MutateThreadBinding ( )

static

Create a Mutator that mutates auto thread binding.

Returns

The mutator created

MutateTileSize()

static Mutator tvm::meta_schedule::Mutator::MutateTileSize ( )

static

Create a Mutator that mutates the decision of instruction Sample-Perfect-Tile.

MutateUnroll()

static Mutator tvm::meta_schedule::Mutator::MutateUnroll ( )

static

Create a Mutator that mutates auto unroll step.

Returns

The mutator created

PyMutator()

static Mutator tvm::meta_schedule::Mutator::PyMutator ( FInitializeWithTuneContext  f_initialize_with_tune_context, FApply  f_apply, FClone  f_clone, FAsString  f_as_string  )

static

Create a mutator with customized methods on the python-side.

Parameters

f_initialize_with_tune_context	The packed function of InitializeWithTuneContext.
f_apply	The packed function of Apply.
f_clone	The packed function of Clone.
f_as_string	The packed function of AsString.

Returns

The mutator created.

TVM_FFI_DEFINE_OBJECT_REF_METHODS_NULLABLE()

tvm::meta_schedule::Mutator::TVM_FFI_DEFINE_OBJECT_REF_METHODS_NULLABLE	(	Mutator	,
		ObjectRef	,
		MutatorNode
	)

---

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

• include/tvm/meta_schedule/mutator.h