instruction.h File Reference

#include <tvm/ffi/reflection/registry.h>
#include <tvm/ir/prim/expr.h>
#include <utility>

Include dependency graph for instruction.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
class	tvm::s_tir::InstructionKindNode
	Kind of an instruction, e.g. Split, Reorder, etc. Besides the name, every kind of instruction has its own properties, including: 1) A boolean indicating if the instruction is pure, i.e. change nothing in the schedule state 2) A functor that applies the instruction to a TensorIR schedule 3) A functor that converts the instruction to a statement in python syntax 4) A functor that serialize its attributes to JSON 5) A functor that deserialize its attributes from JSON. More...
class	tvm::s_tir::InstructionKind
	Managed reference to InstructionKindNode. More...
class	tvm::s_tir::InstructionNode
	Schedule instructions each corresponds to a schedule primitive. More...
class	tvm::s_tir::Instruction
	Managed reference to InstructionNode. More...
class	tvm::s_tir::InstructionKindRegEntry
	An entry in the registry of InstructionKind. More...

Namespaces
namespace	tvm
	An object that builds and maintains block scope and StmtSref mapping for Dependence analysis.
namespace	tvm::s_tir

Macros
#define	TVM_INST_KIND_REGISTER_VAR_DEF    [[maybe_unused]] static ::tvm::s_tir::InstructionKindRegEntry& __make_##InstructionKind
	A helper macro to register InstructionKind, only used in TVM_REGISTER_INST_KIND
#define	TVM_REGISTER_INST_KIND(InstructionKindName)
	Register an InstructionKind.

Typedefs
using	tvm::s_tir::FInstructionApply = ffi::TypedFunction< ffi::Array< Any >(Schedule sch, const ffi::Array< Any > &inputs, const ffi::Array< Any > &attrs, const Any &decision)>
	Type of the functor that applies the instruction to a TensorIR schedule.
using	tvm::s_tir::FInstructionAsPython = ffi::TypedFunction< ffi::String(const ffi::Array< Any > &inputs, const ffi::Array< Any > &attrs, const Any &decision, const ffi::Array< ffi::String > &outputs)>
	Type of the functor that converts the instruction to a statement in python syntax.
using	tvm::s_tir::FInstructionAttrsAsJSON = ffi::TypedFunction< ffi::ObjectRef(ffi::Array< Any > attrs)>
	Type of the functor that serialize its attributes to JSON.
using	tvm::s_tir::FInstructionAttrsFromJSON = ffi::TypedFunction< ffi::Array< Any >(ffi::ObjectRef json_attrs)>
	Type of the functor that deserialize its attributes from JSON.

Macro Definition Documentation

TVM_INST_KIND_REGISTER_VAR_DEF

#define TVM_INST_KIND_REGISTER_VAR_DEF    [[maybe_unused]] static ::tvm::s_tir::InstructionKindRegEntry& __make_##InstructionKind

A helper macro to register InstructionKind, only used in TVM_REGISTER_INST_KIND

Note

This macro is not user-facing.

See also

TVM_REGISTER_INST_KIND

TVM_REGISTER_INST_KIND

#define TVM_REGISTER_INST_KIND

(

InstructionKindName

)

Value:

  TVM_FFI_STR_CONCAT(TVM_INST_KIND_REGISTER_VAR_DEF, __COUNTER__) = \
      ::tvm::s_tir::InstructionKindRegEntry::RegisterOrGet(InstructionKindName).set_name()

Register an InstructionKind.

Parameters

InstructionKindName

The name of the InstructionKind

Example:

TVM_REGISTER_INST_KIND("ComputeInline")
    .set_is_pure(false)
    .set_apply_to_schedule(ApplyToSchedule)
    .set_attrs_as_json(AttrsAsJSON)
    .set_attrs_from_json(AttrsFromJSON)
    .set_as_python(AsPython);