tvm::te::ScanOpNode Class Reference

Symbolic scan. More...

#include <operation.h>

Inheritance diagram for tvm::te::ScanOpNode:

Collaboration diagram for tvm::te::ScanOpNode:

Public Member Functions
	ScanOpNode ()
	constructor
int	num_outputs () const final
PrimType	output_dtype (size_t i) const final
	Get the primitive element type of the i-th output tensor.
ffi::Array< PrimExpr >	output_shape (size_t i) const final
	Get shape of i-th output tensor.
ffi::Array< Tensor >	InputTensors () const final
	List all the input Tensors.
	TVM_FFI_DECLARE_OBJECT_INFO_FINAL ("te.ScanOp", ScanOpNode, OperationNode)
Public Member Functions inherited from tvm::te::OperationNode
virtual	~OperationNode ()
	TVM_FFI_DECLARE_OBJECT_INFO ("te.Operation", OperationNode, ffi::Object)

Static Public Member Functions
static void	RegisterReflection ()
Static Public Member Functions inherited from tvm::te::OperationNode
static void	RegisterReflection ()

Public Attributes
IterVar	scan_axis
	IterVar to scan over.
ffi::Array< Tensor >	init
	the initialization tensors
ffi::Array< Tensor >	update
	the update function represented by tensor
ffi::Array< Tensor >	state_placeholder
	The placeholder to refer as states in update.
ffi::Array< Tensor >	inputs
	the inputs to the scan, these are optionally provided But they can be helpful to provide hints to speedup get of scan body.
ffi::Array< IterVar >	spatial_axis_
	Spatial axis to indicate spatial dimension of each output. They corresponds to flattened spatial axis of the outputs.
Public Attributes inherited from tvm::te::OperationNode
std::string	name
	optional name of the operation
std::string	tag
	optional tag of the operation
ffi::Map< ffi::String, ffi::Any >	attrs
	additional attributes of the operation

Detailed Description

Symbolic scan.

Constructor & Destructor Documentation

ScanOpNode()

tvm::te::ScanOpNode::ScanOpNode ( )

inline

constructor

Member Function Documentation

InputTensors()

ffi::Array< Tensor > tvm::te::ScanOpNode::InputTensors ( ) const

finalvirtual

List all the input Tensors.

Returns

List of input tensors.

Implements tvm::te::OperationNode.

num_outputs()

int tvm::te::ScanOpNode::num_outputs ( ) const

finalvirtual

Returns

number of outputs

Implements tvm::te::OperationNode.

output_dtype()

PrimType tvm::te::ScanOpNode::output_dtype ( size_t  i ) const

finalvirtual

Get the primitive element type of the i-th output tensor.

Parameters

i	The output index.

Returns

primitive element type of i-th output.

Implements tvm::te::OperationNode.

output_shape()

ffi::Array< PrimExpr > tvm::te::ScanOpNode::output_shape ( size_t  i ) const

finalvirtual

Get shape of i-th output tensor.

Parameters

i	The output index.

Returns

shape of i-th output.

Implements tvm::te::OperationNode.

RegisterReflection()

static void tvm::te::ScanOpNode::RegisterReflection ( )

inlinestatic

TVM_FFI_DECLARE_OBJECT_INFO_FINAL()

tvm::te::ScanOpNode::TVM_FFI_DECLARE_OBJECT_INFO_FINAL	(	"te.ScanOp"	,
		ScanOpNode	,
		OperationNode
	)

Member Data Documentation

init

ffi::Array<Tensor> tvm::te::ScanOpNode::init

the initialization tensors

inputs

ffi::Array<Tensor> tvm::te::ScanOpNode::inputs

the inputs to the scan, these are optionally provided But they can be helpful to provide hints to speedup get of scan body.

scan_axis

IterVar tvm::te::ScanOpNode::scan_axis

IterVar to scan over.

spatial_axis_

ffi::Array<IterVar> tvm::te::ScanOpNode::spatial_axis_

Spatial axis to indicate spatial dimension of each output. They corresponds to flattened spatial axis of the outputs.

[output[0].axis[1], output[0].axis[2]... output[k].axis[j]...] These are auxiliary data structure for storing result of bound inference. They do not corresponds to splittable iterations, thus the name comes with underscore.

state_placeholder

ffi::Array<Tensor> tvm::te::ScanOpNode::state_placeholder

The placeholder to refer as states in update.

update

ffi::Array<Tensor> tvm::te::ScanOpNode::update

the update function represented by tensor

---

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

• include/tvm/te/operation.h