Managed Tensor. The array is backed by reference counted blocks. More...

#include <tensor.h>

Inheritance diagram for tvm::runtime::Tensor:

Collaboration diagram for tvm::runtime::Tensor:

Public Types
using	Container = ffi::TensorObj

Public Member Functions
	Tensor ()=default

	Tensor (ObjectPtr< ffi::TensorObj > data)
	constructor. More...

	Tensor (ffi::UnsafeInit tag)

	Tensor (ffi::Tensor &&other)

	Tensor (const ffi::Tensor &other)

ffi::Shape	Shape () const

runtime::DataType	DataType () const

void	CopyFrom (const DLTensor *other)
	Copy data content from another array. More...

void	CopyFrom (const Tensor &other)

void	CopyFromBytes (const void *data, size_t nbytes)
	Copy data content from a byte buffer. More...

void	CopyTo (DLTensor *other) const
	Copy data content into another array. More...

void	CopyTo (const Tensor &other) const

void	CopyToBytes (void *data, size_t nbytes) const
	Copy data content into another array. More...

Tensor	CopyTo (const Device &dev, ffi::Optional< ffi::String > mem_scope=std::nullopt) const
	Copy the data to another device. More...

bool	Load (dmlc::Stream *stream)
	Load Tensor from stream. More...

void	Save (dmlc::Stream *stream) const
	Save Tensor to stream. More...

Tensor	CreateView (ffi::Shape shape, DLDataType dtype, uint64_t relative_byte_offset=0) const
	Create a Tensor that shares the data memory with the current one. More...

Static Public Member Functions
static Tensor	FromDLPack (DLManagedTensor *tensor)

static Tensor	FromDLPackVersioned (DLManagedTensorVersioned *tensor)

static Tensor	Empty (ffi::Shape shape, DLDataType dtype, Device dev, ffi::Optional< ffi::String > mem_scope=std::nullopt)
	Create an empty Tensor. More...

static void	CopyFromTo (const DLTensor from, DLTensor to, TVMStreamHandle stream=nullptr)
	Function to copy data from one array to another. More...

static void	CopyToBytes (const DLTensor from, void to, size_t nbytes, TVMStreamHandle stream=nullptr)
	Function to copy data from one array to a byte buffer. More...

Detailed Description

Managed Tensor. The array is backed by reference counted blocks.

Member Typedef Documentation

◆ Container

using tvm::runtime::Tensor::Container = ffi::TensorObj

Constructor & Destructor Documentation

◆ Tensor() [1/5]

tvm::runtime::Tensor::Tensor ( )

default

◆ Tensor() [2/5]

tvm::runtime::Tensor::Tensor ( ObjectPtr< ffi::TensorObj > data )

inlineexplicit

constructor.

Parameters

data	ObjectPtr to the data container.

◆ Tensor() [3/5]

tvm::runtime::Tensor::Tensor ( ffi::UnsafeInit tag )

inlineexplicit

◆ Tensor() [4/5]

tvm::runtime::Tensor::Tensor ( ffi::Tensor && other )

inline

◆ Tensor() [5/5]

tvm::runtime::Tensor::Tensor ( const ffi::Tensor & other )

inline

Member Function Documentation

◆ CopyFrom() [1/2]

void tvm::runtime::Tensor::CopyFrom ( const DLTensor * other )

inline

Copy data content from another array.

Parameters

other The source array to be copied from.

Note: The copy may happen asynchronously if it involves a GPU context. TVMSynchronize is necessary.

◆ CopyFrom() [2/2]

void tvm::runtime::Tensor::CopyFrom ( const Tensor & other )

inline

◆ CopyFromBytes()

void tvm::runtime::Tensor::CopyFromBytes	(	const void *	data,
		size_t	nbytes
	)

Copy data content from a byte buffer.

Parameters

data	The source bytes to be copied from.
nbytes	The size of the buffer in bytes Must be equal to the size of the Tensor.

Note: The copy always triggers a TVMSynchronize.

◆ CopyFromTo()

static void tvm::runtime::Tensor::CopyFromTo	(	const DLTensor *	from,
		DLTensor *	to,
		TVMStreamHandle	stream = `nullptr`
	)

static

Function to copy data from one array to another.

Parameters

from	The source array.
to	The target array.
stream	The stream used in copy.

◆ CopyTo() [1/3]

Tensor tvm::runtime::Tensor::CopyTo	(	const Device &	dev,
		ffi::Optional< ffi::String >	mem_scope = `std::nullopt`
	)		const

Copy the data to another device.

Parameters

dev	The target device.
mem_scope	The memory scope of the target array.

Returns: The array under another device.

Note: The copy always triggers a TVMSynchronize.

◆ CopyTo() [2/3]

void tvm::runtime::Tensor::CopyTo ( const Tensor & other ) const

inline

◆ CopyTo() [3/3]

void tvm::runtime::Tensor::CopyTo ( DLTensor * other ) const

inline

Copy data content into another array.

Parameters

other The source array to be copied from.

Note: The copy may happen asynchronously if it involves a GPU context. TVMSynchronize is necessary.

◆ CopyToBytes() [1/2]

static void tvm::runtime::Tensor::CopyToBytes	(	const DLTensor *	from,
		void *	to,
		size_t	nbytes,
		TVMStreamHandle	stream = `nullptr`
	)

static

Function to copy data from one array to a byte buffer.

Parameters

from	The source array.
to	The target byte buffer.
nbytes	The size of the data buffer.
stream	The stream used in copy.

◆ CopyToBytes() [2/2]

void tvm::runtime::Tensor::CopyToBytes	(	void *	data,
		size_t	nbytes
	)		const

Copy data content into another array.

Parameters

data	The source bytes to be copied from.
nbytes	The size of the data buffer. Must be equal to the size of the Tensor.

Note: The copy always triggers a TVMSynchronize.

◆ CreateView()

Tensor tvm::runtime::Tensor::CreateView	(	ffi::Shape	shape,
		DLDataType	dtype,
		uint64_t	relative_byte_offset = `0`
	)		const

Create a Tensor that shares the data memory with the current one.

Parameters

shape	The shape of the new array.
dtype	The data type of the new array.
relative_byte_offset	The offset of the output Tensor, relative to the current byte offset.

By default, the offset of the view is the same as the offset of the current array.

Note: The new array must not allow access of addresses which would be out of bounds in the current array. If the new array is larger than the current array, or if the relative_byte_offset would place the end of the new array outside the bounds of the current array, this function will raise an exception.

◆ DataType()

runtime::DataType tvm::runtime::Tensor::DataType ( ) const

inline

◆ Empty()

static Tensor tvm::runtime::Tensor::Empty	(	ffi::Shape	shape,
		DLDataType	dtype,
		Device	dev,
		ffi::Optional< ffi::String >	mem_scope = `std::nullopt`
	)

static

Create an empty Tensor.

Parameters

shape	The shape of the new array.
dtype	The data type of the new array.
dev	The device of the array.
mem_scope	The memory scope of the array.

Returns: The created Array

◆ FromDLPack()

static Tensor tvm::runtime::Tensor::FromDLPack ( DLManagedTensor * tensor )

inlinestatic

◆ FromDLPackVersioned()

static Tensor tvm::runtime::Tensor::FromDLPackVersioned ( DLManagedTensorVersioned * tensor )

inlinestatic

◆ Load()

bool tvm::runtime::Tensor::Load ( dmlc::Stream * stream )

inline

Load Tensor from stream.

Parameters

stream The input data stream

Returns: Whether load is successful

◆ Save()

void tvm::runtime::Tensor::Save ( dmlc::Stream * stream ) const

inline

Save Tensor to stream.

Parameters

stream The output data stream

◆ Shape()

ffi::Shape tvm::runtime::Tensor::Shape ( ) const

inline

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

include/tvm/runtime/tensor.h

Public Types

Public Member Functions

Static Public Member Functions

Detailed Description

Member Typedef Documentation

◆ Container

Constructor & Destructor Documentation

◆ Tensor() [1/5]

◆ Tensor() [2/5]

◆ Tensor() [3/5]

◆ Tensor() [4/5]

◆ Tensor() [5/5]

Member Function Documentation

◆ CopyFrom() [1/2]

◆ CopyFrom() [2/2]

◆ CopyFromBytes()

◆ CopyFromTo()

◆ CopyTo() [1/3]

◆ CopyTo() [2/3]

◆ CopyTo() [3/3]

◆ CopyToBytes() [1/2]

◆ CopyToBytes() [2/2]

◆ CreateView()

◆ DataType()

◆ Empty()

◆ FromDLPack()

◆ FromDLPackVersioned()

◆ Load()

◆ Save()

◆ Shape()