tf::cudaGraphBase< Creator, Deleter > Class Template Reference

class to create a CUDA graph with uunique ownership More...

#include <taskflow/cuda/cuda_graph.hpp>

Inheritance diagram for tf::cudaGraphBase< Creator, Deleter >:

Collaboration diagram for tf::cudaGraphBase< Creator, Deleter >:

Public Types
using	base_type = std::unique_ptr<std::remove_pointer_t<cudaGraph_t>, Deleter>
	base std::unique_ptr type

Public Member Functions
template<typename... ArgsT>
	cudaGraphBase (ArgsT &&... args)
	constructs a cudaGraph object by passing the given arguments to the executable CUDA graph creator
	cudaGraphBase (cudaGraphBase &&)=default
	constructs a cudaGraph from the given rhs using move semantics
cudaGraphBase &	operator= (cudaGraphBase &&)=default
	assign the rhs to *this using move semantics
size_t	num_nodes () const
	queries the number of nodes in a native CUDA graph
size_t	num_edges () const
	queries the number of edges in a native CUDA graph
bool	empty () const
	queries if the graph is empty
void	dump (std::ostream &os)
	dumps the CUDA graph to a DOT format through the given output stream
cudaTask	noop ()
	creates a no-operation task
template<typename C >
cudaTask	host (C &&callable, void *user_data)
	creates a host task that runs a callable on the host
template<typename F , typename... ArgsT>
cudaTask	kernel (dim3 g, dim3 b, size_t s, F f, ArgsT... args)
	creates a kernel task
cudaTask	memset (void *dst, int v, size_t count)
	creates a memset task that fills untyped data with a byte value
cudaTask	memcpy (void *tgt, const void *src, size_t bytes)
	creates a memcpy task that copies untyped data in bytes
template<typename T , std::enable_if_t< is_pod_v< T > &&(sizeof(T)==1||sizeof(T)==2||sizeof(T)==4), void > * = nullptr>
cudaTask	zero (T *dst, size_t count)
	creates a memset task that sets a typed memory block to zero
template<typename T , std::enable_if_t< is_pod_v< T > &&(sizeof(T)==1||sizeof(T)==2||sizeof(T)==4), void > * = nullptr>
cudaTask	fill (T *dst, T value, size_t count)
	creates a memset task that fills a typed memory block with a value
template<typename T , std::enable_if_t<!std::is_same_v< T, void >, void > * = nullptr>
cudaTask	copy (T *tgt, const T *src, size_t num)
	creates a memcopy task that copies typed data
template<typename C >
cudaTask	single_task (C c)
	runs a callable with only a single kernel thread
template<typename I , typename C , typename E = cudaDefaultExecutionPolicy>
cudaTask	for_each (I first, I last, C callable)
	applies a callable to each dereferenced element of the data array
template<typename I , typename C , typename E = cudaDefaultExecutionPolicy>
cudaTask	for_each_index (I first, I last, I step, C callable)
	applies a callable to each index in the range with the step size
template<typename I , typename O , typename C , typename E = cudaDefaultExecutionPolicy>
cudaTask	transform (I first, I last, O output, C op)
	applies a callable to a source range and stores the result in a target range
template<typename I1 , typename I2 , typename O , typename C , typename E = cudaDefaultExecutionPolicy>
cudaTask	transform (I1 first1, I1 last1, I2 first2, O output, C op)
	creates a task to perform parallel transforms over two ranges of items

Detailed Description

template<typename Creator, typename Deleter>
class tf::cudaGraphBase< Creator, Deleter >

class to create a CUDA graph with uunique ownership

Template Parameters

Creator	functor to create the stream (used in constructor)
Deleter	functor to delete the stream (used in destructor)

This class wraps a cudaGraph_t handle with std::unique_ptr to ensure proper resource management and automatic cleanup.

Constructor & Destructor Documentation

cudaGraphBase()

template<typename Creator , typename Deleter >

template<typename... ArgsT>

tf::cudaGraphBase< Creator, Deleter >::cudaGraphBase ( ArgsT &&... args )

inlineexplicit

constructs a cudaGraph object by passing the given arguments to the executable CUDA graph creator

Constructs a cudaGraph object by passing the given arguments to the executable CUDA graph creator

Parameters

args	arguments to pass to the executable CUDA graph creator

Member Function Documentation

copy()

template<typename Creator , typename Deleter >

template<typename T , std::enable_if_t<!std::is_same_v< T, void >, void > * >

cudaTask tf::cudaGraphBase< Creator, Deleter >::copy	(	T *	tgt,
		const T *	src,
		size_t	num )

creates a memcopy task that copies typed data

Template Parameters

T	element type (non-void)

Parameters

tgt	pointer to the target memory block
src	pointer to the source memory block
num	number of elements to copy

Returns

a tf::cudaTask handle

A copy task transfers num*sizeof(T) bytes of data from a source location to a target location. Direction can be arbitrary among CPUs and GPUs.

dump()

template<typename Creator , typename Deleter >

void tf::cudaGraphBase< Creator, Deleter >::dump

(

std::ostream &

os

)

dumps the CUDA graph to a DOT format through the given output stream

Parameters

os	target output stream

fill()

template<typename Creator , typename Deleter >

template<typename T , std::enable_if_t< is_pod_v< T > &&(sizeof(T)==1||sizeof(T)==2||sizeof(T)==4), void > * >

cudaTask tf::cudaGraphBase< Creator, Deleter >::fill	(	T *	dst,
		T	value,
		size_t	count )

creates a memset task that fills a typed memory block with a value

Template Parameters

T	element type (size of T must be either 1, 2, or 4)

Parameters

dst	pointer to the destination device memory area
value	value to fill for each element of type T
count	number of elements

Returns

a tf::cudaTask handle

A fill task fills the first count elements of type T with value in a device memory area pointed by dst. The value to fill is interpreted in type T rather than byte.

for_each()

template<typename Creator , typename Deleter >

template<typename I , typename C , typename E >

cudaTask tf::cudaGraphBase< Creator, Deleter >::for_each	(	I	first,
		I	last,
		C	callable )

applies a callable to each dereferenced element of the data array

Template Parameters

I	iterator type
C	callable type
E	execution poligy (default tf::cudaDefaultExecutionPolicy)

Parameters

first	iterator to the beginning (inclusive)
last	iterator to the end (exclusive)
callable	a callable object to apply to the dereferenced iterator

Returns

a tf::cudaTask handle

This method is equivalent to the parallel execution of the following loop on a GPU:

for(auto itr = first; itr != last; itr++) {
  callable(*itr);
}

for_each_index()

template<typename Creator , typename Deleter >

template<typename I , typename C , typename E >

cudaTask tf::cudaGraphBase< Creator, Deleter >::for_each_index	(	I	first,
		I	last,
		I	step,
		C	callable )

applies a callable to each index in the range with the step size

Template Parameters

I	index type
C	callable type
E	execution poligy (default tf::cudaDefaultExecutionPolicy)

Parameters

first	beginning index
last	last index
step	step size
callable	the callable to apply to each element in the data array

Returns

a tf::cudaTask handle

This method is equivalent to the parallel execution of the following loop on a GPU:

// step is positive [first, last)
for(auto i=first; i<last; i+=step) {
  callable(i);
}
 
// step is negative [first, last)
for(auto i=first; i>last; i+=step) {
  callable(i);
}

host()

template<typename Creator , typename Deleter >

template<typename C >

cudaTask tf::cudaGraphBase< Creator, Deleter >::host	(	C &&	callable,
		void *	user_data )

creates a host task that runs a callable on the host

Template Parameters

C	callable type

Parameters

callable	a callable object with neither arguments nor return (i.e., constructible from std::function<void()>)
user_data	a pointer to the user data

Returns

a tf::cudaTask handle

A host task can only execute CPU-specific functions and cannot do any CUDA calls (e.g., cudaMalloc).

kernel()

template<typename Creator , typename Deleter >

template<typename F , typename... ArgsT>

cudaTask tf::cudaGraphBase< Creator, Deleter >::kernel	(	dim3	g,
		dim3	b,
		size_t	s,
		F	f,
		ArgsT...	args )

creates a kernel task

Template Parameters

F	kernel function type
ArgsT	kernel function parameters type

Parameters

g	configured grid
b	configured block
s	configured shared memory size in bytes
f	kernel function
args	arguments to forward to the kernel function by copy

Returns

a tf::cudaTask handle

memcpy()

template<typename Creator , typename Deleter >

cudaTask tf::cudaGraphBase< Creator, Deleter >::memcpy	(	void *	tgt,
		const void *	src,
		size_t	bytes )

creates a memcpy task that copies untyped data in bytes

Parameters

tgt	pointer to the target memory block
src	pointer to the source memory block
bytes	bytes to copy

Returns

a tf::cudaTask handle

A memcpy task transfers bytes of data from a source location to a target location. Direction can be arbitrary among CPUs and GPUs.

memset()

template<typename Creator , typename Deleter >

cudaTask tf::cudaGraphBase< Creator, Deleter >::memset	(	void *	dst,
		int	v,
		size_t	count )

creates a memset task that fills untyped data with a byte value

Parameters

dst	pointer to the destination device memory area
v	value to set for each byte of specified memory
count	size in bytes to set

Returns

a tf::cudaTask handle

A memset task fills the first count bytes of device memory area pointed by dst with the byte value v.

noop()

template<typename Creator , typename Deleter >

cudaTask tf::cudaGraphBase< Creator, Deleter >::noop

(

)

creates a no-operation task

Returns

a tf::cudaTask handle

An empty node performs no operation during execution, but can be used for transitive ordering. For example, a phased execution graph with 2 groups of n nodes with a barrier between them can be represented using an empty node and 2*n dependency edges, rather than no empty node and n^2 dependency edges.

single_task()

template<typename Creator , typename Deleter >

template<typename C >

cudaTask tf::cudaGraphBase< Creator, Deleter >::single_task

(

C

c

)

runs a callable with only a single kernel thread

Template Parameters

C	callable type

Parameters

c	callable to run by a single kernel thread

Returns

a tf::cudaTask handle

transform() [1/2]

template<typename Creator , typename Deleter >

template<typename I , typename O , typename C , typename E >

cudaTask tf::cudaGraphBase< Creator, Deleter >::transform	(	I	first,
		I	last,
		O	output,
		C	op )

applies a callable to a source range and stores the result in a target range

Template Parameters

I	input iterator type
O	output iterator type
C	unary operator type
E	execution poligy (default tf::cudaDefaultExecutionPolicy)

Parameters

first	iterator to the beginning of the input range
last	iterator to the end of the input range
output	iterator to the beginning of the output range
op	the operator to apply to transform each element in the range

Returns

a tf::cudaTask handle

This method is equivalent to the parallel execution of the following loop on a GPU:

while (first != last) {
  *output++ = callable(*first++);
}

transform() [2/2]

template<typename Creator , typename Deleter >

template<typename I1 , typename I2 , typename O , typename C , typename E >

cudaTask tf::cudaGraphBase< Creator, Deleter >::transform	(	I1	first1,
		I1	last1,
		I2	first2,
		O	output,
		C	op )

creates a task to perform parallel transforms over two ranges of items

Template Parameters

I1	first input iterator type
I2	second input iterator type
O	output iterator type
C	unary operator type
E	execution poligy (default tf::cudaDefaultExecutionPolicy)

Parameters

first1	iterator to the beginning of the input range
last1	iterator to the end of the input range
first2	iterato
output	iterator to the beginning of the output range
op	binary operator to apply to transform each pair of items in the two input ranges

Returns

cudaTask handle

This method is equivalent to the parallel execution of the following loop on a GPU:

while (first1 != last1) {
  *output++ = op(*first1++, *first2++);
}

zero()

template<typename Creator , typename Deleter >

template<typename T , std::enable_if_t< is_pod_v< T > &&(sizeof(T)==1||sizeof(T)==2||sizeof(T)==4), void > * >

cudaTask tf::cudaGraphBase< Creator, Deleter >::zero	(	T *	dst,
		size_t	count )

creates a memset task that sets a typed memory block to zero

Template Parameters

T	element type (size of T must be either 1, 2, or 4)

Parameters

dst	pointer to the destination device memory area
count	number of elements

Returns

a tf::cudaTask handle

A zero task zeroes the first count elements of type T in a device memory area pointed by dst.

---

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

• taskflow/cuda/cuda_graph.hpp
• taskflow/cuda/algorithm/for_each.hpp
• taskflow/cuda/algorithm/transform.hpp