Provided by: nvidia-cuda-dev_10.1.243-3_amd64 
NAME
Graph Management -
Functions
cudaError_t cudaGraphAddChildGraphNode (cudaGraphNode_t *pGraphNode, cudaGraph_t graph,
const cudaGraphNode_t *pDependencies, size_t numDependencies, cudaGraph_t childGraph)
Creates a child graph node and adds it to a graph.
cudaError_t cudaGraphAddDependencies (cudaGraph_t graph, const cudaGraphNode_t *from,
const cudaGraphNode_t *to, size_t numDependencies)
Adds dependency edges to a graph.
cudaError_t cudaGraphAddEmptyNode (cudaGraphNode_t *pGraphNode, cudaGraph_t graph, const
cudaGraphNode_t *pDependencies, size_t numDependencies)
Creates an empty node and adds it to a graph.
cudaError_t cudaGraphAddHostNode (cudaGraphNode_t *pGraphNode, cudaGraph_t graph, const
cudaGraphNode_t *pDependencies, size_t numDependencies, const struct
cudaHostNodeParams *pNodeParams)
Creates a host execution node and adds it to a graph.
cudaError_t cudaGraphAddKernelNode (cudaGraphNode_t *pGraphNode, cudaGraph_t graph, const
cudaGraphNode_t *pDependencies, size_t numDependencies, const struct
cudaKernelNodeParams *pNodeParams)
Creates a kernel execution node and adds it to a graph.
cudaError_t cudaGraphAddMemcpyNode (cudaGraphNode_t *pGraphNode, cudaGraph_t graph, const
cudaGraphNode_t *pDependencies, size_t numDependencies, const struct cudaMemcpy3DParms
*pCopyParams)
Creates a memcpy node and adds it to a graph.
cudaError_t cudaGraphAddMemsetNode (cudaGraphNode_t *pGraphNode, cudaGraph_t graph, const
cudaGraphNode_t *pDependencies, size_t numDependencies, const struct cudaMemsetParams
*pMemsetParams)
Creates a memset node and adds it to a graph.
cudaError_t cudaGraphChildGraphNodeGetGraph (cudaGraphNode_t node, cudaGraph_t *pGraph)
Gets a handle to the embedded graph of a child graph node.
cudaError_t cudaGraphClone (cudaGraph_t *pGraphClone, cudaGraph_t originalGraph)
Clones a graph.
cudaError_t cudaGraphCreate (cudaGraph_t *pGraph, unsigned int flags)
Creates a graph.
cudaError_t cudaGraphDestroy (cudaGraph_t graph)
Destroys a graph.
cudaError_t cudaGraphDestroyNode (cudaGraphNode_t node)
Remove a node from the graph.
cudaError_t cudaGraphExecDestroy (cudaGraphExec_t graphExec)
Destroys an executable graph.
cudaError_t cudaGraphExecKernelNodeSetParams (cudaGraphExec_t hGraphExec, cudaGraphNode_t
node, const struct cudaKernelNodeParams *pNodeParams)
Sets the parameters for a kernel node in the given graphExec.
cudaError_t cudaGraphGetEdges (cudaGraph_t graph, cudaGraphNode_t *from, cudaGraphNode_t
*to, size_t *numEdges)
Returns a graph's dependency edges.
cudaError_t cudaGraphGetNodes (cudaGraph_t graph, cudaGraphNode_t *nodes, size_t
*numNodes)
Returns a graph's nodes.
cudaError_t cudaGraphGetRootNodes (cudaGraph_t graph, cudaGraphNode_t *pRootNodes, size_t
*pNumRootNodes)
Returns a graph's root nodes.
cudaError_t cudaGraphHostNodeGetParams (cudaGraphNode_t node, struct cudaHostNodeParams
*pNodeParams)
Returns a host node's parameters.
cudaError_t cudaGraphHostNodeSetParams (cudaGraphNode_t node, const struct
cudaHostNodeParams *pNodeParams)
Sets a host node's parameters.
cudaError_t cudaGraphInstantiate (cudaGraphExec_t *pGraphExec, cudaGraph_t graph,
cudaGraphNode_t *pErrorNode, char *pLogBuffer, size_t bufferSize)
Creates an executable graph from a graph.
cudaError_t cudaGraphKernelNodeGetParams (cudaGraphNode_t node, struct
cudaKernelNodeParams *pNodeParams)
Returns a kernel node's parameters.
cudaError_t cudaGraphKernelNodeSetParams (cudaGraphNode_t node, const struct
cudaKernelNodeParams *pNodeParams)
Sets a kernel node's parameters.
cudaError_t cudaGraphLaunch (cudaGraphExec_t graphExec, cudaStream_t stream)
Launches an executable graph in a stream.
cudaError_t cudaGraphMemcpyNodeGetParams (cudaGraphNode_t node, struct cudaMemcpy3DParms
*pNodeParams)
Returns a memcpy node's parameters.
cudaError_t cudaGraphMemcpyNodeSetParams (cudaGraphNode_t node, const struct
cudaMemcpy3DParms *pNodeParams)
Sets a memcpy node's parameters.
cudaError_t cudaGraphMemsetNodeGetParams (cudaGraphNode_t node, struct cudaMemsetParams
*pNodeParams)
Returns a memset node's parameters.
cudaError_t cudaGraphMemsetNodeSetParams (cudaGraphNode_t node, const struct
cudaMemsetParams *pNodeParams)
Sets a memset node's parameters.
cudaError_t cudaGraphNodeFindInClone (cudaGraphNode_t *pNode, cudaGraphNode_t
originalNode, cudaGraph_t clonedGraph)
Finds a cloned version of a node.
cudaError_t cudaGraphNodeGetDependencies (cudaGraphNode_t node, cudaGraphNode_t
*pDependencies, size_t *pNumDependencies)
Returns a node's dependencies.
cudaError_t cudaGraphNodeGetDependentNodes (cudaGraphNode_t node, cudaGraphNode_t
*pDependentNodes, size_t *pNumDependentNodes)
Returns a node's dependent nodes.
cudaError_t cudaGraphNodeGetType (cudaGraphNode_t node, enum cudaGraphNodeType *pType)
Returns a node's type.
cudaError_t cudaGraphRemoveDependencies (cudaGraph_t graph, const cudaGraphNode_t *from,
const cudaGraphNode_t *to, size_t numDependencies)
Removes dependency edges from a graph.
Detailed Description
\brief graph management functions of the CUDA runtime API (cuda_runtime_api.h)
This section describes the graph management functions of CUDA runtime application
programming interface.
Function Documentation
cudaError_t cudaGraphAddChildGraphNode (cudaGraphNode_t * pGraphNode, cudaGraph_t graph, const
cudaGraphNode_t * pDependencies, size_t numDependencies, cudaGraph_t childGraph)
Creates a new node which executes an embedded graph, and adds it to graph with
numDependencies dependencies specified via pDependencies. It is possible for
numDependencies to be 0, in which case the node will be placed at the root of the graph.
pDependencies may not have any duplicate entries. A handle to the new node will be
returned in pGraphNode.
The node executes an embedded child graph. The child graph is cloned in this call.
Parameters:
pGraphNode - Returns newly created node
graph - Graph to which to add the node
pDependencies - Dependencies of the node
numDependencies - Number of dependencies
childGraph - The graph to clone into this node
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphChildGraphNodeGetGraph, cudaGraphCreate, cudaGraphDestroyNode,
cudaGraphAddEmptyNode, cudaGraphAddKernelNode, cudaGraphAddHostNode,
cudaGraphAddMemcpyNode, cudaGraphAddMemsetNode, cudaGraphClone
cudaError_t cudaGraphAddDependencies (cudaGraph_t graph, const cudaGraphNode_t * from, const
cudaGraphNode_t * to, size_t numDependencies)
The number of dependencies to be added is defined by numDependencies Elements in pFrom and
pTo at corresponding indices define a dependency. Each node in pFrom and pTo must belong
to graph.
If numDependencies is 0, elements in pFrom and pTo will be ignored. Specifying an existing
dependency will return an error.
Parameters:
graph - Graph to which dependencies are added
from - Array of nodes that provide the dependencies
to - Array of dependent nodes
numDependencies - Number of dependencies to be added
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphRemoveDependencies, cudaGraphGetEdges, cudaGraphNodeGetDependencies,
cudaGraphNodeGetDependentNodes
cudaError_t cudaGraphAddEmptyNode (cudaGraphNode_t * pGraphNode, cudaGraph_t graph, const
cudaGraphNode_t * pDependencies, size_t numDependencies)
Creates a new node which performs no operation, and adds it to graph with numDependencies
dependencies specified via pDependencies. It is possible for numDependencies to be 0, in
which case the node will be placed at the root of the graph. pDependencies may not have
any duplicate entries. A handle to the new node will be returned in pGraphNode.
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.
Parameters:
pGraphNode - Returns newly created node
graph - Graph to which to add the node
pDependencies - Dependencies of the node
numDependencies - Number of dependencies
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
See also:
cudaGraphCreate, cudaGraphDestroyNode, cudaGraphAddChildGraphNode,
cudaGraphAddKernelNode, cudaGraphAddHostNode, cudaGraphAddMemcpyNode,
cudaGraphAddMemsetNode
cudaError_t cudaGraphAddHostNode (cudaGraphNode_t * pGraphNode, cudaGraph_t graph, const
cudaGraphNode_t * pDependencies, size_t numDependencies, const struct cudaHostNodeParams *
pNodeParams)
Creates a new CPU execution node and adds it to graph with numDependencies dependencies
specified via pDependencies and arguments specified in pNodeParams. It is possible for
numDependencies to be 0, in which case the node will be placed at the root of the graph.
pDependencies may not have any duplicate entries. A handle to the new node will be
returned in pGraphNode.
When the graph is launched, the node will invoke the specified CPU function. Host nodes
are not supported under MPS with pre-Volta GPUs.
Parameters:
pGraphNode - Returns newly created node
graph - Graph to which to add the node
pDependencies - Dependencies of the node
numDependencies - Number of dependencies
pNodeParams - Parameters for the host node
Returns:
cudaSuccess, cudaErrorNotSupported, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaLaunchHostFunc, cudaGraphHostNodeGetParams, cudaGraphHostNodeSetParams,
cudaGraphCreate, cudaGraphDestroyNode, cudaGraphAddChildGraphNode,
cudaGraphAddEmptyNode, cudaGraphAddKernelNode, cudaGraphAddMemcpyNode,
cudaGraphAddMemsetNode
cudaError_t cudaGraphAddKernelNode (cudaGraphNode_t * pGraphNode, cudaGraph_t graph, const
cudaGraphNode_t * pDependencies, size_t numDependencies, const struct cudaKernelNodeParams
* pNodeParams)
Creates a new kernel execution node and adds it to graph with numDependencies dependencies
specified via pDependencies and arguments specified in pNodeParams. It is possible for
numDependencies to be 0, in which case the node will be placed at the root of the graph.
pDependencies may not have any duplicate entries. A handle to the new node will be
returned in pGraphNode.
The cudaKernelNodeParams structure is defined as:
struct cudaKernelNodeParams
{
void* func;
dim3 gridDim;
dim3 blockDim;
unsigned int sharedMemBytes;
void **kernelParams;
void **extra;
};
When the graph is launched, the node will invoke kernel func on a (gridDim.x x gridDim.y x
gridDim.z) grid of blocks. Each block contains (blockDim.x x blockDim.y x blockDim.z)
threads.
sharedMem sets the amount of dynamic shared memory that will be available to each thread
block.
Kernel parameters to func can be specified in one of two ways:
1) Kernel parameters can be specified via kernelParams. If the kernel has N parameters,
then kernelParams needs to be an array of N pointers. Each pointer, from kernelParams[0]
to kernelParams[N-1], points to the region of memory from which the actual parameter will
be copied. The number of kernel parameters and their offsets and sizes do not need to be
specified as that information is retrieved directly from the kernel's image.
2) Kernel parameters can also be packaged by the application into a single buffer that is
passed in via extra. This places the burden on the application of knowing each kernel
parameter's size and alignment/padding within the buffer. The extra parameter exists to
allow this function to take additional less commonly used arguments. extra specifies a
list of names of extra settings and their corresponding values. Each extra setting name is
immediately followed by the corresponding value. The list must be terminated with either
NULL or CU_LAUNCH_PARAM_END.
• CU_LAUNCH_PARAM_END, which indicates the end of the extra array;
• CU_LAUNCH_PARAM_BUFFER_POINTER, which specifies that the next value in extra will be a
pointer to a buffer containing all the kernel parameters for launching kernel func;
• CU_LAUNCH_PARAM_BUFFER_SIZE, which specifies that the next value in extra will be a
pointer to a size_t containing the size of the buffer specified with
CU_LAUNCH_PARAM_BUFFER_POINTER;
The error cudaErrorInvalidValue will be returned if kernel parameters are specified with
both kernelParams and extra (i.e. both kernelParams and extra are non-NULL).
The kernelParams or extra array, as well as the argument values it points to, are copied
during this call.
Note:
Kernels launched using graphs must not use texture and surface references. Reading or
writing through any texture or surface reference is undefined behavior. This
restriction does not apply to texture and surface objects.
Parameters:
pGraphNode - Returns newly created node
graph - Graph to which to add the node
pDependencies - Dependencies of the node
numDependencies - Number of dependencies
pNodeParams - Parameters for the GPU execution node
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidDeviceFunction
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaLaunchKernel, cudaGraphKernelNodeGetParams, cudaGraphKernelNodeSetParams,
cudaGraphCreate, cudaGraphDestroyNode, cudaGraphAddChildGraphNode,
cudaGraphAddEmptyNode, cudaGraphAddHostNode, cudaGraphAddMemcpyNode,
cudaGraphAddMemsetNode
cudaError_t cudaGraphAddMemcpyNode (cudaGraphNode_t * pGraphNode, cudaGraph_t graph, const
cudaGraphNode_t * pDependencies, size_t numDependencies, const struct cudaMemcpy3DParms *
pCopyParams)
Creates a new memcpy node and adds it to graph with numDependencies dependencies specified
via pDependencies. It is possible for numDependencies to be 0, in which case the node will
be placed at the root of the graph. pDependencies may not have any duplicate entries. A
handle to the new node will be returned in pGraphNode.
When the graph is launched, the node will perform the memcpy described by pCopyParams. See
cudaMemcpy3D() for a description of the structure and its restrictions.
Memcpy nodes have some additional restrictions with regards to managed memory, if the
system contains at least one device which has a zero value for the device attribute
cudaDevAttrConcurrentManagedAccess.
Parameters:
pGraphNode - Returns newly created node
graph - Graph to which to add the node
pDependencies - Dependencies of the node
numDependencies - Number of dependencies
pCopyParams - Parameters for the memory copy
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaMemcpy3D, cudaGraphMemcpyNodeGetParams, cudaGraphMemcpyNodeSetParams,
cudaGraphCreate, cudaGraphDestroyNode, cudaGraphAddChildGraphNode,
cudaGraphAddEmptyNode, cudaGraphAddKernelNode, cudaGraphAddHostNode,
cudaGraphAddMemsetNode
cudaError_t cudaGraphAddMemsetNode (cudaGraphNode_t * pGraphNode, cudaGraph_t graph, const
cudaGraphNode_t * pDependencies, size_t numDependencies, const struct cudaMemsetParams *
pMemsetParams)
Creates a new memset node and adds it to graph with numDependencies dependencies specified
via pDependencies. It is possible for numDependencies to be 0, in which case the node will
be placed at the root of the graph. pDependencies may not have any duplicate entries. A
handle to the new node will be returned in pGraphNode.
The element size must be 1, 2, or 4 bytes. When the graph is launched, the node will
perform the memset described by pMemsetParams.
Parameters:
pGraphNode - Returns newly created node
graph - Graph to which to add the node
pDependencies - Dependencies of the node
numDependencies - Number of dependencies
pMemsetParams - Parameters for the memory set
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidDevice
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaMemset2D, cudaGraphMemsetNodeGetParams, cudaGraphMemsetNodeSetParams,
cudaGraphCreate, cudaGraphDestroyNode, cudaGraphAddChildGraphNode,
cudaGraphAddEmptyNode, cudaGraphAddKernelNode, cudaGraphAddHostNode,
cudaGraphAddMemcpyNode
cudaError_t cudaGraphChildGraphNodeGetGraph (cudaGraphNode_t node, cudaGraph_t * pGraph)
Gets a handle to the embedded graph in a child graph node. This call does not clone the
graph. Changes to the graph will be reflected in the node, and the node retains ownership
of the graph.
Parameters:
node - Node to get the embedded graph for
pGraph - Location to store a handle to the graph
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphAddChildGraphNode, cudaGraphNodeFindInClone
cudaError_t cudaGraphClone (cudaGraph_t * pGraphClone, cudaGraph_t originalGraph)
This function creates a copy of originalGraph and returns it in pGraphClone. All
parameters are copied into the cloned graph. The original graph may be modified after this
call without affecting the clone.
Child graph nodes in the original graph are recursively copied into the clone.
Parameters:
pGraphClone - Returns newly created cloned graph
originalGraph - Graph to clone
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorMemoryAllocation
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphCreate, cudaGraphNodeFindInClone
cudaError_t cudaGraphCreate (cudaGraph_t * pGraph, unsigned int flags)
Creates an empty graph, which is returned via pGraph.
Parameters:
pGraph - Returns newly created graph
flags - Graph creation flags, must be 0
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorMemoryAllocation
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphAddChildGraphNode, cudaGraphAddEmptyNode, cudaGraphAddKernelNode,
cudaGraphAddHostNode, cudaGraphAddMemcpyNode, cudaGraphAddMemsetNode,
cudaGraphInstantiate, cudaGraphDestroy, cudaGraphGetNodes, cudaGraphGetRootNodes,
cudaGraphGetEdges, cudaGraphClone
cudaError_t cudaGraphDestroy (cudaGraph_t graph)
Destroys the graph specified by graph, as well as all of its nodes.
Parameters:
graph - Graph to destroy
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphCreate
cudaError_t cudaGraphDestroyNode (cudaGraphNode_t node)
Removes node from its graph. This operation also severs any dependencies of other nodes on
node and vice versa.
Parameters:
node - Node to remove
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphAddChildGraphNode, cudaGraphAddEmptyNode, cudaGraphAddKernelNode,
cudaGraphAddHostNode, cudaGraphAddMemcpyNode, cudaGraphAddMemsetNode
cudaError_t cudaGraphExecDestroy (cudaGraphExec_t graphExec)
Destroys the executable graph specified by graphExec.
Parameters:
graphExec - Executable graph to destroy
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphInstantiate, cudaGraphLaunch
cudaError_t cudaGraphExecKernelNodeSetParams (cudaGraphExec_t hGraphExec, cudaGraphNode_t
node, const struct cudaKernelNodeParams * pNodeParams)
Sets the parameters of a kernel node in an executable graph hGraphExec. The node is
identified by the corresponding node node in the non-executable graph, from which the
executable graph was instantiated.
node must not have been removed from the original graph. The func field of nodeParams
cannot be modified and must match the original value. All other values can be modified.
The modifications take effect at the next launch of hGraphExec. Already enqueued or
running launches of hGraphExec are not affected by this call. node is also not modified by
this call.
Parameters:
hGraphExec - The executable graph in which to set the specified node
node - kernel node from the graph from which graphExec was instantiated
pNodeParams - Updated Parameters to set
Returns:
cudaSuccess, cudaErrorInvalidValue,
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphAddKernelNode, cudaGraphKernelNodeSetParams, cudaGraphInstantiate
cudaError_t cudaGraphGetEdges (cudaGraph_t graph, cudaGraphNode_t * from, cudaGraphNode_t *
to, size_t * numEdges)
Returns a list of graph's dependency edges. Edges are returned via corresponding indices
in from and to; that is, the node in to[i] has a dependency on the node in from[i]. from
and to may both be NULL, in which case this function only returns the number of edges in
numEdges. Otherwise, numEdges entries will be filled in. If numEdges is higher than the
actual number of edges, the remaining entries in from and to will be set to NULL, and the
number of edges actually returned will be written to numEdges.
Parameters:
graph - Graph to get the edges from
from - Location to return edge endpoints
to - Location to return edge endpoints
numEdges - See description
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphGetNodes, cudaGraphGetRootNodes, cudaGraphAddDependencies,
cudaGraphRemoveDependencies, cudaGraphNodeGetDependencies,
cudaGraphNodeGetDependentNodes
cudaError_t cudaGraphGetNodes (cudaGraph_t graph, cudaGraphNode_t * nodes, size_t * numNodes)
Returns a list of graph's nodes. nodes may be NULL, in which case this function will
return the number of nodes in numNodes. Otherwise, numNodes entries will be filled in. If
numNodes is higher than the actual number of nodes, the remaining entries in nodes will be
set to NULL, and the number of nodes actually obtained will be returned in numNodes.
Parameters:
graph - Graph to query
nodes - Pointer to return the nodes
numNodes - See description
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphCreate, cudaGraphGetRootNodes, cudaGraphGetEdges, cudaGraphNodeGetType,
cudaGraphNodeGetDependencies, cudaGraphNodeGetDependentNodes
cudaError_t cudaGraphGetRootNodes (cudaGraph_t graph, cudaGraphNode_t * pRootNodes, size_t *
pNumRootNodes)
Returns a list of graph's root nodes. pRootNodes may be NULL, in which case this function
will return the number of root nodes in pNumRootNodes. Otherwise, pNumRootNodes entries
will be filled in. If pNumRootNodes is higher than the actual number of root nodes, the
remaining entries in pRootNodes will be set to NULL, and the number of nodes actually
obtained will be returned in pNumRootNodes.
Parameters:
graph - Graph to query
pRootNodes - Pointer to return the root nodes
pNumRootNodes - See description
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphCreate, cudaGraphGetNodes, cudaGraphGetEdges, cudaGraphNodeGetType,
cudaGraphNodeGetDependencies, cudaGraphNodeGetDependentNodes
cudaError_t cudaGraphHostNodeGetParams (cudaGraphNode_t node, struct cudaHostNodeParams *
pNodeParams)
Returns the parameters of host node node in pNodeParams.
Parameters:
node - Node to get the parameters for
pNodeParams - Pointer to return the parameters
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaLaunchHostFunc, cudaGraphAddHostNode, cudaGraphHostNodeSetParams
cudaError_t cudaGraphHostNodeSetParams (cudaGraphNode_t node, const struct cudaHostNodeParams
* pNodeParams)
Sets the parameters of host node node to nodeParams.
Parameters:
node - Node to set the parameters for
pNodeParams - Parameters to copy
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaLaunchHostFunc, cudaGraphAddHostNode, cudaGraphHostNodeGetParams
cudaError_t cudaGraphInstantiate (cudaGraphExec_t * pGraphExec, cudaGraph_t graph,
cudaGraphNode_t * pErrorNode, char * pLogBuffer, size_t bufferSize)
Instantiates graph as an executable graph. The graph is validated for any structural
constraints or intra-node constraints which were not previously validated. If
instantiation is successful, a handle to the instantiated graph is returned in pGraphExec.
If there are any errors, diagnostic information may be returned in pErrorNode and
pLogBuffer. This is the primary way to inspect instantiation errors. The output will be
null terminated unless the diagnostics overflow the buffer. In this case, they will be
truncated, and the last byte can be inspected to determine if truncation occurred.
Parameters:
pGraphExec - Returns instantiated graph
graph - Graph to instantiate
pErrorNode - In case of an instantiation error, this may be modified to indicate a
node contributing to the error
pLogBuffer - A character buffer to store diagnostic messages
bufferSize - Size of the log buffer in bytes
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphCreate, cudaGraphLaunch, cudaGraphExecDestroy
cudaError_t cudaGraphKernelNodeGetParams (cudaGraphNode_t node, struct cudaKernelNodeParams *
pNodeParams)
Returns the parameters of kernel node node in pNodeParams. The kernelParams or extra array
returned in pNodeParams, as well as the argument values it points to, are owned by the
node. This memory remains valid until the node is destroyed or its parameters are
modified, and should not be modified directly. Use cudaGraphKernelNodeSetParams to update
the parameters of this node.
The params will contain either kernelParams or extra, according to which of these was most
recently set on the node.
Parameters:
node - Node to get the parameters for
pNodeParams - Pointer to return the parameters
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidDeviceFunction
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaLaunchKernel, cudaGraphAddKernelNode, cudaGraphKernelNodeSetParams
cudaError_t cudaGraphKernelNodeSetParams (cudaGraphNode_t node, const struct
cudaKernelNodeParams * pNodeParams)
Sets the parameters of kernel node node to pNodeParams.
Parameters:
node - Node to set the parameters for
pNodeParams - Parameters to copy
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidResourceHandle,
cudaErrorMemoryAllocation
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaLaunchKernel, cudaGraphAddKernelNode, cudaGraphKernelNodeGetParams
cudaError_t cudaGraphLaunch (cudaGraphExec_t graphExec, cudaStream_t stream)
Executes graphExec in stream. Only one instance of graphExec may be executing at a time.
Each launch is ordered behind both any previous work in stream and any previous launches
of graphExec. To execute a graph concurrently, it must be instantiated multiple times into
multiple executable graphs.
Parameters:
graphExec - Executable graph to launch
stream - Stream in which to launch the graph
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphInstantiate, cudaGraphExecDestroy
cudaError_t cudaGraphMemcpyNodeGetParams (cudaGraphNode_t node, struct cudaMemcpy3DParms *
pNodeParams)
Returns the parameters of memcpy node node in pNodeParams.
Parameters:
node - Node to get the parameters for
pNodeParams - Pointer to return the parameters
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaMemcpy3D, cudaGraphAddMemcpyNode, cudaGraphMemcpyNodeSetParams
cudaError_t cudaGraphMemcpyNodeSetParams (cudaGraphNode_t node, const struct cudaMemcpy3DParms
* pNodeParams)
Sets the parameters of memcpy node node to pNodeParams.
Parameters:
node - Node to set the parameters for
pNodeParams - Parameters to copy
Returns:
cudaSuccess, cudaErrorInvalidValue,
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaMemcpy3D, cudaGraphAddMemcpyNode, cudaGraphMemcpyNodeGetParams
cudaError_t cudaGraphMemsetNodeGetParams (cudaGraphNode_t node, struct cudaMemsetParams *
pNodeParams)
Returns the parameters of memset node node in pNodeParams.
Parameters:
node - Node to get the parameters for
pNodeParams - Pointer to return the parameters
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaMemset2D, cudaGraphAddMemsetNode, cudaGraphMemsetNodeSetParams
cudaError_t cudaGraphMemsetNodeSetParams (cudaGraphNode_t node, const struct cudaMemsetParams
* pNodeParams)
Sets the parameters of memset node node to pNodeParams.
Parameters:
node - Node to set the parameters for
pNodeParams - Parameters to copy
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaMemset2D, cudaGraphAddMemsetNode, cudaGraphMemsetNodeGetParams
cudaError_t cudaGraphNodeFindInClone (cudaGraphNode_t * pNode, cudaGraphNode_t originalNode,
cudaGraph_t clonedGraph)
This function returns the node in clonedGraph corresponding to originalNode in the
original graph.
clonedGraph must have been cloned from originalGraph via cudaGraphClone. originalNode must
have been in originalGraph at the time of the call to cudaGraphClone, and the
corresponding cloned node in clonedGraph must not have been removed. The cloned node is
then returned via pClonedNode.
Parameters:
pNode - Returns handle to the cloned node
originalNode - Handle to the original node
clonedGraph - Cloned graph to query
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphClone
cudaError_t cudaGraphNodeGetDependencies (cudaGraphNode_t node, cudaGraphNode_t *
pDependencies, size_t * pNumDependencies)
Returns a list of node's dependencies. pDependencies may be NULL, in which case this
function will return the number of dependencies in pNumDependencies. Otherwise,
pNumDependencies entries will be filled in. If pNumDependencies is higher than the actual
number of dependencies, the remaining entries in pDependencies will be set to NULL, and
the number of nodes actually obtained will be returned in pNumDependencies.
Parameters:
node - Node to query
pDependencies - Pointer to return the dependencies
pNumDependencies - See description
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphNodeGetDependentNodes, cudaGraphGetNodes, cudaGraphGetRootNodes,
cudaGraphGetEdges, cudaGraphAddDependencies, cudaGraphRemoveDependencies
cudaError_t cudaGraphNodeGetDependentNodes (cudaGraphNode_t node, cudaGraphNode_t *
pDependentNodes, size_t * pNumDependentNodes)
Returns a list of node's dependent nodes. pDependentNodes may be NULL, in which case this
function will return the number of dependent nodes in pNumDependentNodes. Otherwise,
pNumDependentNodes entries will be filled in. If pNumDependentNodes is higher than the
actual number of dependent nodes, the remaining entries in pDependentNodes will be set to
NULL, and the number of nodes actually obtained will be returned in pNumDependentNodes.
Parameters:
node - Node to query
pDependentNodes - Pointer to return the dependent nodes
pNumDependentNodes - See description
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphNodeGetDependencies, cudaGraphGetNodes, cudaGraphGetRootNodes,
cudaGraphGetEdges, cudaGraphAddDependencies, cudaGraphRemoveDependencies
cudaError_t cudaGraphNodeGetType (cudaGraphNode_t node, enum cudaGraphNodeType * pType)
Returns the node type of node in pType.
Parameters:
node - Node to query
pType - Pointer to return the node type
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphGetNodes, cudaGraphGetRootNodes, cudaGraphChildGraphNodeGetGraph,
cudaGraphKernelNodeGetParams, cudaGraphKernelNodeSetParams,
cudaGraphHostNodeGetParams, cudaGraphHostNodeSetParams, cudaGraphMemcpyNodeGetParams,
cudaGraphMemcpyNodeSetParams, cudaGraphMemsetNodeGetParams,
cudaGraphMemsetNodeSetParams
cudaError_t cudaGraphRemoveDependencies (cudaGraph_t graph, const cudaGraphNode_t * from,
const cudaGraphNode_t * to, size_t numDependencies)
The number of pDependencies to be removed is defined by numDependencies. Elements in pFrom
and pTo at corresponding indices define a dependency. Each node in pFrom and pTo must
belong to graph.
If numDependencies is 0, elements in pFrom and pTo will be ignored. Specifying a non-
existing dependency will return an error.
Parameters:
graph - Graph from which to remove dependencies
from - Array of nodes that provide the dependencies
to - Array of dependent nodes
numDependencies - Number of dependencies to be removed
Returns:
cudaSuccess, cudaErrorInvalidValue
Note:
Graph objects are not threadsafe. .
Note that this function may also return error codes from previous, asynchronous
launches.
See also:
cudaGraphAddDependencies, cudaGraphGetEdges, cudaGraphNodeGetDependencies,
cudaGraphNodeGetDependentNodes
Author
Generated automatically by Doxygen from the source code.