5.20. Graph Management

This section describes the graph management functions of the low-level CUDA driver application programming interface.

Functions

CUresult cuGraphAddChildGraphNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies, CUgraph childGraph )
Creates a child graph node and adds it to a graph.
CUresult cuGraphAddDependencies ( CUgraph hGraph, const CUgraphNode* from, const CUgraphNode* to, size_t numDependencies )
Adds dependency edges to a graph.
CUresult cuGraphAddEmptyNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies )
Creates an empty node and adds it to a graph.
CUresult cuGraphAddHostNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies, const CUDA_HOST_NODE_PARAMS* nodeParams )
Creates a host execution node and adds it to a graph.
CUresult cuGraphAddKernelNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies, const CUDA_KERNEL_NODE_PARAMS* nodeParams )
Creates a kernel execution node and adds it to a graph.
CUresult cuGraphAddMemcpyNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies, const CUDA_MEMCPY3D* copyParams, CUcontext ctx )
Creates a memcpy node and adds it to a graph.
CUresult cuGraphAddMemsetNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies, const CUDA_MEMSET_NODE_PARAMS* memsetParams, CUcontext ctx )
Creates a memset node and adds it to a graph.
CUresult cuGraphChildGraphNodeGetGraph ( CUgraphNode hNode, CUgraph* phGraph )
Gets a handle to the embedded graph of a child graph node.
CUresult cuGraphClone ( CUgraph* phGraphClone, CUgraph originalGraph )
Clones a graph.
CUresult cuGraphCreate ( CUgraph* phGraph, unsigned int  flags )
Creates a graph.
CUresult cuGraphDestroy ( CUgraph hGraph )
Destroys a graph.
CUresult cuGraphDestroyNode ( CUgraphNode hNode )
Remove a node from the graph.
CUresult cuGraphExecDestroy ( CUgraphExec hGraphExec )
Destroys an executable graph.
CUresult cuGraphExecHostNodeSetParams ( CUgraphExec hGraphExec, CUgraphNode hNode, const CUDA_HOST_NODE_PARAMS* nodeParams )
Sets the parameters for a host node in the given graphExec.
CUresult cuGraphExecKernelNodeSetParams ( CUgraphExec hGraphExec, CUgraphNode hNode, const CUDA_KERNEL_NODE_PARAMS* nodeParams )
Sets the parameters for a kernel node in the given graphExec.
CUresult cuGraphExecMemcpyNodeSetParams ( CUgraphExec hGraphExec, CUgraphNode hNode, const CUDA_MEMCPY3D* copyParams, CUcontext ctx )
Sets the parameters for a memcpy node in the given graphExec.
CUresult cuGraphExecMemsetNodeSetParams ( CUgraphExec hGraphExec, CUgraphNode hNode, const CUDA_MEMSET_NODE_PARAMS* memsetParams, CUcontext ctx )
Sets the parameters for a memset node in the given graphExec.
CUresult cuGraphExecUpdate ( CUgraphExec hGraphExec, CUgraph hGraph, CUgraphNode* hErrorNode_out, CUgraphExecUpdateResult* updateResult_out )
Check whether an executable graph can be updated with a graph and perform the update if possible.
CUresult cuGraphGetEdges ( CUgraph hGraph, CUgraphNode* from, CUgraphNode* to, size_t* numEdges )
Returns a graph's dependency edges.
CUresult cuGraphGetNodes ( CUgraph hGraph, CUgraphNode* nodes, size_t* numNodes )
Returns a graph's nodes.
CUresult cuGraphGetRootNodes ( CUgraph hGraph, CUgraphNode* rootNodes, size_t* numRootNodes )
Returns a graph's root nodes.
CUresult cuGraphHostNodeGetParams ( CUgraphNode hNode, CUDA_HOST_NODE_PARAMS* nodeParams )
Returns a host node's parameters.
CUresult cuGraphHostNodeSetParams ( CUgraphNode hNode, const CUDA_HOST_NODE_PARAMS* nodeParams )
Sets a host node's parameters.
CUresult cuGraphInstantiate ( CUgraphExec* phGraphExec, CUgraph hGraph, CUgraphNode* phErrorNode, char* logBuffer, size_t bufferSize )
Creates an executable graph from a graph.
CUresult cuGraphKernelNodeCopyAttributes ( CUgraphNode dst, CUgraphNode src )
Copies attributes from source node to destination node.
CUresult cuGraphKernelNodeGetAttribute ( CUgraphNode hNode, CUkernelNodeAttrID attr, CUkernelNodeAttrValue* value_out )
Queries node attribute.
CUresult cuGraphKernelNodeGetParams ( CUgraphNode hNode, CUDA_KERNEL_NODE_PARAMS* nodeParams )
Returns a kernel node's parameters.
CUresult cuGraphKernelNodeSetAttribute ( CUgraphNode hNode, CUkernelNodeAttrID attr, const CUkernelNodeAttrValue* value )
Sets node attribute.
CUresult cuGraphKernelNodeSetParams ( CUgraphNode hNode, const CUDA_KERNEL_NODE_PARAMS* nodeParams )
Sets a kernel node's parameters.
CUresult cuGraphLaunch ( CUgraphExec hGraphExec, CUstream hStream )
Launches an executable graph in a stream.
CUresult cuGraphMemcpyNodeGetParams ( CUgraphNode hNode, CUDA_MEMCPY3D* nodeParams )
Returns a memcpy node's parameters.
CUresult cuGraphMemcpyNodeSetParams ( CUgraphNode hNode, const CUDA_MEMCPY3D* nodeParams )
Sets a memcpy node's parameters.
CUresult cuGraphMemsetNodeGetParams ( CUgraphNode hNode, CUDA_MEMSET_NODE_PARAMS* nodeParams )
Returns a memset node's parameters.
CUresult cuGraphMemsetNodeSetParams ( CUgraphNode hNode, const CUDA_MEMSET_NODE_PARAMS* nodeParams )
Sets a memset node's parameters.
CUresult cuGraphNodeFindInClone ( CUgraphNode* phNode, CUgraphNode hOriginalNode, CUgraph hClonedGraph )
Finds a cloned version of a node.
CUresult cuGraphNodeGetDependencies ( CUgraphNode hNode, CUgraphNode* dependencies, size_t* numDependencies )
Returns a node's dependencies.
CUresult cuGraphNodeGetDependentNodes ( CUgraphNode hNode, CUgraphNode* dependentNodes, size_t* numDependentNodes )
Returns a node's dependent nodes.
CUresult cuGraphNodeGetType ( CUgraphNode hNode, CUgraphNodeType* type )
Returns a node's type.
CUresult cuGraphRemoveDependencies ( CUgraph hGraph, const CUgraphNode* from, const CUgraphNode* to, size_t numDependencies )
Removes dependency edges from a graph.

Functions

CUresult cuGraphAddChildGraphNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies, CUgraph childGraph )
Creates a child graph node and adds it to a graph.
Parameters
phGraphNode
- Returns newly created node
hGraph
- Graph to which to add the node
dependencies
- Dependencies of the node
numDependencies
- Number of dependencies
childGraph
- The graph to clone into this node
Description

Creates a new node which executes an embedded graph, and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

The node executes an embedded child graph. The child graph is cloned in this call.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphChildGraphNodeGetGraph, cuGraphCreate, cuGraphDestroyNode, cuGraphAddEmptyNode, cuGraphAddKernelNode, cuGraphAddHostNode, cuGraphAddMemcpyNode, cuGraphAddMemsetNode, cuGraphClone

CUresult cuGraphAddDependencies ( CUgraph hGraph, const CUgraphNode* from, const CUgraphNode* to, size_t numDependencies )
Adds dependency edges to a graph.
Parameters
hGraph
- 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
Description

The number of dependencies to be added is defined by numDependencies Elements in from and to at corresponding indices define a dependency. Each node in from and to must belong to hGraph.

If numDependencies is 0, elements in from and to will be ignored. Specifying an existing dependency will return an error.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphRemoveDependencies, cuGraphGetEdges, cuGraphNodeGetDependencies, cuGraphNodeGetDependentNodes

CUresult cuGraphAddEmptyNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies )
Creates an empty node and adds it to a graph.
Parameters
phGraphNode
- Returns newly created node
hGraph
- Graph to which to add the node
dependencies
- Dependencies of the node
numDependencies
- Number of dependencies
Description

Creates a new node which performs no operation, and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

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.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphCreate, cuGraphDestroyNode, cuGraphAddChildGraphNode, cuGraphAddKernelNode, cuGraphAddHostNode, cuGraphAddMemcpyNode, cuGraphAddMemsetNode

CUresult cuGraphAddHostNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies, const CUDA_HOST_NODE_PARAMS* nodeParams )
Creates a host execution node and adds it to a graph.
Parameters
phGraphNode
- Returns newly created node
hGraph
- Graph to which to add the node
dependencies
- Dependencies of the node
numDependencies
- Number of dependencies
nodeParams
- Parameters for the host node
Description

Creates a new CPU execution node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

When the graph is launched, the node will invoke the specified CPU function. Host nodes are not supported under MPS with pre-Volta GPUs.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuLaunchHostFunc, cuGraphHostNodeGetParams, cuGraphHostNodeSetParams, cuGraphCreate, cuGraphDestroyNode, cuGraphAddChildGraphNode, cuGraphAddEmptyNode, cuGraphAddKernelNode, cuGraphAddMemcpyNode, cuGraphAddMemsetNode

CUresult cuGraphAddKernelNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies, const CUDA_KERNEL_NODE_PARAMS* nodeParams )
Creates a kernel execution node and adds it to a graph.
Parameters
phGraphNode
- Returns newly created node
hGraph
- Graph to which to add the node
dependencies
- Dependencies of the node
numDependencies
- Number of dependencies
nodeParams
- Parameters for the GPU execution node
Description

Creates a new kernel execution node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

The CUDA_KERNEL_NODE_PARAMS structure is defined as:

‎  typedef struct CUDA_KERNEL_NODE_PARAMS_st {
            CUfunction func;
            unsigned int gridDimX;
            unsigned int gridDimY;
            unsigned int gridDimZ;
            unsigned int blockDimX;
            unsigned int blockDimY;
            unsigned int blockDimZ;
            unsigned int sharedMemBytes;
            void **kernelParams;
            void **extra;
        } CUDA_KERNEL_NODE_PARAMS;

When the graph is launched, the node will invoke kernel func on a (gridDimX x gridDimY x gridDimZ) grid of blocks. Each block contains (blockDimX x blockDimY x blockDimZ) threads.

sharedMemBytes 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 for non-cooperative kernels 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.

The error CUDA_ERROR_INVALID_VALUE will be returned if kernel parameters are specified with both kernelParams and extra (i.e. both kernelParams and extra are non-NULL). CUDA_ERROR_INVALID_VALUE will be returned if extra is used for a cooperative kernel.

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.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuLaunchKernel, cuLaunchCooperativeKernel, cuGraphKernelNodeGetParams, cuGraphKernelNodeSetParams, cuGraphCreate, cuGraphDestroyNode, cuGraphAddChildGraphNode, cuGraphAddEmptyNode, cuGraphAddHostNode, cuGraphAddMemcpyNode, cuGraphAddMemsetNode

CUresult cuGraphAddMemcpyNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies, const CUDA_MEMCPY3D* copyParams, CUcontext ctx )
Creates a memcpy node and adds it to a graph.
Parameters
phGraphNode
- Returns newly created node
hGraph
- Graph to which to add the node
dependencies
- Dependencies of the node
numDependencies
- Number of dependencies
copyParams
- Parameters for the memory copy
ctx
- Context on which to run the node
Description

Creates a new memcpy node and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

When the graph is launched, the node will perform the memcpy described by copyParams. See cuMemcpy3D() 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 CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If one or more of the operands refer to managed memory, then using the memory type CU_MEMORYTYPE_UNIFIED is disallowed for those operand(s). The managed memory will be treated as residing on either the host or the device, depending on which memory type is specified.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuMemcpy3D, cuGraphMemcpyNodeGetParams, cuGraphMemcpyNodeSetParams, cuGraphCreate, cuGraphDestroyNode, cuGraphAddChildGraphNode, cuGraphAddEmptyNode, cuGraphAddKernelNode, cuGraphAddHostNode, cuGraphAddMemsetNode

CUresult cuGraphAddMemsetNode ( CUgraphNode* phGraphNode, CUgraph hGraph, const CUgraphNode* dependencies, size_t numDependencies, const CUDA_MEMSET_NODE_PARAMS* memsetParams, CUcontext ctx )
Creates a memset node and adds it to a graph.
Parameters
phGraphNode
- Returns newly created node
hGraph
- Graph to which to add the node
dependencies
- Dependencies of the node
numDependencies
- Number of dependencies
memsetParams
- Parameters for the memory set
ctx
- Context on which to run the node
Description

Creates a new memset node and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

The element size must be 1, 2, or 4 bytes. When the graph is launched, the node will perform the memset described by memsetParams.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuMemsetD2D32, cuGraphMemsetNodeGetParams, cuGraphMemsetNodeSetParams, cuGraphCreate, cuGraphDestroyNode, cuGraphAddChildGraphNode, cuGraphAddEmptyNode, cuGraphAddKernelNode, cuGraphAddHostNode, cuGraphAddMemcpyNode

CUresult cuGraphChildGraphNodeGetGraph ( CUgraphNode hNode, CUgraph* phGraph )
Gets a handle to the embedded graph of a child graph node.
Parameters
hNode
- Node to get the embedded graph for
phGraph
- Location to store a handle to the graph
Description

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.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphAddChildGraphNode, cuGraphNodeFindInClone

CUresult cuGraphClone ( CUgraph* phGraphClone, CUgraph originalGraph )
Clones a graph.
Parameters
phGraphClone
- Returns newly created cloned graph
originalGraph
- Graph to clone
Description

This function creates a copy of originalGraph and returns it in * phGraphClone. 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.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphCreate, cuGraphNodeFindInClone

CUresult cuGraphCreate ( CUgraph* phGraph, unsigned int  flags )
Creates a graph.
Parameters
phGraph
- Returns newly created graph
flags
- Graph creation flags, must be 0
Description

Creates an empty graph, which is returned via phGraph.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphAddChildGraphNode, cuGraphAddEmptyNode, cuGraphAddKernelNode, cuGraphAddHostNode, cuGraphAddMemcpyNode, cuGraphAddMemsetNode, cuGraphInstantiate, cuGraphDestroy, cuGraphGetNodes, cuGraphGetRootNodes, cuGraphGetEdges, cuGraphClone

CUresult cuGraphDestroy ( CUgraph hGraph )
Destroys a graph.
Parameters
hGraph
- Graph to destroy
Description

Destroys the graph specified by hGraph, as well as all of its nodes.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphCreate

CUresult cuGraphDestroyNode ( CUgraphNode hNode )
Remove a node from the graph.
Parameters
hNode
- Node to remove
Description

Removes hNode from its graph. This operation also severs any dependencies of other nodes on hNode and vice versa.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphAddChildGraphNode, cuGraphAddEmptyNode, cuGraphAddKernelNode, cuGraphAddHostNode, cuGraphAddMemcpyNode, cuGraphAddMemsetNode

CUresult cuGraphExecDestroy ( CUgraphExec hGraphExec )
Destroys an executable graph.
Parameters
hGraphExec
- Executable graph to destroy
Description

Destroys the executable graph specified by hGraphExec, as well as all of its executable nodes. If the executable graph is in-flight, it will not be terminated, but rather freed asynchronously on completion.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphInstantiate, cuGraphLaunch

CUresult cuGraphExecHostNodeSetParams ( CUgraphExec hGraphExec, CUgraphNode hNode, const CUDA_HOST_NODE_PARAMS* nodeParams )
Sets the parameters for a host node in the given graphExec.
Parameters
hGraphExec
- The executable graph in which to set the specified node
hNode
- Host node from the graph which was used to instantiate graphExec
nodeParams
- The updated parameters to set
Description

Updates the work represented by hNode in hGraphExec as though hNode had contained nodeParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphInstantiate, cuGraphExecKernelNodeSetParamscuGraphExecMemcpyNodeSetParamscuGraphExecMemsetNodeSetParams

CUresult cuGraphExecKernelNodeSetParams ( CUgraphExec hGraphExec, CUgraphNode hNode, const CUDA_KERNEL_NODE_PARAMS* nodeParams )
Sets the parameters for a kernel node in the given graphExec.
Parameters
hGraphExec
- The executable graph in which to set the specified node
hNode
- kernel node from the graph from which graphExec was instantiated
nodeParams
- Updated Parameters to set
Description

Sets the parameters of a kernel node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

hNode 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 only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphAddKernelNode, cuGraphKernelNodeSetParams, cuGraphInstantiate

CUresult cuGraphExecMemcpyNodeSetParams ( CUgraphExec hGraphExec, CUgraphNode hNode, const CUDA_MEMCPY3D* copyParams, CUcontext ctx )
Sets the parameters for a memcpy node in the given graphExec.
Parameters
hGraphExec
- The executable graph in which to set the specified node
hNode
- Memcpy node from the graph which was used to instantiate graphExec
copyParams
- The updated parameters to set
ctx
- Context on which to run the node
Description

Updates the work represented by hNode in hGraphExec as though hNode had contained copyParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

The source and destination memory in copyParams must be allocated from the same contexts as the original source and destination memory. Both the instantiation-time memory operands and the memory operands in copyParams must be 1-dimensional. Zero-length operations are not supported.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Returns CUDA_ERROR_INVALID_VALUE if the memory operands' mappings changed or either the original or new memory operands are multidimensional.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphInstantiate, cuGraphExecKernelNodeSetParamscuGraphExecMemsetNodeSetParamscuGraphExecHostNodeSetParams

CUresult cuGraphExecMemsetNodeSetParams ( CUgraphExec hGraphExec, CUgraphNode hNode, const CUDA_MEMSET_NODE_PARAMS* memsetParams, CUcontext ctx )
Sets the parameters for a memset node in the given graphExec.
Parameters
hGraphExec
- The executable graph in which to set the specified node
hNode
- Memset node from the graph which was used to instantiate graphExec
memsetParams
- The updated parameters to set
ctx
- Context on which to run the node
Description

Updates the work represented by hNode in hGraphExec as though hNode had contained memsetParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

The destination memory in memsetParams must be allocated from the same contexts as the original destination memory. Both the instantiation-time memory operand and the memory operand in memsetParams must be 1-dimensional. Zero-length operations are not supported.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Returns CUDA_ERROR_INVALID_VALUE if the memory operand's mappings changed or either the original or new memory operand are multidimensional.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphInstantiate, cuGraphExecKernelNodeSetParamscuGraphExecMemcpyNodeSetParamscuGraphExecHostNodeSetParams

CUresult cuGraphExecUpdate ( CUgraphExec hGraphExec, CUgraph hGraph, CUgraphNode* hErrorNode_out, CUgraphExecUpdateResult* updateResult_out )
Check whether an executable graph can be updated with a graph and perform the update if possible.
Parameters
hGraphExec
The instantiated graph to be updated
hGraph
The graph containing the updated parameters
hErrorNode_out
The node which caused the permissibility check to forbid the update, if any
updateResult_out
Whether the graph update was permitted. If was forbidden, the reason why
Description

Updates the node parameters in the instantiated graph specified by hGraphExec with the node parameters in a topologically identical graph specified by hGraph.

Limitations:

  • Kernel nodes:
  • Memset and memcpy nodes:
    • The CUDA device(s) to which the operand(s) was allocated/mapped cannot change.

    • The source/destination memory must be allocated from the same contexts as the original source/destination memory.

    • Only 1D memsets can be changed.

  • Additional memcpy node restrictions:
    • Changing either the source or destination memory type(i.e. CU_MEMORYTYPE_DEVICE, CU_MEMORYTYPE_ARRAY, etc.) is not supported.

Note: The API may add further restrictions in future releases. The return code should always be checked.

Some node types are not currently supported:

  • Empty graph nodes(CU_GRAPH_NODE_TYPE_EMPTY)

  • Child graphs(CU_GRAPH_NODE_TYPE_GRAPH).

cuGraphExecUpdate sets updateResult_out to CU_GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED under the following conditions:

  • The count of nodes directly in hGraphExec and hGraph differ, in which case hErrorNode_out is NULL.

  • A node is deleted in hGraph but not not its pair from hGraphExec, in which case hErrorNode_out is NULL.

  • A node is deleted in hGraphExec but not its pair from hGraph, in which case hErrorNode_out is the pairless node from hGraph.

  • The dependent nodes of a pair differ, in which case hErrorNode_out is the node from hGraph.

cuGraphExecUpdate sets updateResult_out to:

  • CU_GRAPH_EXEC_UPDATE_ERROR if passed an invalid value.

  • CU_GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED if the graph topology changed

  • CU_GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED if the type of a node changed, in which case hErrorNode_out is set to the node from hGraph.

  • CU_GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED if the func field of a kernel changed, in which case hErrorNode_out is set to the node from hGraph

  • CU_GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED if any parameters to a node changed in a way that is not supported, in which case hErrorNode_out is set to the node from hGraph.

  • CU_GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED if something about a node is unsupported, like the node's type or configuration, in which case hErrorNode_out is set to the node from hGraph

If updateResult_out isn't set in one of the situations described above, the update check passes and cuGraphExecUpdate updates hGraphExec to match the contents of hGraph. If an error happens during the update, updateResult_out will be set to CU_GRAPH_EXEC_UPDATE_ERROR; otherwise, updateResult_out is set to CU_GRAPH_EXEC_UPDATE_SUCCESS.

cuGraphExecUpdate returns CUDA_SUCCESS when the updated was performed successfully. It returns CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE if the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphInstantiate,

CUresult cuGraphGetEdges ( CUgraph hGraph, CUgraphNode* from, CUgraphNode* to, size_t* numEdges )
Returns a graph's dependency edges.
Parameters
hGraph
- Graph to get the edges from
from
- Location to return edge endpoints
to
- Location to return edge endpoints
numEdges
- See description
Description

Returns a list of hGraph'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.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphGetNodes, cuGraphGetRootNodes, cuGraphAddDependencies, cuGraphRemoveDependencies, cuGraphNodeGetDependencies, cuGraphNodeGetDependentNodes

CUresult cuGraphGetNodes ( CUgraph hGraph, CUgraphNode* nodes, size_t* numNodes )
Returns a graph's nodes.
Parameters
hGraph
- Graph to query
nodes
- Pointer to return the nodes
numNodes
- See description
Description

Returns a list of hGraph'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.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphCreate, cuGraphGetRootNodes, cuGraphGetEdges, cuGraphNodeGetType, cuGraphNodeGetDependencies, cuGraphNodeGetDependentNodes

CUresult cuGraphGetRootNodes ( CUgraph hGraph, CUgraphNode* rootNodes, size_t* numRootNodes )
Returns a graph's root nodes.
Parameters
hGraph
- Graph to query
rootNodes
- Pointer to return the root nodes
numRootNodes
- See description
Description

Returns a list of hGraph's root nodes. rootNodes may be NULL, in which case this function will return the number of root nodes in numRootNodes. Otherwise, numRootNodes entries will be filled in. If numRootNodes is higher than the actual number of root nodes, the remaining entries in rootNodes will be set to NULL, and the number of nodes actually obtained will be returned in numRootNodes.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphCreate, cuGraphGetNodes, cuGraphGetEdges, cuGraphNodeGetType, cuGraphNodeGetDependencies, cuGraphNodeGetDependentNodes

CUresult cuGraphHostNodeGetParams ( CUgraphNode hNode, CUDA_HOST_NODE_PARAMS* nodeParams )
Returns a host node's parameters.
Parameters
hNode
- Node to get the parameters for
nodeParams
- Pointer to return the parameters
Description

Returns the parameters of host node hNode in nodeParams.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuLaunchHostFunc, cuGraphAddHostNode, cuGraphHostNodeSetParams

CUresult cuGraphHostNodeSetParams ( CUgraphNode hNode, const CUDA_HOST_NODE_PARAMS* nodeParams )
Sets a host node's parameters.
Parameters
hNode
- Node to set the parameters for
nodeParams
- Parameters to copy
Description

Sets the parameters of host node hNode to nodeParams.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuLaunchHostFunc, cuGraphAddHostNode, cuGraphHostNodeGetParams

CUresult cuGraphInstantiate ( CUgraphExec* phGraphExec, CUgraph hGraph, CUgraphNode* phErrorNode, char* logBuffer, size_t bufferSize )
Creates an executable graph from a graph.
Parameters
phGraphExec
- Returns instantiated graph
hGraph
- Graph to instantiate
phErrorNode
- In case of an instantiation error, this may be modified to indicate a node contributing to the error
logBuffer
- A character buffer to store diagnostic messages
bufferSize
- Size of the log buffer in bytes
Description

Instantiates hGraph 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 graphExec.

If there are any errors, diagnostic information may be returned in errorNode and logBuffer. 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.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphCreate, cuGraphLaunch, cuGraphExecDestroy

CUresult cuGraphKernelNodeCopyAttributes ( CUgraphNode dst, CUgraphNode src )
Copies attributes from source node to destination node.
Parameters
dst
Destination node
src
Source node For list of attributes see CUkernelNodeAttrID
Description

Copies attributes from source node src to destination node dst. Both node must have the same context.

Note:

Note that this function may also return error codes from previous, asynchronous launches.

See also:

CUaccessPolicyWindow

CUresult cuGraphKernelNodeGetAttribute ( CUgraphNode hNode, CUkernelNodeAttrID attr, CUkernelNodeAttrValue* value_out )
Queries node attribute.
Parameters
hNode
attr
value_out
Description

Queries attribute attr from node hNode and stores it in corresponding member of value_out.

Note:

Note that this function may also return error codes from previous, asynchronous launches.

See also:

CUaccessPolicyWindow

CUresult cuGraphKernelNodeGetParams ( CUgraphNode hNode, CUDA_KERNEL_NODE_PARAMS* nodeParams )
Returns a kernel node's parameters.
Parameters
hNode
- Node to get the parameters for
nodeParams
- Pointer to return the parameters
Description

Returns the parameters of kernel node hNode in nodeParams. The kernelParams or extra array returned in nodeParams, 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 cuGraphKernelNodeSetParams 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.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuLaunchKernel, cuGraphAddKernelNode, cuGraphKernelNodeSetParams

CUresult cuGraphKernelNodeSetAttribute ( CUgraphNode hNode, CUkernelNodeAttrID attr, const CUkernelNodeAttrValue* value )
Sets node attribute.
Parameters
hNode
attr
value
Description

Sets attribute attr on node hNode from corresponding attribute of value.

Note:

Note that this function may also return error codes from previous, asynchronous launches.

See also:

CUaccessPolicyWindow

CUresult cuGraphKernelNodeSetParams ( CUgraphNode hNode, const CUDA_KERNEL_NODE_PARAMS* nodeParams )
Sets a kernel node's parameters.
Parameters
hNode
- Node to set the parameters for
nodeParams
- Parameters to copy
Description

Sets the parameters of kernel node hNode to nodeParams.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuLaunchKernel, cuGraphAddKernelNode, cuGraphKernelNodeGetParams

CUresult cuGraphLaunch ( CUgraphExec hGraphExec, CUstream hStream )
Launches an executable graph in a stream.
Parameters
hGraphExec
- Executable graph to launch
hStream
- Stream in which to launch the graph
Description

Executes hGraphExec in hStream. Only one instance of hGraphExec may be executing at a time. Each launch is ordered behind both any previous work in hStream and any previous launches of hGraphExec. To execute a graph concurrently, it must be instantiated multiple times into multiple executable graphs.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphInstantiate, cuGraphExecDestroy

CUresult cuGraphMemcpyNodeGetParams ( CUgraphNode hNode, CUDA_MEMCPY3D* nodeParams )
Returns a memcpy node's parameters.
Parameters
hNode
- Node to get the parameters for
nodeParams
- Pointer to return the parameters
Description

Returns the parameters of memcpy node hNode in nodeParams.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuMemcpy3D, cuGraphAddMemcpyNode, cuGraphMemcpyNodeSetParams

CUresult cuGraphMemcpyNodeSetParams ( CUgraphNode hNode, const CUDA_MEMCPY3D* nodeParams )
Sets a memcpy node's parameters.
Parameters
hNode
- Node to set the parameters for
nodeParams
- Parameters to copy
Description

Sets the parameters of memcpy node hNode to nodeParams.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuMemcpy3D, cuGraphAddMemcpyNode, cuGraphMemcpyNodeGetParams

CUresult cuGraphMemsetNodeGetParams ( CUgraphNode hNode, CUDA_MEMSET_NODE_PARAMS* nodeParams )
Returns a memset node's parameters.
Parameters
hNode
- Node to get the parameters for
nodeParams
- Pointer to return the parameters
Description

Returns the parameters of memset node hNode in nodeParams.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuMemsetD2D32, cuGraphAddMemsetNode, cuGraphMemsetNodeSetParams

CUresult cuGraphMemsetNodeSetParams ( CUgraphNode hNode, const CUDA_MEMSET_NODE_PARAMS* nodeParams )
Sets a memset node's parameters.
Parameters
hNode
- Node to set the parameters for
nodeParams
- Parameters to copy
Description

Sets the parameters of memset node hNode to nodeParams.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuMemsetD2D32, cuGraphAddMemsetNode, cuGraphMemsetNodeGetParams

CUresult cuGraphNodeFindInClone ( CUgraphNode* phNode, CUgraphNode hOriginalNode, CUgraph hClonedGraph )
Finds a cloned version of a node.
Parameters
phNode
- Returns handle to the cloned node
hOriginalNode
- Handle to the original node
hClonedGraph
- Cloned graph to query
Description

This function returns the node in hClonedGraph corresponding to hOriginalNode in the original graph.

hClonedGraph must have been cloned from hOriginalGraph via cuGraphClone. hOriginalNode must have been in hOriginalGraph at the time of the call to cuGraphClone, and the corresponding cloned node in hClonedGraph must not have been removed. The cloned node is then returned via phClonedNode.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphClone

CUresult cuGraphNodeGetDependencies ( CUgraphNode hNode, CUgraphNode* dependencies, size_t* numDependencies )
Returns a node's dependencies.
Parameters
hNode
- Node to query
dependencies
- Pointer to return the dependencies
numDependencies
- See description
Description

Returns a list of node's dependencies. dependencies may be NULL, in which case this function will return the number of dependencies in numDependencies. Otherwise, numDependencies entries will be filled in. If numDependencies is higher than the actual number of dependencies, the remaining entries in dependencies will be set to NULL, and the number of nodes actually obtained will be returned in numDependencies.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphNodeGetDependentNodes, cuGraphGetNodes, cuGraphGetRootNodes, cuGraphGetEdges, cuGraphAddDependencies, cuGraphRemoveDependencies

CUresult cuGraphNodeGetDependentNodes ( CUgraphNode hNode, CUgraphNode* dependentNodes, size_t* numDependentNodes )
Returns a node's dependent nodes.
Parameters
hNode
- Node to query
dependentNodes
- Pointer to return the dependent nodes
numDependentNodes
- See description
Description

Returns a list of node's dependent nodes. dependentNodes may be NULL, in which case this function will return the number of dependent nodes in numDependentNodes. Otherwise, numDependentNodes entries will be filled in. If numDependentNodes is higher than the actual number of dependent nodes, the remaining entries in dependentNodes will be set to NULL, and the number of nodes actually obtained will be returned in numDependentNodes.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphNodeGetDependencies, cuGraphGetNodes, cuGraphGetRootNodes, cuGraphGetEdges, cuGraphAddDependencies, cuGraphRemoveDependencies

CUresult cuGraphNodeGetType ( CUgraphNode hNode, CUgraphNodeType* type )
Returns a node's type.
Parameters
hNode
- Node to query
type
- Pointer to return the node type
Description

Returns the node type of hNode in type.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphGetNodes, cuGraphGetRootNodes, cuGraphChildGraphNodeGetGraph, cuGraphKernelNodeGetParams, cuGraphKernelNodeSetParams, cuGraphHostNodeGetParams, cuGraphHostNodeSetParams, cuGraphMemcpyNodeGetParams, cuGraphMemcpyNodeSetParams, cuGraphMemsetNodeGetParams, cuGraphMemsetNodeSetParams

CUresult cuGraphRemoveDependencies ( CUgraph hGraph, const CUgraphNode* from, const CUgraphNode* to, size_t numDependencies )
Removes dependency edges from a graph.
Parameters
hGraph
- 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
Description

The number of dependencies to be removed is defined by numDependencies. Elements in from and to at corresponding indices define a dependency. Each node in from and to must belong to hGraph.

If numDependencies is 0, elements in from and to will be ignored. Specifying a non-existing dependency will return an error.

Note:
  • Graph objects are not threadsafe. More here.

  • Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuGraphAddDependencies, cuGraphGetEdges, cuGraphNodeGetDependencies, cuGraphNodeGetDependentNodes