cuda_sys

Function cudaGraphExecUpdate

Source 
pub unsafe extern "C" fn cudaGraphExecUpdate(
    hGraphExec: cudaGraphExec_t,
    hGraph: cudaGraph_t,
    resultInfo: *mut cudaGraphExecUpdateResultInfo,
) -> cudaError_t
Expand description

\brief Check whether an executable graph can be updated with a graph and perform the update if possible

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

Limitations:

  • Kernel nodes:
    • The owning context of the function cannot change.
    • A node whose function originally did not use CUDA dynamic parallelism cannot be updated to a function which uses CDP.
    • A node whose function originally did not make device-side update calls cannot be updated to a function which makes device-side update calls.
    • A cooperative node cannot be updated to a non-cooperative node, and vice-versa.
    • If the graph was instantiated with cudaGraphInstantiateFlagUseNodePriority, the priority attribute cannot change. Equality is checked on the originally requested priority values, before they are clamped to the device’s supported range.
    • If \p hGraphExec was not instantiated for device launch, a node whose function originally did not use device-side cudaGraphLaunch() cannot be updated to a function which uses device-side cudaGraphLaunch() unless the node resides on the same device as nodes which contained such calls at instantiate-time. If no such calls were present at instantiation, these updates cannot be performed at all.
    • Neither \p hGraph nor \p hGraphExec may contain device-updatable 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.
    • For 2d memsets, only address and assinged value may be updated.
    • For 1d memsets, updating dimensions is also allowed, but may fail if the resulting operation doesn’t map onto the work resources already allocated for the node.
  • Additional memcpy node restrictions:
    • Changing either the source or destination memory type(i.e. CU_MEMORYTYPE_DEVICE, CU_MEMORYTYPE_ARRAY, etc.) is not supported.
  • Conditional nodes:
    • Changing node parameters is not supported.
    • Changeing parameters of nodes within the conditional body graph is subject to the rules above.
    • Conditional handle flags and default values are updated as part of the graph update.

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

cudaGraphExecUpdate sets the result member of \p resultInfo to cudaGraphExecUpdateErrorTopologyChanged under the following conditions:

  • The count of nodes directly in \p hGraphExec and \p hGraph differ, in which case resultInfo->errorNode is set to NULL.
  • \p hGraph has more exit nodes than \p hGraph, in which case resultInfo->errorNode is set to one of the exit nodes in hGraph.
  • A node in \p hGraph has a different number of dependencies than the node from \p hGraphExec it is paired with, in which case resultInfo->errorNode is set to the node from \p hGraph.
  • A node in \p hGraph has a dependency that does not match with the corresponding dependency of the paired node from \p hGraphExec. resultInfo->errorNode will be set to the node from \p hGraph. resultInfo->errorFromNode will be set to the mismatched dependency. The dependencies are paired based on edge order and a dependency does not match when the nodes are already paired based on other edges examined in the graph.

cudaGraphExecUpdate sets \p the result member of \p resultInfo to:

  • cudaGraphExecUpdateError if passed an invalid value.
  • cudaGraphExecUpdateErrorTopologyChanged if the graph topology changed
  • cudaGraphExecUpdateErrorNodeTypeChanged if the type of a node changed, in which case \p hErrorNode_out is set to the node from \p hGraph.
  • cudaGraphExecUpdateErrorFunctionChanged if the function of a kernel node changed (CUDA driver < 11.2)
  • cudaGraphExecUpdateErrorUnsupportedFunctionChange if the func field of a kernel changed in an unsupported way(see note above), in which case \p hErrorNode_out is set to the node from \p hGraph
  • cudaGraphExecUpdateErrorParametersChanged if any parameters to a node changed in a way that is not supported, in which case \p hErrorNode_out is set to the node from \p hGraph
  • cudaGraphExecUpdateErrorAttributesChanged if any attributes of a node changed in a way that is not supported, in which case \p hErrorNode_out is set to the node from \p hGraph
  • cudaGraphExecUpdateErrorNotSupported if something about a node is unsupported, like the node’s type or configuration, in which case \p hErrorNode_out is set to the node from \p hGraph

If the update fails for a reason not listed above, the result member of \p resultInfo will be set to cudaGraphExecUpdateError. If the update succeeds, the result member will be set to cudaGraphExecUpdateSuccess.

cudaGraphExecUpdate returns cudaSuccess when the updated was performed successfully. It returns cudaErrorGraphExecUpdateFailure if the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.

\param hGraphExec The instantiated graph to be updated \param hGraph The graph containing the updated parameters \param resultInfo the error info structure

\return ::cudaSuccess, ::cudaErrorGraphExecUpdateFailure, \note_graph_thread_safety \notefnerr \note_init_rt \note_callback

\sa ::cudaGraphInstantiate