|
@@ -542,6 +542,12 @@ Here we have disabled the kernel function call to skip the actual computation
|
|
|
time and only keep submission time, and we have asked StarPU to fake running on
|
|
time and only keep submission time, and we have asked StarPU to fake running on
|
|
|
MPI node 2 out of 1024 nodes.
|
|
MPI node 2 out of 1024 nodes.
|
|
|
|
|
|
|
|
|
|
+To tune the placement of tasks among MPI nodes, one can use
|
|
|
|
|
+STARPU_EXECUTE_ON_NODE or STARPU_EXECUTE_ON_DATA to specify an explicit
|
|
|
|
|
+node, or the node of a given data (e.g. one of the parameters), or use
|
|
|
|
|
+starpu_mpi_node_selection_register_policy and STARPU_NODE_SELECTION_POLICY
|
|
|
|
|
+to provide a dynamic policy.
|
|
|
|
|
+
|
|
|
A function starpu_mpi_task_build() is also provided with the aim to
|
|
A function starpu_mpi_task_build() is also provided with the aim to
|
|
|
only construct the task structure. All MPI nodes need to call the
|
|
only construct the task structure. All MPI nodes need to call the
|
|
|
function, only the node which is to execute the task will return a
|
|
function, only the node which is to execute the task will return a
|
