|
|
@@ -2,7 +2,7 @@
|
|
|
*
|
|
|
* Copyright (C) 2010-2017 CNRS
|
|
|
* Copyright (C) 2011-2013,2017 Inria
|
|
|
- * Copyright (C) 2009-2011,2013-2017 Université de Bordeaux
|
|
|
+ * Copyright (C) 2009-2011,2013-2018 Université de Bordeaux
|
|
|
*
|
|
|
* StarPU is free software; you can redistribute it and/or modify
|
|
|
* it under the terms of the GNU Lesser General Public License as published by
|
|
|
@@ -501,7 +501,37 @@ each task, only the MPI node which owns the data being written to (here,
|
|
|
<c>data_handles[x][y]</c>) will actually run the task. The other MPI nodes will
|
|
|
automatically send the required data.
|
|
|
|
|
|
-This can be a concern with a growing number of nodes. To avoid this, the
|
|
|
+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
|
|
|
+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
|
|
|
+valid task structure, others will return <c>NULL</c>. That node must submit that task.
|
|
|
+All nodes then need to call the function starpu_mpi_task_post_build() -- with the same
|
|
|
+list of arguments as starpu_mpi_task_build() -- to post all the
|
|
|
+necessary data communications.
|
|
|
+
|
|
|
+\code{.c}
|
|
|
+struct starpu_task *task;
|
|
|
+task = starpu_mpi_task_build(MPI_COMM_WORLD, &cl,
|
|
|
+ STARPU_RW, data_handles[0],
|
|
|
+ STARPU_R, data_handles[1],
|
|
|
+ 0);
|
|
|
+if (task) starpu_task_submit(task);
|
|
|
+starpu_mpi_task_post_build(MPI_COMM_WORLD, &cl,
|
|
|
+ STARPU_RW, data_handles[0],
|
|
|
+ STARPU_R, data_handles[1],
|
|
|
+ 0);
|
|
|
+\endcode
|
|
|
+
|
|
|
+\section MPIInsertPruning Pruning MPI task insertion
|
|
|
+
|
|
|
+Making all MPI nodes process the whole graph can be a concern with a growing
|
|
|
+number of nodes. To avoid this, the
|
|
|
application can prune the task for loops according to the data distribution,
|
|
|
so as to only submit tasks on nodes which have to care about them (either to
|
|
|
execute them, or to send the required data).
|
|
|
@@ -554,33 +584,6 @@ 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
|
|
|
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
|
|
|
-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
|
|
|
-valid task structure, others will return <c>NULL</c>. That node must submit that task.
|
|
|
-All nodes then need to call the function starpu_mpi_task_post_build() -- with the same
|
|
|
-list of arguments as starpu_mpi_task_build() -- to post all the
|
|
|
-necessary data communications.
|
|
|
-
|
|
|
-\code{.c}
|
|
|
-struct starpu_task *task;
|
|
|
-task = starpu_mpi_task_build(MPI_COMM_WORLD, &cl,
|
|
|
- STARPU_RW, data_handles[0],
|
|
|
- STARPU_R, data_handles[1],
|
|
|
- 0);
|
|
|
-if (task) starpu_task_submit(task);
|
|
|
-starpu_mpi_task_post_build(MPI_COMM_WORLD, &cl,
|
|
|
- STARPU_RW, data_handles[0],
|
|
|
- STARPU_R, data_handles[1],
|
|
|
- 0);
|
|
|
-\endcode
|
|
|
-
|
|
|
\section MPITemporaryData Temporary Data
|
|
|
|
|
|
To be able to use starpu_mpi_task_insert(), one has to call
|
