Per the developer conference, let's be a little nicer during MPI_Finalize and ease up on the cpu by inserting usleep into the loop over opal_progress while waiting for the RTE barrier to complete. This is a non-performant area of the code, and while most codes may call finalize at close-to-similar times, there are some that may choose to have one or more procs continue to perform some work prior to finalizing.

So save a little power while we are waiting.

cmr=v1.8.2:reviewer=jladd:subject=save power during finalize

This commit was SVN r32077.

ompi/mca/rte/rte.h

@@ -2,6 +2,7 @@
  * Copyright (c) 2012      Los Alamos National Security, LLC.  All rights reserved.
  * Copyright (c) 2013      Mellanox Technologies, Inc.
  *                         All rights reserved.
+ * Copyright (c) 2014      Intel, Inc. All rights reserved.
  *
  * $COPYRIGHT$
  * 
@@ -250,6 +251,18 @@ OMPI_DECLSPEC extern mca_base_framework_t ompi_rte_base_framework;
         }                                                               \
     }while(0);
 
+#define OMPI_LAZY_WAIT_FOR_COMPLETION(flg)                              \
+    do {                                                                \
+        opal_output_verbose(1, ompi_rte_base_framework.framework_output, \
+                            "%s lazy waiting on RTE event at %s:%d",    \
+                            OMPI_NAME_PRINT(OMPI_PROC_MY_NAME),         \
+                            __FILE__, __LINE__);                        \
+        while ((flg)) {                                                 \
+            opal_progress();                                            \
+            usleep(100);                                                \
+        }                                                               \
+    }while(0);
+
 typedef struct {
     opal_list_item_t super;
     ompi_process_name_t name;

ompi/runtime/ompi_mpi_finalize.c

@@ -217,7 +217,7 @@ int ompi_mpi_finalize(void)
     }
 
     /* wait for barrier to complete */
-    OMPI_WAIT_FOR_COMPLETION(coll->active);
+    OMPI_LAZY_WAIT_FOR_COMPLETION(coll->active);
     OBJ_RELEASE(coll);
 
     /* check for timing request - get stop time and report elapsed