diff --git a/configure.ac b/configure.ac
index 3abba020e3..6348daedb9 100644
--- a/configure.ac
+++ b/configure.ac
@@ -3,7 +3,7 @@
 # Copyright (c) 2004-2009 The Trustees of Indiana University and Indiana
 #                         University Research and Technology
 #                         Corporation.  All rights reserved.
-# Copyright (c) 2004-2014 The University of Tennessee and The University
+# Copyright (c) 2004-2015 The University of Tennessee and The University
 #                         of Tennessee Research Foundation.  All rights
 #                         reserved.
 # Copyright (c) 2004-2007 High Performance Computing Center Stuttgart,
@@ -1379,6 +1379,7 @@ AC_CONFIG_FILES([
     test/support/Makefile
     test/threads/Makefile
     test/util/Makefile
+    test/monitoring/Makefile
 ])
 AC_CONFIG_FILES([contrib/dist/mofed/debian/rules],
                 [chmod +x contrib/dist/mofed/debian/rules])
diff --git a/ompi/mca/pml/monitoring/Makefile.am b/ompi/mca/pml/monitoring/Makefile.am
new file mode 100644
index 0000000000..504a2c6fd4
--- /dev/null
+++ b/ompi/mca/pml/monitoring/Makefile.am
@@ -0,0 +1,41 @@
+#
+# Copyright (c) 2013-2015 The University of Tennessee and The University
+#                         of Tennessee Research Foundation.  All rights
+#                         reserved.
+# Copyright (c) 2013-2015 Inria.  All rights reserved.
+# $COPYRIGHT$
+#
+# Additional copyrights may follow
+#
+# $HEADER$
+#
+
+monitoring_sources  = \
+	pml_monitoring.c \
+	pml_monitoring.h \
+	pml_monitoring_comm.c \
+	pml_monitoring_comm.h \
+	pml_monitoring_component.c \
+	pml_monitoring_component.h \
+	pml_monitoring_hdr.h \
+	pml_monitoring_iprobe.c \
+	pml_monitoring_irecv.c \
+	pml_monitoring_isend.c \
+	pml_monitoring_start.c
+
+if MCA_BUILD_ompi_pml_monitoring_DSO
+component_noinst =
+component_install = mca_pml_monitoring.la
+else
+component_noinst = libmca_pml_monitoring.la
+component_install =
+endif
+
+mcacomponentdir = $(pkglibdir)
+mcacomponent_LTLIBRARIES = $(component_install)
+mca_pml_monitoring_la_SOURCES = $(monitoring_sources)
+mca_pml_monitoring_la_LDFLAGS = -module -avoid-version
+
+noinst_LTLIBRARIES = $(component_noinst)
+libmca_pml_monitoring_la_SOURCES = $(monitoring_sources)
+libmca_pml_monitoring_la_LDFLAGS = -module -avoid-version
diff --git a/ompi/mca/pml/monitoring/README b/ompi/mca/pml/monitoring/README
new file mode 100644
index 0000000000..8361027d65
--- /dev/null
+++ b/ompi/mca/pml/monitoring/README
@@ -0,0 +1,181 @@
+
+ Copyright (c) 2013-2015 The University of Tennessee and The University
+                         of Tennessee Research Foundation.  All rights
+                         reserved.
+ Copyright (c) 2013-2015 Inria.  All rights reserved.
+ $COPYRIGHT$
+
+ Additional copyrights may follow
+
+ $HEADER$
+
+===========================================================================
+
+Low level communication monitoring interface in Open MPI
+
+Introduction
+------------
+This interface traces and monitors all messages sent by MPI before they go to the
+communication channels. At that levels all communication are point-to-point communications:
+collectives are already decomposed in send and receive calls.
+
+The monitoring is stored internally by each process and output on stderr at the end of the
+application (during MPI_Finalize()).
+
+
+Enabling the monitoring
+-----------------------
+To enable the monitoring add  --mca pml_monitoring_enable x to the mpirun command line.
+If x = 1 it monitors internal and external tags indifferently and aggregate everything.
+If x = 2 it monitors internal tags and external tags separately.
+If x = 0 the monitoring is disabled.
+Other value of x are not supported.
+
+Internal tags are tags < 0. They are used to tag send and receive coming from
+collective operations or from protocol communications
+
+External tags are tags >=0. They are used by the application in point-to-point communication.
+
+Therefore, distinguishing external and internal tags help to distinguish between point-to-point
+and other communication (mainly collectives).
+
+Output format
+-------------
+The output of the monitoring looks like (with --mca pml_monitoring_enable 2):
+I	0	1	108 bytes	27 msgs sent
+E	0	1	1012 bytes	30 msgs sent
+E	0	2	23052 bytes	61 msgs sent
+I	1	2	104 bytes	26 msgs sent
+I	1	3	208 bytes	52 msgs sent
+E	1	0	860 bytes	24 msgs sent
+E	1	3	2552 bytes	56 msgs sent
+I	2	3	104 bytes	26 msgs sent
+E	2	0	22804 bytes	49 msgs sent
+E	2	3	860 bytes	24 msgs sent
+I	3	0	104 bytes	26 msgs sent
+I	3	1	204 bytes	51 msgs sent
+E	3	1	2304 bytes	44 msgs sent
+E	3	2	860 bytes	24 msgs sent
+
+Where:
+  - the first column distinguishes internal (I)  and external (E) tags.
+  - the second column is the sender rank
+  - the third column is the receiver rank
+  - the fourth column is the number of bytes sent
+  - the last column is the number of messages.
+
+In this example process 0 as sent 27 messages to process 1 using point-to-point call
+for 108 bytes and 30 messages with collectives and protocol related communication
+for 1012 bytes to process 1.
+
+If the monitoring was called with --mca pml_monitoring_enable 1 everything is aggregated
+under the internal tags. With te above example, you have:
+I	0	1	1120 bytes	57 msgs sent
+I	0	2	23052 bytes	61 msgs sent
+I	1	0	860 bytes	24 msgs sent
+I	1	2	104 bytes	26 msgs sent
+I	1	3	2760 bytes	108 msgs sent
+I	2	0	22804 bytes	49 msgs sent
+I	2	3	964 bytes	50 msgs sent
+I	3	0	104 bytes	26 msgs sent
+I	3	1	2508 bytes	95 msgs sent
+I	3	2	860 bytes	24 msgs sent
+
+Monitoring phases
+-----------------
+If one wants to monitor phases of the application, it is possible to flush the monitoring
+at the application level. In this case all the monitoring since the last flush is stored
+by every process in a file.
+
+An example of how to flush such monitoring is given in test/monitoring/monitoring_test.c
+
+Moreover, all the different flushed phased are aggregated at runtime and output at the end
+of the application as described above.
+
+Example
+-------
+A working example is given in test/monitoring/monitoring_test.c
+It features, MPI_COMM_WORLD monitoring , sub-communicator monitoring, collective and
+point-to-point communication monitoring and  phases monitoring
+
+To compile:
+> make monitoring_test
+
+Helper scripts
+--------------
+Two perl scripts are provided in test/monitoring
+- aggregate_profile.pl is for aggregating monitoring phases of different processes
+  This script aggregates the profiles generated by the flush_monitoring function.
+  The files need to be in in given format: name_<phase_id>_<process_id>
+  They are then aggregated by phases.
+  If one needs the profile of all the phases he can concatenate the different files,
+  or use the output of the monitoring system done at MPI_Finalize
+  in the example it should be call as:
+   ./aggregate_profile.pl prof/phase to generate
+   prof/phase_1.prof
+   prof/phase_2.prof
+
+- profile2mat.pl is for transforming a the monitoring output into a communication matrix.
+   Take a profile file and aggregates all the recorded communicator into matrices.
+   It generated a matrices for the number of messages, (msg),
+   for the total bytes transmitted (size) and
+   the average number of bytes per messages (avg)
+
+   The output matrix is symmetric
+
+Do not forget to enable the execution right to these scripts.
+
+For instance, the provided examples store phases output in ./prof
+
+If you type:
+> mpirun -np 4 --mca pml_monitoring_enable 2 ./monitoring_test
+you should have the following output
+Proc 3 flushing monitoring to: ./prof/phase_1_3.prof
+Proc 0 flushing monitoring to: ./prof/phase_1_0.prof
+Proc 2 flushing monitoring to: ./prof/phase_1_2.prof
+Proc 1 flushing monitoring to: ./prof/phase_1_1.prof
+Proc 1 flushing monitoring to: ./prof/phase_2_1.prof
+Proc 3 flushing monitoring to: ./prof/phase_2_3.prof
+Proc 0 flushing monitoring to: ./prof/phase_2_0.prof
+Proc 2 flushing monitoring to: ./prof/phase_2_2.prof
+I	2	3	104 bytes	26 msgs sent
+E	2	0	22804 bytes	49 msgs sent
+E	2	3	860 bytes	24 msgs sent
+I	3	0	104 bytes	26 msgs sent
+I	3	1	204 bytes	51 msgs sent
+E	3	1	2304 bytes	44 msgs sent
+E	3	2	860 bytes	24 msgs sent
+I	0	1	108 bytes	27 msgs sent
+E	0	1	1012 bytes	30 msgs sent
+E	0	2	23052 bytes	61 msgs sent
+I	1	2	104 bytes	26 msgs sent
+I	1	3	208 bytes	52 msgs sent
+E	1	0	860 bytes	24 msgs sent
+E	1	3	2552 bytes	56 msgs sent
+
+you can parse the phases with:
+> /aggregate_profile.pl prof/phase
+Building prof/phase_1.prof
+Building prof/phase_2.prof
+
+And you can build the different communication matrices of phase 1 with:
+> ./profile2mat.pl prof/phase_1.prof
+prof/phase_1.prof -> all
+prof/phase_1_size_all.mat
+prof/phase_1_msg_all.mat
+prof/phase_1_avg_all.mat
+
+prof/phase_1.prof -> external
+prof/phase_1_size_external.mat
+prof/phase_1_msg_external.mat
+prof/phase_1_avg_external.mat
+
+prof/phase_1.prof -> internal
+prof/phase_1_size_internal.mat
+prof/phase_1_msg_internal.mat
+prof/phase_1_avg_internal.mat
+
+Credit
+------
+Designed by George Bosilca <bosilca@icl.utk.edu> and
+Emmanuel Jeannot <emmanuel.jeannot@inria.fr>
diff --git a/ompi/mca/pml/monitoring/pml_monitoring.c b/ompi/mca/pml/monitoring/pml_monitoring.c
new file mode 100644
index 0000000000..672a5ad09f
--- /dev/null
+++ b/ompi/mca/pml/monitoring/pml_monitoring.c
@@ -0,0 +1,237 @@
+/*
+ * Copyright (c) 2013-2015 The University of Tennessee and The University
+ *                         of Tennessee Research Foundation.  All rights
+ *                         reserved.
+ * Copyright (c) 2013-2015 Inria.  All rights reserved.
+ * $COPYRIGHT$
+ *
+ * Additional copyrights may follow
+ *
+ * $HEADER$
+ */
+
+#include <ompi_config.h>
+#include <pml_monitoring.h>
+#include "opal/class/opal_hash_table.h"
+typedef struct _transtlator_t{
+  int *ranks;
+  int size;
+} translator_t;
+
+
+void initialize_monitoring( void );
+void monitor_send_data(int world_rank, size_t data_size, int tag);
+void output_monitoring( void );
+void finalize_monitoring( void );
+int filter_monitoring( void ); /* returns 1 if we distinguish positive (point-to-point) and negative (collective and meta messages) tags*/
+int ompi_mca_pml_monitoring_flush(char* filename);
+
+
+MPI_Group group_world;
+
+/* array for stroring monitoring data*/
+size_t *sent_data = NULL;
+int *messages_count = NULL;
+size_t *filtered_sent_data = NULL;
+int *filtered_messages_count = NULL;
+size_t *all_sent_data = NULL;
+int *all_messages_count = NULL;
+size_t *all_filtered_sent_data = NULL;
+int *all_filtered_messages_count = NULL;
+
+int init_done = 0;
+int nbprocs = -1;
+int my_rank = -1;
+opal_hash_table_t *translation_ht = NULL;
+
+
+mca_pml_monitoring_module_t mca_pml_monitoring = {
+    mca_pml_monitoring_add_procs,
+    mca_pml_monitoring_del_procs,
+    mca_pml_monitoring_enable,
+    NULL,
+    mca_pml_monitoring_add_comm,
+    mca_pml_monitoring_del_comm,
+    mca_pml_monitoring_irecv_init,
+    mca_pml_monitoring_irecv,
+    mca_pml_monitoring_recv,
+    mca_pml_monitoring_isend_init,
+    mca_pml_monitoring_isend,
+    mca_pml_monitoring_send,
+    mca_pml_monitoring_iprobe,
+    mca_pml_monitoring_probe,
+    mca_pml_monitoring_start,
+    mca_pml_monitoring_improbe,
+    mca_pml_monitoring_mprobe,
+    mca_pml_monitoring_imrecv,
+    mca_pml_monitoring_mrecv,
+    mca_pml_monitoring_dump,
+    NULL,
+    65535,
+    INT_MAX
+};
+
+int mca_pml_monitoring_add_procs(struct ompi_proc_t **procs,
+                                 size_t nprocs)
+{
+    /**
+     * Create the monitoring hashtable only for my MPI_COMM_WORLD. We choose
+     * to ignore by now all other processes.
+     */
+    if(NULL == translation_ht) {
+        size_t i;
+        uint64_t key;
+
+        nbprocs = nprocs;
+
+        translation_ht = OBJ_NEW(opal_hash_table_t);
+        opal_hash_table_init(translation_ht, 2048);
+
+
+        for( i = 0; i < nprocs; i++ ) {
+            /* rank : ompi_proc_local_proc in procs */
+            if( procs[i] == ompi_proc_local_proc)
+                my_rank = i;
+            key = *((uint64_t*)&(procs[i]->super.proc_name));
+	    /* store the rank (in COMM_WORLD) of the process
+	       with its name (a uniq opal ID) as key  in the hash table*/
+            opal_hash_table_set_value_uint64(translation_ht,
+                                             key,
+                                             (void*)(uintptr_t)i);
+        }
+    }
+    return pml_selected_module.pml_add_procs(procs, nprocs);
+}
+
+
+int mca_pml_monitoring_del_procs(struct ompi_proc_t **procs,
+                                 size_t nprocs)
+{
+    return pml_selected_module.pml_del_procs(procs, nprocs);
+}
+
+int mca_pml_monitoring_dump(struct ompi_communicator_t* comm,
+                            int verbose)
+{
+    return pml_selected_module.pml_dump(comm, verbose);
+}
+
+
+void finalize_monitoring( void ){
+
+    if(filter_monitoring()){
+        free(filtered_sent_data);
+        free(filtered_messages_count);
+    }
+
+    free(sent_data);
+    free(messages_count);
+    opal_hash_table_remove_all( translation_ht );
+    free(translation_ht);
+
+}
+void initialize_monitoring( void ){
+
+    sent_data      = (size_t*)calloc(nbprocs, sizeof(size_t));
+    messages_count = (int*)   calloc(nbprocs, sizeof(int));
+    all_sent_data      = (size_t*)calloc(nbprocs, sizeof(size_t));
+    all_messages_count = (int*)   calloc(nbprocs, sizeof(int));
+
+    if(filter_monitoring()){
+        filtered_sent_data      = (size_t*)calloc(nbprocs, sizeof(size_t));
+        filtered_messages_count = (int*)   calloc(nbprocs, sizeof(int));
+        all_filtered_sent_data      = (size_t*)calloc(nbprocs, sizeof(size_t));
+        all_filtered_messages_count = (int*)   calloc(nbprocs, sizeof(int));
+    }
+
+    init_done = 1;
+}
+
+
+
+void monitor_send_data(int world_rank, size_t data_size, int tag){
+
+    if ( !init_done )
+        initialize_monitoring();
+
+    /* distinguishses positive and negative tags if requested */
+    if((tag<0) && (filter_monitoring())){
+        filtered_sent_data[world_rank] += data_size;
+        filtered_messages_count[world_rank]++;
+    }else{ /* if filtered monitoring is not activated data is aggregated indifferently */
+        sent_data[world_rank] += data_size;
+        messages_count[world_rank]++;
+    }
+    /*printf("%d Send dest = %d(%d:comm_world=%d), size = %ld ajouté dans : %d\n",my_rank, dest_rank, comm->c_my_rank, MPI_COMM_WORLD->c_my_rank, data_size, rank); fflush(stdout);*/
+
+
+}
+
+void output_monitoring( void ){
+    int i;
+    for (i = 0 ; i < nbprocs ; i++) {
+        all_sent_data[i] += sent_data[i];
+        all_messages_count[i] += messages_count[i];
+        if(all_sent_data[i] > 0) {
+            fprintf(stderr, "I\t%d\t%d\t%ld bytes\t%d msgs sent\n", my_rank, i, all_sent_data[i], all_messages_count[i]); fflush(stderr);
+        }
+    }
+
+    if(filter_monitoring()){
+        for (i = 0 ; i < nbprocs ; i++) {
+            all_filtered_sent_data[i] += filtered_sent_data[i];
+            all_filtered_messages_count[i] += filtered_messages_count[i];
+            if(all_filtered_sent_data[i] > 0) {
+                fprintf(stderr, "E\t%d\t%d\t%ld bytes\t%d msgs sent\n", my_rank, i, all_filtered_sent_data[i], all_filtered_messages_count[i]); fflush(stderr);
+            }
+        }
+    }
+}
+
+
+/*
+   Flushes the monitoring into filename
+   Useful for phases (see exmple in test/monitoring)
+*/
+
+int ompi_mca_pml_monitoring_flush(char* filename) {
+  FILE *pf;
+  int i;
+
+
+  pf = fopen(filename, "w");
+
+  if(!pf)
+    return -1;
+
+  fprintf(stderr,"Proc %d flushing monitoring to: %s\n", my_rank, filename);
+
+  for (i = 0 ; i < nbprocs ; i++) {
+    if(sent_data[i] > 0) {
+      fprintf(pf, "I\t%d\t%d\t%ld bytes\t%d msgs sent\n", my_rank, i, sent_data[i], messages_count[i]); fflush(pf);
+      /* aggregate  data in general array*/
+      all_sent_data[i] += sent_data[i];
+      all_messages_count[i] += messages_count[i];
+      /* reset phase array */
+      messages_count[i] = 0;
+      sent_data[i] = 0;
+    }
+  }
+
+  if(filter_monitoring()){
+    for (i = 0 ; i < nbprocs ; i++) {
+      if(filtered_sent_data[i] > 0) {
+    fprintf(pf, "E\t%d\t%d\t%ld bytes\t%d msgs sent\n", my_rank, i, filtered_sent_data[i], filtered_messages_count[i]); fflush(pf);
+      /* aggregate  data in general array*/
+      all_filtered_sent_data[i] += filtered_sent_data[i];
+      all_filtered_messages_count[i] += filtered_messages_count[i];
+      /* reset phase array */
+      filtered_messages_count[i] = 0;
+      filtered_sent_data[i] = 0;
+      }
+    }
+  }
+
+  fclose(pf);
+  return 0;
+}
diff --git a/ompi/mca/pml/monitoring/pml_monitoring.h b/ompi/mca/pml/monitoring/pml_monitoring.h
new file mode 100644
index 0000000000..dbae8e1eee
--- /dev/null
+++ b/ompi/mca/pml/monitoring/pml_monitoring.h
@@ -0,0 +1,141 @@
+/*
+ * Copyright (c) 2013-2015 The University of Tennessee and The University
+ *                         of Tennessee Research Foundation.  All rights
+ *                         reserved.
+ * Copyright (c) 2013-2015 Inria.  All rights reserved.
+ * $COPYRIGHT$
+ *
+ * Additional copyrights may follow
+ *
+ * $HEADER$
+ */
+
+#ifndef MCA_PML_MONITORING_H
+#define MCA_PML_MONITORING_H
+
+BEGIN_C_DECLS
+
+#include <ompi_config.h>
+#include <ompi/communicator/communicator.h>
+#include <ompi/datatype/ompi_datatype.h>
+#include <ompi/mca/pml/pml.h>
+#include <ompi/mca/pml/pml.h>
+
+typedef mca_pml_base_module_t mca_pml_monitoring_module_t;
+
+extern mca_pml_base_component_t pml_selected_component;
+extern mca_pml_base_module_t pml_selected_module;
+extern mca_pml_monitoring_module_t mca_pml_monitoring;
+OMPI_DECLSPEC extern mca_pml_base_component_2_0_0_t mca_pml_monitoring_component;
+
+/*
+ * PML interface functions.
+ */
+
+extern int mca_pml_monitoring_add_comm(struct ompi_communicator_t* comm);
+
+extern int mca_pml_monitoring_del_comm(struct ompi_communicator_t* comm);
+
+extern int mca_pml_monitoring_add_procs(struct ompi_proc_t **procs,
+                                        size_t nprocs);
+
+extern int mca_pml_monitoring_del_procs(struct ompi_proc_t **procs,
+                                        size_t nprocs);
+
+extern int mca_pml_monitoring_enable(bool enable);
+
+extern int mca_pml_monitoring_iprobe(int dst,
+                                     int tag,
+                                     struct ompi_communicator_t* comm,
+                                     int *matched,
+                                     ompi_status_public_t* status );
+
+extern int mca_pml_monitoring_probe(int dst,
+                                    int tag,
+                                    struct ompi_communicator_t* comm,
+                                    ompi_status_public_t* status );
+
+extern int mca_pml_monitoring_improbe(int dst,
+                                      int tag,
+                                      struct ompi_communicator_t* comm,
+                                      int *matched,
+                                      struct ompi_message_t **message,
+                                      ompi_status_public_t* status );
+
+extern int mca_pml_monitoring_mprobe(int dst,
+                                     int tag,
+                                     struct ompi_communicator_t* comm,
+                                     struct ompi_message_t **message,
+                                     ompi_status_public_t* status );
+
+extern int mca_pml_monitoring_isend_init(void *buf,
+                                         size_t count,
+                                         ompi_datatype_t *datatype,
+                                         int dst,
+                                         int tag,
+                                         mca_pml_base_send_mode_t mode,
+                                         struct ompi_communicator_t* comm,
+                                         struct ompi_request_t **request);
+
+extern int mca_pml_monitoring_isend(void *buf,
+                                    size_t count,
+                                    ompi_datatype_t *datatype,
+                                    int dst,
+                                    int tag,
+                                    mca_pml_base_send_mode_t mode,
+                                    struct ompi_communicator_t* comm,
+                                    struct ompi_request_t **request);
+
+extern int mca_pml_monitoring_send(void *buf,
+                                   size_t count,
+                                   ompi_datatype_t *datatype,
+                                   int dst,
+                                   int tag,
+                                   mca_pml_base_send_mode_t mode,
+                                   struct ompi_communicator_t* comm);
+
+extern int mca_pml_monitoring_irecv_init(void *buf,
+                                         size_t count,
+                                         ompi_datatype_t *datatype,
+                                         int src,
+                                         int tag,
+                                         struct ompi_communicator_t* comm,
+                                         struct ompi_request_t **request);
+
+extern int mca_pml_monitoring_irecv(void *buf,
+                                    size_t count,
+                                    ompi_datatype_t *datatype,
+                                    int src,
+                                    int tag,
+                                    struct ompi_communicator_t* comm,
+                                    struct ompi_request_t **request);
+
+extern int mca_pml_monitoring_recv(void *buf,
+                                   size_t count,
+                                   ompi_datatype_t *datatype,
+                                   int src,
+                                   int tag,
+                                   struct ompi_communicator_t* comm,
+                                   ompi_status_public_t* status);
+
+extern int mca_pml_monitoring_imrecv(void *buf,
+                                     size_t count,
+                                     ompi_datatype_t *datatype,
+                                     struct ompi_message_t **message,
+                                     struct ompi_request_t **request);
+
+extern int mca_pml_monitoring_mrecv(void *buf,
+                                    size_t count,
+                                    ompi_datatype_t *datatype,
+                                    struct ompi_message_t **message,
+                                    ompi_status_public_t* status);
+
+extern int mca_pml_monitoring_dump(struct ompi_communicator_t* comm,
+                                   int verbose);
+
+extern int mca_pml_monitoring_start(size_t count,
+                                    ompi_request_t** requests);
+
+END_C_DECLS
+
+#endif  /* MCA_PML_MONITORING_H */
diff --git a/ompi/mca/pml/monitoring/pml_monitoring_comm.c b/ompi/mca/pml/monitoring/pml_monitoring_comm.c
new file mode 100644
index 0000000000..047a15bfd3
--- /dev/null
+++ b/ompi/mca/pml/monitoring/pml_monitoring_comm.c
@@ -0,0 +1,27 @@
+/*
+ * Copyright (c) 2013-2015 The University of Tennessee and The University
+ *                         of Tennessee Research Foundation.  All rights
+ *                         reserved.
+ * Copyright (c) 2013-2015 Inria.  All rights reserved.
+ * $COPYRIGHT$
+ *
+ * Additional copyrights may follow
+ *
+ * $HEADER$
+ */
+
+#include <ompi_config.h>
+#include <pml_monitoring.h>
+
+extern void output_monitoring( void );
+
+
+int mca_pml_monitoring_add_comm(struct ompi_communicator_t* comm)
+{
+    return pml_selected_module.pml_add_comm(comm);
+}
+
+int mca_pml_monitoring_del_comm(struct ompi_communicator_t* comm)
+{
+    return pml_selected_module.pml_del_comm(comm);
+}
diff --git a/ompi/mca/pml/monitoring/pml_monitoring_component.c b/ompi/mca/pml/monitoring/pml_monitoring_component.c
new file mode 100644
index 0000000000..491f5f9f78
--- /dev/null
+++ b/ompi/mca/pml/monitoring/pml_monitoring_component.c
@@ -0,0 +1,155 @@
+/*
+ * Copyright (c) 2013-2015 The University of Tennessee and The University
+ *                         of Tennessee Research Foundation.  All rights
+ *                         reserved.
+ * Copyright (c) 2013-2015 Inria.  All rights reserved.
+ * $COPYRIGHT$
+ *
+ * Additional copyrights may follow
+ *
+ * $HEADER$
+ */
+
+#include <ompi_config.h>
+#include <pml_monitoring.h>
+#include <ompi/constants.h>
+#include <ompi/mca/pml/base/base.h>
+#include <opal/mca/base/mca_base_component_repository.h>
+
+static int mca_pml_monitoring_enabled = 0;
+static int mca_pml_monitoring_active = 0;
+mca_pml_base_component_t pml_selected_component;
+mca_pml_base_module_t pml_selected_module;
+
+extern void output_monitoring( void );
+extern void finalize_monitoring( void );
+extern int  ompi_mca_pml_monitoring_flush(char* filename);
+int filter_monitoring( void );
+
+
+
+/* Return 1 if the the seperation between internal tags and external tags is enabled*/
+int filter_monitoring( void )
+{
+    if (mca_pml_monitoring_enabled == 2)
+        return 1;
+    else
+        return 0;
+}
+
+static unsigned long hidden_fct = (unsigned long)((void*)ompi_mca_pml_monitoring_flush);
+int mca_pml_monitoring_enable(bool enable)
+{
+    /* If we reach this point we were succesful at hijacking the interface of
+     * the real PML, and we are now correctly interleaved between the upper
+     * layer and the real PML.
+     */
+    mca_base_component_var_register(&mca_pml_monitoring_component.pmlm_version, "flush",
+                                    "Hidden argument to provide the flush function pointer",
+                                    MCA_BASE_VAR_TYPE_UNSIGNED_LONG, NULL, 0, 0,
+                                    OPAL_INFO_LVL_1,
+                                    MCA_BASE_VAR_SCOPE_CONSTANT,
+                                    &hidden_fct);
+    return pml_selected_module.pml_enable(enable);
+}
+
+static int mca_pml_monitoring_component_open(void)
+{
+    if( mca_pml_monitoring_enabled ) {
+        opal_pointer_array_add(&mca_pml_base_pml,
+                               strdup(mca_pml_monitoring_component.pmlm_version.mca_component_name));
+    }
+    return OMPI_SUCCESS;
+}
+
+static int mca_pml_monitoring_component_close(void)
+{
+    if( mca_pml_monitoring_enabled ) {
+        if( !mca_pml_monitoring_active ) {
+            /* Save a copy of the selected PML */
+            pml_selected_component = mca_pml_base_selected_component;
+            pml_selected_module = mca_pml;
+            /* And now install the interception layer */
+            mca_pml_base_selected_component = mca_pml_monitoring_component;
+            mca_pml = mca_pml_monitoring;
+            mca_pml.pml_progress = pml_selected_module.pml_progress;
+            /* Bump my ref count up to avoid getting released too early */
+            mca_base_component_repository_retain_component(mca_pml_monitoring_component.pmlm_version.mca_type_name,
+                                                           mca_pml_monitoring_component.pmlm_version.mca_component_name);
+            mca_pml_monitoring_active = 1;
+        }
+    }
+    return OMPI_SUCCESS;
+}
+
+static mca_pml_base_module_t*
+mca_pml_monitoring_component_init(int* priority,
+                                  bool enable_progress_threads,
+                                  bool enable_mpi_threads)
+{
+    if( mca_pml_monitoring_enabled ) {
+        *priority = 0;  /* I'm up but don't select me */
+        return &mca_pml_monitoring;
+    }
+    return NULL;
+}
+
+static int mca_pml_monitoring_component_finish(void)
+{
+    if( mca_pml_monitoring_enabled && mca_pml_monitoring_active ) {
+        /* It is over... Output what has been monitored*/
+        output_monitoring();
+        /* Free internal data structure */
+        finalize_monitoring();
+        /* Call the original PML and then close */
+        mca_pml_monitoring_active = 0;
+        mca_pml_monitoring_enabled = 0;
+        /* Restore the original PML */
+        mca_pml_base_selected_component = pml_selected_component;
+        mca_pml = pml_selected_module;
+        /* Redirect the close call to the original PML */
+        pml_selected_component.pmlm_finalize();
+        /**
+         * We should never release the last ref on the current component or face forever punishement.
+         */
+        /* mca_base_component_repository_release(&mca_pml_monitoring_component.pmlm_version); */
+    }
+    return OMPI_SUCCESS;
+}
+
+static int mca_pml_monitoring_component_register(void)
+{
+    (void)mca_base_component_var_register(&mca_pml_monitoring_component.pmlm_version, "enable",
+                                          "Enable the monitoring at the PML level. This value should be different than 0 in order for the monitoring to be enabled (default disable)", MCA_BASE_VAR_TYPE_INT, NULL, 0, 0,
+                                          OPAL_INFO_LVL_9,
+                                          MCA_BASE_VAR_SCOPE_READONLY, &mca_pml_monitoring_enabled);
+    return OMPI_SUCCESS;
+}
+
+mca_pml_base_component_2_0_0_t mca_pml_monitoring_component = {
+
+    /* First, the mca_base_component_t struct containing meta
+       information about the component itself */
+
+    {
+        MCA_PML_BASE_VERSION_2_0_0,
+
+        "monitoring", /* MCA component name */
+        OMPI_MAJOR_VERSION,  /* MCA component major version */
+        OMPI_MINOR_VERSION,  /* MCA component minor version */
+        OMPI_RELEASE_VERSION,  /* MCA component release version */
+        mca_pml_monitoring_component_open,  /* component open */
+        mca_pml_monitoring_component_close, /* component close */
+        NULL,
+        mca_pml_monitoring_component_register
+    },
+    {
+        /* The component is checkpoint ready */
+        MCA_BASE_METADATA_PARAM_CHECKPOINT
+    },
+
+    mca_pml_monitoring_component_init,  /* component init */
+    mca_pml_monitoring_component_finish   /* component finalize */
+
+};
+
diff --git a/ompi/mca/pml/monitoring/pml_monitoring_iprobe.c b/ompi/mca/pml/monitoring/pml_monitoring_iprobe.c
new file mode 100644
index 0000000000..ec34cb5d27
--- /dev/null
+++ b/ompi/mca/pml/monitoring/pml_monitoring_iprobe.c
@@ -0,0 +1,57 @@
+/*
+ * Copyright (c) 2013-2015 The University of Tennessee and The University
+ *                         of Tennessee Research Foundation.  All rights
+ *                         reserved.
+ * Copyright (c) 2013-2015 Inria.  All rights reserved.
+ * $COPYRIGHT$
+ *
+ * Additional copyrights may follow
+ *
+ * $HEADER$
+ */
+
+#include <ompi_config.h>
+#include <pml_monitoring.h>
+
+
+/* EJ: nothing to do here */
+
+int mca_pml_monitoring_iprobe( int dst,
+                               int tag,
+                               struct ompi_communicator_t* comm,
+                               int *matched,
+                               ompi_status_public_t* status )
+{
+    return pml_selected_module.pml_iprobe(dst, tag, comm,
+                                          matched, status);
+}
+
+int mca_pml_monitoring_probe( int dst,
+                              int tag,
+                              struct ompi_communicator_t* comm,
+                              ompi_status_public_t* status )
+{
+    return pml_selected_module.pml_probe(dst, tag, comm, status);
+}
+
+int mca_pml_monitoring_improbe(int dst,
+                               int tag,
+                               struct ompi_communicator_t* comm,
+                               int *matched,
+                               struct ompi_message_t **message,
+                               ompi_status_public_t* status)
+{
+    return pml_selected_module.pml_improbe(dst, tag, comm,
+                                           matched, message, status);
+}
+
+
+int mca_pml_monitoring_mprobe(int dst,
+                              int tag,
+                              struct ompi_communicator_t* comm,
+                              struct ompi_message_t **message,
+                              ompi_status_public_t* status)
+{
+    return pml_selected_module.pml_mprobe(dst, tag, comm, message, status);
+}
+
diff --git a/ompi/mca/pml/monitoring/pml_monitoring_irecv.c b/ompi/mca/pml/monitoring/pml_monitoring_irecv.c
new file mode 100644
index 0000000000..91b247c7c5
--- /dev/null
+++ b/ompi/mca/pml/monitoring/pml_monitoring_irecv.c
@@ -0,0 +1,80 @@
+/*
+ * Copyright (c) 2013-2015 The University of Tennessee and The University
+ *                         of Tennessee Research Foundation.  All rights
+ *                         reserved.
+ * Copyright (c) 2013-2015 Inria.  All rights reserved.
+ * $COPYRIGHT$
+ *
+ * Additional copyrights may follow
+ *
+ * $HEADER$
+ */
+
+#include <ompi_config.h>
+#include <pml_monitoring.h>
+
+
+/* EJ: loging is done on the sender. Nothing to do here */
+
+int mca_pml_monitoring_irecv_init(void *buf,
+                                  size_t count,
+                                  ompi_datatype_t *datatype,
+                                  int src,
+                                  int tag,
+                                  struct ompi_communicator_t* comm,
+                                  struct ompi_request_t **request)
+{
+    return pml_selected_module.pml_irecv_init(buf, count, datatype,
+                                              src, tag, comm, request);
+}
+
+
+int mca_pml_monitoring_irecv(void *buf,
+                             size_t count,
+                             ompi_datatype_t *datatype,
+                             int src,
+                             int tag,
+                             struct ompi_communicator_t* comm,
+                             struct ompi_request_t **request)
+{
+    return pml_selected_module.pml_irecv(buf, count, datatype,
+                                         src, tag, comm, request);
+}
+
+
+int mca_pml_monitoring_recv(void *buf,
+                            size_t count,
+                            ompi_datatype_t *datatype,
+                            int src,
+                            int tag,
+                            struct ompi_communicator_t* comm,
+                            ompi_status_public_t* status)
+{
+    return pml_selected_module.pml_recv(buf, count, datatype,
+                                        src, tag, comm, status);
+}
+
+
+int mca_pml_monitoring_imrecv(void *buf,
+                              size_t count,
+                              ompi_datatype_t *datatype,
+                              struct ompi_message_t **message,
+                              struct ompi_request_t **request)
+{
+    return pml_selected_module.pml_imrecv(buf, count, datatype,
+                                          message, request);
+}
+
+
+int mca_pml_monitoring_mrecv(void *buf,
+                             size_t count,
+                             ompi_datatype_t *datatype,
+                             struct ompi_message_t **message,
+                             ompi_status_public_t* status)
+
+{
+    return pml_selected_module.pml_mrecv(buf, count, datatype,
+                                         message, status);
+}
+
+
diff --git a/ompi/mca/pml/monitoring/pml_monitoring_isend.c b/ompi/mca/pml/monitoring/pml_monitoring_isend.c
new file mode 100644
index 0000000000..b8fc4f18a8
--- /dev/null
+++ b/ompi/mca/pml/monitoring/pml_monitoring_isend.c
@@ -0,0 +1,91 @@
+/*
+ * Copyright (c) 2013-2015 The University of Tennessee and The University
+ *                         of Tennessee Research Foundation.  All rights
+ *                         reserved.
+ * Copyright (c) 2013-2015 Inria.  All rights reserved.
+ * $COPYRIGHT$
+ *
+ * Additional copyrights may follow
+ *
+ * $HEADER$
+ */
+
+#include <ompi_config.h>
+#include <pml_monitoring.h>
+
+extern void monitor_send_data(int dest_rank, size_t data_size, int tag);
+extern opal_hash_table_t *get_hashtable(void);
+extern opal_hash_table_t *translation_ht;
+
+int mca_pml_monitoring_isend_init(void *buf,
+                                  size_t count,
+                                  ompi_datatype_t *datatype,
+                                  int dst,
+                                  int tag,
+                                  mca_pml_base_send_mode_t mode,
+                                  struct ompi_communicator_t* comm,
+                                  struct ompi_request_t **request)
+{
+    return pml_selected_module.pml_isend_init(buf, count, datatype,
+                                              dst, tag, mode, comm, request);
+}
+
+int mca_pml_monitoring_isend(void *buf,
+                             size_t count,
+                             ompi_datatype_t *datatype,
+                             int dst,
+                             int tag,
+                             mca_pml_base_send_mode_t mode,
+                             struct ompi_communicator_t* comm,
+                             struct ompi_request_t **request)
+{
+
+    /* find the processor of teh destination */
+    ompi_proc_t *proc = ompi_group_get_proc_ptr(comm->c_remote_group, dst);
+    int world_rank;
+
+    /* find its name*/
+    uint64_t key = *((uint64_t*)&(proc->super.proc_name));
+    /**
+     * If this fails the destination is not part of my MPI_COM_WORLD
+     * Lookup its name in the rank hastable to get its MPI_COMM_WORLD rank
+     */
+    if(OPAL_SUCCESS == opal_hash_table_get_value_uint64(translation_ht, key, (void *)&world_rank)) {
+        size_t type_size, data_size;
+        ompi_datatype_type_size(datatype, &type_size);
+        data_size = count*type_size;
+        monitor_send_data(world_rank, data_size, tag);
+    }
+
+    return pml_selected_module.pml_isend(buf, count, datatype,
+                                         dst, tag, mode, comm, request);
+}
+
+int mca_pml_monitoring_send(void *buf,
+                            size_t count,
+                            ompi_datatype_t *datatype,
+                            int dst,
+                            int tag,
+                            mca_pml_base_send_mode_t mode,
+                            struct ompi_communicator_t* comm)
+{
+
+    ompi_proc_t *proc = ompi_group_get_proc_ptr(comm->c_remote_group, dst);
+    int world_rank;
+    uint64_t key = *((uint64_t*) &(proc->super.proc_name));
+
+    /**
+     * If this fails the destination is not part of my MPI_COM_WORLD
+     */
+    if(OPAL_SUCCESS == opal_hash_table_get_value_uint64(translation_ht, key, (void *)&world_rank)) {
+        size_t type_size, data_size;
+        ompi_datatype_type_size(datatype, &type_size);
+        data_size = count*type_size;
+        monitor_send_data(world_rank, data_size, tag);
+    }
+
+
+    return pml_selected_module.pml_send(buf, count, datatype,
+                                        dst, tag, mode, comm);
+}
+
diff --git a/ompi/mca/pml/monitoring/pml_monitoring_start.c b/ompi/mca/pml/monitoring/pml_monitoring_start.c
new file mode 100644
index 0000000000..5b503977e7
--- /dev/null
+++ b/ompi/mca/pml/monitoring/pml_monitoring_start.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2013-2015 The University of Tennessee and The University
+ *                         of Tennessee Research Foundation.  All rights
+ *                         reserved.
+ * Copyright (c) 2013-2015 Inria.  All rights reserved.
+ * $COPYRIGHT$
+ *
+ * Additional copyrights may follow
+ *
+ * $HEADER$
+ */
+
+#include <ompi_config.h>
+#include <pml_monitoring.h>
+#include <opal/class/opal_hash_table.h>
+#include <ompi/mca/pml/base/pml_base_request.h>
+
+extern void monitor_send_data(int dest_rank, size_t data_size, int tag);
+extern opal_hash_table_t *translation_ht;
+
+
+/* manage persistant requests*/
+int mca_pml_monitoring_start(size_t count,
+                             ompi_request_t** requests)
+{
+    size_t i;
+
+    for( i = 0; i < count; i++ ) {
+        mca_pml_base_request_t *pml_request = (mca_pml_base_request_t*)requests[i];
+        ompi_proc_t *proc;
+        int world_rank;
+
+        if(NULL == pml_request) {
+            continue;
+        }
+        if(OMPI_REQUEST_PML != requests[i]->req_type) {
+            continue;
+        }
+        if(MCA_PML_REQUEST_SEND != pml_request->req_type) {
+            continue;
+        }
+
+        proc = ompi_group_get_proc_ptr(pml_request->req_comm->c_remote_group, pml_request->req_peer);
+        uint64_t key = *((uint64_t*) &(proc->super.proc_name));
+
+
+        /**
+         * If this fails the destination is not part of my MPI_COM_WORLD
+         */
+        if(OPAL_SUCCESS == opal_hash_table_get_value_uint64(translation_ht, key, (void *)&world_rank)) {
+            size_t type_size, data_size;
+            ompi_datatype_type_size(pml_request->req_datatype, &type_size);
+            data_size = pml_request->req_count * type_size;
+            monitor_send_data(world_rank, data_size, 1);
+        }
+    }
+    return pml_selected_module.pml_start(count, requests);
+}
+
diff --git a/test/Makefile.am b/test/Makefile.am
index 268a9f100f..5252fd5f53 100644
--- a/test/Makefile.am
+++ b/test/Makefile.am
@@ -2,7 +2,7 @@
 # Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
 #                         University Research and Technology
 #                         Corporation.  All rights reserved.
-# Copyright (c) 2004-2005 The University of Tennessee and The University
+# Copyright (c) 2004-2015 The University of Tennessee and The University
 #                         of Tennessee Research Foundation.  All rights
 #                         reserved.
 # Copyright (c) 2004-2009 High Performance Computing Center Stuttgart,
@@ -19,5 +19,5 @@
 #
 
 # support needs to be first for dependencies
-SUBDIRS = support asm class threads datatype util
+SUBDIRS = support asm class threads datatype util monitoring
 DIST_SUBDIRS = event $(SUBDIRS)
diff --git a/test/monitoring/Makefile.am b/test/monitoring/Makefile.am
new file mode 100644
index 0000000000..db85187bf9
--- /dev/null
+++ b/test/monitoring/Makefile.am
@@ -0,0 +1,21 @@
+#
+# Copyright (c) 2013-2015 The University of Tennessee and The University
+#                         of Tennessee Research Foundation.  All rights
+#                         reserved.
+# Copyright (c) 2013-2015 Inria.  All rights reserved.
+# $COPYRIGHT$
+#
+# Additional copyrights may follow
+#
+# $HEADER$
+#
+
+# This test requires multiple processes to run. Don't run it as part
+# of 'make check'
+if PROJECT_OMPI
+    noinst_PROGRAMS = monitoring_test
+
+    monitoring_test_SOURCES = monitoring_test.c
+    monitoring_test_LDFLAGS = $(WRAPPER_EXTRA_LDFLAGS)
+    monitoring_test_LDADD = $(top_builddir)/ompi/libmpi.la $(top_builddir)/opal/libopen-pal.la
+endif
diff --git a/test/monitoring/aggregate_profile.pl b/test/monitoring/aggregate_profile.pl
new file mode 100644
index 0000000000..da6d3780b0
--- /dev/null
+++ b/test/monitoring/aggregate_profile.pl
@@ -0,0 +1,71 @@
+#!/usr/bin/perl -w
+
+#
+# Copyright (c) 2013-2015 The University of Tennessee and The University
+#                         of Tennessee Research Foundation.  All rights
+#                         reserved.
+# Copyright (c) 2013-2015 Inria.  All rights reserved.
+# $COPYRIGHT$
+#
+# Additional copyrights may follow
+#
+# $HEADER$
+#
+
+#
+# Author Emmanuel Jeannot <emmanuel.jeannot@inria.fr>
+#
+# This script aggregates the profiles generated by the flush_monitoring function.
+# The files need to be in in given format: name_<phase_id>_<process_id>
+# They are then aggregated by phases.
+# If one needs the profile of all the phases he can concatenate the different files,
+# or use the output of the monitoring system done at MPI_Finalize
+# in the example it should be call as:
+# ./aggregate_profile.pl prof/phase to generate
+# prof/phase_1.prof
+# prof/phase_2.prof
+#
+# ensure that this script as the executable right: chmod +x ...
+#
+
+die "$0 <name of the  profile>\n\tProfile files should be of the form  \"name_phaseid_processesid.prof\"\n\tFor instance if you saved the monitoring into phase_0_0.prof, phase_0_1.prof, ..., phase_1_0.prof etc you should call: $0 phase\n" if ($#ARGV!=0);
+
+$name = $ARGV[0];
+
+@files = glob ($name."*");
+
+%phaseid = ();
+
+
+# Detect the different phases
+foreach $file (@files) {
+  ($id)=($file =~ m/$name\_(\d+)_\d+/);
+  $phaseid{$id} = 1 if ($id);
+}
+
+# for each phases aggregate the files
+foreach $id (sort {$a <=> $b} keys %phaseid) {
+  aggregate($name."_".$id);
+}
+
+
+
+
+sub aggregate{
+  $phase = $_[0];
+
+  print "Building $phase.prof\n";
+
+  open OUT,">$phase.prof";
+
+  @files = glob ($phase."*");
+
+  foreach $file ( @files) {
+    open IN,$file;
+    while (<IN>) {
+      print OUT;
+    }
+    close IN;
+  }
+  close OUT;
+}
diff --git a/test/monitoring/monitoring_test.c b/test/monitoring/monitoring_test.c
new file mode 100644
index 0000000000..6e85c7491b
--- /dev/null
+++ b/test/monitoring/monitoring_test.c
@@ -0,0 +1,213 @@
+/*
+ * Copyright (c) 2013-2015 The University of Tennessee and The University
+ *                         of Tennessee Research Foundation.  All rights
+ *                         reserved.
+ * Copyright (c) 2013-2015 Inria.  All rights reserved.
+ * $COPYRIGHT$
+ *
+ * Additional copyrights may follow
+ *
+ * $HEADER$
+ */
+
+/*
+pml monitoring tester.
+
+Designed by George Bosilca <bosilca@icl.utk.edu> and  Emmanuel Jeannot <emmanuel.jeannot@inria.fr>
+Contact the authors for questions.
+
+To be run as:
+
+mpirun -np 4 --mca pml_monitoring_enable 2 ./monitoring_test
+pm
+Then, the output should be:
+
+flushing to ./prof/phase_1_2.prof
+flushing to ./prof/phase_1_0.prof
+flushing to ./prof/phase_1_3.prof
+flushing to ./prof/phase_2_1.prof
+flushing to ./prof/phase_2_3.prof
+flushing to ./prof/phase_2_0.prof
+flushing to ./prof/phase_2_2.prof
+I	0	1	108 bytes	27 msgs sent
+E	0	1	1012 bytes	30 msgs sent
+E	0	2	23052 bytes	61 msgs sent
+I	1	2	104 bytes	26 msgs sent
+I	1	3	208 bytes	52 msgs sent
+E	1	0	860 bytes	24 msgs sent
+E	1	3	2552 bytes	56 msgs sent
+I	2	3	104 bytes	26 msgs sent
+E	2	0	22804 bytes	49 msgs sent
+E	2	3	860 bytes	24 msgs sent
+I	3	0	104 bytes	26 msgs sent
+I	3	1	204 bytes	51 msgs sent
+E	3	1	2304 bytes	44 msgs sent
+E	3	2	860 bytes	24 msgs sent
+
+or as
+
+mpirun -np 4 --mca pml_monitoring_enable 1 ./monitoring_test
+
+for an output as:
+
+flushing to ./prof/phase_1_1.prof
+flushing to ./prof/phase_1_0.prof
+flushing to ./prof/phase_1_2.prof
+flushing to ./prof/phase_1_3.prof
+flushing to ./prof/phase_2_1.prof
+flushing to ./prof/phase_2_3.prof
+flushing to ./prof/phase_2_2.prof
+flushing to ./prof/phase_2_0.prof
+I	0	1	1120 bytes	57 msgs sent
+I	0	2	23052 bytes	61 msgs sent
+I	1	0	860 bytes	24 msgs sent
+I	1	2	104 bytes	26 msgs sent
+I	1	3	2760 bytes	108 msgs sent
+I	2	0	22804 bytes	49 msgs sent
+I	2	3	964 bytes	50 msgs sent
+I	3	0	104 bytes	26 msgs sent
+I	3	1	2508 bytes	95 msgs sent
+I	3	2	860 bytes	24 msgs sent
+*/
+
+
+
+#include <stdio.h>
+#include "mpi.h"
+
+/* opal mca header taken from opal/mca/base/mca_base_var.h
+   Required to flush monitoring phases
+*/
+int mca_base_var_find_by_name (const char *full_name, int *vari);
+int mca_base_var_get_value (int vari, const void *value,
+                void *source, /* should be mca_base_var_source_t *source,
+                         but we do not need it
+                         and we do not know what is mca_base_var_source_t */
+                const char **source_file);
+
+
+int main(argc, argv)
+     int argc;
+     char **argv;
+{
+    int rank, size, n, to, from, tagno;
+    MPI_Status status;
+    MPI_Comm newcomm;
+    MPI_Request request;
+    char filename[1024];
+
+
+    /* first phase : make a token circulated in MPI_COMM_WORLD */
+    n = -1;
+    MPI_Init(&argc, &argv);
+    MPI_Comm_rank(MPI_COMM_WORLD, &rank);
+    MPI_Comm_size(MPI_COMM_WORLD, &size);
+    to = (rank + 1) % size;
+    from = (rank - 1) % size;
+    tagno = 201;
+    if (rank == 0){
+        n=25;
+        MPI_Isend(&n,1,MPI_INT,to,tagno,MPI_COMM_WORLD,&request);
+    }
+    while (1){
+        MPI_Irecv(&n,1,MPI_INT,from,tagno,MPI_COMM_WORLD, &request);
+        MPI_Wait(&request,&status);
+        if (rank == 0) {n--;tagno++;}
+        MPI_Isend(&n,1,MPI_INT,to,tagno,MPI_COMM_WORLD, &request);
+        if (rank != 0) {n--;tagno++;}
+        if (n<0){
+            break;
+        }
+    }
+
+
+    /* flush the monitoring of the first phase */
+    int fctidx;
+    void* fct;
+    int (*flush_monitoring)(char*) = NULL;
+    /*
+       Get the function pointer of the flushing function of the monitoring
+       This uses  Opal low level interface
+    */
+    mca_base_var_find_by_name( "pml_monitoring_flush", &fctidx);
+    if(fctidx){
+        mca_base_var_get_value(fctidx, &fct, NULL, NULL);
+        flush_monitoring = *(unsigned long*)fct;
+    }
+    /* Build one file per processes
+       Evevry thing that has been monitored by each
+       process since the last flush will be output in filename*/
+
+    /*
+       Requires directory prof to be created.
+       Filename format should display the phase number
+       and the process rank for ease of parsing with
+       aggregate_profile.pl script
+     */
+    sprintf(filename,"./prof/phase_1_%d.prof",rank);
+    if(flush_monitoring){
+        int r = flush_monitoring(filename);
+    if(r == -1){
+      fprintf(stderr, "Process %d cannot save monitoring in %s\n", rank, filename);
+    }
+    }
+
+    /*
+       Second phase. Work with different communicators.
+       even ranls will circulate a token
+       while odd ranks wil perform a all_to_all
+    */
+    MPI_Comm_split(MPI_COMM_WORLD,rank%2,rank,&newcomm);
+
+    /* the filename for flushing monitoring now uses 2 as phase number! */
+    sprintf(filename,"./prof/phase_2_%d.prof",rank);
+
+
+    if(rank%2){ /*even ranks (in COMM_WORD) circulate a token*/
+        int old_rank=rank;
+        MPI_Comm_rank(newcomm,&rank);
+        MPI_Comm_size(newcomm,&size);
+        if( size > 1 ) {
+            to = (rank + 1) % size;;
+            from = (rank - 1) % size ;
+            tagno = 201;
+            if (rank == 0){
+                n=50;
+                MPI_Send(&n,1,MPI_INT,to,tagno,newcomm);
+            }
+            while (1){
+                MPI_Recv(&n,1,MPI_INT,from,tagno,newcomm, &status);
+                if (rank == 0) {n--;tagno++;}
+                MPI_Send(&n,1,MPI_INT,to,tagno,newcomm);
+                if (rank != 0) {n--;tagno++;}
+                if (n<0){
+          if(flush_monitoring){
+            int r = flush_monitoring(filename);
+            if(r == -1){
+              fprintf(stderr, "Process %d cannot save monitoring in %s\n", old_rank, filename);
+            }
+          }
+          break;
+                }
+            }
+        }
+    }else{ /*odd ranks (in COMM_WORD) will perform a all_to_all and a barrier*/
+        int send_buff[10240];
+        int recv_buff[10240];
+        MPI_Comm_rank(newcomm,&rank);
+        MPI_Comm_size(newcomm,&size);
+        MPI_Alltoall(send_buff,10240/size, MPI_INT,recv_buff,10240/size,MPI_INT,newcomm);
+        MPI_Comm_split(newcomm,rank%2,rank,&newcomm);
+        MPI_Barrier(newcomm);
+        if(flush_monitoring){
+      int r = flush_monitoring(filename);
+      if(r == -1){
+        fprintf(stderr, "Process %d cannot save monitoring in %s\n", rank, filename);
+      }
+    }
+    }
+
+    /* Now, in MPI_Finalize(), the pml_monitoring library outputs, in STDERR, the aggregated recorded monitoring of all the phases*/
+    MPI_Finalize();
+    return 0;
+}
diff --git a/test/monitoring/prof/phase_1_0.prof b/test/monitoring/prof/phase_1_0.prof
new file mode 100644
index 0000000000..500401685b
--- /dev/null
+++ b/test/monitoring/prof/phase_1_0.prof
@@ -0,0 +1 @@
+I	0	1	108 bytes	27 msgs sent
diff --git a/test/monitoring/prof/phase_1_1.prof b/test/monitoring/prof/phase_1_1.prof
new file mode 100644
index 0000000000..1a314c842c
--- /dev/null
+++ b/test/monitoring/prof/phase_1_1.prof
@@ -0,0 +1 @@
+I	1	2	104 bytes	26 msgs sent
diff --git a/test/monitoring/prof/phase_1_2.prof b/test/monitoring/prof/phase_1_2.prof
new file mode 100644
index 0000000000..da71c785a6
--- /dev/null
+++ b/test/monitoring/prof/phase_1_2.prof
@@ -0,0 +1 @@
+I	2	3	104 bytes	26 msgs sent
diff --git a/test/monitoring/prof/phase_1_3.prof b/test/monitoring/prof/phase_1_3.prof
new file mode 100644
index 0000000000..c2da632079
--- /dev/null
+++ b/test/monitoring/prof/phase_1_3.prof
@@ -0,0 +1 @@
+I	3	0	104 bytes	26 msgs sent
diff --git a/test/monitoring/prof/phase_2_0.prof b/test/monitoring/prof/phase_2_0.prof
new file mode 100644
index 0000000000..a74fe68244
--- /dev/null
+++ b/test/monitoring/prof/phase_2_0.prof
@@ -0,0 +1,2 @@
+I	0	1	20 bytes	4 msgs sent
+I	0	2	20528 bytes	9 msgs sent
diff --git a/test/monitoring/prof/phase_2_1.prof b/test/monitoring/prof/phase_2_1.prof
new file mode 100644
index 0000000000..43328d3520
--- /dev/null
+++ b/test/monitoring/prof/phase_2_1.prof
@@ -0,0 +1,2 @@
+I	1	0	20 bytes	4 msgs sent
+I	1	3	236 bytes	56 msgs sent
diff --git a/test/monitoring/prof/phase_2_2.prof b/test/monitoring/prof/phase_2_2.prof
new file mode 100644
index 0000000000..5dc7d16ada
--- /dev/null
+++ b/test/monitoring/prof/phase_2_2.prof
@@ -0,0 +1,2 @@
+I	2	0	20528 bytes	9 msgs sent
+I	2	3	20 bytes	4 msgs sent
diff --git a/test/monitoring/prof/phase_2_3.prof b/test/monitoring/prof/phase_2_3.prof
new file mode 100644
index 0000000000..bc2c365b29
--- /dev/null
+++ b/test/monitoring/prof/phase_2_3.prof
@@ -0,0 +1,2 @@
+I	3	1	232 bytes	55 msgs sent
+I	3	2	20 bytes	4 msgs sent
diff --git a/test/monitoring/profile2mat.pl b/test/monitoring/profile2mat.pl
new file mode 100644
index 0000000000..a6ea6a52bb
--- /dev/null
+++ b/test/monitoring/profile2mat.pl
@@ -0,0 +1,123 @@
+#!/usr/bin/perl -w
+
+#
+# Copyright (c) 2013-2015 The University of Tennessee and The University
+#                         of Tennessee Research Foundation.  All rights
+#                         reserved.
+# Copyright (c) 2013-2015 Inria.  All rights reserved.
+# $COPYRIGHT$
+#
+# Additional copyrights may follow
+#
+# $HEADER$
+#
+
+#
+# Author Emmanuel Jeannot <emmanuel.jeannot@inria.fr>
+#
+# Take a profile file and aggregates all the recorded communicaton into matrices.
+# It generated a matrices for teh number of messages, (msg),
+# for the total bytes transmitted (size) and
+# the average nulber of bytes per messages (avg)
+#
+# The output matix is symetric
+#
+# If possible it creates file with "internal" tags (collexctive and eta data),
+# "external" tags (point to point messages)  and "all" (every messgaes).
+#
+# ensure that this script as the executable right: chmod +x ...
+#
+
+
+if($#ARGV < 0){
+   die("Usage: $0 <\".prof\" filename>\n");
+}else{
+   $filename=$ARGV[0];
+}
+
+profile($filename,"I|E","all");
+if ( profile($filename,"E","external") ){
+   profile($filename,"I","internal");
+}
+
+sub profile{
+   my $filename= $_[0];
+   my $filter= $_[1];
+   my $suffix= $_[2];
+   my $done = 0;
+
+   $outfile=$filename;
+   $outfile=~s/\.prof$/_size_$suffix\.mat/;
+
+
+   open IN,"<$filename";
+   $n=0;
+   @mat1=();
+   @mat2=();
+   @mat3=();
+   $i=0;
+   while (<IN>) {
+      $i++;
+      if (($f,$p1,$p2,$s,$m)=/^($filter)\s+(\d+)\s+(\d+)\s+(\d+)\D+(\d+)/){
+	 $done = 1;
+	 $f++;
+	 #print "$p1 | $p2 | $s | $m\n";
+	 $mat1[$p1][$p2]+=$s;
+	 $mat1[$p2][$p1]+=$s;
+	 $mat2[$p1][$p2]+=$m;
+	 $mat2[$p2][$p1]+=$m;
+	 $n=$p1 if ($p1>$n);
+	 $n=$p2 if ($p2>$n);
+      }else {
+	 # print("file $filename line $i: $_\n");
+      }
+   }
+   close IN;
+
+   #print "$done\n";
+
+   foreach $i (0..$n) {
+      foreach $j (0..$n) {
+	 $mat1[$i][$j]+=0;
+	 $mat2[$i][$j]+=0;
+	 $mat1[$i][$j]/=2;
+	 $mat2[$i][$j]/=2;
+	 if ($mat2[$i][$j]){
+	    $mat3[$i][$j]=$mat1[$i][$j]/$mat2[$i][$j] ;
+	    #printf"%f\t%f\t%f\n",$mat1[$i][$j],$mat2[$i][$j],$mat3[$i][$j];
+	 }else{
+	    $mat3[$i][$j]=0;
+	 }
+      }
+   }
+
+
+   if ($done) {
+      print "$filename -> $suffix\n";
+      save_file($outfile,$n,\@mat1);
+      $outfile=~s/_size/_msg/;
+      save_file($outfile,$n,\@mat2);
+      $outfile=~s/_msg/_avg/;
+      save_file($outfile,$n,\@mat3);
+      print"\n";
+   }
+   return $done;
+}
+
+
+sub save_file{
+   my $outfile=$_[0];
+   my $n=$_[1];
+   my @mat=@{$_[2]};
+   $s=$n+1;
+   print "$outfile\n";
+   open OUT,">$outfile";
+   foreach $i (0..$n) {
+      foreach $j (0..$n) {
+	 printf OUT "%.0f ",$mat[$i][$j];
+      }
+      print OUT "\n";
+   }
+ #  print"\n------------\n\n";
+   close OUT;
+}