tau memory_instrumentation (v4.0.x)

.gitignore

@@ -199,6 +199,8 @@ ompi/mca/rte/orte/mpirun.1
 
 ompi/mca/sharedfp/addproc/mca_sharedfp_addproc_control
 
+ompi/mca/topo/treematch/config.h
+
 ompi/mpi/c/profile/p*.c
 
 ompi/mpi/fortran/configure-fortran-output.h
@@ -399,6 +401,24 @@ opal/mca/pmix/ext3x/ext3x_client.c
 opal/mca/pmix/ext3x/ext3x_component.c
 opal/mca/pmix/ext3x/ext3x_server_north.c
 opal/mca/pmix/ext3x/ext3x_server_south.c
+opal/mca/pmix/pmix3x/pmix/config/mca_library_paths.txt
+opal/mca/pmix/pmix3x/pmix/config/test-driver
+opal/mca/pmix/pmix3x/pmix/test/run_tests00.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests01.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests02.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests03.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests04.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests05.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests06.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests07.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests08.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests09.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests10.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests11.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests12.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests13.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests14.pl
+opal/mca/pmix/pmix3x/pmix/test/run_tests15.pl
 
 opal/tools/opal-checkpoint/opal-checkpoint
 opal/tools/opal-checkpoint/opal-checkpoint.1

NEWS

@@ -14,7 +14,7 @@ Copyright (c) 2006      Sun Microsystems, Inc.  All rights reserved.
                         Use is subject to license terms.
 Copyright (c) 2006-2018 Los Alamos National Security, LLC.  All rights
                         reserved.
-Copyright (c) 2010-2018 IBM Corporation.  All rights reserved.
+Copyright (c) 2010-2019 IBM Corporation.  All rights reserved.
 Copyright (c) 2012      Oak Ridge National Labs.  All rights reserved.
 Copyright (c) 2012      Sandia National Laboratories.  All rights reserved.
 Copyright (c) 2012      University of Houston. All rights reserved.
@@ -57,6 +57,51 @@ included in the vX.Y.Z section and be denoted as:
    (** also appeared: A.B.C)  -- indicating that this item was previously
                                  included in release version vA.B.C.
 
+4.0.2 -- September, 2019
+------------------------
+- Update embedded PMIx to 3.1.4
+- Fix an issue with env processing when running as root.
+  Thanks to Simon Byrne for reporting and providing a fix.
+- Fix Fortran MPI_FILE_GET_POSITION return code bug.
+  Thanks to Wei-Keng Liao for reporting.
+- Fix user defined datatypes/ops leak in nonblocking base collective
+  component.  Thanks to Andrey Maslennikov for verifying fix.
+- Fixed shared memory not working with spawned processes.
+  Thanks to @rodarima for reporting.
+- Fix data corruption of overlapping datatypes on sends.
+  Thanks to DKRZ for reporting.
+- Fix segfault in oob_tcp component on close with active listeners.
+  Thanks to Orivej Desh for reporting and providing a fix.
+- Fix divide by zero segfault in ompio.
+  Thanks to @haraldkl for reporting and providing a fix.
+- Fix finalize of flux compnents.
+  Thanks to Stephen Herbein and Jim Garlick for providing a fix.
+- Fix osc_rdma_acc_single_intrinsic regression.
+  Thanks to Joseph Schuchart for reporting and providing a fix.
+- Fix hostnames with large integers.
+  Thanks to @perrynzhou for reporting and providing a fix.
+- Fix Deadlock in MPI_Fetch_and_op when using UCX
+  Thanks to Joseph Schuchart for reporting.
+- Fix the SLURM plm for mpirun-based launching.
+  Thanks to Jordon Hayes for reporting and providing a fix.
+- Prevent grep failure in rpmbuild from aborting.
+  Thanks to Daniel Letai for reporting.
+- Fix btl/vader finalize sequence.
+  Thanks to Daniel Vollmer for reporting.
+- Fix pml/ob1 local handle sent during PUT control message.
+  Thanks to @EmmanuelBRELLE for reporting and providing a fix.
+- Fix Memory leak with persistent MPI sends and the ob1 "get" protocol.
+  Thanks to @s-kuberski for reporting.
+- v4.0.x: mpi: mark MPI_COMBINER_{HVECTOR,HINDEXED,STRUCT}_INTEGER
+  removed unless configured with --enable-mpi1-compatibility
+- Fix make-authors.pl when run in a git submodule.
+  Thanks to Michael Heinz for reporting and providing a fix.
+- Fix deadlock with mpi_assert_allow_overtaking in MPI_Issend.
+  Thanks to Joseph Schuchart and George Bosilca for reporting.
+- Add compilation flag to allow unwinding through files that are
+  present in the stack when attaching with MPIR.
+  Thanks to James A Clark for reporting and providing a fix.
+
 4.0.1 -- March, 2019
 --------------------
 

VERSION

@@ -5,7 +5,9 @@
 #                         All rights reserved.
 # Copyright (c) 2017      Los Alamos National Security, LLC.  All rights
 #                         reserved.
-# Copyright (c) 2018      IBM Corporation.  All rights reserved.
+# Copyright (c) 2019      Triad National Security, LLC. All rights
+#                         reserved.
+# Copyright (c) 2018-2019 IBM Corporation.  All rights reserved.
 # Copyright (c) 2018      Research Organization for Information Science
 #                         and Technology (RIST).  All rights reserved.
 
@@ -28,7 +30,7 @@ release=2
 # requirement is that it must be entirely printable ASCII characters
 # and have no white space.
 
-greek=a1
+greek=rc2
 
 # If repo_rev is empty, then the repository version number will be
 # obtained during "make dist" via the "git describe --tags --always"
@@ -86,16 +88,16 @@ date="Unreleased developer copy"
 # Version numbers are described in the Libtool current:revision:age
 # format.
 
-libmpi_so_version=60:1:20
-libmpi_cxx_so_version=60:0:20
-libmpi_mpifh_so_version=60:1:20
+libmpi_so_version=60:2:20
+libmpi_cxx_so_version=60:1:20
+libmpi_mpifh_so_version=60:2:20
 libmpi_usempi_tkr_so_version=60:0:20
 libmpi_usempi_ignore_tkr_so_version=60:0:20
-libmpi_usempif08_so_version=60:0:20
-libopen_rte_so_version=60:1:20
-libopen_pal_so_version=60:1:20
+libmpi_usempif08_so_version=60:1:20
+libopen_rte_so_version=60:2:20
+libopen_pal_so_version=60:2:20
 libmpi_java_so_version=60:0:20
-liboshmem_so_version=61:0:21
+liboshmem_so_version=62:0:22
 libompitrace_so_version=60:0:20
 
 # "Common" components install standalone libraries that are run-time
@@ -104,7 +106,7 @@ libompitrace_so_version=60:0:20
 # components-don't-affect-the-build-system abstraction.
 
 # OMPI layer
-libmca_ompi_common_ompio_so_version=60:1:19
+libmca_ompi_common_ompio_so_version=60:2:19
 libmca_ompi_common_monitoring_so_version=60:0:10
 
 # ORTE layer
@@ -113,6 +115,6 @@ libmca_orte_common_alps_so_version=60:0:20
 # OPAL layer
 libmca_opal_common_cuda_so_version=60:0:20
 libmca_opal_common_sm_so_version=60:0:20
-libmca_opal_common_ucx_so_version=60:0:20
+libmca_opal_common_ucx_so_version=60:1:20
 libmca_opal_common_ugni_so_version=60:0:20
 libmca_opal_common_verbs_so_version=60:0:20

config/ompi_check_ucx.m4

@@ -120,7 +120,8 @@ AC_DEFUN([OMPI_CHECK_UCX],[
                                   UCP_ATOMIC_POST_OP_XOR,
                                   UCP_ATOMIC_FETCH_OP_FAND,
                                   UCP_ATOMIC_FETCH_OP_FOR,
-                                  UCP_ATOMIC_FETCH_OP_FXOR],
+                                  UCP_ATOMIC_FETCH_OP_FXOR,
+                                  UCP_PARAM_FIELD_ESTIMATED_NUM_PPN],
                                  [], [],
                                  [#include <ucp/api/ucp.h>])
                   AC_CHECK_DECLS([UCP_WORKER_ATTR_FIELD_ADDRESS_FLAGS],
@@ -135,9 +136,11 @@ AC_DEFUN([OMPI_CHECK_UCX],[
           [$1_CPPFLAGS="[$]$1_CPPFLAGS $ompi_check_ucx_CPPFLAGS"
            $1_LDFLAGS="[$]$1_LDFLAGS $ompi_check_ucx_LDFLAGS"
            $1_LIBS="[$]$1_LIBS $ompi_check_ucx_LIBS"
+           AC_DEFINE([HAVE_UCX], [1], [have ucx])
            $2],
           [AS_IF([test ! -z "$with_ucx" && test "$with_ucx" != "no"],
                  [AC_MSG_ERROR([UCX support requested but not found.  Aborting])])
+           AC_DEFINE([HAVE_UCX], [0], [have ucx])
            $3])
 
     OPAL_VAR_SCOPE_POP

config/opal_configure_options.m4

@@ -120,6 +120,7 @@ else
 fi
 AC_DEFINE_UNQUOTED(OPAL_ENABLE_MEM_PROFILE, $WANT_MEM_PROFILE,
     [Whether we want the memory profiling or not])
+AM_CONDITIONAL([OPAL_ENABLE_MEM_PROFILE], [test "$WANT_MEM_PROFILE" = "1"])
 
 #
 # Developer picky compiler options

contrib/platform/mellanox/optimized.conf

@@ -78,3 +78,8 @@ opal_event_include=epoll
 
 bml_r2_show_unreach_errors = 0
 
+# alltoall algorithm selection settings for tuned coll mca
+coll_tuned_alltoall_large_msg              = 250000
+coll_tuned_alltoall_min_procs              = 2048
+coll_tuned_alltoall_algorithm_max_requests = 8
+

ompi/communicator/comm_init.c

@@ -35,6 +35,7 @@
 
 #include "opal/util/bit_ops.h"
 #include "opal/util/info_subscriber.h"
+#include "opal/util/memprof.h"
 #include "opal/mca/pmix/pmix.h"
 #include "ompi/constants.h"
 #include "ompi/mca/pml/pml.h"
@@ -242,6 +243,7 @@ ompi_communicator_t *ompi_comm_allocate ( int local_size, int remote_size )
 
     /* create new communicator element */
     new_comm = OBJ_NEW(ompi_communicator_t);
+    OPAL_MEMPROF_START_ALLOC(new_comm->super.s_base.obj_class->cls_name, 0, 0);
     new_comm->super.s_info = NULL;
     new_comm->c_local_group = ompi_group_allocate ( local_size );
     if ( 0 < remote_size ) {
@@ -258,6 +260,7 @@ ompi_communicator_t *ompi_comm_allocate ( int local_size, int remote_size )
 
     /* fill in the inscribing hyper-cube dimensions */
     new_comm->c_cube_dim = opal_cube_dim(local_size);
+    OPAL_MEMPROF_STOP_ALLOC(new_comm->super.s_base.obj_class->cls_name, 0);
 
     return new_comm;
 }

ompi/datatype/ompi_datatype.h

@@ -1,6 +1,6 @@
 /* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
 /*
- * Copyright (c) 2009-2013 The University of Tennessee and The University
+ * Copyright (c) 2009-2019 The University of Tennessee and The University
  *                         of Tennessee Research Foundation.  All rights
  *                         reserved.
  * Copyright (c) 2009      Oak Ridge National Labs.  All rights reserved.

ompi/datatype/ompi_datatype_create_contiguous.c

@@ -3,7 +3,7 @@
  * Copyright (c) 2004-2006 The Trustees of Indiana University and Indiana
  *                         University Research and Technology
  *                         Corporation.  All rights reserved.
- * Copyright (c) 2004-2013 The University of Tennessee and The University
+ * Copyright (c) 2004-2019 The University of Tennessee and The University
  *                         of Tennessee Research Foundation.  All rights
  *                         reserved.
  * Copyright (c) 2004-2006 High Performance Computing Center Stuttgart,
@@ -29,13 +29,12 @@ int32_t ompi_datatype_create_contiguous( int count, const ompi_datatype_t* oldTy
 {
     ompi_datatype_t* pdt;
 
-    if( 0 == count ) {
-        pdt = ompi_datatype_create( 0 );
-        ompi_datatype_add( pdt, &ompi_mpi_datatype_null.dt, 0, 0, 0 );
-    } else {
-        pdt = ompi_datatype_create( oldType->super.desc.used + 2 );
-        opal_datatype_add( &(pdt->super), &(oldType->super), count, 0, (oldType->super.ub - oldType->super.lb) );
+    if( (0 == count) || (0 == oldType->super.size) ) {
+        return ompi_datatype_duplicate( &ompi_mpi_datatype_null.dt, newType);
     }
+
+    pdt = ompi_datatype_create( oldType->super.desc.used + 2 );
+    opal_datatype_add( &(pdt->super), &(oldType->super), count, 0, (oldType->super.ub - oldType->super.lb) );
     *newType = pdt;
     return OMPI_SUCCESS;
 }

ompi/datatype/ompi_datatype_create_darray.c

@@ -192,9 +192,7 @@ int32_t ompi_datatype_create_darray(int size,
     if (ndims < 1) {
         /* Don't just return MPI_DATATYPE_NULL as that can't be
            MPI_TYPE_FREE()ed, and that seems bad */
-        *newtype = ompi_datatype_create(0);
-        ompi_datatype_add(*newtype, &ompi_mpi_datatype_null.dt, 0, 0, 0);
-        return MPI_SUCCESS;
+        return ompi_datatype_duplicate( &ompi_mpi_datatype_null.dt, newtype);
     }
 
     rc = ompi_datatype_type_extent(oldtype, &orig_extent);