Merge branch 'worleyph/cime/taskmap' into master (PR #2458)

Currently MPI task to compute node mapping information is
output in two locations, once in CAM, where it is
truncated after the first 256 MPI tasks, and once in CLM,
where it is truncated after the first 100 MPI tasks,
both only for these two components. This is not useful in current
production runs. The use of environment variables, such as
MPICH_CPUMASK_DISPLAY on Cray systems, generate data that are
unnecessarily verbose for our needs. Here a share routine is
introduced that writes out one line per compute node. Each line
contains the compute node name and the list of MPI tasks assigned
to that node for a given communicator. This is then called
in the driver and writes out the task-to-node mapping for the
entire coupled model. Separate branches will then introduce
this into the individual components, replacing the current logic
in both CAM and CLM, for example.

The share routine also optionally returns the number of compute
nodes and the task-to-node mapping, which is needed in the
internal CAM load balancing.

With the call to the shr_taskmap_write routine in the
driver, the mapping data generated by the system when setting
the corresponding environment variable is redundant. This
is removed for the systems currently setting the variable.

Fixes #2457

BFB

* origin/worleyph/cime/taskmap:
  Avoid empty env blocks
  Remove unnecessary white space in task-to-node map output
  Modify driver output format
  Uncomment MV2_CPU_MAPPING definition for Anvil
  Modify task map output format
  Unset environment variables to output task-to-node mapping
  Output MPI task to compute node mapping

config/e3sm/machines/config_machines.xml

@@ -183,7 +183,7 @@
   <environment_variables>
     <env name="MPICH_ENV_DISPLAY">1</env>
     <env name="MPICH_VERSION_DISPLAY">1</env>
-    <env name="MPICH_CPUMASK_DISPLAY">1</env>
+    <!--env name="MPICH_CPUMASK_DISPLAY">1</env-->
 
     <env name="OMP_STACKSIZE">64M</env>
     <env name="OMP_PROC_BIND">spread</env>
@@ -327,7 +327,7 @@
 
     <env name="MPICH_ENV_DISPLAY">1</env>
     <env name="MPICH_VERSION_DISPLAY">1</env>
-    <env name="MPICH_CPUMASK_DISPLAY">1</env>
+    <!--env name="MPICH_CPUMASK_DISPLAY">1</env-->
 
     <env name="OMP_STACKSIZE">128M</env>
     <env name="OMP_PROC_BIND">spread</env>
@@ -483,7 +483,7 @@
   <environment_variables>
     <env name="MPICH_ENV_DISPLAY">1</env>
     <env name="MPICH_VERSION_DISPLAY">1</env>
-    <env name="MPICH_CPUMASK_DISPLAY">1</env>
+    <!--env name="MPICH_CPUMASK_DISPLAY">1</env-->
 
     <env name="OMP_STACKSIZE">128M</env>
     <env name="OMP_PROC_BIND">spread</env>
@@ -1675,14 +1675,12 @@
     <environment_variables>
       <env name="MPICH_ENV_DISPLAY">1</env>
       <env name="MPICH_VERSION_DISPLAY">1</env>
+      <!--env name="MPICH_CPUMASK_DISPLAY">1</env-->
       <env name="MPAS_TOOL_DIR">/projects/ccsm/acme/tools/mpas</env>
       <env name="HDF5_DISABLE_VERSION_CHECK">2</env>
       <env name="labeling"> </env>
       <env name="SMP_VARS"> </env>
     </environment_variables>
-    <environment_variables SMP_PRESENT="TRUE">
-      <env name="MPICH_CPUMASK_DISPLAY">1</env>
-    </environment_variables>
     <environment_variables SMP_PRESENT="TRUE" compiler="intel">
       <env name="SMP_VARS">-e OMP_NUM_THREADS=$ENV{OMP_NUM_THREADS} -e OMP_STACKSIZE=128M -e KMP_AFFINITY=granularity=thread,scatter</env>
     </environment_variables>
@@ -2247,7 +2245,7 @@
         <env name="MPILIB">$MPILIB</env>
         <env name="MPICH_ENV_DISPLAY">1</env>
         <env name="MPICH_VERSION_DISPLAY">1</env>
-        <env name="MPICH_CPUMASK_DISPLAY">1</env>
+        <!--env name="MPICH_CPUMASK_DISPLAY">1</env-->
         <env name="MPSTKZ">128M</env>
         <env name="OMP_STACKSIZE">128M</env>
       </environment_variables>

src/drivers/mct/shr/seq_comm_mct.F90

@@ -16,12 +16,14 @@ module seq_comm_mct
 !!! the namelist).  ARE OTHER PROTECTIONS/CHECKS NEEDED???
 
 
-  use mct_mod     , only : mct_world_init, mct_world_clean, mct_die
-  use shr_sys_mod , only : shr_sys_abort, shr_sys_flush
-  use shr_mpi_mod , only : shr_mpi_chkerr, shr_mpi_bcast, shr_mpi_max
-  use shr_file_mod, only : shr_file_getUnit, shr_file_freeUnit
-  use esmf        , only : ESMF_LogKind_Flag, ESMF_LOGKIND_NONE
-  use esmf        , only : ESMF_LOGKIND_SINGLE, ESMF_LOGKIND_MULTI
+  use mct_mod        , only : mct_world_init, mct_world_clean, mct_die
+  use shr_sys_mod    , only : shr_sys_abort, shr_sys_flush
+  use shr_mpi_mod    , only : shr_mpi_chkerr, shr_mpi_bcast, shr_mpi_max
+  use shr_file_mod   , only : shr_file_getUnit, shr_file_freeUnit
+  use shr_taskmap_mod, only : shr_taskmap_write
+  use perf_mod       , only : t_startf, t_stopf
+  use esmf           , only : ESMF_LogKind_Flag, ESMF_LOGKIND_NONE
+  use esmf           , only : ESMF_LOGKIND_SINGLE, ESMF_LOGKIND_MULTI
 
   implicit none
 
@@ -222,6 +224,7 @@ subroutine seq_comm_init(global_comm_in, driver_comm_in, nmlfile, drv_comm_id)
     integer, pointer :: comps(:) ! array with component ids
     integer, pointer :: comms(:) ! array with mpicoms
     integer :: nu
+    character(len=8) :: c_global_numpes ! global number of pes
     character(len=seq_comm_namelen) :: valid_comps(ncomps)
 
     integer :: &
@@ -291,6 +294,17 @@ subroutine seq_comm_init(global_comm_in, driver_comm_in, nmlfile, drv_comm_id)
        call shr_sys_abort(trim(subname)//' ERROR decomposition error ')
     endif
 
+    ! output task-to-node mapping
+    if (mype == 0) then
+       write(c_global_numpes,'(i8)') global_numpes
+       write(logunit,100) trim(adjustl(c_global_numpes))
+100    format(/,a,' pes participating in computation of coupled model')
+       call shr_sys_flush(logunit)
+    endif
+    call t_startf("shr_taskmap_write")
+    call shr_taskmap_write(logunit, GLOBAL_COMM_IN, 'GLOBAL')
+    call t_stopf("shr_taskmap_write")
+
     ! Initialize gloiam on all IDs
 
     global_mype = mype