Changeset 622 for palm/trunk/SOURCE/poisfft.f90

Timestamp:

Dec 10, 2010 8:08:13 AM (13 years ago)

Author:

raasch

Message:

New:
---

Optional barriers included in order to speed up collective operations
MPI_ALLTOALL and MPI_ALLREDUCE. This feature is controlled with new initial
parameter collective_wait. Default is .FALSE, but .TRUE. on SGI-type
systems. (advec_particles, advec_s_bc, buoyancy, check_for_restart,
cpu_statistics, data_output_2d, data_output_ptseries, flow_statistics,
global_min_max, inflow_turbulence, init_3d_model, init_particles, init_pegrid,
init_slope, parin, pres, poismg, set_particle_attributes, timestep,
read_var_list, user_statistics, write_compressed, write_var_list)

Adjustments for Kyushu Univ. (lcrte, ibmku). Concerning hybrid
(MPI/openMP) runs, the number of openMP threads per MPI tasks can now
be given as an argument to mrun-option -O. (mbuild, mrun, subjob)

Changed:

---

Initialization of the module command changed for SGI-ICE/lcsgi (mbuild, subjob)

Errors:

---

File:

• palm/trunk/SOURCE/poisfft.f90 (modified) (5 diffs)

palm/trunk/SOURCE/poisfft.f90

@@ -4 +4 @@
 ! Current revisions:
 ! -----------------
-! 
+! optional barriers included in order to speed up collective operations
 !
 ! Former revisions:
@@ -718 +718 @@
 !--    Transpose array
        CALL cpu_log( log_point_s(32), 'mpi_alltoall', 'start' )
+       IF ( collective_wait )  CALL MPI_BARRIER( comm2d, ierr )
        CALL MPI_ALLTOALL( work(nxl,1,0),      sendrecvcount_xy, MPI_REAL, &
                           f_out(1,1,nys_x,1), sendrecvcount_xy, MPI_REAL, &
@@ -756 +757 @@
 !--    Transpose array
        CALL cpu_log( log_point_s(32), 'mpi_alltoall', 'start' )
+       IF ( collective_wait )  CALL MPI_BARRIER( comm2d, ierr )
        CALL MPI_ALLTOALL( f_in(1,1,nys_x,1), sendrecvcount_xy, MPI_REAL, &
                           work(nxl,1,0),     sendrecvcount_xy, MPI_REAL, &
@@ -1073 +1075 @@
 !--    Transpose array
        CALL cpu_log( log_point_s(32), 'mpi_alltoall', 'start' )
+       IF ( collective_wait )  CALL MPI_BARRIER( comm2d, ierr )
        CALL MPI_ALLTOALL( work(nys,1,0),      sendrecvcount_xy, MPI_REAL, &
                           f_out(1,1,nxl_y,1), sendrecvcount_xy, MPI_REAL, &
@@ -1107 +1110 @@
 !--    Transpose array
        CALL cpu_log( log_point_s(32), 'mpi_alltoall', 'start' )
+       IF ( collective_wait )  CALL MPI_BARRIER( comm2d, ierr )
        CALL MPI_ALLTOALL( f_in(1,1,nxl_y,1), sendrecvcount_xy, MPI_REAL, &
                           work(nys,1,0),     sendrecvcount_xy, MPI_REAL, &