#! /bin/bash

exec=./ft.$1.16

if [ $2 == 'v20' ] ; then
mpiexec -genvall -genv I_MPI_DEBUG 5 \
 -genv OMP_NUM_THREADS=1 \
 -genv I_MPI_FABRICS=shm:ofi \
 -genv I_OFI_RXM_BUFFER_SIZE=4194304 \
 -genv I_MPI_SHM=ON \
 -genv I_MPI_ADJUST_ALLTOALL=2 \
 -host bubbles3 -n 4 ${exec} : \
 -host ives3 -n 4 ${exec} : \
 -host blaze3 -n 4 ${exec} : \
 -host brahms3 -n 4 ${exec}
else
mpiexec -genvall -genv I_MPI_DEBUG 5 \
 -genv OMP_NUM_THREADS=1 \
 -genv I_MPI_SHM=ON \
 -genv I_MPI_FABRICS=shm:tcp \
 -genv I_MPI_TCP_BUFFER_SIZE 2097152 \
 -genv I_MPI_TCP_NETMASK=192.168.3.0/24 \
 -genv I_MPI_ADJUST_ALLTOALL=2 \
 -host ives3 -n 4 ${exec} : \
 -host bubbles3 -n 8 ${exec} : \
 -host brahms3 -n 4 ${exec}

fi
exit
exit


$ ./run_ft16 C v20
[0] MPI startup(): Intel(R) MPI Library, Version 2021.1  Build 20201112
[0] MPI startup(): Copyright (C) 2003-2020 Intel Corporation.  All rights reserved.
[0] MPI startup(): library kind: release
MPI startup(): "ON" shm transport is not supported. "bdw_sse" shm transport will be used.
[0] MPI startup(): libfabric version: 1.11.1a1-impi
[0] MPI startup(): libfabric provider: tcp;ofi_rxm
[0] MPI startup(): Rank    Pid      Node name  Pin cpu
[0] MPI startup(): 0       2836     bubbles    {0,1}
[0] MPI startup(): 1       5100     bubbles    {2,3}
[0] MPI startup(): 2       5328     bubbles    {4,5}
[0] MPI startup(): 3       2908     bubbles    {6,7}
[0] MPI startup(): 4       6216     ives       {0,1,2,3}
[0] MPI startup(): 5       5444     ives       {4,5,6,7}
[0] MPI startup(): 6       4448     ives
[0] MPI startup(): 7       3508     ives
[0] MPI startup(): 8       12164    blaze      {0,1,2,3}
[0] MPI startup(): 9       2592     blaze      {4,5,6,7}
[0] MPI startup(): 10      12148    blaze
[0] MPI startup(): 11      5520     blaze
[0] MPI startup(): 12      5552     brahms     {0}
[0] MPI startup(): 13      5020     brahms     {1}
[0] MPI startup(): 14      5916     brahms     {2}
[0] MPI startup(): 15      5028     brahms     {3}
[0] MPI startup(): I_MPI_ROOT=C:\Program Files (x86)\Intel\oneAPI\mpi\2021.1.1\env\..
[0] MPI startup(): I_MPI_ONEAPI_ROOT=C:\Program Files (x86)\Intel\oneAPI\mpi\2021.1.1
u0] MPI startup(): I_MPI_HYDRA_TOPOLIB=hwloc
[0] MPI startup(): I_MPI_FABRICS=shm:ofi
[0] MPI startup(): I_MPI_SHM=ON
[0] MPI startup(): I_MPI_ADJUST_ALLTOALL=2
[0] MPI startup(): I_MPI_DEBUG=5


 NAS Parallel Benchmarks 3.3 -- FT Benchmark

 No input file inputft.data. Using compiled defaults
 Size                :  512x 512x 512
 Iterations          :             20
 Number of processes :             16
 Processor array     :         1x  16
 Layout type         :             1D
 T =    1     Checksum =    5.195078707457D+02    5.149019699238D+02
 T =    2     Checksum =    5.155422171134D+02    5.127578201997D+02
 T =    3     Checksum =    5.144678022222D+02    5.122251847514D+02
 T =    4     Checksum =    5.140150594328D+02    5.121090289018D+02
 T =    5     Checksum =    5.137550426810D+02    5.121143685824D+02
 T =    6     Checksum =    5.135811056728D+02    5.121496764568D+02
 T =    7     Checksum =    5.134569343165D+02    5.121870921893D+02
 T =    8     Checksum =    5.133651975661D+02    5.122193250322D+02
 T =    9     Checksum =    5.132955192805D+02    5.122454735794D+02
 T =   10     Checksum =    5.132410471738D+02    5.122663649603D+02
 T =   11     Checksum =    5.131971141679D+02    5.122830879827D+02
 T =   12     Checksum =    5.131605205716D+02    5.122965869718D+02
 T =   13     Checksum =    5.131290734194D+02    5.123075927445D+02
 T =   14     Checksum =    5.131012720314D+02    5.123166486553D+02
 T =   15     Checksum =    5.130760908195D+02    5.123241541685D+02
 T =   16     Checksum =    5.130528295923D+02    5.123304037599D+02
 T =   17     Checksum =    5.130310107773D+02    5.123356167976D+02
 T =   18     Checksum =    5.130103090133D+02    5.123399592211D+02
 T =   19     Checksum =    5.129905029333D+02    5.123435588985D+02
 T =   20     Checksum =    5.129714421109D+02    5.123465164008D+02
 Result verification successful
 class = C


 FT Benchmark Completed.
 Class           =                        C
 Size            =            512x 512x 512
 Iterations      =                       20
 Time in seconds =                    23.60
 Total processes =                       16
 Compiled procs  =                       16
 Mop/s total     =                 16792.70
 Mop/s/process   =                  1049.54
 Operation type  =           floating point
 Verification    =               SUCCESSFUL
 Version         =                      3.3
 Compile date    =              22 Mar 2021

 Compile options:
    MPIF77       = mpiifort.bat
    FLINK        = $(MPIF77)
    FMPI_LIB     = (none)
    FMPI_INC     = (none)
    FFLAGS       = -fpp -O3 -Qipo -QxHOST -Qmkl:sequential
    FLINKFLAGS   = (none)
    RAND         = randi8


 Please send the results of this run to:

 NPB Development Team
 Internet: npb@nas.nasa.gov

 If email is not available, send this to:

 MS T27A-1
 NASA Ames Research Center
 Moffett Field, CA  94035-1000

 Fax: 650-604-3957