On 04/06/2011 03:38 PM, Nehemiah Dacres wrote:
I am also trying to get netlib's hpl to run via sun cluster tools so i am trying to compile it and am having trouble. Which is the proper mpi library to give?
naturally this isn't going to work

MPdir        = /opt/SUNWhpc/HPC8.2.1c/sun/
MPinc        = -I$(MPdir)/include
MPlib        = $(MPdir)/lib/libmpi.a
Is there a reason you are trying to link with a static libmpi.  You really want to link with libmpi.so.  It also seems like whatever Makefile you are using is not using mpicc, is that true.  The reason that is important is mpicc would pick up the right libs you needed.  Which brings me to Ralph's comment, if you really want to go around the mpicc way of compiling use mpicc --showme, copy the compile line shown in that commands output and insert your files accordingly.

--td

because that doesn't exist
/opt/SUNWhpc-O/HPC8.2.1c/sun/lib/libotf.a  /opt/SUNWhpc-O/HPC8.2.1c/sun/lib/libvt.fmpi.a  /opt/SUNWhpc-O/HPC8.2.1c/sun/lib/libvt.omp.a
/opt/SUNWhpc-O/HPC8.2.1c/sun/lib/libvt.a   /opt/SUNWhpc-O/HPC8.2.1c/sun/lib/libvt.mpi.a   /opt/SUNWhpc-O/HPC8.2.1c/sun/lib/libvt.ompi.a

is what I have for listing *.a  in the lib directory. none of those are equivilant becasue they are all linked with vampire trace if I am reading the names right. I've already tried putting  /opt/SUNWhpc-O/HPC8.2.1c/sun/lib/libvt.mpi.a for this and it didnt work giving errors like

On Wed, Apr 6, 2011 at 12:42 PM, Terry Dontje <terry.dontje@oracle.com> wrote:
Something looks fishy about your numbers.  The first two sets of numbers look the same and the last set do look better for the most part.  Your mpirun command line looks weird to me with the "-mca orte_base_help_aggregate btl,openib,self," did something get chopped off with the text copy?  You should have had a "-mca btl openib,self".  Can you do a run with "-mca btl tcp,self", it should be slower.

I really wouldn't have expected another compiler over IB to be that dramatically lower performing.

--td



On 04/06/2011 12:40 PM, Nehemiah Dacres wrote:
also, I'm not sure if I'm reading the results right. According to the last run, did using the sun compilers (update 1 )  result in higher performance with sunct?

On Wed, Apr 6, 2011 at 11:38 AM, Nehemiah Dacres <dacresni@slu.edu> wrote:
some tests I did. I hope this isn't an abuse of the list. please tell me if it is but thanks to all those who helped me.

this  goes to say that the sun MPI works with programs not compiled with sun’s compilers.
this first test was run as a base case to see if MPI works., the sedcond run is to see the speed up using OpenIB provides
jian@therock ~]$ mpirun -machinefile list /opt/iba/src/mpi_apps/mpi_stress/mpi_stress
Start mpi_stress at Wed Apr  6 10:56:29 2011

  Size (bytes)         TxMessages      TxMillionBytes/s       TxMessages/s
            32              10000                  2.77           86485.67
            64              10000                  5.76           90049.42
           128              10000                 11.00           85923.85
           256              10000                 18.78           73344.43
           512              10000                 34.47           67331.98
          1024              10000                 34.81           33998.09
          2048              10000                 17.31            8454.27
          4096              10000                 18.34            4476.61
          8192              10000                 25.43            3104.28
         16384              10000                 15.56             949.50
         32768              10000                 13.95             425.74

         65536              10000                  9.88             150.79
        131072               8192                 11.05              84.31
        262144               4096                 13.12              50.04
        524288               2048                 16.54              31.55
       1048576               1024                 19.92              18.99
       2097152                512                 22.54              10.75
       4194304                256                 25.46               6.07

Iteration 0 : errors = 0, total = 0 (495 secs, Wed Apr  6 11:04:44 2011)
After 1 iteration(s), 8 mins and 15 secs, total errors = 0

here is the infiniband run

[jian@therock ~]$ mpirun -mca orte_base_help_aggregate btl,openib,self, -machinefile list /opt/iba/src/mpi_apps/mpi_stress/mpi_stress
Start mpi_stress at Wed Apr  6 11:07:06 2011

  Size (bytes)         TxMessages      TxMillionBytes/s       TxMessages/s
        32              10000                  2.72           84907.69
        64              10000                  5.83           91097.94
       128              10000                 10.75           83959.63
       256              10000                 18.53           72384.48
       512              10000                 34.96           68285.00
      1024              10000                 11.40           11133.10
      2048              10000                 20.88           10196.34
      4096              10000                 10.13            2472.13
      8192              10000                 19.32            2358.25
     16384              10000                 14.58             890.10
     32768              10000                 15.85             483.61
     65536              10000                  9.04             137.95
     131072        8192                 10.90              83.12
    262144                   4096                 13.57              51.76
    524288                  2048                 16.82              32.08
   1048576        1024                 19.10              18.21
   2097152                512                 22.13              10.55
   4194304                256                 21.66               5.16

Iteration 0 : errors = 0, total = 0 (511 secs, Wed Apr  6 11:15:37 2011)
After 1 iteration(s), 8 mins and 31 secs, total errors = 0
compiled with the sun compilers i think
[jian@therock ~]$ mpirun -mca orte_base_help_aggregate btl,openib,self, -machinefile list sunMpiStress
Start mpi_stress at Wed Apr  6 11:23:18 2011

  Size (bytes)         TxMessages      TxMillionBytes/s       TxMessages/s
            32              10000                  2.60           81159.60
            64              10000                  5.19           81016.95
           128              10000                 10.23           79953.34
           256              10000                 16.74           65406.52
           512              10000                 23.71           46304.92
          1024              10000                 54.62           53340.73
          2048              10000                 45.75           22340.58
          4096              10000                 29.32            7158.87
          8192              10000                 28.61            3492.77
         16384              10000                184.03           11232.26
         32768              10000                215.69            6582.21
         65536              10000                229.88            3507.64
        131072               8192                231.64            1767.25
        262144               4096                220.73             842.00
        524288               2048                121.61             231.95
       1048576               1024                 66.54              63.46
       2097152                512                 44.20              21.08
       4194304                256                 45.17              10.77

Iteration 0 : errors = 0, total = 0 (93 secs, Wed Apr  6 11:24:52 2011)
After 1 iteration(s), 1 mins and 33 secs, total errors = 0

sanity check: was sunMpiStress compiled using the sun compilers or oracle compilerrs ?
[jian@therock ~]$ which mpirun

/opt/SUNWhpc/HPC8.2.1c/sun/bin/mpirun
[jian@therock ~]$ ldd sunMpiStress
   libmpi.so.0 => /opt/SUNWhpc/HPC8.2.1c/sun/lib/lib64/libmpi.so.0 (0x00002b5d2c6c3000)
   libopen-rte.so.0 => /opt/SUNWhpc/HPC8.2.1c/sun/lib/lib64/libopen-rte.so.0 (0x00002b5d2c8c1000)
   libopen-pal.so.0 => /opt/SUNWhpc/HPC8.2.1c/sun/lib/lib64/libopen-pal.so.0 (0x00002b5d2ca19000)
   libnsl.so.1 => /lib64/libnsl.so.1 (0x0000003361400000)
   librt.so.1 => /lib64/librt.so.1 (0x000000335f400000)
   libm.so.6 => /lib64/libm.so.6 (0x000000335e400000)
   libdl.so.2 => /lib64/libdl.so.2 (0x000000335e800000)
   libutil.so.1 => /lib64/libutil.so.1 (0x000000336ba00000)
   libpthread.so.0 => /lib64/libpthread.so.0 (0x000000335ec00000)
   libc.so.6 => /lib64/libc.so.6 (0x000000335e000000)
   /lib64/ld-linux-x86-64.so.2 (0x000000335dc00000)
[jian@therock ~]$ which mpicc
/opt/SUNWhpc/HPC8.2.1c/sun/bin/mpicc
[jian@therock ~]$ mpicc /opt/iba/src/mpi_apps/mpi_stress/mpi_stress.c -o sunMpiStress --showme
cc /opt/iba/src/mpi_apps/mpi_stress/mpi_stress.c -o sunMpiStress -I/opt/SUNWhpc/HPC8.2.1c/sun/include/64 -I/opt/SUNWhpc/HPC8.2.1c/sun/include/64/openmpi -R/opt/mx/lib/lib64 -R/opt/SUNWhpc/HPC8.2.1c/sun/lib/lib64 -L/opt/SUNWhpc/HPC8.2.1c/sun/lib/lib64 -lmpi -lopen-rte -lopen-pal -lnsl -lrt -lm -ldl -lutil -lpthread
[jian@therock ~]$ which cc
/opt/sun/sunstudio12.1/bin/cc

looks like it!






--
Nehemiah I. Dacres
System Administrator 
Advanced Technology Group Saint Louis University

_______________________________________________ users mailing list


--
Oracle
Terry D. Dontje | Principal Software Engineer
Developer Tools Engineering | +1.781.442.2631
Oracle - Performance Technologies
95 Network Drive, Burlington, MA 01803
Email terry.dontje@oracle.com




_______________________________________________
users mailing list
users@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users



--
Nehemiah I. Dacres
System Administrator 
Advanced Technology Group Saint Louis University

_______________________________________________ users mailing list users@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users


--
Oracle
Terry D. Dontje | Principal Software Engineer
Developer Tools Engineering | +1.781.442.2631
Oracle - Performance Technologies
95 Network Drive, Burlington, MA 01803
Email terry.dontje@oracle.com