SGI Techpubs Library

Linux  »  Man Pages
find in page



NAME
       perfcatch - profile performance of an MPI or SHMEM program

SYNOPSIS
       perfcatch [-v | -vofed | -i] cmd args

DESCRIPTION
       perfcatch will run an MPI or SHMEM program with a wrapper
       profiling library that prints communication and synchronization
       call profiling information to a summary file upon program
       completion.  The MPI profiling result file-- MPI_PROFILING_STATS
       by default--will be created in the current working directory.

       To use perfcatch with an SGI Message Passing Toolkit MPI program,
       insert the perfcatch command in front of the executable name.
       Here are some examples:

               mpirun -np 64 perfcatch a.out arg1
               mpirun host1 32, host2 64 perfcatch a.out arg1

       To use perfcatch with Intel MPI, add the -i options.  Here
       is one example:

               mpiexec -np 64 perfcatch -i a.out arg1

OPTIONS
       None      support MPT
       -v        support Voltaire  MPI
       -vofed    support Voltaire  OFED MPI
       -i        support Intel MPI

MPI PROFILING RESULT FILE
       The MPI Profiling result file has a summary statistics section
       followed by a rank-by-rank profiling information section.
       The summary statistics section reports some overall statistics,
       including the percent time each rank spent in MPI functions,
       and the MPI process that spent the least and the most time
       int MPI functions.   Similar reports are made about system
       time usage.

       The rank-by-rank profiling information section lists every
       profiled MPI function called by a particular MPI process.
       The number of calls and the total time consumed by these
       calls is reported.  Some functions report additional information
       such as average data counts and communication peer lists.

ENVIRONMENT VARIABLES
       MPI_PROFILING_STATS_FILE
               Specifies the file where MPI profiling results are written.
               If not specified, the file "MPI_PROFILING_STATS" will be
               written.

NOTES
       SHMEM function profiling is only available when using SGI MPT MPI.

       On clusters, the profiling results file must reside on a globally
       writable filesystem, such as NFS, CXFS, or Lustre.

       cc -Wall  -fPIC   -c -o perf.o perf.c

MPI FUNCTIONS PROFILED
       NOTE: some functions may not be implemented in all languages as indicated
       below.

       Language(s)   Function

       C Fortran     mpi_allgather
       C Fortran     mpi_allgatherv
       C Fortran     mpi_allreduce
       C Fortran     mpi_alltoall
       C Fortran     mpi_alltoallv
       C Fortran     mpi_barrier
       C Fortran     mpi_bcast
       C Fortran     mpi_comm_create
       C Fortran     mpi_comm_free
       C Fortran     mpi_comm_group
       C Fortran     mpi_comm_rank
       C Fortran     mpi_finalize
       C Fortran     mpi_gather
       C Fortran     mpi_gatherv
       C Fortran     mpi_get
       C Fortran     mpi_get_count
       C Fortran     mpi_group_difference
       C Fortran     mpi_group_excl
       C Fortran     mpi_group_free
       C Fortran     mpi_group_incl
       C Fortran     mpi_group_intersection
       C Fortran     mpi_group_range_excl
       C Fortran     mpi_group_range_incl
       C Fortran     mpi_group_union
       C Fortran     mpi_ibsend
       C Fortran     mpi_init
       C             mpi_init_thread
       C Fortran     mpi_irecv
       C Fortran     mpi_isend
       C Fortran     mpi_probe
       C Fortran     mpi_put
       C Fortran     mpi_recv
       C Fortran     mpi_reduce
       C Fortran     mpi_scatter
       C Fortran     mpi_scatterv
       C Fortran     mpi_send
       C Fortran     mpi_sendrecv
       C Fortran     mpi_ssend
       C Fortran     mpi_test
       C Fortran     mpi_testany
       C Fortran     mpi_wait
       C Fortran     mpi_waitall
       C Fortran     mpi_waitany
       C Fortran     mpi_win_fence

SHMEM FUNCTIONS PROFILED
       All SHMEM functions are profiled, with the following exceptions:

       shmem_udcflush and other cache flush no-op functions
       shmem_quiet
       shmem_fence

perfcatcher                      October 2014                   perfcatcher(1)

Output converted with man2html


home/search | what's new | help