next up previous
Next: Logfile Creation and Upshot Up: The mpich Programming Environment Previous: Profiling libraries

Accumulation of Time Spent in MPI Routines

The first profiling library is simple. The profiling version of each MPI_Xxx routine just calls PMPI_Wtime (which delivers a time stamp) before and after each call to the corresponding PMPI_Xxx routine. The times are accumulated in each process and written out, one file per process, in the profiling version of MPI_Finalize. The files are then available for use in either a global or process-by-process report. This version does not take into account nested calls, which occur when MPI_Bcast, say, is implemented in terms of MPI_Send and MPI_Recv.



Karen D. Toonen
1998-11-19