IntelĀ® MPI Benchmarks 4.0
This pattern performs collective access from all processes to a common file, with an explicit file pointer.
This benchmark is based on the following MPI routines:
MPI_File_read_at_all/MPI_File_write_at_all for the blocking mode
MPI_File_.._at_all_begin/MPI_File_.._at_all_end for the nonblocking mode
All other parameters and the measuring method are the same as for the P_[ACTION]_expl benchmark.
See Also