Greetings Craig, I do apologize for the delay. > Hi, > > I need to develop a parallel (MPI) netCDF-4 I/O capability for a new > numerical model. The parallel file system on the supercomputing cluster I am > using cannot handle more than 64 processes trying to read from/write to a > single file. > > Are there any Fortran examples available using 'nfmpi_' calls? I couldn't > find any here: I found an example of using parallel I/O in FORTRAN, but it does not use nfmpi_. However, I'll pass it along in case you find it helpful: http://www.unidata.ucar.edu/software/netcdf/workshops/most-recent/pnetcdf/index.html > > http://www.unidata.ucar.edu/software/netcdf/examples/programs/ > > Also, are there any benchmarking programs available for parallel netCDF-4 I/O? There is the --enable-benchmarks flag you can pass configure that will enable benchmark tests, but I am not aware of any others. You may have to create a test(s) specific to your needs. Cheers! Sean > > Thank you, > Craig > > --------------------------------------------------- > Dr. Craig A. Mattocks > Atmospheric Research Scientist > Meteorology and Physical Oceanography, MSC 231-B > Rosenstiel School of Marine and Atmospheric Science > University of Miami > 4600 Rickenbacker Causeway > Miami, FL 33149-1301 > phone: (305) 421-4287 > e-mail: address@hidden > --------------------------------------------------- > > Ticket Details =================== Ticket ID: CYS-719544 Department: Support netCDF Priority: Critical Status: Open
NOTE: All email exchanges with Unidata User Support are recorded in the Unidata inquiry tracking system and then made publicly available through the web. If you do not want to have your interactions made available in this way, you must let us know in each email you send to us.