Page 2 of 3. Showing 21 results (0.631 seconds)

  1. What do you need to run Parallel HDF5?

    You need an MPI library with MPII/O support installed on your system. If you use the MPIO VFD, the HDF5 library will use MPII/O for data access so MPII/O must be supported by the file system. If a different driver is used, such as the MPI POSIX VFD, then a POSIX compliant file system is required. (Two examples
    HDF Knowledge BaseDec 14, 2017
  2. What performance can you expect from Parallel HDF5?

    HDF5 cannot do better than MPI I/O on your system. Usually HDF5 parallel applications have little overhead over MPI I/O applications on the same system. If MPI I/O performs well, then you should expect good performance from Parallel HDF5. If you want to compare the performance of MPI I/O and Parallel HDF5 on your
    HDF Knowledge BaseJul 14, 2017
  3. Error: "The MPI_Comm_free() function was called after MPI_FINALIZE was invoked"

    I obtain the following error at the end of my program: The MPICommfree() function was called after MPIFINALIZE was invoked. This is disallowed by the MPI standard. Your MPI job will now abort. What should I look for to resolve this issue? Make sure that all open objects are closed before calling MPIFINALIZE
    HDF Knowledge BaseDec 14, 2017
  4. What if Parallel HDF5 tests fail with a ROMIO error: File locking failed in ADIOI_Set_lock ... ?

    This means that ROMIO, the MPII/O implementation used in mpich and openmpi and many other implementations, is attempting to use file locking when it is not supported by your file system. To resolve that, first you should attempt to rebuild your MPI library to disable file locking. This is the best way to resolve
    HDF Knowledge BaseJul 13, 2017
  5. Problems installing Parallel HDF5 on IBM Regatta (with AIX5)

    compiler that does not support MPI. Follow the instructions in the ./releasedocs/INSTALLparallel file, under the "IBM SP" section. Though it is geared towards … to compile and run some simple MPIIO programs, both C and Fortran90, with the compilers, mpccr and mpxlfr, respectively. Once you get your MPI parallel environment
    HDF Knowledge BaseJul 13, 2017
  6. Dataset gets filtered twice when creating filtered chunk dataset

    USER: When I create a filtered chunked dataset, I noticed that the dataset gets filtered twice: when the empty dataset gets created, and when it gets written. For efficiency, I would like to remove the first filter call (dataset creation) and if possible, avoid the initial disk allocation with empty data. I've tried op
    HDF Knowledge BaseDec 11, 2018
  7. How is HDF5 different than HDF4

    What are the Most Noticeable Differences between HDF4 and HDF5? The HDF5 Format is completely different from HDF4. For most users it will never be necessary to know about the file format for either format. Most users will work with the Data Model and APIs. The HDF4 and HDF5 Data Models and APIs are considerably differe
    HDF Knowledge BaseMay 01, 2019
  8. How do you build HDF5 on BlueGene/L?

    find out from your sysadmin what the MPI compilers on the system are. Building: You should run the ./configure script through yodconfigure like so: ./bin … a hello world MPI program and try to run it on a compute node like this: mpirun np 1 cwd /g/g23/xxxx/test.out If that doesn't work, either the command
    HDF Knowledge BaseJul 14, 2017
  9. GPFS Optimizations

    of aggregators. (See How to pass hints to MPI from HDF5.) faq hdf5 kbarticle parallel
    HDF Knowledge BaseAug 24, 2017
  10. Closing my HDF5 file, I get a segfault with an error "MPI_FILE_SET_SIZE(76): Inconsistent arguments to collective routine"

    between all the ranks. hdf5 kbarticle parallel troubleshooting mpi
    HDF Knowledge BaseJul 13, 2017