Difference between revisions of "Main Page/PIO"
Line 11: | Line 11: | ||
These three approaches produce one file per processor and we will refer them as ''old libraries''. <br> | These three approaches produce one file per processor and we will refer them as ''old libraries''. <br> | ||
− | : '''param(81) = 1''': use nek5000 http://nek5000.mcs.anl.gov/ old_output format (ASCII, fld format) ---> xxx.fld. <br> | + | : '''param(81) = 1''': use nek5000 (http://nek5000.mcs.anl.gov/) old_output format (ASCII, fld format) ---> xxx.fld. <br> |
: '''param(81) = 2''': use Fortran I/O library (ASCII, VTK format) ---> ascii-xxx.vtk. <br> | : '''param(81) = 2''': use Fortran I/O library (ASCII, VTK format) ---> ascii-xxx.vtk. <br> | ||
: '''param(81) = 3''': use C-POSIX I/O libraries (binary, VTK format) ---> binary-xxx.vtk. <br> | : '''param(81) = 3''': use C-POSIX I/O libraries (binary, VTK format) ---> binary-xxx.vtk. <br> | ||
Line 20: | Line 20: | ||
Jing Fu et. al, Parallel I/O performance for application-level checkpointing | Jing Fu et. al, Parallel I/O performance for application-level checkpointing | ||
− | on the Blue Gene/P" http://www.mcs.anl.gov/~mmin/ICS2011.pdf. | + | on the Blue Gene/P" http://www.mcs.anl.gov/~mmin/ICS2011.pdf |
+ | |||
+ | Jing Fu et. al, Parallel I/O performance for application-level checkpointing | ||
+ | on the Blue Gene/P. | ||
Revision as of 10:58, 12 June 2011
This is the document page for parallel I/O library developed for NekCEM.
Background
- File Format
- Binary (used for production, compact size), or ASCII (used for debugging, human-readable)
Usage Introduction:
For traditional I/O approaches based on one file per processor, users can use #1,2,3
in .rea file for a specific example, by parameter 81.
These three approaches produce one file per processor and we will refer them as old libraries.
- param(81) = 1: use nek5000 (http://nek5000.mcs.anl.gov/) old_output format (ASCII, fld format) ---> xxx.fld.
- param(81) = 2: use Fortran I/O library (ASCII, VTK format) ---> ascii-xxx.vtk.
- param(81) = 3: use C-POSIX I/O libraries (binary, VTK format) ---> binary-xxx.vtk.
Several advanced parallel I/O approaches were developed. Performance for those approaches are detailed in
Jing Fu et. al, Parallel I/O performance for application-level checkpointing on the Blue Gene/P" http://www.mcs.anl.gov/~mmin/ICS2011.pdf
Jing Fu et. al, Parallel I/O performance for application-level checkpointing on the Blue Gene/P.
- param(81) = 4: collective for N processors IO to 1 file ---> mpi-binary-N1-xxx.vtk
- param(81) = 5: collective IO for N processors to multiple M-files ---> mpi-binary-NM-xxx.vtk.
- param(81) = 6: reduced-blocking IO for N processors to 1 file with M writers ---> mpi-binary-NM1-xxx.vtk.
- param(81) = 7: reduced-blocking IO for N processors to 1 file with M writers ---> mpi-ascii-NM1-xxx.vtk.
- param(81) = 8: reduced-blocking IO for N processors to multiple M-files with M writers ---> mpi-binary-NMM-xxx.vtk.
Note that param(82) and param(83) need to be set correctly in *.rea file.
- param(82) = number of output files,
- param(83) = max number of fields to be written.
The output files with param(81)=2,3,4,5,6,7,8 cab be visualized with ParaView and VisIt.
The output with param(81)=1 can be visualized with nek5000 visualization tool, postx