[petsc-users] MPI-IO

[Barry Smith]

On Jul 21, 2014, at 10:55 AM, Jed Brown <jed at jedbrown.org> wrote:

> Barry Smith <bsmith at mcs.anl.gov> writes:
>>    We should change this to use a PetscViewerFormat instead of special casing it.
> 
> It's not really a "format”,

   Many of them are not “format”, :-)

typedef enum {
  PETSC_VIEWER_DEFAULT,
  PETSC_VIEWER_ASCII_MATLAB,
  PETSC_VIEWER_ASCII_MATHEMATICA,
  PETSC_VIEWER_ASCII_IMPL,
  PETSC_VIEWER_ASCII_INFO,
  PETSC_VIEWER_ASCII_INFO_DETAIL,
  PETSC_VIEWER_ASCII_COMMON,
  PETSC_VIEWER_ASCII_SYMMODU,
  PETSC_VIEWER_ASCII_INDEX,
  PETSC_VIEWER_ASCII_DENSE,
  PETSC_VIEWER_ASCII_MATRIXMARKET,
  PETSC_VIEWER_ASCII_VTK,
  PETSC_VIEWER_ASCII_VTK_CELL,
  PETSC_VIEWER_ASCII_VTK_COORDS,
  PETSC_VIEWER_ASCII_PCICE,
  PETSC_VIEWER_ASCII_PYTHON,
  PETSC_VIEWER_ASCII_FACTOR_INFO,
  PETSC_VIEWER_ASCII_LATEX,
  PETSC_VIEWER_DRAW_BASIC,
  PETSC_VIEWER_DRAW_LG,
  PETSC_VIEWER_DRAW_CONTOUR,
  PETSC_VIEWER_DRAW_PORTS,
  PETSC_VIEWER_VTK_VTS,
  PETSC_VIEWER_VTK_VTR,
  PETSC_VIEWER_VTK_VTU,
  PETSC_VIEWER_BINARY_MATLAB,
  PETSC_VIEWER_NATIVE,
  PETSC_VIEWER_HDF5_VIZ,
  PETSC_VIEWER_NOFORMAT
  } PetscViewerFormat;

> but it would be nice to have a common way to
> address other viewer implementations.

   What do you mean by this?

> 
>>> PETSc devs, do you suppose MPI-IO support is stable enough that we could
>>> make this a default?
>> 
>>     It is not so much a question of stability, it is more a question
>>     of (I believe) MPI IO is just loads slower for what might normal
>>     PETSc users use, it only pays off for large numbers of nodes.
> 
> Do we have current data demonstrating that this is still the case?  It's
> really a failure of the implementations if they can't fall back to the
> dumbest mechanism when it's faster.

   Oh, actually I just remembered what always drove me crazy with MPI IO is that it saves it in native format meaning it is not portable to all systems (which have different endian). Portability before performance :-)