P2Pcontig needed a prototype and clang complaiend about several shadowed
declarations.

Paul Coffman authored Feb 04, 2014 and Rob Latham committed Mar 26, 2014

Two features in this change:
- selection of file domains can result in some i/o nodes with more work
  than others (or some with no work at all), so distribute file domains
  with some awareness of i/o nodes

- since we have some awareness of I/O nodes, select processes that are
  closes to those i/o nodes.

Experimental async-with-pthread I/O approach to hiding some of the I/O
latency/variability from the two-phase collectives.

heavily modified from Paul Coffman's (pkcoffman@us.ibm.com) original work

This reverts commit 3146e104.

In romio-standalone fixes, I zapped the inclusion of mpitypedefs.h, but
the "ensure this large value fits into pointer without overflowing"
check relied on some MPICH-internal macros/routines.  Only Blue Gene
driver uses those routines, so nightly tests didn't flag it.

No reviewer.

Rob Latham authored Oct 28, 2013 and Pavan Balaji committed Oct 31, 2013

MPIR_Type_get_contig_blocks is buggy for certain datatypes (example:
HDF5 multi-dataset IO generated type results in a contig block count of
5 billion.  should be more like 200).  Nothing uses this function except
ROMIO's flattening code.  I'd like to see profiling suggesting the count
of contiguous blocks is a profitable short-circuit before spending a ton
of time debugging it.

Signed-off-by: Pavan Balaji <balaji@mcs.anl.gov>

When flattening a datatype, be mindful of overflowing integers

Signed-off-by: Pavan Balaji <balaji@mcs.anl.gov>

MPI-3 introduced MPI_Count and MPI_Type_size_x.  Use these new routines
throughout ROMIO to support large datatypes.

Still to do:
- update other ADIO drivers

Signed-off-by: Pavan Balaji <balaji@mcs.anl.gov>

This doesn't fix any of the serious bugs or inefficiencies present in
the current external32 implementation.  But it at least fixes some very
valid warnings related to const-ness and passing incorrect pointer
types.

References ticket #1754

Reviewed-by: robl

This reverts r10641 and should fix most/all of tt#1758.  A better fix
should be considered.

Contributed by IBM.  Based on patch 0013 from code discussions.

Adds a new helper function, ADIOI_Err_create_code.

Contributed by IBM.  Based on patch 0012 from code discussions.

No reviewer.

By setting "indent-tabs-mode:nil" we should hopefully begin to slowly
squeeze out hard tabs from the source without a disruptive (to
downstream projects) whitespace-fixing change.

No reviewer.

disabled for the public interfaces, but all internal functions use
const.

No reviewer.

Use automake+libtool instead of simplemake+createshlib.  Parallel make
now works for real, and shared library creation should be more robust on
more platforms.  "make dist" now works, modulo building the documentation,
although for boring reasons we can't actually use it for the final
distribution tarball generation.

This is a massive change and without a doubt has some bugs in it.  We'll
work through them as we find them.

No reviewer.

only exposed in the "trace internal calls" case.

[svn-r8558] back out all the "same romio region" work, now that it lives on the "romio_ident_regions" branch

- hash the datatype in set view so we can get at least one thing out of the i/o path
- use a jenkins hash: it's not cryptographically secure but offers low
  collisions, which is what we really care about

well this sure turned out to be more involved than I imagined.  We do in fact
need to look at more than just the start and end offsets of the file domains.
Comparing MPI datatypes (file views) among all mpi processes requires some
work. In this approach we marshal the datatype into a serialized
representation, hash that representation, then compare that hash among all
processors.

the macro instead of the N places macro gets used..

with in-mpich2 romio

Reviewed by robl.

Many of the key (and for MPI_Info_set, value) arguments are string
literals, which elicit warnings about "discards qualifier" because the
MPI_Info interface is not itself const-correct.  This commit adds
ADIOI_Info_ helper macros that cast away the const qualifier and
converts most uses of MPI_Info_ functions to use the new macros.

Reviewed by robl@.

control systems, dust off the old zoidfs branch and commit to trunk
- simple, unoptimized  ad_zoidfs driver
- initial cut of "file system features"

now) unless enabled with a hint.

approaches can be enabled by hints.  Default takes 'classic' strided (old       listio) path.