William Gropp authored Feb 19, 2014 and Rob Latham committed May 02, 2014

While adding dataloop optimizations, a number of places where there
were errors in text or in nomunclature were found and fixed.

Signed-off-by: Rob Latham <robl@mcs.anl.gov>

William Gropp authored Feb 03, 2014 and Rob Latham committed May 02, 2014

With these optimizations, most of the datatype performance tests should
pass.  However, indexperf still fails, since these optimizations to not
address the pattern in indexperf.

Signed-off-by: Rob Latham <robl@mcs.anl.gov>

  MPI_Comm_split hang w/ collective_offload=yes on plinux w/o fca

Signed-off-by: Michael Blocksome <blocksom@us.ibm.com>

No review since F08 binding is experimental now.

No review since F08 binding is experimental now.

No review since F08 binding is experimental now.

Copies a sampling of tests from the f90 directory and converts them
to use the f08 bindings.

No review since it is experimental.

Adds configure logic and a stub Makefile for Fortran 2008 tests.

No review since F08 binding is experimental now.

No review since F08 binding is experimental now.

This includes a configure test to check if the compiler supports F08.

No review since F08 binding is experimental now.

This script is used to generate C wrapper files

No review since F08 binding is experimental now.

The script will
1) generate PMPI files. For PMPI specific procedure names, we use PMPIR_* instead
   of PMPI_*, since the later is reserved by MPI.
2) generate use_mpi_f08/Makefile.mk

No review since F08 binding is experimental now.

Redesigned the binding infrastructer and gave an almost complete F08 binding.
Remaining tasks include :

1) supporting non-contiguous subarray on the C wrapper side.
2) Use a script to autoset the now hard-coded compile time constants.

The directory structure is as following:

use_mpi_f08/                      --- To put F08 binding header files
use_mpi_f08/wrappers_f/           --- To put Fortran wrapper files
use_mpi_f08/wrappers_f/profiling/ --- To put PMPI Fortran wrapper files
use_mpi_f08/wrappers_c/           --- To put C wrapper files (auto-gen'ed or not)

Note we use *.F90 suffix instead of *.f90, since .F90 supports macro preprocess.
This leaves room for future revision. Additionally, the tests directory is removed
since it should not be there.

No review since F08 binding is experimental now.

The MPI-3 standard is broken in a bunch of ways with respect to
subarrays support.  For example, it is unclear as to which functions
can be passed a subarray and which cannot.  This is being fixed by the
WG.  In the meanwhile, we'll disable subarray types.

No review since F08 binding is experimental now.

The code is provided by Steve Oyanagi and Bill Long from Cray.

No review since F08 binding is experimental now.

for one-sided communication, the completion of a local operation is when
the completion handler of the operation is activated. The datatype
associated with the operation can not be freed until the completion
handler is activated which is MPIDI_Win_DoneCB. In the current code, the
mapped datatype is unmapped immediately freed after the routine gets the
control from PAMI calls. The calls could be PAMI_Send, PAMI_Get, PAMI_Rget,
PAMI_Put and PAMI_Rget. Please note that the datatype is needed for PAMI
to process the data.

The fix is to unmap the datatype in MPIDI_Win_DoneCB() and remove all
"unmap" datatype operations from put and get operations.

Signed-off-by: Michael Blocksome <blocksom@us.ibm.com>

MPID_Win_allocated_shared(), the routine could obtain memory space via either
shmget() or MPIU_Malloc() if one task on a node. In MPID_Win_free(), the
routine only frees shared memory space.

The fix is to free none-shared space if there is one.

Signed-off-by: Michael Blocksome <blocksom@us.ibm.com>

Request based RMA communication operations require that each operation
allocates a communication request object and associates it with the request
handle (the argument request) that can be used to wait or test for
completion. Both the structures for the request handle and the window
structure are not being freed. The problem is when the request handle
is created, the ref_count of the object is set to 2. When
MPID_Request_releas_inline() is called by a request based RMA operation,
the ref_count of the handle is decremented to 1. The allocated memory spaces
are freed only if ref_count is equal to 0.

To fix the problem, set the ref_count to 1 when the request handle is
created. In MPID_Request_release_inline, the routine decrements the
ref_count to 0 which leads the memory space be freed.

Signed-off-by: Michael Blocksome <blocksom@us.ibm.com>

In MPID_Win_accumulate, when processing non-contiguous datatype
for origin, the ref_count of datatype is incremented by one which
prevents the space allocated for contents and datatloop from being freed.

  MPID_Datatype_add_ref(req->origin.dt.pointer);

In the routine, the data is processed by MPIR_Localcopy and no need to
increment the reference count (ref_count) of the object by 1.

Signed-off-by: Michael Blocksome <blocksom@us.ibm.com>

No reviewer

Tested using the mpich testsuite and the following command:

  make testing MPITEST_PROGRAM_WRAPPER=" --ranks-per-node=8 --block R00-M1-N10 --timeout 60 --envs BG_MAPCOMMONHEAP=1 : " MPIEXEC=runjob V=1

The configure script could accidentally override the user's selection
of Fortran compiler for mpif77. Move AC_PROG_F77 until after we've
potentially set F77 = FC.

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

Lisandro Dalcin authored Apr 23, 2014 and Rob Latham committed Apr 28, 2014

The standard says a user-defined error code without a string should
return "", not NULL.

Closes #2067

Signed-off-by: Rob Latham <robl@mcs.anl.gov>

a successful test gives ' No Errors'

Lisandro Dalcin authored Apr 22, 2014 and Rob Latham committed Apr 28, 2014

The MPI-3 standard says (pp.354, lines 39-40):

"""
If MPI_ERROR_STRING is called when no string has been set, it will
return a empty
string (all spaces in Fortran, "" in C).
"""

RobL added bits to hook into the test infrastrucutre.

Signed-off-by: Rob Latham <robl@mcs.anl.gov>

if there are a lot of mpi processes with memory errors, the output can
get horribly jumbled if the "memory at address" bit is emitted in one
fprintf call and the "at file/line" bit emitted in a second.  For each
memory region, Build up the address/file-name string in memory and make
one fprintf (instead of two) per memory region.

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

This has been essentially removed for a while now and has been
throwing an error when someone uses it.  This patch gets rid of the
code for good.

Signed-off-by: Junchao Zhang <jczhang@mcs.anl.gov>

The --enable-f77 and --enable-fc options are deprecated in favor of
--enable-fortran.  However, instead of just breaking existing scripts
that use them, allow them to be used as well.

In the next major release (3.2), we should remove these options and
throw an error if someone uses them.

Signed-off-by: Junchao Zhang <jczhang@mcs.anl.gov>

No ABI changes.  Just update the release count.

Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

This test is behaving badly now as well. Given the overhaul of the ft system
that's coming, we're marking these tests as xfail now instead of putting a lot
of work into fixing them. They'll get cleaned up when the ULFM changes go in.

No reviewer

We moved away from --enable-f77 and --enable-fc to --enable-fortran.

No reviewer.

Pavan Balaji authored Apr 23, 2014 and Kenneth Raffenetti committed Apr 25, 2014

We need a better way to maintain consistency between environment
variables common to the MPICH library and mpiexec.  This patch doesn't
do that, but manually moves all of the variables controlling the port
range to mpiexec as well.

Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

Some NTFS deployments don't like the optimization where one process
creates a file and all processes open.  From Mark Allen: "On windows
when multiple hosts were used, it ended up that in ad_ntfs_open.c rank 0
used CreateFile() with OPEN_ALWAYS and everybody else used
OPEN_EXISTING, and those ranks all saw ERROR_FILE_NOT_FOUND.  As a fix I
added a retry loop and eventually (within 4-5 sec) the remote ranks
would see the file."

Simply have all processes create the file, as was done long long ago.

Signed-off-by: Mark Allen <markalle@us.ibm.com>

Before returning a larger than size 1 communicator in comm_split type,
make sure that the platform gives us the right tools to support shared
memory.  For example, on FreeBSD, pthread_mutexes don't work
correctly, even though they are a part of POSIX.  In such cases, we
return a size 1 communicator in comm_split_type.

Signed-off-by: Xin Zhao <xinzhao3@illinois.edu>

No reviewer.

Pavan Balaji authored Apr 16, 2014 and Pavan Balaji committed Apr 23, 2014

The user can now enable/disable fortran using the --enable-fortran
option, instead of separate --enable-f77 and --enable-fc.  Expert
users can control specific Fortran standards to use with
--enable-fortran=f77,f90 (and f08 in the future).

Also allow the user to specify only "FC".  If "F77" is not specified,
we use the same compiler as FC.

We now use mpifort as the primary Fortran wrapper, with mpif90 as a
symlink to it for backward compatibility.  If the user specifies a
different F77 compiler than the FC compiler, or if FFLAGS and FCFLAGS
are different, then a separate mpif77 is generated.  Otherwise, mpif77
is a symlink to mpifort.

Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

Pavan Balaji authored Apr 16, 2014 and Pavan Balaji committed Apr 23, 2014

Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

Pavan Balaji authored Apr 16, 2014 and Pavan Balaji committed Apr 23, 2014

Also squash bad white space changes in the move and replace f90
references with fc.

Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>