of the original datatype are allowed (not in type map nor extent). Make it
clear in the code.
Allow 0-count cases to the contiguous memory check.
This commit was SVN r28568.
of the Fortran datatypes. This patch prevent the copy of the
datatype description from the OPAL to the OMPI layer in order
to decrease the memory requirements.
This commit was SVN r28553.
some relevant updates/new functionality in the opal/mca/hwloc and
orte/mca/rmaps bases. This work was mainly developed by Mellanox,
with a bunch of advice from Ralph Castain, and some minor advice from
Brice Goglin and Jeff Squyres.
Even though this is mainly Mellanox's work, Jeff is committing only
for logistical reasons (he holds the hg+svn combo tree, and can
therefore commit it directly back to SVN).
-----
Implemented distance-based mapping algorithm as a new "mindist"
component in the rmaps framework. It allows mapping processes by NUMA
due to PCI locality information as reported by the BIOS - from the
closest to device to furthest.
To use this algorithm, specify:
{{{mpirun --map-by dist:<device_name>}}}
where <device_name> can be mlx5_0, ib0, etc.
There are two modes provided:
1. bynode: load-balancing across nodes
1. byslot: go through slots sequentially (i.e., the first nodes are
more loaded)
These options are regulated by the optional ''span'' modifier; the
command line parameter looks like:
{{{mpirun --map-by dist:<device_name>,span}}}
So, for example, if there are 2 nodes, each with 8 cores, and we'd
like to run 10 processes, the mindist algorithm will place 8 processes
to the first node and 2 to the second by default. But if you want to
place 5 processes to each node, you can add a span modifier in your
command line to do that.
If there are two NUMA nodes on the node, each with 4 cores, and we run
6 processes, the mindist algorithm will try to find the NUMA closest
to the specified device, and if successful, it will place 4 processes
on that NUMA but leaving the remaining two to the next NUMA node.
You can also specify the number of cpus per MPI process. This option
is handled so that we map as many processes to the closest NUMA as we
can (number of available processors at the NUMA divided by number of
cpus per rank) and then go on with the next closest NUMA.
The default binding option for this mapping is bind-to-numa. It works
if you don't specify any binding policy. But if you specified binding
level that was "lower" than NUMA (i.e hwthread, core, socket) it would
bind to whatever level you specify.
This commit was SVN r28552.
of the OPAL datatype descriptions upon MPI_Init. Now each layer (OPAL
and OMPI) uses it's own descriptions for the predefined datatypes,
thus preventing over-writing of the other layer data description.
This commit was SVN r28535.
- fixed compiler warnings when compiling for 32-bit
- MPI wrapper generator scripts:
- removed non-posix call to length(array)
- exit scripts if any statement returns a non-true return value (set -e)
This commit was SVN r28524.
- general:
- incremented version number to 5.14.4
- fixed Coverity CIDs: 72002, 72099, 72273, 710580, 710664, 710665, 710666
- VT libs:
- fixed "incompatible declaration" errors when building against an MPI-3 implementation
Since MPI-3 the C keyword "const" is added to all relevant MPI API parameters
(e.g. MPI_Send(void* sendbuf, ...) -> MPI_Send(const void* sendbuf, ...)).
Prepending the macro CONST to these parameters which is defined either to "const" (if MPI-3) or to nothing (if MPI-1/2).
- fixed potential buffer overflow when reading the filter file
- CUDA tracing:
- enabled access to CUPTI counters for CUDA tracing via CUPTI
- enabled GPU memory usage tracing independent of the CUDA API
- enabled recording of CUDA synchronization and implicit synchronization in blocking CUDA memory copies for CUDA tracing via CUPTI
- enabled recording of synchronous peer-to-peer CUDA memory copies for CUDA tracing via CUPTI
- consider CUDA data transfers as not idle for option 'pure_idle'
- fixed identification of the CUDA device ID for CUDA tracing via CUPTI
- fixed region filtering for applications using the CUDA runtime API wrapper
- compiler wrappers: add path to mpi.h to the PDT parser command and preprocessor flags
This commit was SVN r28494.
in generated executables on systems that support it. Use
--disable-wrapper-rpath to disable this behavior. See text in
README about --disable-wrapper-rpath for more details.
This commit was SVN r28479.
The following Trac tickets were found above:
Ticket 376 --> https://svn.open-mpi.org/trac/ompi/ticket/376
functions will now show_help() their own error messages if something
goes wrong (per r28470).
This commit was SVN r28471.
The following SVN revision numbers were found above:
r28470 --> open-mpi/ompi@2ff95a7739
