http://www.open-mpi.org/community/lists/devel/2015/01/16820.php,
coll ML has two pending issues: a deadlock and a performance critical
on every communicator creation. After confirmation over IM from
Pasha, the ML collective module will be disabled until it is
fixed. Token to Pasha.
We recognize that this means other users of OPAL will need to "wrap" the opal_process_name_t if they desire to abstract it in some fashion. This is regrettable, and we are looking at possible alternatives that might mitigate that requirement. Meantime, however, we have to put the needs of the OMPI community first, and are taking this step to restore hetero and SPARC support.
These two macros set the prefix for the OPAL and ORTE libraries,
respectively. Specifically, the OPAL library will be named
libPREFIXopen-pal.la and the ORTE library will be named
libPREFIXopen-rte.la.
These macros must be called, even if the prefix argument is empty.
The intent is that Open MPI will call these macros with an empty
prefix, but other projects (such as ORCM) will call these macros with
a non-empty prefix. For example, ORCM libraries can be named
liborcm-open-pal.la and liborcm-open-rte.la.
This scheme is necessary to allow running Open MPI applications under
systems that use their own versions of ORTE and OPAL. For example,
when running MPI applications under ORTE, if the ORTE and OPAL
libraries between OMPI and ORCM are not identical (which, because they
are released at different times, are likely to be different), we need
to ensure that the OMPI applications link against their ORTE and OPAL
libraries, but the ORCM executables link against their ORTE and OPAL
libraries.
of the topology is higher than the communicator size
It is possible to have a topology degree higher than the size of the communicator.
For example, a periodic cartesian communicator on MPI_COMM_SELF. This will leave
the neighborhood collectives with a request buffer that is too small.
This commits introduces a semantic change :
from now, c_topo must be set before invoking coll_select
A problem was found with the libnbc MPI_Iallgather
routine when using intercommunicators. Special
thanks to Takahiro Kawashima(Fujitsu) for the patch
and a test case. Verified master fails without the
patch and the test passes with the patch applied.
fixes#219
of the topology is higher than the communicator size
It is possible to have a topology degree higher than the size of the communicator.
For example, a periodic cartesian communicator on MPI_COMM_SELF. This will leave
the neighborhood collectives with a request buffer that is too small. This commit
adds a call that will dynamically increase the size of the request buffer if it
is too small.
A better fix would be to create the topology *before* calling the coll_select
routine on a communicator. This will take some discussion and the solution will
not likely be ready anytime soon.
Thanks to Lisandro Dalcin for reporting this.
Original thread: http://www.open-mpi.org/community/lists/devel/2014/08/15713.php
cmr=v1.8.3:reviewer=jsquyres
This commit was SVN r32796.
reviewed by miked
cmr=v1.8.3:reviewer=ompi-rm1.8
This commit was SVN r32753.
The following SVN revision numbers were found above:
r32735 --> open-mpi/ompi@5fecf65daf
reviewed by miked
cmr=v1.8.3:reviewer=ompi-rm1.8
This commit was SVN r32740.
The following SVN revision numbers were found above:
r32735 --> open-mpi/ompi@5fecf65daf
when CHECK_AND_RECYCLE detects an error, a message is displayed
if the error occurs on an intrinsic communicator, then abort
the program (instead of trying to free the communicator)
cmr=v1.8.3:reviewer=hjelmn
This commit was SVN r32659.
The only user of this code was coll/sm. I implemented a basic replacement
for the removed code. This gets the trunk compiling again with
--disable-dlopen.
This commit was SVN r32333.
WHAT: Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL
All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies. This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP. Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose. UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs. A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.
This commit was SVN r32317.
new flag to ompi_info that allows a user to print all MCA variables of a specific type.
--type version_string
This command will print all MCA variables of type version_string.
This feature was developed by Elena Shipunova and was reviewed by Josh Ladd.
This commit was SVN r32166.
the other collective modules. If we endup without some of the
collective the code will raise an error anyway.
cmr=v1.8.2:reviewer=hjelmn
This commit was SVN r32096.
This changeset :
- always call the low/level implementation for :
* MPI_Alltoallv
* MPI_Neighbor_alltoallv
* MPI_Alltoallw
* MPI_Neighbor_alltoallv
- fix mca_coll_tuned_alltoallv_intra_basic_inplace
so zero size types are correctly handled
cmr=v1.8.2:reviewer=bosilca:ticket=4715
This commit was SVN r32013.
The following Trac tickets were found above:
Ticket 4715 --> https://svn.open-mpi.org/trac/ompi/ticket/4715
Correctly handle the corner case in MPI_Alltoallv when
some tasks have no data to transfer and some other tasks
do have data to transfer.
This test case is covered in ibm/collective/alltoallv_somezeros
from the ompi-tests repo.
cmr=v1.8.2:reviewer=bosilca
This commit was SVN r31985.
Avoid sending/receiving zero size messages in order to be compliant
with the top-level modification
cmr=v1.8.2:ticket=4651:reviewer=bosilca
This commit was SVN r31836.
The following Trac tickets were found above:
Ticket 4651 --> https://svn.open-mpi.org/trac/ompi/ticket/4651
This commit :
- Correctly retrieve the communicator size when
checking memory and parameters
- Ensure (sendtype,sendcount) and (recvtype,recvcount)
matches and return with MPI_ERR_TRUNCATE otherwise
- Return with MPI_SUCCESS without invoking the low level
if no data is going to be transferred
- Fixes trac:4506
cmr=v1.8.2:reviewer=bosilca
This commit was SVN r31815.
The following Trac tickets were found above:
Ticket 4506 --> https://svn.open-mpi.org/trac/ompi/ticket/4506
It is essential to call mca_base_framework_close for every framework
that is opened. coll/ml was not doing this so neither bcol nor sbgp
were getting cleaned up. This commit fixes this omission.
Also fixed a leak caused by calling OBJ_DESTRUCT for something created
with OBJ_NEW. With these changes coll/ml appears to be valgrind clean.
cmr=v1.8.2:reviewer=manjugv
This commit was SVN r31743.
MPI_Cart_Create/MPI_Graph_create/MPI_Dist_Graph
Fixes trac:4581
This commit was SVN r31716.
The following Trac tickets were found above:
Ticket 4581 --> https://svn.open-mpi.org/trac/ompi/ticket/4581
top_ompi_srcdir -> OMPI_TOP_SRCDIR
top_ompi_builddir -> OMPI_TOP_BUILDDIR
We also split the srcdir/builddir flags according to their local tree (e.g., OPAL_TOP_SRCDIR), and tied them all together in configure.ac. Renamed ompi_ignore and ompi_unignore to be opal_<foo> as these are agnostic markers.
Only thing left is ompilibdir being treated similar to what we dif for srcdir/builddir. Coming soon.
This commit was SVN r31678.
Patch from Gilles Gouaillardet on #4517 to fix handling 0-sized
messages in coll tuned with MPI_ALLTOALLV and MPI_IN_PLACE.
Reviewed by Jeff Squyres.
Fixes trac:4517
cmr=v1.8.2:reviewer=ompi-rm1.8
This commit was SVN r31521.
The following Trac tickets were found above:
Ticket 4517 --> https://svn.open-mpi.org/trac/ompi/ticket/4517
Patch from Gilles Gouaillardet on #4506 to correctly handle 0-sized
messages in coll/basic MPI_Alltoallv and MPI_Alltoallw.
Reviewed by Jeff Squyres.
Fixes trac:4506.
cmr=v1.8.2:reviewer=ompi-rm1.8
This commit was SVN r31519.
The following Trac tickets were found above:
Ticket 4506 --> https://svn.open-mpi.org/trac/ompi/ticket/4506
Ensure to also OBJ_RELEASE the neightbor and ineighbor modules.
Fixes trac:4444 (this patch is from that ticket).
This commit was SVN r31516.
The following Trac tickets were found above:
Ticket 4444 --> https://svn.open-mpi.org/trac/ompi/ticket/4444
The file coll_ml_ibarrier.c wasn't included in coll/ml's Makefile.am
and the setup code from coll_ml_hier_algorithms_ibarrier.c was not
being called. It looks like this code is stale and has long since been
replaced by the code in coll_ml_barrier.c
Once all these little CMRs are approved I may make it into one roll-up
CMR to make it easier on the RM.
cmr=v1.8.1:reviewer=manjugv
This commit was SVN r31418.
a segmentation fault in the reduce cleanup
Some of the changes address false warnings produced by scan-build. I
added asserts and changed some malloc calls to calloc to silence these
warnings.
The was one issue in cleanup for reduce since the component_functions
member is changed by the allreduce call. There may be other issues
with how this code works but releasing the allocated
component_functions after setting up the static functions addresses
the primary issue (SIGSEGV).
cmr=v1.8.1:reviewer=manjugv
This commit was SVN r31417.
some of the collective modules, the shared memory and the profiling
interface. I left out VT, dynamic fcoll and seq rmaps.
cmr=v1.8.1:reviewer=jsquyres:subject=silence Coverity reported warnings
This commit was SVN r31309.
Discussed this with Manju and we decided to back this one out until a later time.
This reverts commit r31188 and closes trac:4435
This commit was SVN r31282.
The following SVN revision numbers were found above:
r31188 --> open-mpi/ompi@f1dd589092
The following Trac tickets were found above:
Ticket 4435 --> https://svn.open-mpi.org/trac/ompi/ticket/4435
There were a couple of issues with the memory leak fixes and several more verbose
issues. This fixes those issues.
cmr=v1.8.1:ticket=trac:4473
This commit was SVN r31273.
The following Trac tickets were found above:
Ticket 4473 --> https://svn.open-mpi.org/trac/ompi/ticket/4473
Thanks to ggouaillardet for finding and fixing these issues.
Closes trac:4460
cmr=v1.8.1:reviewer=manjugv
This commit was SVN r31264.
The following Trac tickets were found above:
Ticket 4460 --> https://svn.open-mpi.org/trac/ompi/ticket/4460
The error doesn't prevent the user from running so there is no reason
to display it unless the user requested it (through coll_ml_verbose).
cmr=v1.8:reviewer=jsquyres
This commit was SVN r31242.
a hierarchy actually matches a bcol that is in use.
There was a bug in one of the paths to calculate the ml buffer size. I fixed
the bug and squashed all the paths together to avoid further issues (the
result was correct in another path that calculated the same value).
Additionally, the i_hier was being used as the bcol_index. This is not
correct in a couple of cases so I added a variable to keep track of the
real bcol_index.
cmr=v1.8:reviewer=pasha
This commit was SVN r31189.
bound.
This case is correctly handled by coll/ml so remove the check that diables
coll/ml in the not bound case.
cmr=v1.8:reviewer=manjugv
This commit was SVN r31188.
This patch fixes two leaks:
- Fix typo in fallback collective code that caused coll/ml to retain
the ibcast module twice but only release it once. One of those ibcast
saves was supposed to be bcast.
- Do not check for module initialization in the module destructor. It
is possible to destruct a module that is partially setup.
cmr=v1.8:reviewer=manjugv
This commit was SVN r31187.
This isn't causing any errors that I know about but it does fix an
annoying valgrind warning. Simple fix, no review required.
cmr=v1.7.5:reviewer=ompi-rm1.7
This commit was SVN r31130.
There are situations where coll/ml does not initialize properly. These will
eventually need to be fixed but in the meantime it is better to not always
print an error message because the collective framework can still fall back
on another collective module. This commit reduces the verbose output.
cmr=v1.7.5:reviewer=manjugv
This commit was SVN r31129.
It is usually not a good idea to assert when something is not implemented
or something goes wrong. Replace asserts with debug output and return.
cmr=v1.7.5:reviewer=manjugv
This commit was SVN r31128.
Also fixed spelling: IS_NOT_RECHABLE -> IS_NOT_REACHABLE.
Also mark a few places where opal_show_help() should have been used;
Manju will take care of these.
This commit was SVN r31104.
In r31071 I modified the logic to not increment the hierarchy level if
no processes were selected by that sbgp. That fixed a problem seen on
systems where we don't support process binding. The problem is there
is a case where we actually did select processes yet the number of
selected processes is 0. We need to increment the hierarchy in this case
as well.
This should fix the segmentation fault found by recent MTT runs. Once
this is committed to 1.7.5 remove the .ompi_ignore's from coll/ml and
bcol/ptpcoll. Tested with ompi-tests/ibm.
cmr=v1.7.5:reviewer=rhc
This commit was SVN r31081.
The following SVN revision numbers were found above:
r31071 --> open-mpi/ompi@1911d97044
This was causing JVMs to run out of stack space, and all manner of
badness ensued.
Instead, use the heap -- that's what it's there for.
cmr=v1.7.5:reviewer=rhc:subject=make coll/ml use the heap for large debug array
This commit was SVN r31073.
fails to select any processes on any nodes.
Also modified basesmsocket to only print debugging info to the framework
output.
cmr=v1.7.5:reviewer=jsquyres
This commit was SVN r31071.
- -check-shmem-params is OFF by default. It checks OSHMEM API params and will abort on bad input
- hcoll do not save fallback coll pointers for unsupported collectives.
fixed by Val, Roman, reviewed by Miked/Igor
cmr=v1.7.5:reviewer=ompi-rm1.7
This commit was SVN r30995.
This is hot-fix patch for the issue reported by Ralph.
In future we plan to restructure ml data structure layout.
Tested by Nathan.
cmr=v1.7.5:ticket=trac:4158
This commit was SVN r30619.
The following Trac tickets were found above:
Ticket 4158 --> https://svn.open-mpi.org/trac/ompi/ticket/4158
This commit was SVN r30605.
The following SVN revision numbers were found above:
r30600 --> open-mpi/ompi@7d2c4cb468
r30602 --> open-mpi/ompi@9e751a0302
r30604 --> open-mpi/ompi@3012c280cf
Revision number ranges (suitable for "git log"):
r30602-30604 --> open-mpi/ompi@9e751a03^..3012c280
them, but it's going to take a little time (at least one day). So
Nathan says it's ok to .ompi_ignore coll ml until he's able to fix it.
This commit was SVN r30600.
Several changes are contained in this commit:
- Clean up tabs and trailing whitespaces
- Use consistent indentation in changed files
- Remove unused code. None of the removed code will ever have been
used in a trunk build.
- Clean up the smcm code quite a bit
- Do not fflush stderr and use opal_output instead of fprintf.
These changes have been tested on Cray XE-6 and PSM systems.
cmr=v1.7.5:ticket=trac:4158
This commit was SVN r30533.
The following Trac tickets were found above:
Ticket 4158 --> https://svn.open-mpi.org/trac/ompi/ticket/4158
This commit fixes one warning that should have caused coll/ml to segfault
on reduce. The fix should be correct but we will continue to investigate.
cmr=v1.7.5:ticket=trac:4158
This commit was SVN r30477.
The following Trac tickets were found above:
Ticket 4158 --> https://svn.open-mpi.org/trac/ompi/ticket/4158
After IM with Nathan, apply patch from ticket after verification by Paul Hargrove that it fixes the problem on non-x86 32-bit platforms
Verified by Paul, RM-approved
cmr=v1.7.4:reviewer=ompi-gk1.7
This commit was SVN r30411.
The following Trac tickets were found above:
Ticket 4143 --> https://svn.open-mpi.org/trac/ompi/ticket/4143
allgather.
The new collectives provide a signifigant performance increase over tuned for
small and medium messages. We are initially setting the priority lower than
tuned until this has had some time to soak in the trunk. Please set
coll_ml_priority to 90 for MTT runs.
Credit for this work goes to Manjunath Gorentla Venkata (ORNL), Pavel Shamis (ORNL),
and Nathan Hjelm (LANL).
Commit details (for reference):
Import ORNL's collectives for MPI_Allreduce, MPI_Reduce, and MPI_Allgather.
We need to take the basesmuma header into account when calculating the
ptpcoll small message thresholds. Add a define to bcol.h indicating the
maximum header size so we can take the header into account while not
making ptpcoll dependent on information from basesmuma.
This resolves an issue with allreduce where ptpcoll overwrites the
header of the next buffer in the basesmuma bank.
Fix reduce and make a sequential collective launcher in coll_ml_inlines.h
The root calculation for reduce was wrong for any root != 0. There are
four possibilities for the root:
- The root is not the current process but is in the current hierarchy. In
this case the root is the index of the global root as specified in the
root vector.
- The root is not the current process and is not in the next level of the
hierarchy. In this case 0 must be the local root since this process will
never communicate with the real root.
- The root is not the current process but will be in next level of the
hierarchy. In this case the current process must be the root.
- I am the root. The root is my index.
Tested with IMB which rotates the root on every call to MPI_Reduce. Consider
IMB the reproducer for the issue this commit solves.
Make the bcast algorithm decision an enumerated variable
Resolve various asset failures when destructing coll ml requests.
Two issues:
- Always reset the request to be invalid before returning it to the
free list. This will avoid an asset in ompi_request_t's destructor.
OMPI_REQUEST_FINI does this (and also releases the fortran handle
index).
- Never explicitly construct or destruct the superclass of an opal
object. This screws up the class function tables and will cause
either an assert failure or a segmentation fault when destructing
coll ml requests.
Cleanup allgather.
I removed the duplicate non-blocking and blocking functions and modeled
the cleanup after what I found in allreduce. Also cleaned up the code
somewhat.
Don't bother copying from the send to the recieve buffer in
bcol_basesmuma_allreduce_intra_fanin_fanout if the pointers are the
same.
The eliminates a warning about memcpy and aliasing and avoids an
unnecessary call to memcpy.
Alwasy call CHECK_AND_RELEASE on memsync collectives.
There was a call to OBJ_RELEASE on the collective communicator but
because CHECK_AND_RECYLCE was never called there was not matching call
to OBJ_RELEASE. This caused coll ml to leak communicators.
Make allreduce use the sequential collective launcher in coll_ml_inlines.h
Just launch the next collective in the component progress.
I am a little unsure about this patch. There appears to be some sort
of race between collectives that causes buffer exhaustion in some cases
(IMB Allreduce is a reproducer). Changing progress to only launch the
next bcol seems to resolve the issue but might not be the best fix.
Note that I see little-no performance penalty for this change.
Fix allreduce when there are extra sources.
There was an issue with the buffer offset calculation when there are
extra sources. In the case of extra sources == 1 the offset was set
to buffer_size (just past the header of the next buffer). I adjusted
the buffer size to take into accoun the maximum header size (see the
earlier commit that added this) and simplified the offset calculation.
Make reduce/allreduce non-blocking. This is required for MPI_Comm_idup
to work correctly.
This has been tested with various layouts using the ibm testsuite and
imb and appears to have the same performance as the old blocking version.
Fix allgather for non-contiguous layouts and simplify parsing the
topology.
Some things in this patch:
- There were several comments to the effect that level 0 of the
hierarchy MUST contain all of the ranks. At least one function
made this assumption but it was not true. I changed the sbgp
components and the coll ml initization code to enforce this
requirement.
- Ensure that hierarchy level 0 has the ranks in the correct
scatter gather order. This removes the need for a separate
sort list and fixes the offset calculation for allgather.
- There were several passes over the hierarchy to determine
properties of the hierarchy. I eliminated these extra passes
and the memory allocation associated with them and calculate the
tree properties on the fly. The same DFS recursion also handles
the re-order of level 0.
All these changes have been verified with MPI_Allreduce, MPI_Reduce, and
MPI_Allgather. All functions now pass all IBM/Open MPI, and IMB tests.
coll/ml: correct pointer usage for MPI_BOTTOM
Since contiguous datatypes are copied via memcpy (bypassing the convertor) we
need to adjust for the lb of the datatype. This corrects problems found testing
code that uses MPI_BOTTOM (NULL) as the send pointer.
Add fallback collectives for allreduce and reduce.
cmr=v1.7.5:reviewer=pasha
This commit was SVN r30363.
Adds coll_hcoll_np mca parameter similar to that of fca component (defaults to 32). Those who use hcoll be aware that from now on the communicators less than 32 procs will run w/o hcoll by default. - Resolves fallback issue in case libhcoll runs out of allowed contexts. The solution is moving hcoll_context_create from comm_enable to comm_query. Shortly, comm_enable should never return OMPI_ERROR in the coll component with highest priority (hcoll). Otherwise the ompi coll_base_select will unselect the coll funtion pointers and module references leaving the communicator w/o coll pointer. This will cause the fail. Same behavior can be reproduced even with tuned if one would hardcore some "return OMPI_ERROR" into it's module_enable funtion. - Additionally, removed all the dead code under #if 0; removed unused variables (path for library, active_modules list) and classes (module list wrapper)
Fixed by Val, Reviewed by Devendar/Josh/Miked
cmr=v1.7.4:reviewer=ompi-rm1.7
This commit was SVN r30341.
Set comm attribute with keyval.
Wait for pending hcoll module tasks in comm delete callback where PML
still valid on the communicator. safely destroy hcoll context during
hcoll module destructor.
Author: Devendar Bureddy
reviewed by miked
cmr=v1.7.4:reviewer=ompi-rm1.7
This commit was SVN r30175.
- HCOLL close without init
- Call hcoll progress after comm finalize
- mpirun default for coll_hcoll_enable is 1
fixed by Igor, reviewed by miked
cmr=v1.7.4:reviewer=ompi-rm1.7
This commit was SVN r30156.
configury/Makefile.am changes; this commit renames the internal
installdirs.h framework struct field names to match the configry macro
names:
* pkgdatdir -> ompidatadir
* pkglibdir -> ompilibdir
* pkgincludedir -> ompiincludedir
This commit was SVN r30145.
The following SVN revision numbers were found above:
r30140 --> open-mpi/ompi@8b778903d8
pkg{data,lib,includedir}, use our own ompi{data,lib,includedir}, which is
always set to {datadir,libdir,includedir}/openmpi. This will keep us from
having help files in prefix/share/open-rte when building without Open MPI,
but in prefix/share/openmpi when building with Open MPI.
This commit was SVN r30140.
- Modifications to coll/hcoll component related to the changes in the libhcoll API.
Now, hcoll_destroy_context accepts one more parameter that indicates if the context was
really destroyed as a result of the call.
This new "non-blocking" context destruction fixes hang discovered in IMB with mcast enabled.
- Clean up all the left contexts (if any) on the comm_world destruction.
fixed by Val, reviewed by miked
cmr=v1.7.4:reviewer=ompi-rm1.7
This commit was SVN r30055.
(aka the root). This commit is based on a patch provided by Pierre
Jolivet.
Fix all the output to match the failing MPI call.
This commit was SVN r29761.
To support the new mpool two changes were made to the mpool infrastructure:
1) Added an mpool flag to indicate that an mpool does not need the memory
hooks to use the leave pinned protocols. This flag is checked in the
mpool lookup.
2) Add a mpool context to the base registration. This new member is used
by the udreg mpool to store the udreg context associated with the
particular registration. The new member will not break the ABI
compatibility as the new member is only currently used by the udreg
mpool.
Dynamics support for Cray systems makes use of the global rank provided by
orte to give the ugni library a unique rank for each process. Dynamics
support is not available under direct-launch (srun.)
cmr=v1.7.4
This commit was SVN r29719.
Only use Portals on communicators with more than one rank
Fix computation of number of children when using the hypercube tree
This commit was SVN r29616.
