1
1
Граф коммитов

513 Коммитов

Автор SHA1 Сообщение Дата
Shiqing Fan
f43862420c Convert the bad dos line endings to unix style for all windows related files.
This commit was SVN r24137.
2010-12-02 12:08:08 +00:00
Mike Dubman
956e030f28 support for dynamic rules to control offload
This commit was SVN r24094.
2010-11-29 04:11:57 +00:00
Mike Dubman
5a7d76bb9c resolve many warnings, comply to c99
This commit was SVN r24040.
2010-11-11 12:14:31 +00:00
Mike Dubman
f9bebe53f9 - fix fca support for MPI_IN_PLACE in allgather and allgatherv collectives
This commit was SVN r23841.
2010-10-06 19:09:02 +00:00
Mike Dubman
f525245498 - support for MPI_IN_PLACE during gather ops
- fix ABI check and message

This commit was SVN r23840.
2010-10-06 16:27:45 +00:00
Jeff Squyres
73bcc4a36b Fix mistake that came in via the ompi-agen tree in r23764. The mistake wasn't part of the core autogen upgrade; it was an additional 'bonus' cleanup. Oops. The mistake will always create a set of directories under installdir, even if you do not --with-devel-headers. The set of directories will be empty, but still -- they should not be there at all. This commit fixes that -- the directories are not created at all if you do not --with-devel-headers
This commit was SVN r23801.

The following SVN revision numbers were found above:
  r23764 --> open-mpi/ompi@40a2bfa238
2010-09-24 22:53:28 +00:00
Mike Dubman
58aa7fd161 enabling *gather*
This commit was SVN r23773.
2010-09-20 06:29:54 +00:00
Mike Dubman
f754bde8eb fixing r23764 leftovers, adopting Jeff's note
This commit was SVN r23772.

The following SVN revision numbers were found above:
  r23764 --> open-mpi/ompi@40a2bfa238
2010-09-20 06:27:43 +00:00
Mike Dubman
bd9a1f28a3 revert r23764 in ompi/mca/coll/fca
This commit was SVN r23771.

The following SVN revision numbers were found above:
  r23764 --> open-mpi/ompi@40a2bfa238
2010-09-20 06:06:45 +00:00
Ralph Castain
40a2bfa238 WARNING: Work on the temp branch being merged here encountered problems with bugs in subversion. Considerable effort has gone into validating the branch. However, not all conditions can be checked, so users are cautioned that it may be advisable to not update from the trunk for a few days to allow MTT to identify platform-specific issues.
This merges the branch containing the revamped build system based around converting autogen from a bash script to a Perl program. Jeff has provided emails explaining the features contained in the change.

Please note that configure requirements on components HAVE CHANGED. For example. a configure.params file is no longer required in each component directory. See Jeff's emails for an explanation.

This commit was SVN r23764.
2010-09-17 23:04:06 +00:00
Mike Dubman
104d57f69a * Support allgatherv, convert displs and rcounts arrays to bytes.
* change comm_init API - no need to pass local rank groups, fca calculates that on its own.
* remove local rank list from module - libfca maintains that now.
* in fca_bcast and fca_reduce - pass root rank index and let libfca figure out the local rank index.

This commit was SVN r23716.
2010-09-05 09:49:59 +00:00
Mike Dubman
48274c1c77 better control for enable/disable specific coll APIs
This commit was SVN r23708.
2010-09-02 09:22:24 +00:00
Mike Dubman
8ef56bf258 * drop support for FCA v1.2
* add support for FCA ABI
* add support for allgather

This commit was SVN r23705.
2010-09-01 11:29:10 +00:00
Mike Dubman
fca50c4a09 comply to code-style: no c++ style commends
This commit was SVN r23645.
2010-08-24 13:42:21 +00:00
Mike Dubman
9cb2e0490b removed #if 0
This commit was SVN r23643.
2010-08-24 13:32:28 +00:00
Mike Dubman
a036c24253 revert fix to comply with #2534
- use op->o_name directly
- cosmetic prints

This commit was SVN r23614.
2010-08-15 11:04:34 +00:00
Mike Dubman
16d7169680 refactoring:
* split fca_open() into fca_register() and fca_open()

This commit was SVN r23598.
2010-08-12 12:05:23 +00:00
Mike Dubman
ba5bc9b674 fixes:
* fixup lookup of supported ops by name:
        in ompi 1.5.x the op string representation were changed from MPI_XXX to MPI_OP_XXX (relative to OMPI 1.4.x)
		* keep compat between diff versions of FCA
		* better error handling (return error if symbol not found)
		* register to opal_progress and call fca_progress API

This commit was SVN r23597.
2010-08-12 08:15:55 +00:00
Mike Dubman
7d1a8a154d fca:
- keep compat to fca v1.2 and fca 2.0
- fix segv
- keep compat to ompi 1.4.x

This commit was SVN r23569.
2010-08-08 13:28:41 +00:00
Mike Dubman
2914d11793 fix datatype API
This commit was SVN r23552.
2010-08-04 14:01:54 +00:00
Shiqing Fan
a096cc9082 it's not a component for Windows, so get rid of the Windows support files.
This commit was SVN r23543.
2010-08-02 17:12:40 +00:00
Mike Dubman
7cbe9b43c2 initial release of Voltaire FCA (fabric collective accelerator) collective component
- compatible with FCA v1.2

This commit was SVN r23539.
2010-08-02 11:25:53 +00:00
Jeff Squyres
87e17a41da Ensure that the com_rules[] array entries are initialized to NULL in
case individual entries aren't used, but dynamic rules are enabled
(i.e., at least one or more of them are not NULL, meaning that they'll
all be assumed to be either NULL or a valid value).

This commit was SVN r23361.
2010-07-07 14:04:18 +00:00
Jeff Squyres
c8bb7537e7 Remove include/opal/sys/cache.h -- its only purpose in life was to
#define CACHE_LINE_SIZE to 128.  This name has a conflict on NetBSD,
and it seems kinda odd to have a header file that ''only'' defines a
single value.  Also, we'll soon be raising hwloc to be a first-class
item, so having this file around seemed kinda weird.

Therefore, I replaced CACHE_LINE_SIZE with opal_cache_line_size, an
int (in opal/runtime/opal_init.c and opal/runtime/opal.h) on the
rationale that we can fill this in at runtime with hwloc info (trunk
and v1.5/beyond, only).  The only place we ''needed'' a compile-time
CACHE_LINE_SIZE was in the BTL SM (for struct padding), so I made a
new BTL_SM_ preprocessor macro with the old CACHE_LINE_SIZE value
(128).  That use isn't suitable for run-time hwloc information,
anyway.

This commit was SVN r23349.
2010-07-06 14:33:36 +00:00
Samuel Gutierrez
2fb7c344fc Added a new System V (sysv) shared memory component for Open MPI.
Configure Option:
--enable-sysv

MCA Parameter:
mpi_common_sm

mpi_common_sm accepts a comma delimited list of: [sysv],mmap (order
dependent).  The first component that is successfully selected is used. For
example, -mca mpi_common_sm sysv,mmap will first try sysv. If sysv is not
successfully selected, then mmap will be used.  mmap will be used if 
mpi_common_sm is not provided.

Notes:
Please make certain that your system's shmmax limit, or equivalent, is larger
than mpool_sm_min_size.  Otherwise, shmget may fail.

This commit was SVN r23260.
2010-06-09 16:58:52 +00:00
Edgar Gabriel
f6598138ba fix some instances, where we might have allocated 0 bytes. Also, for allgather
make sure that we do not call coll_gather and coll_bcast in the very same
instances, since some collective (intra) modules do not seem to like the fact
if they are called for scount or rcount being zero (for regular
intra-communicator operations, this is handled on the MPI API layer).

Fixes trac:2405

This commit was SVN r23188.

The following Trac tickets were found above:
  Ticket 2405 --> https://svn.open-mpi.org/trac/ompi/ticket/2405
2010-05-20 22:23:44 +00:00
George Bosilca
c51932c250 Don't forget to initialize "line" in all cases.
This commit was SVN r23178.
2010-05-19 21:19:45 +00:00
Abhishek Kulkarni
afbe3e99c6 * Wrap all the direct error-code checks of the form (OMPI_ERR_* == ret) with
(OMPI_ERR_* = OPAL_SOS_GET_ERR_CODE(ret)), since the return value could be a
 SOS-encoded error. The OPAL_SOS_GET_ERR_CODE() takes in a SOS error and returns
 back the native error code.

* Since OPAL_SUCCESS is preserved by SOS, also change all calls of the form
  (OPAL_ERROR == ret) to (OPAL_SUCCESS != ret). We thus avoid having to
  decode 'ret' to get the native error code.

This commit was SVN r23162.
2010-05-17 23:08:56 +00:00
Jeff Squyres
181331d65e Very minor nits/updates.
This commit was SVN r22977.
2010-04-15 14:44:55 +00:00
Rainer Keller
f6e4694d67 - Print the name correctly when a certain sync module is disabled
This should be cmr'd to v1.5 and v1.4.2 (but the svn post hook won't
   let me at the moment).

This commit was SVN r22827.
2010-03-13 21:07:34 +00:00
Jeff Squyres
5ec2d8764b Amendment to r22671: change the name of the new communicator flag from
INTERNAL to EXTRA_RETAIN, because not all "internal" communicators
have this flag set (only internal communicators with CIDs less than
their parent).  Hence, what this flag ''really'' means is that there
was an extra RETAIN performed on it.  So name the flag just that --
EXTRA_RETAIN -- indicating that an extra RETAIN has occurred.

This commit was SVN r22690.

The following SVN revision numbers were found above:
  r22671 --> open-mpi/ompi@61dee816db
2010-02-23 21:24:07 +00:00
Edgar Gabriel
61dee816db This commit fixes a bug on how to deal with the potential if a 'dependent'
communicator that we created has a lower CID than the parent comm. This can
happen when using the hierarch collective communication module or for
inter-communicators (since we make a duplicate of the original communicator).
This is not a problem as long as the user calls MPI_Comm_free on the parent 
communicator.  However, if the communicators are not freed by the user but
released by Open MPI in MPI_Finalize, we walk through the list of still
available communicators and free them one by one. Thus, local_comm is freed
before the actual inter-communicator. However, the local_comm pointer in the
inter communicator will still contain the 'previous' address of the local_comm
and thus this will lead to a segmentation violation. In order to prevent that
from happening, we increase the reference counter local_comm by one if its CID
is lower than the parent. We cannot increase however its reference counter if
the CID of local_comm is larger than the CID of the inter communicators, since
a regular MPI_Comm_free would leave in that the case the local_comm hanging
around and thus we would not recycle CID's properly, which was the reason and
the cause for this trouble.

This commit fixes tickets 2094 and 2166. Note however, that I want to close
them manually, since a slightly different patch is required for the 1.4
series. This commit will have to be applied for the 1.5 series. And I will
need a volunteer to review it.

This commit was SVN r22671.
2010-02-19 23:45:30 +00:00
George Bosilca
3bceb20b1c Only get the receive datatype extent on the root process, as every
other process should ignore this value. Thanks to Michael Hofmann
for investigating this issue.

This commit closes trac:2268.

This commit was SVN r22639.

The following Trac tickets were found above:
  Ticket 2268 --> https://svn.open-mpi.org/trac/ompi/ticket/2268
2010-02-17 16:01:50 +00:00
George Bosilca
144143a3ff Remove an unused local variable.
This commit was SVN r22566.
2010-02-05 22:27:24 +00:00
George Bosilca
bc7ceb3587 We enable the dynamic decision if the user force it via an MCA argument or set it in the
decision file. In addition do a fine grain activation, i.e. per collective function.

This commit was SVN r22510.
2010-01-29 09:03:59 +00:00
Shiqing Fan
ad763c327d Restore several linked libraries that were deleted by mistake in r22405.
This commit was SVN r22415.

The following SVN revision numbers were found above:
  r22405 --> open-mpi/ompi@872a4047ba
2010-01-14 21:50:42 +00:00
Shiqing Fan
872a4047ba Fix the bug that caused by ADD_DEPENDENCIES() from different version of CMake.
In CMake 2.6 and earlier, this function add dependencies for targets and also link the target libraries automatically, but in CMake 2.8,this behavior has been changed, i.e. it will only add the dependencies but no link, which will cause linking errors at compilation time.

This commit was SVN r22405.
2010-01-14 18:10:20 +00:00
George Bosilca
f0303a8b25 Indentation.
This commit was SVN r22254.
2009-12-02 22:03:52 +00:00
George Bosilca
3a2f071018 If the user asked for dynamic rules but "forget" to provide them, nicely
complain and switch back to the default behavior (fixed rules).

This commit was SVN r22109.
2009-10-19 17:58:47 +00:00
Jeff Squyres
0f8ac9223f Refs trac:2023, #2027.
This commit does a bunch of things:

 * Address all remaining code review items from CMR #2023:

   * Defer mmap setup to be lazy; only set it up the first time we
     invoke a collective.  In this way, we don't penalize apps that
     make lots of communicators but don't invoke collectives on them
     (per #2027).
   * Remove the extra assignments of mca_coll_sm_one (fixing a
     convertor count setup that was the real problem).
   * Remove another extra/unnecessary assignment.
   * Increase libevent polling frequency when using the RML to
     bootstrap mmap'ed memory.
   * Fix a minor procs-related memory leak in btl_sm.
 * Commit a datatype fix that George and I discovered along the way to
   fixing the coll sm.
 * Improve error messages when mmap fails, potentially trying to
   de-alloc any allocated memory when that happens.
 * Fix a previously-unnoticed confusion between extent and true_extent
   in coll sm reduce.

This commit was SVN r22049.

The following Trac tickets were found above:
  Ticket 2023 --> https://svn.open-mpi.org/trac/ompi/ticket/2023
2009-10-02 17:13:56 +00:00
Shiqing Fan
96e9ffa016 Fix a type cast.
This commit was SVN r22034.
2009-09-30 14:02:47 +00:00
Jeff Squyres
152bc14079 Rename the help file to be consistent with others; add it to the Makefile.am.
This commit was SVN r22005.
2009-09-23 20:28:49 +00:00
Jeff Squyres
1ef988c3d9 A slight optimization: no longer call sched_yield() when polling for
shmem progress (or the Windows equiv).  Instead, poll hard on the
condition, but periocially call opal_progress().  This allows
badly-formed apps (e.g., the ibm test communicator/bsend_free) to
actually complete.

To be clear, there are far too many apps out there that assume that
MPI collectives will actually progress the rest of MPI.  I don't like
putting in a feature to enable broken apps, but I have a dim
recollection of this issue coming up before (apps "hanging" when
testing the sm coll because they assumed that calling collectives
would trigger other MPI progress).  Rather than have people claim that
OMPI is broken, I prefer to put in this "workaround".  :-(

Indeed, the bsend_free test ''may'' be coded that way for exactly that
reason...?  I don't remember offhand...

This commit was SVN r21984.
2009-09-21 22:20:44 +00:00
Jeff Squyres
533633b8cb Fixes trac:1988. The little bug that turned out to be huge. Yoinks.
* Various cosmetic/style updates in the btl sm
 * Clean up concept of mpool module (I think that code was written way
   back when the concept of "modules" was fuzzy)
 * Bring over some old fixes from the /tmp/timattox-sm-coll/ tree to
   fix potential segv's when mmap'ed regions were at different
   addresses in different processes (thanks Tim!).
 * Change sm coll to no longer use mpool as its main source of shmem;
   rather, just mmap its own segment (because it's fixed size --
   there was nothing to be gained by using mpool; shedding the use of
   mpool saved a lot of complexity in the sm coll setup).  This
   effectively made Tim's fixes moot (because now everything is an
   offset into the mmap that is computed locally; there are no global
   pointers).  :-)
 * Slightly updated common/sm to allow making mmap's for a specific
   set of procs (vs. ''all'' procs in the process).  This potentially
   allows for same-host-inter-proc mmaps -- yay!
 * Fixed many, many things in the coll sm (particularly in reduce):
   * Fixed handling of MPI_IN_PLACE in reduce and allreduce
   * Fixed handling of non-contiguous datatypes in reduce
   * Changed the order of reductions to go from process (n-1)'s data
     to process 0's data, because that's how all other OMPI coll
     components work
   * Fixed lots of usage of ddt functions
   * When using a non-contiguous datatype, if the root process is not
     (n-1), now we used a 2nd convertor to copy from shmem to the rbuf
     (saves a memory copy vs. what was done before)
   * Lots and lots of little cleanups, clarifications, and minor
     optimizations (although still more could be done -- e.g., I think
     the use of write memory barriers is fairly sub-optimal; they
     could be ganged together at the root, for example)

I'm marking this as "fixes trac:1988" and closing the ticket; if something
is still broken, we can re-open the ticket.

This commit was SVN r21967.

The following Trac tickets were found above:
  Ticket 1988 --> https://svn.open-mpi.org/trac/ompi/ticket/1988
2009-09-15 00:25:21 +00:00
Rainer Keller
8e1b23779f - Replace combinations of
#if defined (c_plusplus)
          defined (__cplusplus)
   followed by
      extern "C" {
   and the closing counterpart by BEGIN_C_DECLS and END_C_DECLS.

   Notable exceptions are:
    - opal/include/opal_config_bottom.h:
      This is our generated code, that itself defines BEGIN_C_DECL and
      END_C_DECL
    - ompi/mpi/cxx/mpicxx.h:
      Here we do not include opal_config_bottom.h:                                 
    - Belongs to external code:                                                    
      opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.c        
      opal/mca/backtrace/darwin/MoreBacktrace/MoreDebugging/MoreBacktrace.h        
    - opal/include/opal/prefetch.h:
      Has C++ specific macros that are protected:                                  

    - Had #if ... } #endif  _and_ END_C_DECLS (aka end up with 2x
      END_C_DECLS)
      ompi/mca/btl/openib/btl_openib.h
    - opal/event/event.h has #ifdef __cplusplus as BEGIN_C_DECLS...
    - opal/win32/ompi_process.h: had extern "C"\n {...
      opal/win32/ompi_process.h: dito
    - ompi/mca/btl/pcie/btl_pcie_lex.l: needed to add *_C_DECLS
      ompi/mpi/f90/test/align_c.c: dito
    - ompi/debuggers/msgq_interface.h: used #ifdef __cplusplus
    - ompi/mpi/f90/xml/common-C.xsl: Amend

   Tested on linux using --with-openib and --with-mx

   The following do not contain either opal_config.h, orte_config.h or
   ompi_config.h
   (but possibly other header files, that include one of the above):
      ompi/mca/bml/r2/bml_r2_ft.h
      ompi/mca/btl/gm/btl_gm_endpoint.h
      ompi/mca/btl/gm/btl_gm_proc.h
      ompi/mca/btl/mx/btl_mx_endpoint.h
      ompi/mca/btl/ofud/btl_ofud_endpoint.h
      ompi/mca/btl/ofud/btl_ofud_frag.h
      ompi/mca/btl/ofud/btl_ofud_proc.h
      ompi/mca/btl/openib/btl_openib_mca.h
      ompi/mca/btl/portals/btl_portals_endpoint.h
      ompi/mca/btl/portals/btl_portals_frag.h
      ompi/mca/btl/sctp/btl_sctp_endpoint.h
      ompi/mca/btl/sctp/btl_sctp_proc.h
      ompi/mca/btl/tcp/btl_tcp_endpoint.h
      ompi/mca/btl/tcp/btl_tcp_ft.h
      ompi/mca/btl/tcp/btl_tcp_proc.h
      ompi/mca/btl/template/btl_template_endpoint.h
      ompi/mca/btl/template/btl_template_proc.h
      ompi/mca/btl/udapl/btl_udapl_eager_rdma.h
      ompi/mca/btl/udapl/btl_udapl_endpoint.h
      ompi/mca/btl/udapl/btl_udapl_mca.h
      ompi/mca/btl/udapl/btl_udapl_proc.h
      ompi/mca/mtl/mx/mtl_mx_endpoint.h
      ompi/mca/mtl/mx/mtl_mx.h
      ompi/mca/mtl/psm/mtl_psm_endpoint.h
      ompi/mca/mtl/psm/mtl_psm.h
      ompi/mca/pml/cm/pml_cm_component.h
      ompi/mca/pml/csum/pml_csum_comm.h
      ompi/mca/pml/dr/pml_dr_comm.h
      ompi/mca/pml/dr/pml_dr_component.h
      ompi/mca/pml/dr/pml_dr_endpoint.h
      ompi/mca/pml/dr/pml_dr_recvfrag.h
      ompi/mca/pml/example/pml_example.h
      ompi/mca/pml/ob1/pml_ob1_comm.h
      ompi/mca/pml/ob1/pml_ob1_component.h
      ompi/mca/pml/ob1/pml_ob1_endpoint.h
      ompi/mca/pml/ob1/pml_ob1_rdmafrag.h
      ompi/mca/pml/ob1/pml_ob1_recvfrag.h
      ompi/mca/pml/v/pml_v_output.h
      opal/include/opal/prefetch.h
      opal/mca/timer/aix/timer_aix.h
      opal/util/qsort.h
      test/support/components.h

This commit was SVN r21855.

The following SVN revision numbers were found above:
  r2 --> open-mpi/ompi@58fdc18855
2009-08-20 11:42:18 +00:00
George Bosilca
23e8ce91ba Rework the selection logic for the tuned collectives. All supported collectives
now are able to use the dynamic rules. Moreover, these rules are loaded only once,
and stored at the component level. All communicators are able to use these rules
(not only MPI_COMM_WORLD as until now).
A lot of minor corrections, memory management issues and reduction in the amount
of memory used by the tuned collectives.

This commit was SVN r21825.
2009-08-14 21:06:23 +00:00
Shiqing Fan
bce2f44154 Update related .windows files with proper compiling properties, in order to have a successful DSO build.
This commit was SVN r21805.
2009-08-12 08:55:58 +00:00
Rainer Keller
6c5532072a - Split the datatype engine into two parts: an MPI specific part in
OMPI
   and a language agnostic part in OPAL. The convertor is completely
   moved into OPAL.  This offers several benefits as described in RFC
   http://www.open-mpi.org/community/lists/devel/2009/07/6387.php
   namely:
    - Fewer basic types (int* and float* types, boolean and wchar
    - Fixing naming scheme to ompi-nomenclature.
    - Usability outside of the ompi-layer.
 - Due to the fixed nature of simple opal types, their information is
   completely
   known at compile time and therefore constified
 - With fewer datatypes (22), the actual sizes of bit-field types may be
   reduced
   from 64 to 32 bits, allowing reorganizing the opal_datatype
   structure, eliminating holes and keeping data required in convertor
   (upon send/recv) in one cacheline...
   This has implications to the convertor-datastructure and other parts
   of the code.
 - Several performance tests have been run, the netpipe latency does not
   change with
   this patch on Linux/x86-64 on the smoky cluster.
 - Extensive tests have been done to verify correctness (no new
   regressions) using:
   1. mpi_test_suite on linux/x86-64 using clean ompi-trunk and
    ompi-ddt:
    a. running both trunk and ompi-ddt resulted in no differences
       (except for MPI_SHORT_INT and MPI_TYPE_MIX_LB_UB do now run
       correctly).
    b. with --enable-memchecker and running under valgrind (one buglet
       when run with static found in test-suite, commited)
   2. ibm testsuite on linux/x86-64 using clean ompi-trunk and ompi-ddt:
      all passed (except for the dynamic/ tests failed!! as trunk/MTT)
   3. compilation and usage of HDF5 tests on Jaguar using PGI and
      PathScale compilers.
   4. compilation and usage on Scicortex.
 - Please note, that for the heterogeneous case, (-m32 compiled
   binaries/ompi), neither
   ompi-trunk, nor ompi-ddt branch would successfully launch.

This commit was SVN r21641.
2009-07-13 04:56:31 +00:00
Jeff Squyres
92e40cb20a Enable the coll sync component to barrier before each 1000th collective.
This commit was SVN r21594.
2009-07-02 20:16:45 +00:00
Jeff Squyres
cad12fda5f * Remove an extra blank line from the help file
* Add the help file to the Makefile.am so that it gets installed

This commit was SVN r21567.
2009-06-30 18:58:09 +00:00