1
1
Граф коммитов

466 Коммитов

Автор SHA1 Сообщение Дата
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
Rainer Keller
fbb2834977 - Missed string.h to get rid of warnings...
This commit was SVN r21265.
2009-05-22 23:47:49 +00:00
Rainer Keller
225a1d6d8e - For memcpy and memset need string.h
This commit was SVN r21259.
2009-05-21 22:36:06 +00:00
Greg Koenig
60485ff95f This is a very large change to rename several #define values from
OMPI_* to OPAL_*.  This allows opal layer to be used more independent
from the whole of ompi.

NOTE: 9 "svn mv" operations immediately follow this commit.

This commit was SVN r21180.
2009-05-06 20:11:28 +00:00
Shiqing Fan
cd565923d3 Completely remove ltdl support for Windows build.
This commit was SVN r21170.
2009-05-05 18:59:13 +00:00
George Bosilca
039fed1973 Fix Coverity CID #264.
This commit was SVN r21162.
2009-05-05 13:54:55 +00:00
George Bosilca
db096d7d3a Fix Coverity CID #304.
This commit was SVN r21159.
2009-05-05 13:47:47 +00:00
Rainer Keller
9736af1191 - Fix Coverity CID 182:
Well, well, just do not "call" ompi_comm_rank twice but rather
   reuse variable...

 - Fix Coverity CID 1262:
   Using uninitialized value "(statuses[err_index]).MPI_ERROR"
   Sure, these statuses are only initialized after ompi_request_wait_all,
   so introduce a short-circuit label to jump to...

This commit was SVN r21153.
2009-05-05 12:28:51 +00:00
Rainer Keller
221fb9dbca ... Delayed due to notifier commits earlier this day ...
- Delete unnecessary header files using
   contrib/check_unnecessary_headers.sh after applying
   patches, that include headers, being "lost" due to
   inclusion in one of the now deleted headers...

   In total 817 files are touched.
   In ompi/mpi/c/ header files are moved up into the actual c-file,
   where necessary (these are the only additional #include),
   otherwise it is only deletions of #include (apart from the above
   additions required due to notifier...)

 - To get different MCAs (OpenIB, TM, ALPS), an earlier version was
   successfully compiled (yesterday) on:
   Linux locally using intel-11, gcc-4.3.2 and gcc-SVN + warnings enabled
   Smoky cluster (x86-64 running Linux) using PGI-8.0.2 + warnings enabled
   Lens cluster (x86-64 running Linux) using Pathscale-3.2 + warnings enabled

This commit was SVN r21096.
2009-04-29 01:32:14 +00:00
Shiqing Fan
3d4e0472d6 Add windows support files into the tarball, including .windows, CMakeLists.txt files, and CMake modules. Thanks to Jeff for testing it on Linux.
This commit was SVN r21069.
2009-04-24 16:39:33 +00:00
George Bosilca
c5b1bdd57c Correctly deal with the error case. The problem is tricky: the MPI standard doesn't allow
MPI_ERR_IN_STATUS to be returned from any functions that return only one completed request
(few exception here: wait_some and wait_all and the test versions). As we use an wait_all
in these send_receive functions we should convert the MPI_ERR_IN_STATUS to the real
error, i.e. the one comming from the MPI_ERROR field in the status corresponding to the
failed request.

This commit was SVN r20907.
2009-03-31 23:44:59 +00:00
Rainer Keller
d8cf4c0fec - Get pgcc on XT to complain less:
In case we use memcmp, strlen, strup and friends include <string.h>
   Also several constants.h are not included directly
 - Let's have mca_topo_base_cart_create  return ompi-errors in
   ompi/mca/topo/base/topo_base_cart_create.c

This commit was SVN r20773.
2009-03-13 02:10:32 +00:00
Jeff Squyres
14ee1b7ba2 Refs trac:1826: remove barriers before all non-rooted collective ops.
This commit was SVN r20763.

The following Trac tickets were found above:
  Ticket 1826 --> https://svn.open-mpi.org/trac/ompi/ticket/1826
2009-03-12 02:23:08 +00:00
Rainer Keller
ec0ed48718 - Revert r20739
This commit was SVN r20742.

The following SVN revision numbers were found above:
  r20739 --> open-mpi/ompi@781caee0b6
2009-03-05 21:56:03 +00:00
Rainer Keller
781caee0b6 - First of two or three patches, in orte/util/proc_info.h:
Adapt orte_process_info to orte_proc_info, and
   change orte_proc_info() to orte_proc_info_init().
 - Compiled on linux-x86-64
 - Discussed with Ralph

This commit was SVN r20739.
2009-03-05 20:36:44 +00:00
Shiqing Fan
99b415a7e0 On windows, the mca_common_* libraries should be installed in bin, otherwise the libraries that are dependent on them, e.g. shared build of mca_btl_sm, couldn't be loaded at runtime. This commit fixes the problem.
This commit was SVN r20735.
2009-03-05 14:57:35 +00:00
Rainer Keller
9dea63d63a - Last of intrusive commits (promised)... err for now.
Anyway, this is blocking the move: do not include pml.h
   if not really needed, aka none of the following used:
     mca_pml
     MCA_PML_CALL
     OMPI_ANY_TAG
     OMPI_ANY_SOURCE
     OMPI_PROC_NULL

 - Notable exceptions (deleting in one header->adding):
   - ompi/mca/mtl/psm/
   - ompi/mca/osc/rdma/
   - ompi/mca/btl/openib/btl_openib_endpoint.c depended on
     pml_base_sendreq.h

 - Tested on Linux/x86-64, this time including make check
   (thanks Jeff and Ralph)

This commit was SVN r20725.
2009-03-04 17:06:51 +00:00
Rainer Keller
811f2bd9b4 - As discussed on RFC, move the ompi_bitmap to the
opal layer.
   Add a check against a maximum (actually get rid of ifs internally to
   opal_bitmap.c) -- the functionality to set the current maximum size
   opal_bitmap_set_max_size() is currently only used in attribute.c
   to set the maximum OMPI_FORTRAN_HANDLE_MAX...

   Tested on linux/x86-64 with intel-tests with all_tests_no_perf_f
   run with 6 procs.
   Let's look into MTT as well...

This commit was SVN r20708.
2009-03-03 22:25:13 +00:00
Rich Graham
7ef1550267 add an index to indicate which socket group I belong to.
This commit was SVN r20672.
2009-03-02 14:39:54 +00:00
Rich Graham
daf7673aff gather socket information - not debugged.`
This commit was SVN r20670.
2009-03-02 10:58:12 +00:00
Rainer Keller
96e1b9b747 - Header orte/mca/rml/rml.h is not needed if no occurence of orte_rml
or ORTE_RML.
   As the others compiles fine with -Wimplicit-function-declaration

This commit was SVN r20639.
2009-02-26 03:52:31 +00:00
Terry Dontje
0178b6c45f Added padding to predefined handle structures to maintain library version to
version compatibility.

This commit was SVN r20627.
2009-02-24 17:17:33 +00:00
Shiqing Fan
2148220ce4 Update the share libs dependency for windows build.
This commit was SVN r20625.
2009-02-23 17:49:46 +00:00
Jeff Squyres
3742c3550c Add "sync" collective component. This component is totally
deactivated by default.  It is activated by setting either of the
following two MCA parameters to values greater than 0:

 * coll_sync_barrier_before
 * coll_sync_barrier_after

If !_before is >0, then the sync coll collective will insert itself
before the underlying collective operations and invoke a barrier
before every Nth barrier (N == coll_sync_barrier_before).  Similar for
!_after.  Note that N is a _per communicator_ value; not global to the
MPI process.

If both are 0 (which is the default), this component returns NULL for
the comm query, meaning that it is not insertted into the coll module
stack. 

The intent of this component is to provide a a workaround for
applications with large numbers of collectives of short messages that
can cause unbounded unexpected messages.  Specifically, it is possible
for some iterative collective communication patterns to cause
unbounded unexpected messages.  Forcing a barrier before or after
every Nth collective operation would prevent that behavior by forcing
applications to synchronize (and thereby consume any outstanding
unexpected messages caused by collectives on the same communicator).

Open MPI still needs to bound unexpected messages resource consumption
at the receiver, but this is a viable workaround for at least some
symptoms of the problem.

Additionally, there has been anecdotal evidence of some applications
that "perfom better" when they put barriers after other collective
operations.  This could be due to many factors -- including shortening
the unexpected message queue.  Putting this component in Open MPI
allows people to try this with their own applications and give real
world feedback on this kind of behavior.

This commit was SVN r20584.
2009-02-18 23:32:44 +00:00
Rainer Keller
d81443cc5a - On the way to get the BTLs split out and lessen dependency on orte:
Often, orte/util/show_help.h is included, although no functionality
   is required -- instead, most often opal_output.h, or               
   orte/mca/rml/rml_types.h                                           
   Please see orte_show_help_replacement.sh commited next.            

 - Local compilation (Linux/x86_64) w/ -Wimplicit-function-declaration
   actually showed two *missing* #include "orte/util/show_help.h"     
   in orte/mca/odls/base/odls_base_default_fns.c and                  
   in orte/tools/orte-top/orte-top.c                                  
   Manually added these.                                              

   Let's have MTT the last word.

This commit was SVN r20557.
2009-02-14 02:26:12 +00:00
Jeff Squyres
8b29e27ead Some minor valgrind-inspired cleanups: fix some memory leaks
This commit was SVN r20543.
2009-02-13 03:45:32 +00:00
Tim Mattox
9b83df22ec Fix some "is proc on local node?" logic that got accidentally flipped
by r20496 for the sm BTL, openib BTL on iWarp, and the sm & sm2 coll modules.

This commit was SVN r20515.

The following SVN revision numbers were found above:
  r20496 --> open-mpi/ompi@4cdf91a8d4
2009-02-11 15:02:38 +00:00
Ralph Castain
4cdf91a8d4 Per the RFC, extend the current use of the ompi_proc_t flags field (without changing the field itself).
The prior ompi_proc_t structure had a uint8_t flag field in it, where only one
bit was used to flag that a proc was "local". In that context, "local" was
constrained to mean "local to this node".

This commit provides a greater degree of granularity on the term "local", to include tests
to see if the proc is on the same socket, PC board, node, switch, CU (computing
unit), and cluster.

Add #define's to designate which bits stand for which local condition. This
was added to the OPAL layer to avoid conflicting with the proposed movement of
the BTLs. To make it easier to use, a set of macros have been defined - e.g.,
OPAL_PROC_ON_LOCAL_SOCKET - that test the specific bit. These can be used in
the code base to clearly indicate which sense of locality is being considered.

All locations in the code base that looked at the current proc_t field have
been changed to use the new macros.

Also modify the orte_ess modules so that each returns a uint8_t (to match the
ompi_proc_t field) that contains a complete description of the locality of this
proc. Obviously, not all environments will be capable of providing such detailed
info. Thus, getting a "false" from a test for "on_local_socket" may simply
indicate a lack of knowledge.

This commit was SVN r20496.
2009-02-10 02:20:16 +00:00
Jeff Squyres
4d8a187450 Two major things in this commit:
* New "op" MPI layer framework
 * Addition of the MPI_REDUCE_LOCAL proposed function (for MPI-2.2)

= Op framework =

Add new "op" framework in the ompi layer.  This framework replaces the
hard-coded MPI_Op back-end functions for (MPI_Op, MPI_Datatype) tuples
for pre-defined MPI_Ops, allowing components and modules to provide
the back-end functions.  The intent is that components can be written
to take advantage of hardware acceleration (GPU, FPGA, specialized CPU
instructions, etc.).  Similar to other frameworks, components are
intended to be able to discover at run-time if they can be used, and
if so, elect themselves to be selected (or disqualify themselves from
selection if they cannot run).  If specialized hardware is not
available, there is a default set of functions that will automatically
be used.

This framework is ''not'' used for user-defined MPI_Ops.

The new op framework is similar to the existing coll framework, in
that the final set of function pointers that are used on any given
intrinsic MPI_Op can be a mixed bag of function pointers, potentially
coming from multiple different op modules.  This allows for hardware
that only supports some of the operations, not all of them (e.g., a
GPU that only supports single-precision operations).

All the hard-coded back-end MPI_Op functions for (MPI_Op,
MPI_Datatype) tuples still exist, but unlike coll, they're in the
framework base (vs. being in a separate "basic" component) and are
automatically used if no component is found at runtime that provides a
module with the necessary function pointers.

There is an "example" op component that will hopefully be useful to
those writing meaningful op components.  It is currently
.ompi_ignore'd so that it doesn't impinge on other developers (it's
somewhat chatty in terms of opal_output() so that you can tell when
its functions have been invoked).  See the README file in the example
op component directory.  Developers of new op components are
encouraged to look at the following wiki pages:

  https://svn.open-mpi.org/trac/ompi/wiki/devel/Autogen
  https://svn.open-mpi.org/trac/ompi/wiki/devel/CreateComponent
  https://svn.open-mpi.org/trac/ompi/wiki/devel/CreateFramework

= MPI_REDUCE_LOCAL =

Part of the MPI-2.2 proposal listed here:

    https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/24

is to add a new function named MPI_REDUCE_LOCAL.  It is very easy to
implement, so I added it (also because it makes testing the op
framework pretty easy -- you can do it in serial rather than via
parallel reductions).  There's even a man page!

This commit was SVN r20280.
2009-01-14 23:44:31 +00:00
Edgar Gabriel
1072812bcf not every element in the pointer array list contains a valid entry. Thus, do not try to free elements if the list returns NULL.
This commit was SVN r20275.
2009-01-14 19:11:30 +00:00
George Bosilca
01adc999c5 Correctly forward the right module if we call another collective function. Kudos to
Edgar for figuring out this tricky bug.

This commit was SVN r20267.
2009-01-14 03:22:54 +00:00
Jeff Squyres
11b375f8b5 CIDs 1080-1090: assert() checks were not sufficient to check for
NEGATIVE_RETURNS from _reg_int() because those are not always
checked.  So replace them with real if() checks.

This commit was SVN r20195.
2009-01-03 15:56:25 +00:00
Jeff Squyres
f13ea32830 Remove the code checkig the MCA "coll" parameter for a list of coll
components to use.  This code was rendered obsolete (albiet harmless)
by the MCA base improvements that only open the components that were
specified by each framework's MCA parameter.

This commit was SVN r20176.
2008-12-31 13:40:51 +00:00
Jeff Squyres
759a295cc9 Gaah -- missed one s/m/component/g
This commit was SVN r20175.
2008-12-31 13:35:37 +00:00
Jeff Squyres
955d1e132d Rename a variable to be "component" (not "m"), to emphasize that it is
the component struct, not a module.

This commit was SVN r20174.
2008-12-31 13:32:46 +00:00
Jeff Squyres
865900dd27 Nothing of substance; just indenting changes (''finally'' update this
framework base to 4 space tabs!).

This commit was SVN r20173.
2008-12-31 12:17:08 +00:00
Jeff Squyres
ce313fa391 Minor fixes to a few comments
This commit was SVN r20172.
2008-12-31 11:34:27 +00:00
Jeff Squyres
d533215dac Fix a comment to reflect the right version number
This commit was SVN r20169.
2008-12-30 12:39:32 +00:00
Nysal Jan
ee8ec6f6b5 Remove dead/redundant code. Minimize number of calloc invocations
This commit was SVN r20121.
2008-12-12 10:55:50 +00:00
Shiqing Fan
a5281f0434 - 1/4 commit for Windows Visual Studio and CCP support:
CMakeLists and .windows files.
  In contribs preconfigured and precompiled parts.

This commit was SVN r20108.
2008-12-10 20:59:20 +00:00
Rolf vandeVaart
137729d2f9 Fix warnings (thanks Jeff) from previous fix. This is extra
fix for ticket #1554.

This commit was SVN r19728.
2008-10-10 14:35:52 +00:00
Tim Mattox
de623ea161 Remove a redundant if & goto.
This commit was SVN r19724.
2008-10-09 15:07:56 +00:00
Rolf vandeVaart
aad4427caa Fix the implementation of MPI_Reduce_scatter on intercommunicators.
We still do an interreduce but it is now followed by an intrascatterv.

This fixes trac:1554.

This commit was SVN r19723.

The following Trac tickets were found above:
  Ticket 1554 --> https://svn.open-mpi.org/trac/ompi/ticket/1554
2008-10-09 14:35:20 +00:00
Rolf vandeVaart
13e8975f83 In the case where we detect a value of 0 in the recvcount
array, fall back to the simpler algorithms.  This is not
the optimal solution, but it works.  

This commit was SVN r19702.
2008-10-07 19:44:51 +00:00
Rolf vandeVaart
0a0ddfc934 Handle MPI_IN_PLACE correctly in the ompi_coll_tuned_reduce_scatter_intra_ring function.
We were not adjusting the sendbuf in this case so we were reducing garbage.

This fixes ticket #1506.

This commit was SVN r19673.
2008-10-02 20:01:27 +00:00
George Bosilca
325d006577 Mostly cleanups, and eventually a little bit more scalable add_procs.
There was an argument that was barely used, and on return at the PML
level it contained nothing usable. It has been removed, so now we're
using less memory ...

This commit was SVN r19657.
2008-09-30 15:47:43 +00:00
George Bosilca
6a9514ee08 Make the code match the comment. I checked with Jelena, and based on the papers we
published this is the expected algorithm for the specified message and communicator
size.

This commit closes ticket #1330.

This commit was SVN r19563.
2008-09-15 23:28:40 +00:00
Edgar Gabriel
ef2bb46e45 no need to create and free the groups. We just want to translate the ranks and we can use the internal group structures right away for that operation. Fixes an issue with groups that have not been freed previously, due to the fact that ompi_group_free was not visible here (I know, this could have been solved also by setting OMPI_DECLSPEC on ompi_group_free, but this solution should be faster.)
This commit was SVN r19362.
2008-08-19 13:59:58 +00:00