1
1
Граф коммитов

1451 Коммитов

Автор SHA1 Сообщение Дата
Ralph Castain
c266abb7d2 Change the name of a file.
This commit was SVN r1496.
2004-06-29 04:51:33 +00:00
Ralph Castain
bca14b684c Need to commit these so I can make a name change to one of the files. I'm in the process of making
a substantial revamp of the session directory system, and the ompi_system_info structure, in accordance
with the startup/shutdown design released last week. If you are using either the session directories
or the ompi_system_info structure, I would recommend avoiding them for the next couple of days as these
files are undergoing considerable change. The documentation will be updated as well during this process.

This commit was SVN r1495.
2004-06-29 04:50:40 +00:00
George Bosilca
aae2fc0a78 Add the 2 missing members to the null collective function. Without then
old versions of gcc (like 2.96) complain about a "non constant" symbol.

This commit was SVN r1494.
2004-06-29 04:03:53 +00:00
Jeff Squyres
ec73b251d6 Finish MPI_SCAN basic implementation. Off to bed; exscan tomorrow.
This commit was SVN r1493.
2004-06-29 03:23:01 +00:00
Jeff Squyres
a5a712b31f Lots of changes in this commit, mostly having to do with the first
real commit of the collectives.  MPI_SCAN and MPI_EXSCAN are still not
implemented, but lots of other things are in the critical path and
holding up other people, so it's ok to commit without them:

- better checks for sizes in configure, and add defaults for fortran
  sizes if we don't have a fortran compiler
- fix some logic that was accidentally broken for size checks for the
  file type offset_t
- add some C equivalent types for fortran's complex and double complex
  (for use in internal reduction/op functions)
- additionals and slight reorganization of ompi_mpi_init()
  ompi_mpi_finalize()
- fully implement all top-level MPI collective calls, including all
  param checking for both intra- and inter-communicators (woof)
- change the communicator_t type for stuff that we need in coll, and
  update all references throughout the code base to match
- all kinds of updates to the coll framework base
- next cut of the basic coll module -- has all intracommunicator
  collectives implemented except scan and exscan (see note above).
  All intercommunicator functions return ERR_NOT_IMPLEMENTED.
- MPI_Op is a fixed implementation -- not component-ized yet.  So
  there are generic C loops for all implementations.

This commit was SVN r1491.
2004-06-29 00:02:25 +00:00
Jeff Squyres
735787e12b Remove the set_list_size inline function
This commit was SVN r1490.
2004-06-28 23:52:06 +00:00
Jeff Squyres
c8367bfe6d Now really ditch src/rte/*
This commit was SVN r1489.
2004-06-28 19:56:50 +00:00
Jeff Squyres
fc96f7d781 Arrgh -- back out the previous patch; committed the wrong
configure.ac...

This commit was SVN r1488.
2004-06-28 19:56:21 +00:00
Jeff Squyres
0f7f841fc5 Really get rid of src/rte/*
This commit was SVN r1487.
2004-06-28 19:53:19 +00:00
Ralph Castain
68946c3a0d Cleanup directory no longer being used.
This commit was SVN r1486.
2004-06-28 14:05:13 +00:00
Ralph Castain
97c96a20af Rearrange directories a little to put openmpi command in the tools area. Create a directory for mpiexec.
This commit was SVN r1485.
2004-06-28 14:04:05 +00:00
Ginger Young
5d93beb1c4 Updated
This commit was SVN r1484.
2004-06-25 15:47:09 +00:00
Ginger Young
3e5b973bd7 A finished wrapper that I neglected to commit several days ago.
This commit was SVN r1483.
2004-06-25 15:45:24 +00:00
Ginger Young
497e07fa58 Finally fixed per George's correction.
This commit was SVN r1482.
2004-06-25 15:43:46 +00:00
Ginger Young
4e65b2e824 Finished per MPI spec.
This commit was SVN r1481.
2004-06-25 15:42:13 +00:00
Ginger Young
0c0dd534b7 Back out come fortran<->C table code. It's breaking
things, and not enough of it is written to do anything.

This commit was SVN r1480.
2004-06-25 15:22:36 +00:00
Jeff Squyres
a55f6a972d Don't compile the attr default functions in the profiling layer --
they are never profiled

This commit was SVN r1479.
2004-06-25 15:05:32 +00:00
Ginger Young
61dc0c6a31 Wrong call to request_f2c, should have been request_c2f
This commit was SVN r1478.
2004-06-25 14:30:17 +00:00
Ginger Young
108fe10084 More fortran wrappers, and a little bit of help code.
Reviewed: Tim Woodall

This commit was SVN r1477.
2004-06-25 14:29:21 +00:00
Jeff Squyres
99e268b9ff A few more minor mods; result of more e-mails between WK and myself. :-)
This commit was SVN r1476.
2004-06-25 14:22:15 +00:00
Weikuan Yu
1808494e7e Update with corrections
This commit was SVN r1475.
2004-06-25 13:41:04 +00:00
Jeff Squyres
024ad4f316 Simplify the configure.stub, and make a few fixes:
- Eliminate the DIST_STUB since we're not using AM_CONDITIONAL
  anywhere
- Consolidate all the library searches into a single set of logic
- Fail with AC_MSG_ERROR if any of the required libraries are not
  found
- Slightly simplify the qsnet2 library source search; directly write
  into CPPFLAGS
- Fail if the qs2net library source is not specified

This commit was SVN r1474.
2004-06-25 13:18:39 +00:00
Jeff Squyres
0bfe5bcb07 Had the order of two arguments switched, which dramatically changed
the expected outcome.  :-)

This commit was SVN r1473.
2004-06-25 13:17:19 +00:00
Weikuan Yu
dc4123d6a9 Files change accordingly with MACRO and header file changes.
This commit was SVN r1472.
2004-06-24 23:09:38 +00:00
Tim Woodall
1d6576d1f6 - more appropriate change of MUTEX_LOCK to OMPI_MUTEX_LOCK
(sorry about the last one)

This commit was SVN r1470.
2004-06-24 21:39:08 +00:00
Tim Woodall
84dd3084b0 backed out changed to OMPI_THREAD_LOCK
This commit was SVN r1469.
2004-06-24 21:09:55 +00:00
Tim Woodall
de519a6a43 check for valid progress function
This commit was SVN r1468.
2004-06-24 20:58:40 +00:00
Tim Woodall
9b830472fd changed THREAD_LOCK/THREAD_UNLOCK to OMPI_THREAD_LOCK/OMPI_THREAD_UNLOCK
to prevent conflicts w/ external libraries/headers

This commit was SVN r1467.
2004-06-24 20:51:46 +00:00
Ginger Young
7616c4dc01 Completed fortran wrappers.
This commit was SVN r1466.
2004-06-24 20:34:14 +00:00
Ginger Young
5adbc0f4dc Fortran wrappers finished
This commit was SVN r1465.
2004-06-24 20:28:42 +00:00
Weikuan Yu
6a8704b229 Saves changes to test at OSU
This commit was SVN r1464.
2004-06-24 19:37:42 +00:00
Tim Woodall
ebd9c4d92f - moved src/mca/ptl/base/ptl_base_sendreq.h -> src/mca/pml/base/pml_base_sendreq.h
src/mca/ptl/base/ptl_base_recvreq.h -> src/mca/pml/base/pml_base_recvreq.h
- rename mca_ptl_base_recv_request_t -> mca_pml_base_recv_request_t
         mca_ptl_base_send_request_t -> mca_pml_base_send_request_t

This commit was SVN r1463.
2004-06-24 19:28:30 +00:00
Tim Woodall
13b025abb7 fix for buffered send
This commit was SVN r1462.
2004-06-24 17:03:08 +00:00
Tim Woodall
2ce7ca725b - cleanup of some of the c bindings
- for threaded case - cleanup event libraries progress thread
- cleanup of request handling for persistent sends
- added support for buffered sends

This commit was SVN r1461.
2004-06-24 16:47:00 +00:00
Weikuan Yu
9870766352 Move the static functions into ptl_elan.h for other source files.
This commit was SVN r1454.
2004-06-23 18:53:50 +00:00
Weikuan Yu
5c47ceb2cb Done with the device initialization coding. To be tested.
This commit was SVN r1448.
2004-06-23 16:23:22 +00:00
Jeff Squyres
c64373238a Update svn:ignore
This commit was SVN r1447.
2004-06-23 15:52:59 +00:00
Jeff Squyres
952cbaf196 Since it's not an error to not have an mpool module (at least not
yet), guarantee to initialize the *allow_multi_user_threads so that we
don't get read-from-uninitialized warnings in valgrind.

This commit was SVN r1446.
2004-06-23 15:52:28 +00:00
Tim Woodall
8f98c8a986 disable thread calls if pthreads not available
This commit was SVN r1445.
2004-06-23 14:16:02 +00:00
Tim Woodall
3d7e403cc1 -disable this module by default
-fix check of mmap return value

This commit was SVN r1444.
2004-06-23 14:00:21 +00:00
Jeff Squyres
f6ea9f7758 Fix some more minor memory problems; convert some of the DSO loading
code to use OBJ_* things instead of manual malloc/free.

This commit was SVN r1443.
2004-06-23 13:39:26 +00:00
Jeff Squyres
b9ae47fd76 Fix a minor memory problem.
This commit was SVN r1442.
2004-06-23 13:38:58 +00:00
Jeff Squyres
c895a9c349 Remove some erroneous free()'s -- sessions is now on the stack, not
the heap.

This commit was SVN r1441.
2004-06-23 12:52:54 +00:00
Jeff Squyres
5cbd58bd4a MPI_Init_thread is now done
This commit was SVN r1440.
2004-06-23 01:33:59 +00:00
Jeff Squyres
1353507d22 More fixes for errhandler, particularly in the case where MPI_INIT* is
the one throwing the exception.

This commit was SVN r1439.
2004-06-23 01:32:03 +00:00
Weikuan Yu
dab38d4105 Some finishup init code .
This commit was SVN r1438.
2004-06-23 01:02:42 +00:00
Tim Prins
48f51861d3 Adding a new class which is a red black tree
-reviewed by Tim
adding a small test program for the tree

This commit was SVN r1437.
2004-06-22 20:52:18 +00:00
Jeff Squyres
21ada98b99 While debugging collectives, came across a bug where the name of the
function really needs to be passed down via OMPI_ERR_INIT_FINALIZE.
So fix up that macro, the associated errhandler handling, and all the
MPI function that use that macro.

This commit was SVN r1436.
2004-06-22 20:21:35 +00:00
Jeff Squyres
737614ac0c No need for all those -I's
This commit was SVN r1435.
2004-06-22 20:18:16 +00:00
Weikuan Yu
a11f5c2ac1 Get configure.stub working and changed Makefile.am accordingly
JMS: 
  AM_CPPFLAGS -I${top_ompi_srcdir}/src/include, etc is not passed 
  down to the modules. So have to hardcode them in Makefile.am.
  Probably because modules are configured before top directory.

This commit was SVN r1432.
2004-06-22 17:46:28 +00:00