1
1

18 Коммитов

Автор SHA1 Сообщение Дата
Jeff Squyres
c3c63b57c4 Arf. Anju and I misunderstood each other yesterday -- the OMPI_EXPORT
thingy needs to go on the *declaration*, not the *definition*.  Well,
at least this was all done en masse and via an automated mechanism, so
total time wasted was only about 15 minutes...

This commit was SVN r2858.
2004-09-24 18:33:36 +00:00
Jeff Squyres
4d05abcf8e Perfect brainless late-night hacking -- add the new OMPI_EXPORT macro
to all the MPI f77 and C bindings.  Yay Windows!  ;-)

This commit was SVN r2856.
2004-09-24 10:30:19 +00:00
Brian Barrett
79a2d8b0a1 * remove a whole bunch of unnecessary #include "runtime/runtime.h"s. I
am sure that some will have to be added back in as functionality is
  added (like for comm_spawn.c), but for now might as well compile
  faster :)

This commit was SVN r2780.
2004-09-20 18:42:01 +00:00
Edgar Gabriel
9c64200871 adapting some functions to the new interface of comm_connect_accept. This takes now an additional argument (a tag) to be able to distnguish several ongoing connec/accept/join/spawn operations simultaniously.
This commit was SVN r2742.
2004-09-17 10:12:31 +00:00
Jeff Squyres
726af9ea85 Revamp MPI_Info handling a bit:
- fix a few bugs
- convert/add doxygen comments for internal info functions in
  src/info/info.h (some comments were originally in src/info/info.c)
- make it thread safe
- make MPI_INFO_NULL be a real object (vs ((struct ompi_info_t*) 0))
- add error checking into top-level MPI functions
- add support in MPI_Info for "never freeing MPI handles" as a form of
  debugging i.e., check if see if you accidentally use a freed handle)
- add support for "print out a list of un-freed MPI_Info handles
  during MPI_FINALIZE"

This commit was SVN r2089.
2004-08-12 16:56:24 +00:00
Edgar Gabriel
eb4cec3566 updating the comm-creating functions to the new flow-chart
This commit was SVN r1901.
2004-08-05 16:32:13 +00:00
Edgar Gabriel
d6334fa558 updating the communicator interface functions to the new interfaces and procedures of comm.c
This commit was SVN r1856.
2004-08-03 22:08:23 +00:00
Jeff Squyres
eeee18fce8 Make a pass through all top-level MPI functions
- Mark those who are still not yet implemented:
  - return an error
  - have a grep-able string indicating that they are not yet
    implemented
- ensure every function checks for init/finalize
- add more error checking to a bunch of functions
- unify the error checking -- it reflected about 3 different
  [previous] error checking styles and MPI exception invocation styles

This commit was SVN r1817.
2004-07-30 02:58:53 +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
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
Edgar Gabriel
47ec006930 adding the comm and group MPI interface functions to use the new macro
developed by Jeff for checking of MPI_Init/Finalize

This commit was SVN r1415.
2004-06-18 19:02:52 +00:00
Edgar Gabriel
3f42ad3475 adapting these routines to the new arguments of the comm_cid allocation routine
This commit was SVN r1337.
2004-06-16 22:44:56 +00:00
Edgar Gabriel
5d1574d929 adding the implementatio for the name-publishin functions
adding more details for comm_spawn/multiple, comm_connect/accept
and comm_join.

This commit was SVN r1335.
2004-06-16 21:35:31 +00:00
Edgar Gabriel
fc10938f3c adding parameter verification for all routines involved in
dynamic process management.

Started to sketch the algorithms and the open questions.

Added (if appropriate) the list of info-objects, which we
might have to verify in the according functions.

This commit was SVN r1298.
2004-06-16 01:41:01 +00:00
David Daniel
563ac2a338 First pass of lam -> ompi conversion
This commit was SVN r1191.
2004-06-07 15:33:53 +00:00
Prabhanjan Kambadur
a0983ab473 Changing the bindings files to have the #define of MPI_ functions to PMPI_ functions after the #pragma weak statement
This commit was SVN r1055.
2004-04-20 18:50:43 +00:00
David Daniel
7f8c2c3714 Updating header file names after the great directory reorganization.
This commit was SVN r877.
2004-03-17 18:45:16 +00:00
Jeff Squyres
698685924b Part 2 of The Great Source Reorganization
This commit was SVN r873.
2004-03-17 17:45:44 +00:00