1
1
Граф коммитов

1460 Коммитов

Автор SHA1 Сообщение Дата
Brian Barrett
6026fc98f6 * Fix M4 quoting so that AC 2.60 won't complain
Submitted by: Ralf Wildenhues
Reviewed by: Brian Barrett

This commit was SVN r10129.
2006-05-31 03:39:18 +00:00
Brian Barrett
c723d196c5 Rather than using fragment size to determine fragment type, use an enum.
Do this rather than the my_list pointer because we need to do some
things that are somewhat special because we pre-pin eager fragments but
not send fragments.  Also makes a couple ideas I have slightly easier to
play around with.

This commit was SVN r10127.
2006-05-31 03:34:32 +00:00
George Bosilca
abc580b2d5 Sven patch to check the optimized description before freeing it. For predefined
datatypes the optimized description point to the default description, so special
care should be taken before freeing it.

This commit was SVN r10119.
2006-05-30 16:36:06 +00:00
Jeff Squyres
5f356edb64 Bring over changes from the /tmp/fortran-stuff series:
- Make the F90 bindings compile and link properly with gfortran 4.0,
  4.1, Intel 9.0, PGI 6.1, Sun (don't know version offhand -- the most
  current as of this writing, I think), and NAG 5.2, although some
  have limitations (e.g., NAG can't seem to handle the medium and
  large sizes)
- Building the F90 "small" module size is now the default, even for
  developers
- Split up mpif.h into multiple files because parts of it were toxic
  to the F90 bindings
- Properly specify unsized/unshaped arrays to make the bindings work
  on all known compilers
- Make ompi_info show Fortran 90 bindings size
- XML somewhat lags the generated scripts as of this commit, but
  functionality was my main goal -- the XML can be updated later (if
  at all).

This commit was SVN r10118.
2006-05-30 14:37:41 +00:00
George Bosilca
aa1c1e70c6 Fix the datatype bug noticed by Rainer. Under some circumstances (and only for
predefined datatypes) the optimized description was set to NULL instead of
pointing to some valid description. As for some data, having an optimized
version is not possible (as no optimizations bring any benefit), we have
to make sure this field (opt_desc) is always correctly initialized.

This commit was SVN r10112.
2006-05-27 06:21:27 +00:00
Galen Shipman
2667c52a5d Track fragments by list, not by size..
-- reviewed by Brian, needs to hit all the branches.. 

This commit was SVN r10078.
2006-05-25 18:07:26 +00:00
Galen Shipman
38a0561d9b Allow maximum send size to be less than the eager limit.
Instead of figuring out which free list the fragment belongs to based on size
we simply store a pointer to the list which it belongs in the fragment.

This was reviewed by Brian and should hit all the branches.

This commit was SVN r10072.
2006-05-25 16:57:14 +00:00
Andrew Friedley
fa9ec2afdf Add my sandia username for convenience
This commit was SVN r10071.
2006-05-25 15:49:11 +00:00
Andrew Friedley
8a3d0862ca I can commit! *happy dance*
Trying to remember what I did here.. eager/max messages should work now, no RDMA yet.  A number of other fixes and cleanups.

I do know of two problems:
 Bad stuff happens when flooded with send frags too quickly - the BTL doesn't handle flow control.
 Certain IBM tests turn up a length assertion in the datatype engine - needs more investigation.

This commit was SVN r10070.
2006-05-25 15:47:59 +00:00
Gleb Natapov
f590d8a190 fix eager RDMA on PPC64.
This commit was SVN r10059.
2006-05-25 11:05:12 +00:00
Jeff Squyres
dd44d36be0 Fix for ticket #25. Ensure that in the threaded case where we have
This commit was SVN r10043.
2006-05-24 16:15:07 +00:00
George Bosilca
1c55956db1 Extend Sven patch for pack/unpack.
This commit was SVN r10040.
2006-05-24 14:48:00 +00:00
Jeff Squyres
a553c3444a This has bugged me for a long time: make the "want libltdl" output
like the rest of the output (i.e., "yes" / "no" vs. "1" / "0").

This commit was SVN r10039.
2006-05-24 10:56:47 +00:00
Jeff Squyres
3c265958ba @#$%@#%#%
Fix one more typo that was missed last night.

This commit was SVN r10038.
2006-05-24 10:30:08 +00:00
Jeff Squyres
8c0ebb4897 Drat -- forgot the copyright.
This commit was SVN r10025.
2006-05-23 18:42:11 +00:00
Jeff Squyres
dc9a16581e Unbelieveable how this lived so long. Thanks to Bert Wesarg for
reporting this.

This commit was SVN r10023.
2006-05-23 18:00:44 +00:00
George Bosilca
e832aac7b1 This is always on the critical path so let's make it static inline.
This commit was SVN r10020.
2006-05-23 03:22:15 +00:00
George Bosilca
95d0395578 I'm skeptical about the ability of the compiler to correctly optimize the
loop local variables.

This commit was SVN r10019.
2006-05-23 03:21:15 +00:00
George Bosilca
085cac552f Don't let TCP to create local connections, we have the self BTL for this purpose.
This commit was SVN r10018.
2006-05-23 03:06:32 +00:00
George Bosilca
837221831a Temporary solution for in-bound computation of the next BTL.
This commit was SVN r10016.
2006-05-22 23:28:40 +00:00
Rainer Keller
7cece521c6 - Use calloc as per suggestion of George.
This commit was SVN r10006.
2006-05-22 14:18:44 +00:00
George Bosilca
1dcd70ad80 The master convertor is the one that knows if the peers are
homogeneous or heterogeneous.

This commit was SVN r10005.
2006-05-22 06:22:32 +00:00
George Bosilca
eb149cb9c8 Move the datatype tests in its own directory.
This commit was SVN r10003.
2006-05-22 06:12:43 +00:00
George Bosilca
b8ef0cc749 Minor cleanups.
This commit was SVN r10001.
2006-05-21 05:55:21 +00:00
George Bosilca
e43fbd0082 Remove all useless variables. Minor cleanups.
This commit was SVN r10000.
2006-05-21 05:53:22 +00:00
Galen Shipman
9165882c07 fixes for failover...
This commit was SVN r9998.
2006-05-20 02:39:05 +00:00
Jeff Squyres
faf63c68f8 Merge over from the /tmp/fortran-stuff branch
- split mpif.h into mpif.h and mpif-common.h[.in]
- mpif-common.h is included by various f90 things and contains output
  from configure
- mpif.h defines some f77-specific stuff and then includes
  mpif-common.h 

This commit was SVN r9997.
2006-05-20 02:15:49 +00:00
Brian Barrett
96bf81a329 * datatype_check might need to uptdate the value of count (if we received
less than we posted for).  We were passing by value, so this update was
  not being propgated back up the stack and we could segfault.  Make the
  count argument a pointer so that updates will be passed as expected.

This needs to go to the v1.1 branch

This commit was SVN r9991.
2006-05-19 21:58:12 +00:00
Jeff Squyres
299f4fdb2c Oops -- fix the comment. A victim of cut-n-paste.
This commit was SVN r9971.
2006-05-18 18:10:12 +00:00
Jeff Squyres
942f9e8f8d Fixes for ticket:14. Lengthy discussion is on that ticket and in a
comment in ompi_comm_invalid() in
source:/trunk/ompi/communicator/communicator.h.

Short version:
- ompi_comm_invalid() returns TRUE for MPI_COMM_NULL
- therefore MPI_COMM_C2F needs to explicitly check for MPI_COMM_NULL
  (because it uses ompi_comm_invalid())
- make ~20 MPI functions only call ompi_comm_invalid() instead of
  calling ompi_comm_invalid() *and* checking for MPI_COMM_NULL (~40 MPI
  functions already only called ompi_comm_invalid() -- we should be
  consistent)
- similar issue for ompi_win_invalid(), so I added a cross-referencing
  comment in win.h and fixed MPI_WIN_SET_NAME to only call
  ompi_win_invalid() (and not check for MPI_WIN_NULL)

This commit was SVN r9970.
2006-05-18 18:05:46 +00:00
Jeff Squyres
800ba39152 Fixes for:
- make dist
- proper inclusion of files between trivial and small
- vpath

This commit was SVN r9964.
2006-05-18 11:26:52 +00:00
Gleb Natapov
1c1b87a9f1 init mutex before use.
This commit was SVN r9963.
2006-05-18 09:35:11 +00:00
Jeff Squyres
a7c854f878 Add some comments explaining why these functions have an interface but
no definition.

This commit was SVN r9962.
2006-05-17 22:22:29 +00:00
Jeff Squyres
c3aeaed77b SPAWN_MULTIPLE should actually be in the "small" size, not the
"medium" size.

This commit was SVN r9961.
2006-05-17 21:58:48 +00:00
Craig E Rasmussen
94f463c924 Changes to remove attr_fn functions from the mpi namespace/module.
This commit was SVN r9960.
2006-05-17 21:31:04 +00:00
Jeff Squyres
95c1f12b97 Missed this one yesterday
This commit was SVN r9958.
2006-05-17 16:31:25 +00:00
Jeff Squyres
15758d5f29 Fix AC_DEFINE to match what it's supposed to be defining
This commit was SVN r9952.
2006-05-17 03:26:43 +00:00
George Bosilca
100f6ce56b The trylock return 0 not 1 if the lock was grabbed. My logic around this trylock
was just wrong.

This commit was SVN r9946.
2006-05-16 23:13:48 +00:00
Galen Shipman
deb2254c91 1. mpool_free changes to allow null registrations
2. fix for MPI_Free_mem, was calling deregister but never called mpool_free.. so
we leaked memory. Still an open issue here though, if the memory is alloc'd
and the mpool doesn't create and cache a registration, we will never find the
mpool to free with. 

This commit was SVN r9944.
2006-05-16 22:04:31 +00:00
Jeff Squyres
7b59847765 Ensure that endpoint->endpoint_addr is not NULL before trying to
derefence through it.  It is legal for endpoint_addr to be NULL in the
destructor because if btl_tcp_add_procs() -> btl_tcp_proc_insert()
returns UNREACH, then endpoint_addr will be NULL and we'll OBJ_RELEASE
it.

This commit was SVN r9940.
2006-05-16 19:01:08 +00:00
Jeff Squyres
1f8cc1af65 Add an extra -I so that compilers can find mpi-f90-interfaces.h in a
vpath build.

This commit was SVN r9937.
2006-05-16 17:30:42 +00:00
Jeff Squyres
e24377a89c Back out a pair of commits from George from last week because they
apparently don't work properly: r9869, r9868 (sm btl alignment issues)

This commit was SVN r9936.

The following SVN revision numbers were found above:
  r9868 --> open-mpi/ompi@9b985c3216
  r9869 --> open-mpi/ompi@adedf511fb
2006-05-16 16:48:43 +00:00
Jeff Squyres
d3ff507bc2 Add explicit path to mpi-f90-interfaces.h.sh. Blast; I could have
sworn that I committed this yesterday.

This commit was SVN r9935.
2006-05-16 15:00:23 +00:00
Sven Stork
da7ad0e8b8 - update function name inside debug statement
This commit was SVN r9933.
2006-05-16 14:33:41 +00:00
Jeff Squyres
3e60cd163e Ensure that mpi_sizeof.f90 is added to the build
This commit was SVN r9925.
2006-05-15 19:32:01 +00:00
Jeff Squyres
332954e168 Spell the AC_SUBST'ed names properly
This commit was SVN r9924.
2006-05-15 19:31:38 +00:00
Jeff Squyres
171585ff34 Ensure to put implicit none *before* the header file includes
This commit was SVN r9923.
2006-05-15 19:31:01 +00:00
Craig E Rasmussen
13c113b39c Changed INOUT to IN in MPI_*_SET_ATTR functions.
This commit was SVN r9922.
2006-05-15 17:13:20 +00:00
Craig E Rasmussen
a547a64f93 Changed INOUT to IN in MPI_*_SET_ATTR functions.
This commit was SVN r9916.
2006-05-15 16:00:04 +00:00
Brian Barrett
dcc6b47fa2 * put rdma operations in the send event queue instead of receive because it's
easier to do event accounting that way
* greatly increase receive event and buffer sizes.  We're still about half
  of what Cray defaults to, so I don't feel bad about the increases
* Implement a pre-pinning optimization for eager fragments - will be
  pinned on first use and left pinned for the life of the fragment
* Since we can't have two receive frag callbacks fired at the same time,
  don't have receive free list - just keep one receive fragment in the
  module.  Saves a big free list and all that interaction.

This commit was SVN r9915.
2006-05-14 04:23:26 +00:00