Edgar Gabriel
435ce5f5e6
abstracting group_translate_ranks to an ompi function for internal use.
...
Sorry, everybody will have to rerun autogen.sh, since I added a file ...
This commit was SVN r1854.
2004-08-03 22:06:49 +00:00
Jeff Squyres
d649161279
Fix some minor buglets that were missed in the initial code review.
...
This commit was SVN r1853.
2004-08-03 21:29:23 +00:00
Tim Woodall
1b319f091e
update docs
...
This commit was SVN r1852.
2004-08-03 21:16:18 +00:00
Tim Woodall
8efddcdc05
unused
...
This commit was SVN r1851.
2004-08-03 21:13:21 +00:00
Edgar Gabriel
80a9ede98f
minor modification in the group constructor. The rank is now being initialized to MPI_UNDEFINED.
...
This commit was SVN r1850.
2004-08-03 19:38:50 +00:00
Tim Prins
d209e538f1
-fix 2 bugs in the oob
...
-in some cases failed to call complete function when the message
was sent.
-was freeing the wrong iovec in the base recv function
-added a first cut of a oob test
This commit was SVN r1849.
2004-08-03 16:34:59 +00:00
Ralph Castain
772452105b
Update unit test for name server replica
...
This commit was SVN r1848.
2004-08-03 15:58:08 +00:00
Weikuan Yu
fc814cb1b7
To focus on put/get and get the last communication architecture setup.
...
This commit was SVN r1846.
2004-08-03 05:23:27 +00:00
Sayantan Sur
d8e33483f6
Organized some IB initialization code.
...
This commit was SVN r1845.
2004-08-03 02:08:17 +00:00
Jeff Squyres
71b9c0d362
Add in missing header file.
...
This commit was SVN r1844.
2004-08-03 00:50:14 +00:00
Weikuan Yu
a57e7fd584
get code merged
...
This commit was SVN r1843.
2004-08-03 00:06:25 +00:00
Tim Woodall
e51a55a05e
resolved threading issues in tcp oob
...
This commit was SVN r1842.
2004-08-02 22:16:35 +00:00
Tim Prins
105b8e6b5b
Minor change to check to see if the tree has actually been initialized
...
before trying to destroy it.
This commit was SVN r1841.
2004-08-02 21:27:27 +00:00
Jeff Squyres
8be67851e1
roll back to last night's mpirun -- the previous copy was not intended
...
to be committed and was accidentally included in the massive commit
last night. Sorry... :-(
This commit was SVN r1840.
2004-08-02 21:26:13 +00:00
Tim Woodall
9280e182f5
- changed oob i/f functions to accept tag parameter
...
- tcp implementation in progress
- changed calls to oob to reflect additional parameter
This commit was SVN r1839.
2004-08-02 21:24:00 +00:00
Jeff Squyres
9f15b8c553
Updates for the massive module<-->component name change yesterday
...
This commit was SVN r1838.
2004-08-02 17:07:56 +00:00
Edgar Gabriel
ae3028efe7
adding fortran interface for the MPI-1 communicator functions.
...
This commit was SVN r1837.
2004-08-02 14:35:33 +00:00
Jeff Squyres
91a1458120
Make the mail a little smaller
...
This commit was SVN r1836.
2004-08-02 11:27:19 +00:00
Jeff Squyres
c6cd297755
Oops -- grab the newly-renamed *components* listing file, not the old
...
*modules* listing file.
This commit was SVN r1835.
2004-08-02 11:04:12 +00:00
Jeff Squyres
525e451ac0
Make the report a little more explicit -- show "[default]" when
...
running a configuration with no configure argv
This commit was SVN r1834.
2004-08-02 03:23:53 +00:00
Jeff Squyres
d1bf0f8b06
Expand the unimplemented report to also count how many unimplemented
...
f77 functions there are
This commit was SVN r1833.
2004-08-02 03:03:16 +00:00
Jeff Squyres
952171f2bc
Remove the rest of the krft -- accidentally got left in when I "fixed"
...
the bug a little while ago :-)
This commit was SVN r1832.
2004-08-02 02:51:39 +00:00
Jeff Squyres
cd8f550dc7
- Add greb-able string in non-implemented functions
...
- Fix exception handling when malloc fails
- Combine a few malloc's
This commit was SVN r1831.
2004-08-02 02:35:46 +00:00
Jeff Squyres
eb8cba98af
- massive change for module<-->component name fixes throughout the
...
code base.
- many (most) mca type names have "component" or "module" in them,
as relevant, just to further distinguish the difference between
component data/actions and module data/actions. All developers
are encouraged to perpetuate this convention when you create
types that are specific to a framework, component, or module
- did very little to entire framework (just the basics to make it
compile) because it's just about to be almost entirely replaced
- ditto for io / romio
- did not work on elan or ib components; have to commit and then
convert those on a different machine with the right libraries and
headers
- renamed a bunch of *_module.c files to *_component.c and *module*c
to *component*c (a few still remain, e.g., ptl/ib, ptl/elan, etc.)
- modified autogen/configure/build process to match new filenames
(e.g., output static-components.h instead of static-modules.h)
- removed DOS-style cr/lf stuff in ns/ns.h
- added newline to end of file src/util/numtostr.h
- removed some redundant error checking in the top-level topo
functions
- added a few {} here and there where people "forgot" to put them in
for 1 line blocks ;-)
- removed a bunch of MPI_* types from mca header files (replaced with
corresponding ompi_* types)
- all the ptl components had version numbers in their structs; removed
- converted a few more elements in the MCA base to use the OBJ
interface -- removed some old manual reference counting kruft
This commit was SVN r1830.
2004-08-02 00:24:22 +00:00
Jeff Squyres
dc997f438b
Fix some minor compile errors
...
This commit was SVN r1829.
2004-08-01 22:13:33 +00:00
Weikuan Yu
e1fae8ab7a
Get elan PTL up running again. There is some bug with mca_base_module_close(),
...
triggered by the missing of some PTL. With my really slow connection.
It is really hard to do debugging now. I will update more on this.
This commit was SVN r1828.
2004-07-31 02:44:28 +00:00
Prabhanjan Kambadur
76275092da
These two functions were unimplemented .. (oops)
...
This commit was SVN r1827.
2004-07-30 22:06:09 +00:00
Tim Woodall
c37b1629f8
check for null pointer before calling free
...
This commit was SVN r1826.
2004-07-30 20:45:11 +00:00
Jeff Squyres
90de82789e
Finally commit fixes from code review in Ohio with Anju:
...
- better error checking in top-level MPI API coll functions
- remove boolean flags in coll module struct
- minor fixes in selection logic
This commit was SVN r1825.
2004-07-30 19:14:55 +00:00
Weikuan Yu
1e162da7c7
Commit the code to test at OSU.
...
This commit was SVN r1824.
2004-07-30 17:14:20 +00:00
Tim Woodall
985687112b
changes (bug fixes) based on code review by UBC
...
This commit was SVN r1823.
2004-07-30 16:31:43 +00:00
Tim Woodall
952daced67
fixed regression introduced w/ change to support request allocation/caching w/in pml
...
(should now support more than two processes)
This commit was SVN r1822.
2004-07-30 16:29:56 +00:00
Weikuan Yu
a7471009ac
Modify (*mca_ptl_base_request_init_fn_t) to return error
...
if a particular ptl is not able to alloc a fragment.
This commit was SVN r1821.
2004-07-30 16:09:15 +00:00
Weikuan Yu
8fa019d4e8
Save the code to work from LANL
...
This commit was SVN r1820.
2004-07-30 14:08:38 +00:00
Jeff Squyres
5ae8e39fb2
count how many top-level MPI functions are unimplemented
...
This commit was SVN r1819.
2004-07-30 11:48:20 +00:00
Jeff Squyres
c9cb40d102
Remove now-useless macro.
...
This commit was SVN r1818.
2004-07-30 03:00:01 +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
5f3c72b19f
Make the comments on the fields match ptl.h :-)
...
This commit was SVN r1816.
2004-07-29 01:36:20 +00:00
Brian Barrett
32264acd56
* rename ompi_process_t to mca_ns_{cellid, jobid, vpid}_t, both to fix the
...
confusion over the overused typedef and to conform to the naming MCA
naming convention.
This commit was SVN r1815.
2004-07-27 23:49:08 +00:00
Jeff Squyres
81d35ccf3c
Make the filenames follow the prefix rule
...
This commit was SVN r1814.
2004-07-27 12:02:24 +00:00
Jeff Squyres
4799f629e3
ensure to check for init/finalize
...
This commit was SVN r1813.
2004-07-27 02:30:21 +00:00
Edgar Gabriel
6c8c9e9445
adding the initialization of error-codes, error-classes and internal error codes. These missing statements were the reason, that all error codes were up to now rejected as invalid....
...
This commit was SVN r1812.
2004-07-27 00:49:41 +00:00
Jeff Squyres
584252a4b6
Move some initial data around that was initializing the wrong members,
...
and therefore causing tests to fail
This commit was SVN r1811.
2004-07-26 22:24:56 +00:00
Jeff Squyres
480a552f44
- Check for init/finalize
...
- Use ompi_comm_invalid() to check for invalid communicator
This commit was SVN r1810.
2004-07-26 22:22:40 +00:00
Jeff Squyres
753358336b
Remove annoying compiler warning :-)
...
This commit was SVN r1809.
2004-07-26 22:21:20 +00:00
Weikuan Yu
0a87277c55
have people ignore elan for now
...
This commit was SVN r1806.
2004-07-26 13:06:55 +00:00
Weikuan Yu
04f726852b
Check in some early code.
...
And will put back .ompi_ignore to avoid confusion
This commit was SVN r1805.
2004-07-26 13:05:59 +00:00
Jeff Squyres
0c421ef645
- Minor fixes for topo
...
- Make ompi_info show topo modules
This commit was SVN r1804.
2004-07-26 13:04:32 +00:00
Jeff Squyres
915187c3c3
Fix compile error. Please test compile before committing...
...
This commit was SVN r1803.
2004-07-26 11:18:00 +00:00
Weikuan Yu
e6ee369852
Modified some of lines to be 76 columns only to fit 80x24 screens.
...
A minor point to folks who like long lines:
Our coding style is shiftwidth=4 textwidth=76
This commit was SVN r1801.
2004-07-25 16:15:52 +00:00