1
1
Граф коммитов

7029 Коммитов

Автор SHA1 Сообщение Дата
Galen Shipman
a465047e97 enable timeouts and retransmissions
This commit was SVN r9322.
2006-03-16 22:33:08 +00:00
George Bosilca
229f26dc55 First split of the datatype. More files and a cleaner distribution of functions
in the corresponding files. There are few others changes to come ...

This commit was SVN r9319.
2006-03-16 21:04:34 +00:00
Galen Shipman
3c9ce06f59 Use new csum routines
This commit was SVN r9318.
2006-03-16 20:26:33 +00:00
Galen Shipman
ff75de8c52 more dr work, add destination check on all receives, misc
This commit was SVN r9317.
2006-03-16 19:38:21 +00:00
Josh Hursey
66edc64be0 Minor comment change
This commit was SVN r9316.
2006-03-16 19:00:03 +00:00
Josh Hursey
7fcfd87cd5 Minor date change
This commit was SVN r9315.
2006-03-16 18:59:13 +00:00
Brian Barrett
234adb292b * add ability to try a couple of different collectives for fence
synchronization to see which gives the best performance

This commit was SVN r9314.
2006-03-16 18:40:42 +00:00
Jeff Squyres
8a9e76dfa3 Thanks to Sven for noticing that the increment in scatter should be
per the send datatype, not the receive datatype (MPI-1:105).

This commit was SVN r9312.
2006-03-16 18:18:28 +00:00
Mohamad Chaarawi
b8c9adc833 checking of multiply included/excluded processes in
group_range_incl/excl has now been separated from the implementation.

This commit was SVN r9311.
2006-03-16 17:51:16 +00:00
Tim Woodall
bab5b2a63e check for resource leak
This commit was SVN r9310.
2006-03-16 17:27:54 +00:00
George Bosilca
e79f35fe6c Copy the last fake DT_END_LOOP too when we duplicate the data.
This commit was SVN r9309.
2006-03-16 17:21:10 +00:00
George Bosilca
4aa343990f Remove the segfault in ompi_info, when we try to destruct a not yet
constructed object.

This commit was SVN r9308.
2006-03-16 16:56:22 +00:00
Rainer Keller
d5d552c97b - Delete the compiler-generated comments APP/NO_APP, as some
assemblers do not understand them (SunOS 5.10)

This commit was SVN r9307.
2006-03-16 15:14:00 +00:00
Jeff Squyres
820548a84a Sync against v1.0 NEWS
This commit was SVN r9305.
2006-03-16 14:46:58 +00:00
Jeff Squyres
b00e69bfa8 Add Linux PPC assembly comment
This commit was SVN r9302.
2006-03-16 14:40:03 +00:00
Rainer Keller
2ce64c6fc7 - Add missing signed_char
All hail the moog!

This commit was SVN r9299.
2006-03-16 11:06:59 +00:00
Rainer Keller
a8144cca8d - Fix the return codes -- not OMPI, but MPI..
- Use the datatype-checks of bindings.h within recv.
   However, for the time being disable the check for overlapped,
   as it is not correctly set.

This commit was SVN r9298.
2006-03-16 09:42:46 +00:00
Andrew Friedley
a3e2d2442b Mostly whitespace and other small cleanups.
Fixed configure.m4 to pull in the modified CFLAGS properly.

Some additional error checking and use of OMPI_ENABLE_DEBUG.

This commit was SVN r9296.
2006-03-16 02:38:08 +00:00
George Bosilca
49c40f596b No data validation by default.
This commit was SVN r9295.
2006-03-16 01:35:49 +00:00
Tim Woodall
178d8ea905 use consistent macros for csum
This commit was SVN r9294.
2006-03-16 00:20:43 +00:00
Tim Woodall
9e958f727f additional macros for csum
This commit was SVN r9293.
2006-03-16 00:19:55 +00:00
Tim Woodall
564c177922 corrections for threading support
This commit was SVN r9292.
2006-03-16 00:06:48 +00:00
Tim Woodall
c34f4c2cb7 correct cleanup for threaded case
This commit was SVN r9291.
2006-03-16 00:05:39 +00:00
George Bosilca
612570134f The request management framework has been redesigned. The main idea is
to let the PML (or io, more generally the low level request manager)
to have it's own release function (what was before the req_fini). This
function will only be called from the low level while the req_free will
be called from the upper level (MPI layer) in order to mark the request
as not used by the user anymore.

From the request point of view the requests will be marked as inactive
everytime we read their status (true for persistent as well). As 
MPI_REQUEST_NULL is already marked as inactive, the test and wait functions
are simpler. The drawback is that now we have to change in the
ompi_request_{test|wait} the req_status of the request once we get it's
status.

This commit was SVN r9290.
2006-03-15 22:53:41 +00:00
George Bosilca
fd01a23e7f Remove unused variables.
This commit was SVN r9289.
2006-03-15 22:49:05 +00:00
Sven Stork
bfa59f07b3 - fix wrong write length, we have to write the amount of data that is used and not free
- replace numeric constant by symbolic name

This commit was SVN r9288.
2006-03-15 15:06:09 +00:00
Brian Barrett
115a3cdd1a * add datatype directory to dist_subdirs as well as subdirs. Fixes broken
make dist from last night

This commit was SVN r9287.
2006-03-15 15:03:15 +00:00
Brian Barrett
5c7751f9a2 * configure changes required to support the double compile of the ddt engine.
still need to coordinate some Makefile.am changes with george tomorrow, but
  this is the stuff that will require re-autogening

This commit was SVN r9285.
2006-03-15 03:35:30 +00:00
Brian Barrett
db5bc19785 * work around bumm assembly result on linux ppc32, which was claiming
support for 64 bit opcodes

This commit was SVN r9284.
2006-03-15 03:33:46 +00:00
George Bosilca
d19e924ca8 gcc print out: warning: ISO C90 forbids mixed declarations and code.
This commit was SVN r9283.
2006-03-14 22:27:19 +00:00
George Bosilca
8fb84e90ce It's already done in the send ... we don't have to initialize this
field several times.

This commit was SVN r9282.
2006-03-14 21:55:57 +00:00
Mohamad Chaarawi
c5a8870f6b move the implementation of the group creation functions into according back-end
functions. 

This commit was SVN r9281.
2006-03-14 21:01:46 +00:00
Mohamad Chaarawi
7ecc505f5c generate back-end functions for the group creation
operations. The only item left for this transition is to move the check
for multiply included/excluded processes in group_range_incl/excl to the
MPI layer.

This commit was SVN r9280.
2006-03-14 21:00:55 +00:00
Graham Fagg
fcca36d280 Add missing ifdef
This commit was SVN r9279.
2006-03-14 20:48:50 +00:00
Tim Woodall
0b366e912c macros to compute checksum while moving data
This commit was SVN r9278.
2006-03-14 19:33:27 +00:00
Tim Woodall
92c5e26758 correct scheduling
This commit was SVN r9277.
2006-03-14 18:25:25 +00:00
Tim Woodall
648ca32742 correct include
This commit was SVN r9276.
2006-03-14 14:40:52 +00:00
Edgar Gabriel
6ae01b4c3a minor correction regarding the reference count of ompi_mpi_group_null.
This commit was SVN r9273.
2006-03-13 22:58:27 +00:00
Edgar Gabriel
073c6e6c32 The f2c interface of these routines have to do proper conversation of
fortran strings to c strings, else the name-publishing and name-lookup
and all subsequent calls (e.g. connect/accept) do not work with fortran.

This commit was SVN r9272.
2006-03-13 22:56:56 +00:00
Tim Woodall
11ebf40814 correction
This commit was SVN r9265.
2006-03-13 17:58:00 +00:00
Tim Woodall
a0c816b239 make sure requests are released correctly for status ignore case
This commit was SVN r9264.
2006-03-13 17:44:52 +00:00
Galen Shipman
440417e92c Add max_btls option
This commit was SVN r9263.
2006-03-13 17:03:21 +00:00
Sven Stork
12b94972e2 Fix comment of a paramter.
This commit was SVN r9261.
2006-03-13 09:11:46 +00:00
Brian Barrett
1f6e85af4c Let's try this again, this time with less suck.
* Don't do the .in -> .tmp -> header thing for the prefixes and versions.
  It causes some severe cleanup issues all to save 4 files from rebuilding
  when configure is run.
* Clean up some makefiles so it's clear what is being installed/disted

This commit was SVN r9260.
2006-03-12 17:56:58 +00:00
Brian Barrett
ea7b9cfc81 * Only enable SLURM support in ORTE if on a platform currently supported by
SLURM.  Currently, this includes AIX and Linux.  If the user wants to build
  SLURM on another platform, they can specify --with-slurm.
* Enable/disable the SLURM sds component using the same logic as the PLS and
  RDS components.

This commit was SVN r9259.
2006-03-12 05:32:35 +00:00
Brian Barrett
871957437d * SilverStorm's header files do some evil things that cause some of our
header files to go bad.  Include vapi.h after our headers to solve
  the issue.

This commit was SVN r9258.
2006-03-12 04:45:28 +00:00
Brian Barrett
635f650250 * fix typo
This commit was SVN r9257.
2006-03-12 04:43:59 +00:00
Brian Barrett
c42da09796 * Fix a small bug George noticed - if you change the prefix (or any of the
installation directories) in configure, the files that depend on this
  information are not properly rebuilt.  If you need this information,
  don't setup a -D in the Makefile.am - instead, include 
  opal/install_dirs.h.
* Use the : option in AC_CONFIG_FILES to avoid needing to expose that
  we are playing around with temporary files with our headers to avoid
  rebuilding
* Clean up the version file information a bit, and like the install 
  directory stuff, make sure that there is a dependency so that 
  ompi_info gets rebuilt properly when a version number changes.

This commit was SVN r9256.
2006-03-12 04:35:01 +00:00
Brian Barrett
6b0069b820 * We don't need the ttcompat module loaded into the stream on Solaris, and it
was causing problems (indeed, we don't have it in LAM and it hasn't caused
  problems in the last many many years).  Standard I/O forwarding now works
  properly on Solaris in both 32 and 64 bit builds
* Add NEWS item about standard I/O on platforms without openpty()

This commit was SVN r9255.
2006-03-11 17:56:30 +00:00
Brian Barrett
d041558f85 * protect lock when not building threaded
This commit was SVN r9254.
2006-03-11 03:20:50 +00:00