George Bosilca
e658557d52
Move the convertor creation out of th critical path. If we expect a
...
message from a known peer (not MPI_ANY_SOURCE) then we can attach the
remote proc and initialize the convertor as soon as we know the data-type,
and the count (so basically in the _INIT macro). If it's not the case, then
create them in the _MATCHED macro (as in the original version). Of course,
beforeinitializing the convertor we check that there will be some data
in the message.
This commit, plus the convertor improvements from few days ago, lower the
latency for my test case environment (mvapi) by 0.1 microseconds. The convertor
now is as slim as it can be, I don't think there is anything else to
remove/improve.
This commit was SVN r9843.
2006-05-07 21:03:12 +00:00
George Bosilca
a7542824ed
Generic length computation (moved from the endpoint.h).
...
This commit was SVN r9842.
2006-05-07 20:54:44 +00:00
George Bosilca
569b88e093
The endpoint include is not required.
...
This commit was SVN r9841.
2006-05-07 20:52:55 +00:00
George Bosilca
e63c1dc242
The last commit wans't supposed to bring this function in. It's not yet
...
ready for primetime...
This commit was SVN r9840.
2006-05-07 20:51:43 +00:00
George Bosilca
33aa65f894
Remove useless include.
...
This commit was SVN r9839.
2006-05-07 20:49:45 +00:00
Brian Barrett
7125501573
* Patch from Ralf Wildenhues -- apparently having the ./config instead
...
of config confuses BSD make in VPATH situations. So don't do that.
This commit was SVN r9838.
2006-05-07 19:19:37 +00:00
Galen Shipman
a4c9db0c18
decrease the total bytes in the rcache when a registration is deleted from the
...
cache.
This commit was SVN r9837.
2006-05-07 01:15:33 +00:00
Jeff Squyres
07f1eed04d
Update NEWS w.r.t. MPI_COMM_SPLIT intercomm fix
...
This commit was SVN r9834.
2006-05-05 12:00:33 +00:00
Rainer Keller
0f9b10ff8e
- Update test dup MPI_COMM_WORLD -- so that we may
...
have additional Barriers for output.
This commit was SVN r9831.
2006-05-05 07:42:33 +00:00
George Bosilca
8338a79082
This one belong to the previous commit but it somehow get lost ...
...
This commit was SVN r9830.
2006-05-05 04:32:42 +00:00
George Bosilca
3929ae7010
Add more knowledge into the master convertor. Now all the conversion
...
function are stored in a single location, th master convertor. With the
old information (mainly the remote sizes for each predefined data-type)
now we know everything we need about the remote peers.
This commit was SVN r9829.
2006-05-05 04:30:11 +00:00
George Bosilca
4438be5bcb
Ditch one more function call. Make the initialization step as small as
...
possible.
This commit was SVN r9828.
2006-05-05 03:42:18 +00:00
George Bosilca
a55d4632c6
Continue the cleaning, shrink the convertor initialization function.
...
This commit was SVN r9827.
2006-05-05 03:25:31 +00:00
Jeff Squyres
5e6188a4a8
Update NEWS for INTERCOMM_MERGE fix
...
This commit was SVN r9824.
2006-05-05 02:27:43 +00:00
George Bosilca
c53914ce31
Smallest overhead for contiguous predefined datatypes. There is now a special path
...
in the convertor code for predefined contiguous types.
This commit was SVN r9821.
2006-05-04 22:21:09 +00:00
Rainer Keller
71d328c086
- Add the PERUSE_COMM_REQ_XFER_CONTINUE for recv.
...
This commit was SVN r9820.
2006-05-04 19:31:33 +00:00
Tim Woodall
161e54e6c8
finalize/cleanup failed btl
...
This commit was SVN r9819.
2006-05-04 18:48:45 +00:00
George Bosilca
d8eb9978a6
Rearrange the convertor initialization, in order to make the upgrade required
...
for contiguous types simpler.
This commit was SVN r9818.
2006-05-04 17:36:08 +00:00
Tim Woodall
d8ff8010f3
track wether the vfrag is being retransmitted
...
This commit was SVN r9817.
2006-05-04 17:30:58 +00:00
Tim Woodall
1b26caa95b
first cut at btl failover - seems to be working for simple test case
...
This commit was SVN r9816.
2006-05-04 16:16:26 +00:00
Tim Woodall
350d5b1713
change hardcoded values into mca params
...
This commit was SVN r9815.
2006-05-04 15:20:18 +00:00
Tim Woodall
fdd622544b
added optional copy routine to allow "derived" class
...
of mca_bml_base_endpoint to copy state if an endpoint
is updated (e.g. btl deleted/added)
This commit was SVN r9814.
2006-05-04 15:19:12 +00:00
Tim Woodall
14293acce0
- added cleanup to destructor
...
- added copy routine to copy state from one sequence tracker into another
This commit was SVN r9813.
2006-05-04 15:14:47 +00:00
Brian Barrett
b76b46bcec
* fix some compile issues on Red Storm
...
This commit was SVN r9812.
2006-05-04 14:08:36 +00:00
Brian Barrett
3edcb2620c
* allow buildling of portals pml (have to specify a configure option anyway)
...
* don't built the hostfile ras, as we dont' even use the URM RMGR anymore
This commit was SVN r9811.
2006-05-04 14:08:17 +00:00
Brian Barrett
d101e91b97
* fix matching logic - since tag might be negative, need to mask the proper bits
...
or the bit-wise or changes all the high bits, which is bad
* push convertor creation to init to save a bit of time
* make debugging use macros so that it can go bye-bye
This commit was SVN r9810.
2006-05-04 13:48:32 +00:00
George Bosilca
93ccbc666a
The macro is alreadfy defined in one of the header file.
...
This commit was SVN r9809.
2006-05-04 07:06:58 +00:00
George Bosilca
bdecdc8d41
Cleanup the MX BTL. Remove all mpool related code as there will never be a MX mpool.
...
This commit was SVN r9808.
2006-05-04 06:55:45 +00:00
Brian Barrett
9276127c0d
* add some extra sauce to make sure we close down our processes properly
...
This commit was SVN r9807.
2006-05-04 00:38:49 +00:00
Edgar Gabriel
8c49f14dce
fix a bug in the intercomm-split allgather emulation function.
...
This commit was SVN r9806.
2006-05-03 21:41:10 +00:00
George Bosilca
c5209aad93
The return value is random. Let's return something that make sense.
...
This commit was SVN r9805.
2006-05-03 18:17:00 +00:00
Edgar Gabriel
f962ba2d89
fix the handling of the 'high' argument in Intercomm_merge. The logic
...
was unfortunatly exactly the opposite way round.
This commit was SVN r9803.
2006-05-03 14:43:52 +00:00
Brian Barrett
6db0f2a027
* couple of corrections to compile on Red Storm
...
This commit was SVN r9801.
2006-05-03 13:13:59 +00:00
Jeff Squyres
cc6fec09ba
Update to reflect some directories that are no longer there
...
This commit was SVN r9800.
2006-05-03 12:12:27 +00:00
Rainer Keller
29876af927
- Fix small buglet which causes SIGSEGV (seen with mpitrace/Paraver)
...
This commit was SVN r9799.
2006-05-03 07:53:13 +00:00
Jeff Squyres
87a2458bb1
Make sure to use the C version of the string.
...
This commit was SVN r9796.
2006-05-03 03:29:06 +00:00
Brian Barrett
1aa13c1e5c
* do proper fortran string handling for the MPI-IO functions that take string
...
arguments. Thanks to Bernard Knaepen for bringing this to our attention.
This commit was SVN r9792.
2006-05-02 14:39:11 +00:00
Brian Barrett
10a05dc0d1
* Fix comment about size_t being unsigned
...
* Fix initializer - shouldn't assign a negative value into an unsigned
variable
This commit was SVN r9790.
2006-05-02 12:21:30 +00:00
Brian Barrett
4add400f7d
* properly start with the memory descriptor inactive
...
This commit was SVN r9787.
2006-05-01 20:23:38 +00:00
Brian Barrett
5f939c53be
* first take at send / receive for a poratls pml (still really dumb and simple)
...
This commit was SVN r9786.
2006-05-01 20:03:49 +00:00
Brian Barrett
56f48357b3
* don't try to register callback at init time (will do at window creation time
...
anyway), so that we can run without ob1
This commit was SVN r9785.
2006-05-01 20:03:03 +00:00
Craig E Rasmussen
8a16f844ec
Changes MPI_Intercomm_merge high variable from integer to logical
...
This commit was SVN r9783.
2006-05-01 18:58:35 +00:00
Craig E Rasmussen
0c584d783e
Changes MPI_Intercomm_merge high variable from integer to logical
...
This commit was SVN r9782.
2006-05-01 18:58:05 +00:00
Brian Barrett
4256705ffb
* rename irecv, isend, and iprobe files to recv, send, and probe
...
This commit was SVN r9780.
2006-04-29 22:06:21 +00:00
Brian Barrett
315a889247
Try to get the Portals PML going again, just to get some data for the Cray
...
paper. This is just the shell, for checkpoint. Changes:
* Fix copyrights
* remove cancel code and ptl references
* add dump command
This commit was SVN r9779.
2006-04-29 22:05:20 +00:00
George Bosilca
0aa7587dd7
More timers around the pack/unpack functions.
...
This commit was SVN r9778.
2006-04-29 04:23:49 +00:00
Brian Barrett
52369307f8
Add a feature to the build system that Terry from Sun and I talked about
...
in San Jose. Allow the configure option --disable-binaries to build OMPI,
but not build or install the support binaries (so basically, just build
the libraries).
This commit was SVN r9777.
2006-04-29 02:16:41 +00:00
Brian Barrett
5fed99c2c2
Sending SIZE_MAX from machines with different sizeof(size_t) causes big problems,
...
as the smaller machine's SIZE_MAX won't be SIZE_MAX on the bigger machine, which
can lead to failures along the way -- in this case, with GPR triggers being
improperly fired.
This commit was SVN r9776.
2006-04-28 21:09:42 +00:00
George Bosilca
1af7a797f8
Vector type is the one I work on.
...
This commit was SVN r9774.
2006-04-28 16:20:47 +00:00
George Bosilca
b990870b55
Keep only the fastest version of the homogeneous unpack. Reorder the code
...
to improve the execution path. Some minor clean-ups.
This commit was SVN r9773.
2006-04-28 16:19:54 +00:00