4 months agoFixes #3470: ARM atomics v1.7
jsquyres [Tue, 05 Feb 2013 16:21:25 +0000] rev 21372
Fixes #3470: ARM atomics

---svn-pre-commit-ignore-below---

Patch based on:

r27882 [[BR]]
The patch from ticket #3469 adapted for the trunk.

4 months agoRather than setting up the direct call stuff in ompi_mca (which requires
brbarret [Mon, 04 Feb 2013 23:26:42 +0000] rev 21371
Rather than setting up the direct call stuff in ompi_mca (which requires
modifying ompi_mca for every interface that is direct called), do it in
the framework's .m4 file.

4 months agoThe opal_list_t destructor doesn't release the items on the list prior to destructing or releasing it. Provide two convenience macros for doing so.
rhc [Mon, 04 Feb 2013 19:42:57 +0000] rev 21370
The opal_list_t destructor doesn't release the items on the list prior to destructing or releasing it. Provide two convenience macros for doing so.

4 months agoFixes #3496: Move wrapper orte fix to 1.7 v1.7
jsquyres [Mon, 04 Feb 2013 17:36:55 +0000] rev 21369
Fixes #3496: Move wrapper orte fix to 1.7

---svn-pre-commit-ignore-below---

Custom patch on ticket based on:

r27972 [[BR]]
Need the WRAPPER_EXTRA_* defines for orte_info as well.

4 months agoMTL MXM: push commit r27987 back, now with right user.
vasily [Mon, 04 Feb 2013 06:59:24 +0000] rev 21368
MTL MXM: push commit r27987 back, now with right user.
r27987 - MTL MXM: ver. 2.0 interface changes.

4 months agoRevert revesion -r27986, the reason is - it was submitted with wrong user name.
vasily [Mon, 04 Feb 2013 06:54:24 +0000] rev 21367
Revert revesion -r27986, the reason is - it was submitted with wrong user name.

4 months agoFixes #3498: integrate MXM 2.0 support into v1.7 v1.7
jsquyres [Sun, 03 Feb 2013 14:51:00 +0000] rev 21366
Fixes #3498: integrate MXM 2.0 support into v1.7

---svn-pre-commit-ignore-below---

Custom patch from ticket based on:

r27987 [[BR]]
MTL MXM: ver. 2.0 interface changes.

4 months agoFixes #3494: If we get 0 bytes back for the ACK, it doesn't
jsquyres [Sat, 02 Feb 2013 01:19:03 +0000] rev 21365
Fixes #3494: If we get 0 bytes back for the ACK, it doesn't
necessarily mean an error -- it could (and usually does) mean that the
peer realized that we both initiated a connect at the same time, and
therefore it decided to hang up.

I also added a friendly show_help error message for other cases where
recv_blocking() fails (i.e., "Something went wrong. Kaboom! Your job
will abort...").

4 months agoSync with v1.6 NEWS
jsquyres [Fri, 01 Feb 2013 21:55:43 +0000] rev 21364
Sync with v1.6 NEWS

4 months ago1.6.4rc3 has been released; on to 1.6.4rc4 v1.6
jsquyres [Fri, 01 Feb 2013 21:56:44 +0000] rev 21363
1.6.4rc3 has been released; on to 1.6.4rc4