Please test!
http://www.open-mpi.org/software/ompi/v1.7/
Changes since rc2:
- Major VampirTrace update to 5.14.4.2.
(** also appeared: 1.6.5)
- Fix to set flag==1 when MPI_IPROBE is called with MPI_PROC_NULL.
(** also appeared: 1.6.5)
- Set the Intel Phi device to be ignored by default b
Please test!
http://www.open-mpi.org/software/ompi/v1.6/
Changes since rc1:
- Major VampirTrace update to 5.14.4.2.
(** also to appear: 1.7.2)
- Fix to set flag==1 when MPI_IPROBE is called with MPI_PROC_NULL.
(** also to appear: 1.7.2)
- Set the Intel Phi device to be ignored by default
In working on the upcoming Cisco USNIC BTL, we noticed that btl.sendi is
invoked by OB1 in the non-MCA_BTL_FLAGS_SEND_INPLACE case.
Is there a reason for this? Or is it only because no one who uses INPLACE has
cared about sendi?
--
Jeff Squyres
jsquy...@cisco.com
For corporate legal informati
I'm sorry -- I was not clear:
- I'm adding 3.2.4 as the imb/ directory *today*.
--> You can go update your MTT configs today.
- I'll refrain from removing the IMB-3.2 and imb_3.2.3 directories until
Tuesday.
On Jun 14, 2013, at 11:57 AM, "Jeff Squyres (jsquyres)"
wrote:
> I see we have 2 v
I see we have 2 versions of IMB in the ompi-tests SVN repo: 3.2, and 3.2.3.
I'm going to update the version to 3.2.4 and remove the other two copies
(IMB_3.2 and imb_3.2.3). The new directory will be version-independent so that
we don't have to do an announcement when updating the version again