Updated RFC (w/ discussed changes):
==
[RFC 2/2] merge the OPAL SOS development branch into trunk
==
WHAT: Merge the OPAL SOS development branch into the OMPI t
(Updated RFC, per online/offline discussions)
==
[RFC 1/2] ORTE WDC and improvements to the "notifier" framework
==
WHAT: Merge improvements to the "notifier" f
On May 12, 2010, at 7:50 PM, Jeff Squyres wrote:
On May 12, 2010, at 1:21 PM, Nils Carlson wrote:
Probably not me personally, my employer is considering financing a
masters thesis with the aim of doing an implementation.
Is there a guide for adding support? I took a quick look at the tcp
code
On May 12, 2010, at 1:21 PM, Nils Carlson wrote:
> Probably not me personally, my employer is considering financing a
> masters thesis with the aim of doing an implementation.
>
> Is there a guide for adding support? I took a quick look at the tcp
> code, and it wasn't all that straightforward,
There was a paper from a while back where a group implemented TIPC for OMPI
1.0.2 and showed some decent improvement. It was pretty well done in terms of
what they measured but the over-all gains were of the order of 3-4% improvement
for "real world" applications.
http://www.fz-juelich.de/nic-s
Probably not me personally, my employer is considering financing a
masters thesis with the aim of doing an implementation.
Is there a guide for adding support? I took a quick look at the tcp
code, and it wasn't all that straightforward,
though I suppose a lot of the code is aimed at maximisi
I am personally unaware of anyone working TIPC support for Open MPI -- but that
doesn't mean it isn't happening.
I took a *brief* look at the TIPC web site -- it is sorta analogous to Open-MX?
(i.e., sending raw ethernet frames as opposed to TCP)
We'd love to see a BTL module for TIPC in Open
Hi,
I'm wondering if anyone has looked at adding support in MPI for TIPC,
Transparent Inter-Process Communication protocol?
Considering TIPC's properties this should provide better performance
than TCP on ethernet.
Thanks for any info,
Nils Carlson
