Hmmm...well, a few points here. First, the Phi's sadly don't show up in the
hwloc tree as they apparently are hidden behind the PCIe bridge. I don't know
if there is a way for hwloc to "probe" and find processors on PCI cards, but
that's something I'll have to defer to Jeff and Brice.
So the fi
Jeff,
I know Intel MPI (MPICH based) "just works" with Phi, but you need to do
things like:
mpirun –n 2 –host cpu host.exe : –n 4 –host mic0 mic.exe
if you want to use the Phi for more than just kernel-offload (in which case
they won't have/need an MPI rank).
So, launch procs is PART of the pro
I know the MPICH guys did a bunch of work to support the Phi's. I don't know
exactly what that means (I haven't read their docs about this stuff), but I
suspect that it's more than just launching MPI processes on them...
On May 2, 2013, at 8:54 PM, Paul Hargrove wrote:
> Ralph,
>
> I am not
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 03/05/13 10:47, Ralph Castain wrote:
> We had something similar at one time - I developed it for the
> Roadrunner cluster so you could run MPI tasks on the GPUs. Worked
> well, but eventually fell into disrepair due to lack of use.
OK, interesti
Ralph,
I am not an expert, by any means, but based on a presentation I heard 4
hours ago:
The Xeon and Phi instruction sets have a large intersection, but neither is
a subset of the other.
In particular, Phi has its own SIMD instructions *instead* of Xeon's MMX,
SSEn, etc.
There is also on CMPXCH
On May 2, 2013, at 5:12 PM, Christopher Samuel wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Hi folks,
>
> The new system we're bringing up has 10 nodes with dual Xeon Phi MIC
> cards, are there any plans to support them by launching MPI tasks
> directly on the Phis themselves (
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi folks,
The new system we're bringing up has 10 nodes with dual Xeon Phi MIC
cards, are there any plans to support them by launching MPI tasks
directly on the Phis themselves (rather than just as offload devices
for code on the hosts)?
All the best
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi Ralph, Jeff, Paul,
On 02/05/13 14:14, Ralph Castain wrote:
> Depends on what you think you might want, and how tolerant you and
> your users are about bugs.
>
> The 1.6 series is clearly more mature and stable. It has nearly
> all the MPI-2 stuf
On my trunk MTT runs, I'm getting a bunch of timed out tests with this message:
[node014][[56709,1],31][btl_tcp_endpoint.c:678:mca_btl_tcp_endpoint_complete_connect]
connect() to 10.1.0.7 failed: No route to host (113)
This appeared to be due to a problem with a switch in my cluster, but the
la
On Thu, May 2, 2013 at 5:55 AM, Jeff Squyres (jsquyres)
wrote:
> Given that we know there are compile bugs with XRC in all the v1.7
> releases so far (which seems to show how few people are actually using
> XRC...), there are definitely "growing pains", as Ralph mentioned.
Jeff may be a little
On May 2, 2013, at 12:14 AM, Ralph Castain wrote:
> Personally, even though I'm one of the 1.7 release managers, I'm a little
> leery of recommending it for a production installation until we get further
> down the road. You might consider installing 1.6 as your "base" release, and
> then offe
On May 1, 2013, at 10:32 PM, Orion Poplawski wrote:
> Great! I'll try to take a look at next week.
Hold off on this -- Ralph and I looked at this a bit closer, and the work is
not quite complete yet (read: it doesn't work).
> I noticed another message about using a threaded libevent after all
Depends on what you think you might want, and how tolerant you and your users
are about bugs.
The 1.6 series is clearly more mature and stable. It has nearly all the MPI-2
stuff now, but no MPI-3.
If you think there is something in MPI-3 you might want, then the 1.7 series
could be the way to
13 matches
Mail list logo
