-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi folks,
We've got what we thought would be a fairly standard OMPI (1.6.5)
install which is a single install built with GCC and then setting the
appropriate variables to use the Intel compilers when someone loads
our "intel" module:
$ module show in
Hello,
It seems that the openmpi mercurial mirror
(https://bitbucket.org/ompiteam/ompi-svn-mirror) is not up to date with
the svn reposiory. According to the history the last hg commit is dated
from August 6th (svn r29008), contrary to the svn r29056 from yesterday.
Did something bad happened
Hi,
I am an newbie to all MPI concepts and I would like to understand the MPI
source code thoroughly for
an academic project. So, what I need is an detailed explanation of how every
framework and module
works. It would be really helpful if wise people could point me to right
direction.
Thanks,
Note that according to http://www.ohloh.net/p/openmpi, OMPI is over 3/4M lines
of code. I doubt you will be able to get a thorough understanding of *all* of
OMPI in a semester or two -- indeed, I doubt that any one Open MPI core
developer has a thorough understanding of the whole code base (I k
Oops -- I'll bet this got borked when our hosting provider moved servers
recently. I'll check; thanks for the heads up!
On Aug 22, 2013, at 4:22 AM, Guillaume Papauré
wrote:
> Hello,
>
> It seems that the openmpi mercurial mirror
> (https://bitbucket.org/ompiteam/ompi-svn-mirror) is not up
Looks like it's updated now.
On Aug 22, 2013, at 8:44 AM, Jeff Squyres wrote:
> Oops -- I'll bet this got borked when our hosting provider moved servers
> recently. I'll check; thanks for the heads up!
>
>
> On Aug 22, 2013, at 4:22 AM, Guillaume Papauré
> wrote:
>
>> Hello,
>>
>> It see
Sadly, probably not. :(. You'll prbably have the same problem with c++, too.
There *may* be compatibility command line options for ifort/icpc to make them
link compatible w gfortran/g++, but I've never had much faith in them.
Sent from my phone. No type good.
On Aug 22, 2013, at 2:24 AM, "Ch
Hello Open MPI developers,
I've been away from the Open MPI code for a long time now, but I just
ran across this article that should give developers second thoughts
about using mmap'ed files in performance critical situations.
"Deferring mtime and ctime updates"
http://lwn.net/SubscriberLink/56412
I'm not very keen of seeing BTL modification tainting the PML. I would have
expected support for IPC between GPU must be a BTL-level decision, no a special
path in the PML.
Is there a reason IPC support cannot be hidden down in the SMCUDA BTL?
Thanks,
George.
On Aug 21, 2013, at 23:00 ,
It is ! Thanks !
Le 22/08/2013 15:49, Jeff Squyres (jsquyres) a écrit :
Looks like it's updated now.
On Aug 22, 2013, at 8:44 AM, Jeff Squyres wrote:
Oops -- I'll bet this got borked when our hosting provider moved servers
recently. I'll check; thanks for the heads up!
On Aug 22, 2013, at
Hi George:
The reason it tainted the PML is because the CUDA IPC support makes use of the
large message RDMA protocol of the PML layer. The smcuda btl starts up, but
does not initially support any large message RDMA (RGET,RPUT) protocols. Then
when a GPU buffer is first accessed, the smcuda b
Chris,
.mod files are compiler-specific, and may even be version-specific. You may,
however, be lucky enough to compile the Fortran interface definitions with
ifort and supply that mpi.mod to ifort, even though the actual code was
compiled with gfortran. I have never tried that -- we build se
12 matches
Mail list logo
