Hello,
i need some information for my thesis and i am not sure if it's right
what i found in the internet before.
therefore i want to ask you if the following two sentences are right:
- Open MPI is OS independent and it runs on windows as well as on
linux
- Open MPI dont has data decomp
On Mar 25, 2008, at 5:09 AM, powernetfr...@surfeu.de wrote:
Hello,
i need some information for my thesis and i am not sure if it's right
what i found in the internet before.
therefore i want to ask you if the following two sentences are right:
- Open MPI is OS independent and it runs on windo
Hello,
thanks for your help.
So Open MPI is OS dependent and actually it dont support Windows
plattforms.
I would want to know if (Open) MPI sipports data decomposition and\ or
task level parallelism.
I think that MPI supports task level parallelism.
But i also think that OpenMPI dont support d
I'm new to OpenMPI and would like to know whether there is a common way
for a caller of mpirun to communicate with the mpi processes. Basically
I have a setup where one process is responsible for distributing jobs
to other mpi processes and collecting the respective results afterwards.
Now for exa
On Mar 25, 2008, at 8:34 AM, powernetfr...@surfeu.de wrote:
Hello,
thanks for your help.
So Open MPI is OS dependent and actually it dont support Windows
plattforms.
I would want to know if (Open) MPI sipports data decomposition and\ or
task level parallelism.
I think that MPI supports task lev
There is a chapter in the MPI standard about this. Usually, people
will use comm accept/connect to do such kind of things. No need to
have your own communication protocol.
george.
On Mar 25, 2008, at 10:32 AM, slimti...@gmx.de wrote:
I'm new to OpenMPI and would like to know whether there
Hallöle,
On 13:34 Tue 25 Mar , powernetfr...@surfeu.de wrote:
> So Open MPI is OS dependent and actually it dont support Windows
> plattforms.
Equating "not running on Windows" to "OS dependent" is a bit harsh, as
Open MPI will run on any Unixish OS (Linux, Solaris, BSD...). You
could have s
Could you explain what you mean by "comm accept/connect" ?
jody
On Tue, Mar 25, 2008 at 4:06 PM, George Bosilca wrote:
> There is a chapter in the MPI standard about this. Usually, people
> will use comm accept/connect to do such kind of things. No need to
> have your own communication protoco
MPI-2 standard
CHAPTER 5. PROCESS CREATION AND MANAGEMENT
Section 5.4
george.
On Mar 25, 2008, at 12:37 PM, jody wrote:
Could you explain what you mean by "comm accept/connect" ?
jody
On Tue, Mar 25, 2008 at 4:06 PM, George Bosilca
wrote:
There is a chapter in the MPI standard about thi
And i am also right when i think that Open MPI supports task level
parallism.
because i think that i can create a process for each task (or create a
task pool) and let them communicating over MPI.
am i right?
thanks.
king regards,
oeter
>Ursprüngliche Nachricht
>Von: gent...@gmx.de
>Da
Hi,
On 19:38 Tue 25 Mar , powernetfr...@surfeu.de wrote:
> And i am also right when i think that Open MPI supports task level
> parallism.
> because i think that i can create a process for each task (or create a
> task pool) and let them communicating over MPI.
> am i right?
You could do so
Hello All,
I currently have an application that works perfectly fine on 2 cores, but
I'm moving it to an 8 core machine and I was wondering if OpenMPI had a
built in solution, or if I would have to code this out manually.
Currently, I'm processing on core X and sending the data to core 0 where
This whole issue came up recently in the MPI Forum (the const-ness [or
not] of the MPI C++ objects). I am a fervent believer that all the
predefined C++ MPI objects should be const and that any MPI function
that allows predefined handles as an argument should be a const
argument.
This go
Sorry for the delay in replying; I got caught up in other things...
On Mar 18, 2008, at 3:15 PM, Christopher Irving wrote:
Okay, I'm no longer sure to which spec file you're referring.
I was referring to the one on the SVN trunk:
https://svn.open-mpi.org/trac/ompi/browser/trunk/contrib/dist/l
On Mar 19, 2008, at 1:48 PM, Michael Jennings wrote:
On Tuesday, 18 March 2008, at 18:18:36 (-0700),
Christopher Irving wrote:
Well you're half correct. You're thinking that _prefix is always
defined as /usr.
No, actually I'm not. :)
But in the case were install_in_opt is defined they have
15 matches
Mail list logo
