Dear friends,
I am try to follo the advices about to do login to remote by ssh without
password, for example:
This is one of ...:
SSH without password
Using the below steps, you can ssh to the server from client without the
entering any password.
The machine which run the ssh command is the client
If it is available, yes - though you can control that by setting the
oob_tcp_if_include[exclude] flags
On Apr 5, 2010, at 3:44 PM, David Turner wrote:
> Hi all,
>
> Please, some clarification. I have built Open MPI 1.4.1 against
> our IB verbs layer, and all seems well. But a question has com
Hi all,
Please, some clarification. I have built Open MPI 1.4.1 against
our IB verbs layer, and all seems well. But a question has come
up about IPoIB. While all communications are using the "native"
IB interface (verbs), will mpirun use IPoIB during job launch
and teardown?
If it matters, re
I sent that last message to quick. I was ignoring that MPI_Abort already
takes two args. I've been doing a lot of Perl the past few weeks, so I'm
in a perl state of mind.
I would say add a third arg to MPI_Abort for a programmer-defined error
string, but that would violate the standard, wouldn't
When I try to run the configure utility I get the message that the c++ compiler
can not compile simple c programs. Any ideas?
opmi-1.2.8.tar.gz
Description: GNU Zip compressed data
I would suggest that MPI_Abort take a string as an argument, and print
out the that string when MPI_Abort is called. If a programmer wanted to
NOT have an abort message, they could just omit the argument:
MPI_Abort("Could not open file foo");
or
MPI_Abort();
This would be similar to Perl's die
On Mon, 5 Apr 2010, Rob Latham wrote:
On Tue, Mar 30, 2010 at 11:51:39PM +0100, Ricardo Reis wrote:
If using the master/slace IO model, would it be better to cicle
through all the process and each one would write it's part of the
array into the file. This file would be open in "stream" mode..
On Tue, Mar 30, 2010 at 11:51:39PM +0100, Ricardo Reis wrote:
>
> If using the master/slace IO model, would it be better to cicle
> through all the process and each one would write it's part of the
> array into the file. This file would be open in "stream" mode...
>
> like
>
> do p=0,nprocs-1
Thanks Ralph
Should have considered that.
The assumption would be that anyone who is using the message suppression
option is (or at least should be) wrapping the job launch in some script or
other tool that records a non-0 RC as a job failure or raises a flag for
them to say the job failed.
A
Not all distinctions - the exit status is non-zero. All that is suppressed are
the messages telling you what the error -might- have been.
On Apr 5, 2010, at 7:01 AM, Richard Treumann wrote:
> Why should any software system offer an option which lets the user hide all
> distinction between a run
Le Monday 05 April 2010 15:01:42 Richard Treumann, vous avez écrit :
> Why should any software system offer an option which lets the user hide
> all distinction between a run that succeeded and one that failed?
>
> Dick Treumann - MPI Team
> IBM Systems & Technology Group
> Dept X2ZA / MS P963 -
Why should any software system offer an option which lets the user hide
all distinction between a run that succeeded and one that failed?
Dick Treumann - MPI Team
IBM Systems & Technology Group
Dept X2ZA / MS P963 -- 2455 South Road -- Poughkeepsie, NY 12601
Tele (845) 433-7846 Fax (845
Hi Shiqing,
2010/4/3 Shiqing Fan :
>
> Hi Andrey,
>
> Thanks for your feedback.
I'm pleased to help making openMPI better, at least this way.
>
> Problem 1, 2 and 3 has been fixed in trunk and will be available in future
> release. We'll fix the last two problems as soon as possible.
Glad to hear
13 matches
Mail list logo
