Hi,
I have a 16 node AMD/P4 machine cluster running Oscar 4.2.1 Beta and
FC4. Each machine has two Gigabit network cards. One being realtek8169
all connected to a netgear GS116 gigabit switch with max MTU =1500 and
the other NIC being aDlink Syskonnect chipset gigabit card connected to
a mana
On Fri, Feb 24, 2006 at 04:44:19PM +0100, Benoit Semelin wrote:
> Well I have actually tried with 2 different versions: 8.0.034 and
> 8.1.018. The config.log is attached (I hope this works on the mailing
> list...)
Looks like ifort on your system is generating 32-bit .o files by
default.
confi
I guess I can follow the instructions in the FAQ. Sorry for this.
David
* Correspondence *
> From: "Xiaoning (David) Yang"
> Reply-To: Open MPI Users
> Date: Fri, 24 Feb 2006 14:19:41 -0700
> To: Open MPI Users
> Conversation: Run Open MPI on MAC OS
> Subject: [OMPI users] Run Open
Hi,
How do I set up multiple Macintosh machines to run Open MPI job on them?
I've installed Open MPI on all of them. Now how do I make rsh/ssh work
without asking passwords? Thanks for any help!
David
* Correspondence *
On Feb 24, 2006, at 10:44 AM, Benoit Semelin wrote:
Well I have actually tried with 2 different versions: 8.0.034 and
8.1.018. The config.log is attached (I hope this works on the
mailing list...)
I'm using 3 version of the intel compiler. These 2 plus the latest
9.0 version and I was ab
Thanks, I have configured also for f77 as you suggest.
The configure now completes, however it outputs a strange error message:
*** Fortran 90/95 compiler
checking whether we are using the GNU Fortran compiler... no
checking whether f95 accepts -g... yes
checking for Fortran flag to compile .f f
Thanks for humoring me, I get it now :-).
Scott
> -Original Message-
> From: users-boun...@open-mpi.org
> [mailto:users-boun...@open-mpi.org] On Behalf Of Jeff Squyres
> Sent: Friday, February 24, 2006 4:09 AM
> To: Open MPI Users
> Subject: Re: [OMPI users] couple of subversion questio
configure:3927: checking for C compiler version
configure:3930: gcc --version &5
gcc (GCC) 4.2.0 20060224 (experimental)
Copyright (C) 2006 Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FO
Hello dear Benoit,
On Friday 24 February 2006 15:26, Benoit Semelin wrote:
> The configuring script fails alltogether with intel fortran. That's
> presumably because intel fortran works on opterons in 32 bits mode only.
Could You please email the config.log file?
Also, it would be interesting what
Hello,
I have problems installing Open-mpi on a quadri-opteron workstation.
The configuring script fails alltogether with intel fortran. That's
presumably because intel fortran works on opterons in 32 bits mode only.
The installation works fine with g95 and gfortran (provided I specify
the 64 l
On Feb 24, 2006, at 8:23 AM, Emanuel Ziegler wrote:
So, the question from the mpirun_debug.out-file is, what IP-
addresses do
node01 and node02 have, is the local 10.0.0.1 node01, while
10.1.0.1 is
node02?
Maybe the route on node01 is not correct to node02?
Ok, I figured out the problem, bu
> So, the question from the mpirun_debug.out-file is, what IP-addresses do
> node01 and node02 have, is the local 10.0.0.1 node01, while 10.1.0.1 is
> node02?
> Maybe the route on node01 is not correct to node02?
Ok, I figured out the problem, but didn't solve it completely.
node01 and node02 b
On Feb 24, 2006, at 5:25 AM, Pierre Valiron wrote:
I have tried to build the 1.0.2a8 version on Solaris Opteron with
Sun Studio 11.
The configure fails on attempting to guess the largest fortran
integer. I attach my build script, and output from configure.
Hopefully there is a simple fix.
On Fri, 24 Feb 2006, Emanuel Ziegler wrote:
So "No rout to host" means that the TCP package could not be sent
(usually host down, broken routing table, network interface down,
...). But it's 'ping'able and even rsh works fine.
... or some packet filtering is enabled. Check with 'iptables -L -
Hello Emanual,
can you actually log in using rsh without submitting a password?
I would rather use the ssh-based login using public-keys to login. This is
definitely more secure but in Your first mail, You said, ssh wouldn't work
either?
So, the question from the mpirun_debug.out-file is, what I
On Feb 24, 2006, at 1:13 AM, Scott Weitzenkamp ((sweitzen)) wrote:
Hmmm...I seem to be able to get at some of the tests if I know the
names
of them by reading the mailing lists. Am I checking out private stuff
below or not? I guess svn is a true replacement for CVS (given CVS
can
be very
> >From /usr/include/asm/errno.h:
>
> #define EHOSTUNREACH113 /* No route to host */
Ah, I thought it was an internal openMPI error number and 'grep'ed the
source code without success. So "No rout to host" means that the TCP
package could not be sent (usually host down, broken routi
On Thu, 23 Feb 2006, Emanuel Ziegler wrote:
Unfortunately, I don't know what errno=113 means, but obviously it's a
TCP problem.
From /usr/include/asm/errno.h:
#define EHOSTUNREACH113 /* No route to host */
--
Bogdan Costescu
IWR - Interdisziplinaeres Zentrum fuer Wissenschaftliche
Hi all,
I have tried to build the 1.0.2a8 version on Solaris Opteron with Sun
Studio 11.
The configure fails on attempting to guess the largest fortran integer.
I attach my build script, and output from configure.
Hopefully there is a simple fix.
Pierre.
--
Soutenez le mouvement SAUVONS LA R
> > Actually, our tests repository is private because it contains tests
> > that we do not have permission to redistribute. Hence, you will not
> > be able to check out the ompi-tests repository.
>
> Then maybe we should stop the ompi-tests messages from going
> into the
> s...@open-mpi.org.
20 matches
Mail list logo
