[MITgcm-support] Compiler options for ifort on x86_64
Lucas Merckelbach
lmm at noc.soton.ac.uk
Mon Oct 24 05:41:59 EDT 2005
On Fri, 21 Oct 2005, Constantinos Evangelinos wrote:
> On Friday 21 October 2005 09:17, Lucas Merckelbach wrote:
>> Constantinos, thanks for your message. It helped me a bit, but it didn't
>> solved the problem. Yet, I hope.
>
> I'll need to try things out on an EMT64 system and get back to you.
Thanks!
If you need any assistance in the form of my model setup, I'm happy to
give that to you.
The dimensions that run without any problem at all:
256x256x32 grid points,
and runs into trouble on both amd64 and em64T:
512x512x32
On both platforms the exe immediately returns with "Killed".
In an earlier email I told you on the results of your test program, that
compiled on both platforms using scenario 2) (-mcmodel=medium) and it only
ran on the amd64 and gave a "killed" on the em64t. Well, it gave a
"killed| because a 256x256x32 job was running as well. Without that job,
your test program does run on the em64t as well. could it be related to a
memory problem?
My memory with no jobs running:
nova:~$ free -m
total used free shared buffers cached
Mem: 2008 1818 189 0 45 1109
-/+ buffers/cache: 663 1345
Swap: 4094 521 3572
When I run the test program (declares 6e8 doubles) it eats 80% of my swap
file, so both the mitmodel running and the test program is too much.)
Running two instances of the test program simultaneously paralyses the
system (load goes up to 20), in the end it comes back to life and one of
the exe's made it until the end, the other got Killed as well. But only
after a minute or 5.
What i suspect is that the 512x512x32 is just too big to fit in the
memory. If I enlarge the number of elements in the test program by a
factor of 10 (6e9 elements), it also quits immediately. The transition
between killed and not killed is between 6.5e8 - 7e8 elements. This is
about 77 times larger than what is required for one variable defined on
the whole grid. I can understand that this is pretty tight. Plugging in
more memory, would that help?
If you think that available RAM is the bottelneck here, then please don't
spend too much time on this. I guess for me the solution is to move to the
IA64 platform, where it does seem to work.
Thanks,
lucas
More information about the MITgcm-support
mailing list