Thank you Bruno and Wolfgang. The administrator of my cluster has not
finish installing the new version of deal.ii. My current solution is to use
p4est with one single layer cells (2D), which can be used for my 1D problem
with some modifications. It works well now. Thank you!
Best,
Chenchen
在
On 10/05/2016 08:41 AM, Bruno Turcksin wrote:
Do you know whether automatic
> partitioning uses METIS? But still, I think the old step-17 and 18 should
> work well with version 8.3...
Automatic partitioning does not use METIS and does not work across
nodes.
I believe we only do the automatic p
2016-10-05 10:19 GMT-04:00 Chenchen Liu :
> For "#PBS -l nodes=1:ppn=x",
> when x=1, and use "mpirun -np 1 ./step-17", it works well as a single
> processor.
> when x=1, and use "mpirun -np 4 ./step-17", memory error happens.
> For "#PBS -l nodes=4:ppn=1",
> when I use "mpirun -np 1 ./step-17", it
Hi Bruno,
Thank you for the reply.
For "#PBS -l nodes=1:ppn=x",
when x=1, and use "mpirun -np 1 ./step-17", it works well as a single
processor.
when x=1, and use "mpirun -np 4 ./step-17", memory error happens.
For "#PBS -l nodes=4:ppn=1",
when I use "mpirun -np 1 ./step-17", it works well as
Chenchen,
2016-10-04 18:15 GMT-04:00 Chenchen Liu :
> Second, for "#PBS -l nodes=1:ppn=x", no matter what the value x is, the
> error always exists.
But this is not running across multiple nodes. You are only using one
node, so this the same as running the code on your laptop. What
happens if you
Thank you Bruno for the reply.
First, I did not modify step-17. I just try to run the original code with
no modification. The memory I requested is huge. It is really wired.
Second, for "#PBS -l nodes=1:ppn=x", no matter what the value x is, the
error always exists.
Third, I don't know what is
Chenchen,
On Tuesday, October 4, 2016 at 5:16:12 PM UTC-4, Chenchen Liu wrote:
>
>
> ***Memory allocation failed for SetupCtrl: maxvwgt. Requested size:
> 18446744073709551608 bytes
>
This line says that you are asking for 18446744073 GB of memory...
> It is said that there is a bottleneck for
