On 4/1/23 22:01, Tom Li wrote:
Thanks for your replying.I have tried some times to run my code on the
HPC. It seems that every application runs for a long time, this error(fatal
error in PMPI_Waitwall:See the MPI_ERROR field in MPI_Status for the error
code ) wil happen near "setup matrix-free （CPU/wall）" in the file
dealii-main.cc line 420.I think the MPI function MPI_BARRIER may help. But I
am confused that
how to use this function in my code.
Like I said, it would be useful to know whether the program fails in the same
place every time?
And this is the code How I realize my
PDEs in phase field of solidification. Another question is that when I try to
run my code in dimension3, it seems that this code run much slower than
dimension2. I didn‘ change other things just chang the dimension, is there
something went wrong
during this code.
That makes perfect sense to me. If you think about using a program in 2d that
uses a 100x100 mesh, then that is not so much work to solve the resulting
matrix or size 10,000. If you just run it in 3d, the mesh is now 100x100x100
and the matrix has size 1,000,000. That's clearly going to take a lot longer.
Best
W.
--
------------------------------------------------------------------------
Wolfgang Bangerth email: [email protected]
www: http://www.math.colostate.edu/~bangerth/
--
The deal.II project is located at http://www.dealii.org/
For mailing list/forum options, see
https://groups.google.com/d/forum/dealii?hl=en
---
You received this message because you are subscribed to the Google Groups "deal.II User Group" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/dealii/8c33dd3f-849b-e66a-79e2-6afe3a64aa8b%40colostate.edu.
