Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Memory use of scalapack_f_wrapper::factorize() #234

Open
dreamer2368 opened this issue Aug 3, 2023 · 0 comments
Open

Memory use of scalapack_f_wrapper::factorize() #234

dreamer2368 opened this issue Aug 3, 2023 · 0 comments

Comments

@dreamer2368
Copy link
Collaborator

I'm currently playing with the example 1. Although, I'm having a memory limitation error at merge stage, which I think is somewhat strange:

test@3a4a682f99d7:~/build/examples/prom$ sudo ./poisson_global_rom -merge -ns 3
Options used:
   --mesh ../data/star.mesh
   --order 1
   --id 0 
   --nset 3
   --no-static-condensation
   --no-partial-assembly
   --frequency 1
   --coefficient 1
   --device cpu
   --visit-datafiles
   --visualization
   --no-fom
   --no-offline
   --no-online
   --merge
Device configuration: cpu
Memory configuration: host-std
Number of finite element unknowns: 82561
Opening file: basis0_snapshot.000000
Opening file: basis1_snapshot.000000
Opening file: basis2_snapshot.000000
Creating file: basis.000000
In file '/home/test/libROM/lib/linalg/scalapack_f_wrapper.f90', around line 525: Error allocating 13081962144 bytes: Cannot allocate memory

In file '/home/test/libROM/lib/linalg/scalapack_f_wrapper.f90', around line 525 corresponds to the middle of factorize() function. It's demanding about 13GB of memory for SVD operation of matrix of size (82561, 3), which probably takes about 2 MB of memory.

When I run this on a machine with a larger memory, it works as expected. Although, I'm wondering if this memory usage is an expected size.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant