-
Notifications
You must be signed in to change notification settings - Fork 49
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
fluids: SmartSim Online Data-Driven SGS training #1203
Conversation
39d4bcc
to
b8747ff
Compare
4c18a6f
to
70277b9
Compare
24271ad
to
3bfc51f
Compare
afba1e7
to
c435b71
Compare
3bfc51f
to
8400f94
Compare
b26bb54
to
8837361
Compare
b4e2603
to
36b1d88
Compare
3b15795
to
f67273f
Compare
I hereby declare this PR officially good for review! |
1c9cc74
to
95b1a41
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
With the testing working and Ratel compat checked, I think this can merge.
- It can now setup more than just user->grad_velo_proj
- Adds `-smartsim_diable_calls` which can run with `-sgs_train_enable`, but doesn't call SmartSim library calls. This allows for debugging the training related functions without having to run inside a SmartSim experiment.
- So that other QFunctions can use them for indexing into differential filtered fields
- Returns training data
- Adds `smartsim_weak.c` to handle case where SmartRedis is not built
- This will shutdown the simulation if there's a tensor called `check-run` equal to zeros
Requires that the fluids code be built with SMARTREDIS_DIR set, and in an environment with SmartSim (Python library) installed as well. Co-authored by: Zach Atkins <[email protected]>
2e3eab9
to
4e139b5
Compare
Thanks! I've changed the |
Todo:
Depends on #1223