A Solution to Share: FTorch

C2D3 ECR Conference 2024

Jack Atkinson

ICCS - Cambridge

2024-11-23

Fortran & large-scale simulation

  • Climate Modelling
  • Weather Forecasting
  • Molecular Simulation
  • Fluid Dynamics
  • Engineering Simulation
  • …

Derecho by NCAR
Dawn by Joe Bishop, with permission

Climate models

Machine Learning in Science

We typically think of Deep Learning as an end-to-end process;
a black box with an input and an output1. Typically conducted in Python.

Who’s that Pokémon?

\[\begin{bmatrix}\vdots\\a_{23}\\a_{24}\\a_{25}\\a_{26}\\a_{27}\\\vdots\\\end{bmatrix}=\begin{bmatrix}\vdots\\0\\0\\1\\0\\0\\\vdots\\\end{bmatrix}\] It’s Pikachu!

Neural Net by 3Blue1Brown under fair dealing.
Pikachu © The Pokemon Company, used under fair dealing.

Machine Learning in Science

Neural Net by 3Blue1Brown under fair dealing.
Pikachu © The Pokemon Company, used under fair dealing.

Language interoperation

Many large scientific models are written in Fortran (or C, or C++).
Much machine learning is conducted in Python.

Mathematical Bridge by cmglee used under CC BY-SA 3.0
PyTorch, the PyTorch logo and any related marks are trademarks of The Linux Foundation.”
TensorFlow, the TensorFlow logo and any related marks are trademarks of Google Inc.

FTorch

  • Fortran bindings for PyTorch via C++ libtorch library
    • Load and run models saved from PyTorch
    • feature and future support, and reproducible
    • Make use of the Torch backends for GPU offload
  • Open source project on GitHub
  • Easy to download and build (CMake)
  • Examples suite for new users
  • Full API documentation online at
    cambridge-iccs.github.io/FTorch

Find it on :

/Cambridge-ICCS/FTorch

Some code

 use ftorch
 
 implicit none
 
 real, dimension(5), target :: in_data, out_data  ! Fortran data structures
 
 type(torch_tensor), dimension(1) :: input_tensors, output_tensors  ! Set up Torch data structures
 type(torch_model) :: torch_net
 integer, dimension(1) :: tensor_layout = [1]
 
 in_data = ...  ! Prepare data in Fortran
 
 ! Create Torch input/output tensors from the Fortran arrays
 call torch_tensor_from_array(input_tensors(1), in_data, tensor_layout, torch_kCPU)
 call torch_tensor_from_array(output_tensors(1), out_data, tensor_layout, torch_kCPU)
 
 call torch_model_load(torch_net, 'path/to/saved/model.pt')          ! Load ML model
 call torch_model_forward(torch_net, input_tensors, output_tensors)  ! Infer
 
 call further_code(out_data)  ! Use output data in Fortran immediately
 
 ! Cleanup
call torch_delete(model)
call torch_delete(in_tensors)
call torch_delete(out_tensor)

Actively used in research

  • Uncertainty Quantification of a Machine Learning Subgrid-Scale Parameterization for Atmospheric Gravity Waves (Mansfield and Sheshadri 2024)
    • “Identical” offline networks have very different behaviours when deployed online.
  • Interpretable multiscale Machine Learning-Based Parameterizations of Convection for ICON (Heuer et al. 2023)
    • Online stability improved when non-causal relations (assessed usng SHAP values) eliminated from net
  • Model Bias Correction - Will Chapman WIP
    • Learning model bias from data-assimilation to perform real-time corrections
  • Plus other users in Civil Engineering, Biophysics, CFD, and more.

Thanks

 Jack Atkinson

 jackatkinson.net

 jwa34[AT]cam.ac.uk

 jatkinson1000

 @jatkinson1000@fosstodon.org

RSE Unicorn by Cristin Merritt used with permission

References

Heuer, Helge, Mierk Schwabe, Pierre Gentine, Marco A Giorgetta, and Veronika Eyring. 2023. “Interpretable Multiscale Machine Learning-Based Parameterizations of Convection for ICON.” arXiv Preprint arXiv:2311.03251.
Mansfield, Laura A, and Aditi Sheshadri. 2024. “Uncertainty Quantification of a Machine Learning Subgrid-Scale Parameterization for Atmospheric Gravity Waves.” Authorea Preprints.