How machine learning can improve HPC applications
23 JUL 2018
Together with partners from various scientific domains we are investigating whether and how machine learning and deep learning are suitable technologies to augment, accelerate or replace scientific workloads on a supercomputer. We do this within the SURF Open Innovation Lab project Machine learning enhanced high performance computing applications.
More accurate, faster and cheaper
Traditionally, the main workloads run on a supercomputer consist of various forms of numerical simulations. Recently, scientists have started exploring the use of machine learning techniques to enhance traditional simulations, such as weather predictions. Early results indicate that these models, that combine machine learning and traditional simulation, can improve accuracy, accelerate time to solution and significantly reduce costs.
Augment, accelerate or replace
For us this forms the starting point of the Machine learning enhanced high performance computing applications project. In this project we will investigate whether and how machine learning and deep learning are suitable technologies to augment, accelerate or replace scientific workloads, such as numerical simulations. And in that context, is it a pre- or post-processing step to help filter and understand the input data or ultimate simulation results, or is it something that is poised to (partly) replace the decades-old codes that comprise many HPC workloads?
Use cases in different domains
In the project we selected 4 use cases in different domains that will investigate the enhancement of traditional HPC simulations with machine learning algorithms:
- Machine-Learned turbulence in next-generation weather models – Dr. Chiel van Heerwaarden, Meteorology and Air Quality Group, Wageningen University;
- Generating physics events without an event generator – Dr. Sacha Caron, Experimental High Energy Physics, Radboud University;
- Distinguising biological interfaces from crystal artifacts in biomolecular complexes using deep learning – Prof. Alexandre M.J.J. Bonvin, Computational Structural Biology, Utrecht University;
- Machine learning for accelerating planetary dynamics in stellar clusters – Prof. Simon Portegies Zwart, Computational Astrophysics, Leiden University.
We will stimulate and support these advanced use cases with funding, technical support, etc., to validate the machine learning approach and its potential for HPC, as we believe that machine learning has the potential to emerge as a mainstream tool for many areas of scientific computing.