Understanding ML driven HPC: Applications and Infrastructure

Abstract

We recently outlined the vision of "Learning Everywhere" which captures the possibility and impact of how learning methods and traditional HPC methods can be coupled together. A primary driver of such coupling is the promise that Machine Learning (ML) will give major performance improvements for traditional HPC simulations. Motivated by this potential, the ML around HPC class of integration is of particular significance. In a related follow-up paper, we provided an initial taxonomy for integrating learning around HPC methods. In this paper, which is part of the Learning Everywhere series, we discuss "how" learning methods and HPC simulations are being integrated to enhance effective performance of computations. This paper identifies several modes -substitution, assimilation, and control, in which learning methods integrate with HPC simulations and provide representative applications in each mode. This paper discusses some open research questions and we hope will motivate and clear the ground for MLaroundHPC benchmarks.

DeepDriveMD: Deep-Learning Driven Adaptive Molecular Simulations for Protein Folding

“…1 where DL models and methods can be used to guide either individual simulations by determining optimal parameters of exploration, or by intelligently determining regions of phase space to sample, i.e., enhanced sampling. Needless, to say, these three levels are not mutually exclusive and can operate concurrently and collectively to enhanced global computational efficiency, and giving rise to the concept of Learning Everywhere [32], [33] to enhance computational impact. Although this work investigates and focuses on the computational motif in Fig.…”

“…RCT provide scalable implementations of building blocks in Python and are currently used to support dozens of scientific projects on HPC systems, including several existing and prior INCITE awards. RCT is increasingly being used to support applications that involve the concurrent and adaptive execution of ML and simulation tasks [32]. RCT has been used extensively to support biomolecular sciences algorithms/methods, e.g., replica-exchange, adaptive sampling and high-throughput binding affinity calculations.…”