The Artificial Scientist -- in-transit Machine Learning of Plasma Simulations

TL;DR

This paper presents a streaming machine learning workflow that processes large-scale plasma simulation data in transit, enabling real-time analysis and learning without file system bottlenecks, demonstrated on GPU-accelerated simulations.

Contribution

It introduces a novel in-transit data streaming workflow for machine learning on large-scale simulations, reducing I/O bottlenecks and simplifying data processing.

Findings

Successful implementation on GPU-accelerated plasma simulations.

Avoided catastrophic forgetting using experience replay.

Scalable to exascale supercomputing systems.

Abstract

Increasing HPC cluster sizes and large-scale simulations that produce petabytes of data per run, create massive IO and storage challenges for analysis. Deep learning-based techniques, in particular, make use of these amounts of domain data to extract patterns that help build scientific understanding. Here, we demonstrate a streaming workflow in which simulation data is streamed directly to a machine-learning (ML) framework, circumventing the file system bottleneck. Data is transformed in transit, asynchronously to the simulation and the training of the model. With the presented workflow, data operations can be performed in common and easy-to-use programming languages, freeing the application user from adapting the application output routines. As a proof-of-concept we consider a GPU accelerated particle-in-cell (PIConGPU) simulation of the Kelvin- Helmholtz instability (KHI). We employ experience replay to avoid catastrophic forgetting in learning from this non-steady process in a continual manner. We detail challenges addressed while porting and scaling to Frontier exascale system.