HPAC-ML: A Programming Model for Embedding ML Surrogates in Scientific Applications

TL;DR

HPAC-ML introduces a directive-based programming model that simplifies integrating ML surrogates into scientific applications, enabling significant speedups with minimal accuracy loss.

Contribution

It presents a novel, easy-to-use programming model and runtime support for embedding ML models in scientific applications, facilitating faster computations.

Findings

Achieved up to 83.6x speedup in benchmarks

Tested over 5000 ML models across five benchmarks

Minimal accuracy loss with as low as 0.01 RMSE

Abstract

Recent advancements in Machine Learning (ML) have substantially improved its predictive and computational abilities, offering promising opportunities for surrogate modeling in scientific applications. By accurately approximating complex functions with low computational cost, ML-based surrogates can accelerate scientific applications by replacing computationally intensive components with faster model inference. However, integrating ML models into these applications remains a significant challenge, hindering the widespread adoption of ML surrogates as an approximation technique in modern scientific computing. We propose an easy-to-use directive-based programming model that enables developers to seamlessly describe the use of ML models in scientific applications. The runtime support, as instructed by the programming model, performs data assimilation using the original algorithm and can replace the algorithm with model inference. Our evaluation across five benchmarks, testing over 5000 ML models, shows up to 83.6x speed improvements with minimal accuracy loss (as low as 0.01 RMSE).