GPU coprocessors as a service for deep learning inference in high energy physics

TL;DR

This paper explores using GPU coprocessors to accelerate deep learning inference in high energy physics data processing, aiming to meet increasing computational demands at CERN's LHC without performance loss.

Contribution

It introduces a strategy for integrating GPU-based acceleration into high energy physics workflows, demonstrating potential for maintaining or exceeding current performance levels.

Findings

GPU acceleration significantly speeds up deep learning inference

Seamless integration strategies enable efficient workflow adaptation

Potential to meet future computational demands at CERN

Abstract

In the next decade, the demands for computing in large scientific experiments are expected to grow tremendously. During the same time period, CPU performance increases will be limited. At the CERN Large Hadron Collider (LHC), these two issues will confront one another as the collider is upgraded for high luminosity running. Alternative processors such as graphics processing units (GPUs) can resolve this confrontation provided that algorithms can be sufficiently accelerated. In many cases, algorithmic speedups are found to be largest through the adoption of deep learning algorithms. We present a comprehensive exploration of the use of GPU-based hardware acceleration for deep learning inference within the data reconstruction workflow of high energy physics. We present several realistic examples and discuss a strategy for the seamless integration of coprocessors so that the LHC can maintain, if not exceed, its current performance throughout its running.