Heterogeneous reconstruction of tracks and primary vertices with the CMS pixel tracker

TL;DR

This paper presents a GPU-based heterogeneous reconstruction framework for CMS pixel tracks and vertices, addressing the high computational demands of the HL-LHC era with improved speed and physics performance.

Contribution

The paper introduces a GPU-accelerated implementation of track and vertex reconstruction integrated into CMS software, enhancing processing efficiency for high-luminosity conditions.

Findings

Significant speed-up in reconstruction time using GPUs.

Improved physics output due to more complex algorithms.

Framework successfully integrated into CMS software.

Abstract

The High-Luminosity upgrade of the LHC will see the accelerator reach an instantaneous luminosity of $7\times 10^{34} cm^{-2}s^{-1}$ with an average pileup of $200$ proton-proton collisions. These conditions will pose an unprecedented challenge to the online and offline reconstruction software developed by the experiments. The computational complexity will exceed by far the expected increase in processing power for conventional CPUs, demanding an alternative approach. Industry and High-Performance Computing (HPC) centres are successfully using heterogeneous computing platforms to achieve higher throughput and better energy efficiency by matching each job to the most appropriate architecture. In this paper we will describe the results of a heterogeneous implementation of pixel tracks and vertices reconstruction chain on Graphics Processing Units (GPUs). The framework has been designed and developed to be integrated in the CMS reconstruction software, CMSSW. The speed up achieved by leveraging GPUs allows for more complex algorithms to be executed, obtaining better physics output and a higher throughput.