arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.09633physics.comp-phhep-exphysics.data-an
收藏

基于图神经网络的跟踪即服务

Graph Neural Network-based Tracking as a Service

Haoran Zhao, Andrew Naylor, Shih-Chieh Hsu, Paolo Calafiura, Steven Farrell, Yongbing Feng, Philip Coleman Harris, Elham E Khoda, William Patrick Mccormack, Dyl… 展开作者

Haoran Zhao, Andrew Naylor, Shih-Chieh Hsu, Paolo Calafiura, Steven Farrell, Yongbing Feng, Philip Coleman Harris, Elham E Khoda, William Patrick Mccormack, Dylan Sheldon Rankin, Xiangyang Ju

AI总结:

针对基于GNN的径迹寻找在CPU上计算慢、内存需求大及部署依赖复杂的问题,提出一种在NVIDIA Triton推理服务器中集成自定义后端的“基于GNN的跟踪即服务”方法,并在Perlmutter超级计算机上验证了其性能。

摘要:

最近的研究表明,在稠密环境中使用基于图神经网络(GNN)的算法进行径迹寻找取得了有希望的结果。然而,基于GNN的径迹寻找在CPU上计算速度慢,需要使用协处理器来加速推理时间。此外,大的输入图尺寸要求大的设备内存以进行高效计算,这一要求并非所有用于粒子物理实验的计算设施都能满足,特别是那些缺乏高级GPU的设施。此外,在生产环境中部署基于GNN的径迹寻找算法需要安装所有依赖的软件包,而这些软件包仅被该算法使用。必须解决这些计算挑战,才能成功将基于GNN的径迹寻找算法实施到生产环境中。作为回应,我们引入了一种“基于GNN的跟踪即服务”方法,在NVIDIA Triton推理服务器中集成了一个自定义后端,以促进基于GNN的跟踪。本文介绍了使用NERSC的Perlmutter超级计算机时该方法的性能。

英文摘要:

Recent studies have shown promising results for track finding in dense environments using Graph Neural Network (GNN)-based algorithms. However, GNN-based track finding is computationally slow on CPUs, necessitating the use of coprocessors to accelerate the inference time. Additionally, the large input graph size demands a large device memory for efficient computation, a requirement not met by all computing facilities used for particle physics experiments, particularly those lacking advanced GPUs. Furthermore, deploying the GNN-based track-finding algorithm in a production environment requires the installation of all dependent software packages, exclusively utilized by this algorithm. These computing challenges must be addressed for the successful implementation of GNN-based track-finding algorithm into production settings. In response, we introduce a ``GNN-based tracking as a service'' approach, incorporating a custom backend within the NVIDIA Triton inference server to facilitate GNN-based tracking. This paper presents the performance of this approach using the Perlmutter supercomputer at NERSC.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑