Hardware-accelerated inference for real-time gravitational-wave astronomy
Hardware-accelerated inference for real-time gravitational-wave astronomy
复制标题
DOI：
10.1038/s41550-022-01651-w
复制
发表时间：
2021-08
期刊：
影响因子：
14.1
通讯作者：
A. Gunny;D. Rankin;J. Krupa;M. Saleem;Tri Nguyen;M. Coughlin;P. Harris;E. Katsavounidis;S. Timm;B. Holzman
中科院分区：
文献类型：
--
作者：
A. Gunny;D. Rankin;J. Krupa;M. Saleem;Tri Nguyen;M. Coughlin;P. Harris;E. Katsavounidis;S. Timm;B. Holzman
引力波天文学的计算需求预计在未来五年内至少翻一番。随着公里级干涉仪达到设计灵敏度，实时发送引力波警报对于实现多信使后续行动将变得越来越重要。在这里，我们讨论了一种用于实时数据去噪和天体物理源识别的深度学习推理的新实现和部署。这一目标是通过使用通用的推理即服务模型来实现的，该模型能够适应未来对引力波数据分析的需求。该实现允许硬件加速器的无缝结合，并且还允许使用商业或私有的即服务计算。引力波天文学中的低延迟和离线计算解决了可扩展性和可靠性方面的关键挑战，并提供了一个特别针对深度学习应用优化的数据分析平台。
Computational demands in gravitational-wave astronomy are expected to at least double over the next five years. As kilometre-scale interferometers are brought to design sensitivity, real-time delivery of gravitational-wave alerts will become increasingly important to enable multimessenger follow-up. Here we discuss a novel implementation and deployment of deep learning inference for real-time data denoising and astrophysical source identification. This objective is accomplished using a generic inference-as-a-service model capable of adapting to the future needs of gravitational-wave data analysis. The implementation allows seamless incorporation of hardware accelerators and also enables the use of commercial or private as-a-service computing. Low-latency and offline computing in gravitational-wave astronomy addresses key challenges in scalability and reliability and provides a data analysis platform particularly optimized for deep learning applications.