An Event-Driven Approach to Serverless Seismic Imaging in the Cloud

被引:12
|
作者
Witte, Philipp A. [1 ]
Louboutin, Mathias [1 ]
Modzelewski, Henryk [2 ]
Jones, Charles [3 ]
Selvage, James [3 ]
Herrmann, Felix J. [1 ]
机构
[1] Georgia Inst Technol, Sch Computat Sci & Engn, Atlanta, GA 30308 USA
[2] Univ British Columbia, Dept Earth Ocean & Atmospher Sci, Vancouver, BC V6T 1Z2, Canada
[3] Osokey Ltd, Henley On Thames RG9 1AY, England
关键词
Cloud computing; Imaging; Mathematical model; Computational modeling; Numerical models; Propagation; Benchmark testing; WAVE-FORM INVERSION; FREQUENCY-DOMAIN; ALGORITHM; FOURIER;
D O I
10.1109/TPDS.2020.2982626
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Adapting the cloud for high-performance computing (HPC) is a challenging task, as software for HPC applications hinges on fast network connections and is sensitive to hardware failures. Using cloud infrastructure to recreate conventional HPC clusters is therefore in many cases an infeasible solution for migrating HPC applications to the cloud. As an alternative to the generic lift and shift approach, we consider the specific application of seismic imaging and demonstrate a serverless and event-driven approach for running large-scale instances of this problem in the cloud. Instead of permanently running compute instances, our workflow is based on a serverless architecture with high throughput batch computing and event-driven computations, in which computational resources are only running as long as they are utilized. We demonstrate that this approach is very flexible and allows for resilient and nested levels of parallelization, including domain decomposition for solving the underlying partial differential equations. While the event-driven approach introduces some overhead as computational resources are repeatedly restarted, it inherently provides resilience to instance shut-downs and allows a significant reduction of cost by avoiding idle instances, thus making the cloud a viable alternative to on-premise clusters for large-scale seismic imaging.
引用
收藏
页码:2032 / 2049
页数:18
相关论文
共 50 条
  • [1] An Event-Driven Serverless ETL Pipeline on AWS
    Pogiatzis, Antreas
    Samakovitis, Georgios
    APPLIED SCIENCES-BASEL, 2021, 11 (01): : 1 - 13
  • [2] Formalizing Event-Driven Behavior of Serverless Applications
    Obetz, Matthew
    Das, Anirban
    Castiglia, Timothy
    Patterson, Stacy
    Milanova, Ana
    SERVICE-ORIENTED AND CLOUD COMPUTING (ESOCC 2020), 2020, 12054 : 19 - 29
  • [3] A UML Profile for Multi-Cloud Service Configuration (UMLPMSC) in Event-driven Serverless Applications
    Samea, Fatima
    Azam, Farooque
    Anwar, Muhammad Waseem
    Khan, Mehreen
    Rashid, Muhammad
    2019 8TH INTERNATIONAL CONFERENCE ON SOFTWARE AND COMPUTER APPLICATIONS (ICSCA 2019), 2019, : 431 - 435
  • [4] Event-Driven Serverless Pipelines for Video Coding and Quality Metrics
    Wilmer Moina-Rivera
    Miguel Garcia-Pineda
    Jose M. Claver
    Juan Gutiérrez-Aguado
    Journal of Grid Computing, 2023, 21
  • [5] Event-Driven Serverless Pipelines for Video Coding and Quality Metrics
    Moina-Rivera, Wilmer
    Garcia-Pineda, Miguel
    Claver, Jose M.
    Gutierrez-Aguado, Juan
    JOURNAL OF GRID COMPUTING, 2023, 21 (02)
  • [6] A Proactive Event-Driven Approach for Dynamic QoS Compliance in Cloud of Things
    Nawaz, Falak
    Hussain, Omar Khadeer
    Janjua, Naeem
    Chang, Elizabeth
    2017 IEEE/WIC/ACM INTERNATIONAL CONFERENCE ON WEB INTELLIGENCE (WI 2017), 2017, : 971 - 975
  • [7] On-premises Serverless Computing for Event-Driven Data Processing Applications
    Perez, Alfonso
    Risco, Sebastian
    Naranjo, Diana Maria
    Caballer, Miguel
    Molto, German
    2019 IEEE 12TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING (IEEE CLOUD 2019), 2019, : 414 - 421
  • [8] A serverless gateway for event-driven machine learning inference in multiple clouds
    Naranjo, Diana M.
    Risco, Sebastian
    Molto, German
    Blanquer, Ignacio
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2023, 35 (18):
  • [9] Event-driven approach for predictive and proactive management of SLA violations in the Cloud of Things
    Nawaz, Falak
    Janjua, Naeem Khalid
    Hussain, Omar Khadeer
    Hussain, Farookh Khadeer
    Chang, Elizabeth
    Saberi, Morteza
    FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2018, 84 : 78 - 97
  • [10] Event-Driven Approach for Monitoring and Orchestration of Cloud and Edge-Enabled IoT Systems
    Mouine, Mohamed
    Saied, Mohamed Aymen
    2022 IEEE 15TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING (IEEE CLOUD 2022), 2022, : 273 - 282