XaaS: Acceleration as a Service to Enable Productive High-Performance Cloud Computing

被引:0
|
作者
Hoefler, Torsten [1 ]
Copik, Marcin [1 ]
Beckman, Pete [2 ]
Jones, Andrew [3 ]
Foster, Ian [4 ]
Parashar, Manish [5 ]
Reed, Daniel [6 ]
Troyer, Matthias [3 ]
Schulthess, Thomas [7 ]
Ernst, Daniel [8 ]
Dongarra, Jack [9 ]
机构
[1] Swiss Fed Inst Technol, CH-8093 Zurich, Switzerland
[2] Argonne Natl Lab, Lemont, IL 60439 USA
[3] Microsoft, Redmond, WA 98052 USA
[4] Argonne Natl Lab, Data Sci & Learning Div, Lemont, IL 60439 USA
[5] Utah Univ, Kalhert Sch Comp, Salt Lake City, UT 84112 USA
[6] Univ Utah, Comp Sci & Elect & Comp Engn, Salt Lake City, UT 84117 USA
[7] Swiss Natl Supercomp Ctr, CH-6900 Lugano, Switzerland
[8] Nvidia, Santa Clara, CA 95051 USA
[9] Univ Tennessee, Knoxville, TN 37996 USA
关键词
Cloud computing; Containers; Computational modeling; Computer architecture; Meteorology; Ecosystems; Resource management;
D O I
10.1109/MCSE.2024.3382154
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
High-performance computing (HPC) and the cloud have evolved independently, specializing their innovations into performance or productivity. Acceleration as a Service (XaaS) is a recipe to empower both fields with a shared execution platform that provides transparent access to computing resources, regardless of the underlying cloud or HPC service provider. Bridging HPC and cloud advancements, XaaS presents a unified architecture built on performance-portable containers. Our converged model concentrates on low-overhead, high-performance communication and computing, targeting resource-intensive workloads from climate simulations to machine learning. XaaS lifts the restricted allocation model of Function as a Service (FaaS), allowing users to benefit from the flexibility and efficient resource utilization of serverless computing while supporting long-running and performance-sensitive workloads from HPC.
引用
收藏
页码:40 / 51
页数:12
相关论文
共 50 条
  • [41] Speculation resource provisioning in high-performance computing
    Sri, Leena
    Narayanan, Balaji
    KUWAIT JOURNAL OF SCIENCE, 2017, 44 (01) : 58 - 63
  • [42] A review on the decarbonization of high-performance computing centers
    Silva, C. A.
    Vilaca, R.
    Pereira, A.
    Bessa, R. J.
    RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2024, 189
  • [43] Modular High-Performance Computing Using Chiplets
    Vinnakota, Bapi
    Shalf, John M.
    COMPUTING IN SCIENCE & ENGINEERING, 2023, 25 (06) : 39 - 48
  • [44] Web Portals for High-performance Computing: A Survey
    Calegari, Patrice
    Levrier, Marc
    Balczynski, Pawel
    ACM TRANSACTIONS ON THE WEB, 2019, 13 (01)
  • [45] A survey of high-performance computing scaling challenges
    Geist, Al
    Reed, Daniel A.
    INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2017, 31 (01): : 104 - 113
  • [46] HIGH-PERFORMANCE COMPUTING SYSTEMS - PRESENT AND FUTURE
    BISIANI, R
    FUTURE GENERATION COMPUTER SYSTEMS, 1994, 10 (2-3) : 241 - 248
  • [47] Optimizing FHEW With Heterogeneous High-Performance Computing
    Lei, Xinya
    Guo, Ruixin
    Zhang, Feng
    Wang, Lizhe
    Xu, Rui
    Qu, Guangzhi
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2020, 16 (08) : 5335 - 5344
  • [48] A Survey of High-Performance Computing for Software Verification
    Zakharov, Ilja
    TOOLS AND METHODS OF PROGRAM ANALYSIS, 2018, 779 : 196 - 208
  • [49] High-performance IO for seismic processing on the cloud
    Guimaraes, Antonio
    Lacalle, Luis
    Rodamilans, Charles B.
    Borin, Edson
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2021, 33 (18):
  • [50] Evaluating Cloud Auto-Scaler Resource Allocation Planning Under High-Performance Computing Workloads
    Leochico, Kester
    John, Eugene
    2020 IEEE INTL SYMP ON PARALLEL & DISTRIBUTED PROCESSING WITH APPLICATIONS, INTL CONF ON BIG DATA & CLOUD COMPUTING, INTL SYMP SOCIAL COMPUTING & NETWORKING, INTL CONF ON SUSTAINABLE COMPUTING & COMMUNICATIONS (ISPA/BDCLOUD/SOCIALCOM/SUSTAINCOM 2020), 2020, : 966 - 975