ADIOS 2: The Adaptable Input Output System. A framework for high-performance data management

被引:108
|
作者
Godoy, William F. [1 ]
Podhorszki, Norbert [1 ]
Wang, Ruonan [1 ]
Atkins, Chuck [2 ]
Eisenhauer, Greg [3 ]
Gu, Junmin [4 ]
Davis, Philip [5 ]
Choi, Jong [1 ]
Germaschewski, Kai [6 ,7 ]
Huck, Kevin [8 ]
Huebl, Axel [9 ]
Kim, Mark [1 ]
Kress, James [1 ]
Kurc, Tahsin [10 ]
Liu, Qing [11 ]
Logan, Jeremy [1 ]
Mehta, Kshitij [1 ]
Ostrouchov, George [1 ]
Parashar, Manish [5 ]
Poeschel, Franz [9 ]
Pugmire, David [1 ]
Suchyta, Eric [1 ]
Takahashi, Keichi [1 ]
Thompson, Nick [1 ]
Tsutsumi, Seiji [12 ]
Wan, Lipeng [1 ]
Wolf, Matthew [1 ]
Wu, Kesheng [4 ]
Klasky, Scott [1 ]
机构
[1] Oak Ridge Natl Lab, Oak Ridge, TN 37830 USA
[2] Kitware Inc, Clifton Pk, NY USA
[3] Georgia Inst Technol, Sch Comp Sci, Atlanta, GA 30332 USA
[4] Lawrence Berkeley Natl Lab, Berkeley, CA USA
[5] Rutgers State Univ, Comp Sci Dept, New Brunswick, NJ USA
[6] Univ New Hampshire, Ctr Space Sci, Durham, NH 03824 USA
[7] Univ New Hampshire, Dept Phys, Durham, NH 03824 USA
[8] Univ Oregon, Eugene, OR 97403 USA
[9] Helmholtz Zentrum Dresden Rossendorf, Dresden, Germany
[10] SUNY Stony Brook, Dept Biomed Informat, Stony Brook, NY 11794 USA
[11] New Jersey Inst Technol, Dept Elect & Comp Engn, Newark, NJ 07102 USA
[12] Japan Aerosp Explorat Agcy, Sagamihara, Kanagawa, Japan
关键词
High-performance computing (HPC); Scalable I/O; Luster GPFS file systems; Staging; RDMA; Data science; In-situ; Exascale computing; TABLE DATA SYSTEM; REDUCTION;
D O I
10.1016/j.softx.2020.100561
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
We present ADIOS 2, the latest version of the Adaptable Input Output (I/O) System. ADIOS 2 addresses scientific data management needs ranging from scalable I/O in supercomputers, to data analysis in personal computer and cloud systems. Version 2 introduces a unified application programming interface (API) that enables seamless data movement through files, wide-area-networks, and direct memory access, as well as high-level APIs for data analysis. The internal architecture provides a set of reusable and extendable components for managing data presentation and transport mechanisms for new applications. ADIOS 2 bindings are available in C++11, C, Fortran, Python, and Matlab and are currently used across different scientific communities. ADIOS 2 provides a communal framework to tackle data management challenges as we approach the exascale era of supercomputing. (C) 2020 The Authors. Published by Elsevier B.V.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] INPUT/OUTPUT LINKAGE IN A USER INTERFACE MANAGEMENT SYSTEM.
    Olsen Jr., Dan R.
    Dempsey, Elizabeth P.
    Rogge, Roy
    Computer Graphics (ACM), 1985, 19 (03): : 191 - 197
  • [2] A HIGH-PERFORMANCE ANALOG INPUT-OUTPUT SYSTEM FOR TRANSPUTER APPLICATIONS
    ELPHICK, JR
    CLARKE, T
    LAWES, ST
    MICROPROCESSORS AND MICROSYSTEMS, 1995, 19 (01) : 3 - 8
  • [3] High-performance scientific data management system
    No, JC
    Thakur, R
    Choudhary, A
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2003, 63 (04) : 434 - 447
  • [4] An adaptable, high-performance relation extraction system for complex sentences
    Thomas, Anu
    Sivanesan, Sangeetha
    KNOWLEDGE-BASED SYSTEMS, 2022, 251
  • [5] Prediction of high-performance computing input/output variability and its application to optimization for system configurations
    Xu, Li
    Lux, Thomas
    Chang, Tyler
    Li, Bo
    Hong, Yili
    Watson, Layne
    Butt, Ali
    Yao, Danfeng
    Cameron, Kirk
    QUALITY ENGINEERING, 2021, 33 (02) : 318 - 334
  • [6] Prediction for distributional outcomes in high-performance computing input/output variability
    Xu, Li
    Hong, Yili
    Morris, Max D.
    Cameron, Kirk W.
    JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS, 2024, 73 (03) : 561 - 580
  • [7] High-performance data management in Java
    Lamb, Charles
    Dr Dobb's J, 7 (45-49):
  • [8] Using Input-to-Output Masking for System-Level Vulnerability Estimation in High-Performance Processors
    Haghdoost, Alireza
    Asadi, Hossein
    Baniasadi, Amirali
    15TH CSI INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND DIGITAL SYSTEMS (CADS 2010), 2010, : 91 - 98
  • [9] High-performance flow parallel particle tracing data management system
    Yang C.
    Li Y.
    Zhang J.
    Wang F.
    Yuan X.
    Yuan, Xiaoru (xiaoru.yuan@pku.edu.cn); Yuan, Xiaoru (xiaoru.yuan@pku.edu.cn), 2021, Chinese Society of Astronautics (42):
  • [10] A HIGH-PERFORMANCE SWEEPER OUTPUT POWER LEVELING SYSTEM
    BAKER, GM
    DAVIDSON, MN
    HAAG, LE
    HEWLETT-PACKARD JOURNAL, 1991, 42 (02): : 24 - 28