Custom Data Mapping for Composable Data Management

被引:0
|
作者
Scogland, Tom [1 ]
Earl, Chris [1 ]
de Supinski, Bronis [1 ]
机构
[1] Lawrence Livermore Natl Lab, Livermore, CA 94550 USA
关键词
Deep copy; Complex data; OpenMP;
D O I
10.1007/978-3-319-65578-9_23
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Early experiences with OpenMP 4.0, as well as other directive-based offload models, have shown that deep copy is a key challenge to porting complex applications to offload directives. Without a flexible deep-copy mechanism, pointer-based data structures are at best difficult to manage, particularly when shared memory between the host and device cannot be assumed. Despite the importance of the issue, and the considerable effort expended by vendors, standards bodies and users, no solution has emerged as the clear choice. We propose an approach that combines a restricted compiler-assisted (sometimes called "true") deep copy with a mechanism for users to register their own custom mapping implementations that we call packers. This combination offers the flexibility to address complex cases when necessary while keeping the complexity out of the directives, a balance that serves all cases.
引用
收藏
页码:338 / 347
页数:10
相关论文
共 50 条
  • [1] A Composable Era for Data Management
    Pedreira, Pedro
    [J]. 2023 IEEE 39TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING WORKSHOPS, ICDEW, 2023, : 94 - 94
  • [2] The Composable Data Management System Manifesto
    Pedreira, Pedro
    Erling, Orri
    Karanasos, Konstantinos
    Schneider, Scott
    McKinney, Wes
    Valluri, Satya R.
    Zait, Mohamed
    Nadeau, Jacques
    [J]. PROCEEDINGS OF THE VLDB ENDOWMENT, 2023, 16 (10): : 2679 - 2685
  • [3] A composable data management architecture for scientific applications
    Ma, Y
    Bramley, R
    [J]. CLADE 2005: CHALLENGES OF LARGE APPLICATIONS IN DISTRIBUTED ENVIRONMENTS, PROCEEDINGS, 2005, : 35 - 44
  • [4] Composable data visualizations
    Petricek, Tomas
    [J]. Journal of Functional Programming, 2021, 31
  • [5] Composable data visualizations
    Petricek, Tomas
    [J]. JOURNAL OF FUNCTIONAL PROGRAMMING, 2021, 31
  • [6] Data Management in the Data Lake: A Systematic Mapping
    Zouari, Firas
    Kabachi, Nadia
    Boukadi, Khouloud
    Guegan, Chirine Ghedira
    [J]. IDEAS 2021: 25TH INTERNATIONAL DATABASE ENGINEERING & APPLICATIONS SYMPOSIUM, 2021, : 280 - 284
  • [7] Towards Enterprise Data Management: Data Model Mapping
    Petrasch, Roland
    Kongkachandra, Rachada
    [J]. 2018 4TH IEEE INTERNATIONAL WIE CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (IEEE WIECON-ECE 2018), 2018, : 72 - 74
  • [8] Quantifying Composable Data Center Utilization
    Taubenblatt, Marc
    Tantawi, Asser
    [J]. 2022 IEEE 36TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW 2022), 2022, : 1195 - 1201
  • [9] Extending Composable Data Services into SmartNICs
    Ulmer, Craig
    Liu, Jianshen
    Maltzahn, Carlos
    Curry, Matthew L.
    [J]. 2023 IEEE INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS, IPDPSW, 2023, : 953 - 959
  • [10] Network Topologies for Composable Data Centers
    Ajibola, Opeyemi O.
    El-Gorashi, Taisir E. H.
    Elmirghani, Jaafar M. H.
    [J]. IEEE ACCESS, 2021, 9 : 120955 - 120984