blockNDP: Block-storage Near Data Processing

被引:12
|
作者
Barbalace, Antonio [1 ,2 ]
Decky, Martin
Picorel, Javier
Bhatotia, Pramod [2 ]
机构
[1] Univ Edinburgh, Edinburgh, Midlothian, Scotland
[2] Huawei Res, Shenzhen, Peoples R China
关键词
D O I
10.1145/3429357.3430519
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
We introduce blockNDP, a set of hardware and software protocol and interface extensions to enable block-oriented near data processing (NDP) within emerging solid-state drives (SSDs) integrating processing units. blockNDP is an end-to-end architecture, including a programming model and framework for host and in-storage compute units. blockNDP is the first proposal to be generic, backward compatible - supports existent standards and file systems, portable, and language agnostic. We have implemented and evaluated the effectiveness of blockNDP using two full-system prototypes; one on a new NDP emulation platform - developed atop QEMU, and another on an actual development board - the OpenSSD. Our experimental evaluation demonstrates that blockNDP is not only feasible with a modest effort, < 10K LoC, but it is also able to achieve up to 4x speedups, despite wimpy CPU cores, on a real-world data-driven application such as MySQL.
引用
收藏
页码:8 / 15
页数:8
相关论文
共 50 条
  • [41] Permuting Data on Random-Access Block Storage
    Thonangi, Risi
    Yang, Jun
    [J]. PROCEEDINGS OF THE VLDB ENDOWMENT, 2013, 6 (09): : 721 - 732
  • [42] Data Processing and Storage of Ultrasonic Flaw Detection
    Cheng Hongjie
    Zhao Yuan
    [J]. PROCEEDINGS OF THE SECOND INTERNATIONAL SYMPOSIUM ON TEST AUTOMATION & INSTRUMENTATION, VOLS 1-2, 2008, : 784 - 787
  • [43] Design of Cloud Data Storage and Processing System
    Zhou, Baoke
    Chou, Wusheng
    [J]. 2018 INTERNATIONAL CONFERENCE ON BIG DATA AND ARTIFICIAL INTELLIGENCE (BDAI 2018), 2018, : 6 - 9
  • [44] Data Processing on Distributed Systems Storage Challenges
    Eddoujaji, Mohamed
    Samadi, Hassan
    Bohorma, Mohamed
    [J]. Smart Innovation, Systems and Technologies, 2022, 237 : 795 - 811
  • [45] Data block prefetching and caching in a hierarchical storage model
    Vakali, A
    [J]. INFORMATION SCIENCES, 2000, 128 (1-2) : 19 - 41
  • [46] ExtraV: Boosting Graph Processing Near Storage with a Coherent Accelerator
    Lee, Jinho
    Kim, Heesu
    Yoo, Sungjoo
    Choi, Kiyoung
    Hofstee, H. Peter
    Nam, Gi-Joon
    Nutter, Mark R.
    Jamsek, Damir
    [J]. PROCEEDINGS OF THE VLDB ENDOWMENT, 2017, 10 (12): : 1706 - 1717
  • [47] Near-Storage Acceleration of Database Query Processing with SmartSSDs
    Soltaniyeh, Mohammadreza
    Dos Reis, Veronica Lagrange Moutinho
    Bryson, Matthew
    Martin, Richard
    Nagarakatte, Santosh
    [J]. 2021 IEEE 29TH ANNUAL INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE CUSTOM COMPUTING MACHINES (FCCM 2021), 2021, : 265 - 265
  • [48] Block storing method for efficient storage of near group impedance in MLFMA
    Zhao, H. P.
    Hu, J.
    Nie, Z. P.
    [J]. ELECTRONICS LETTERS, 2008, 44 (20) : 1171 - 1173
  • [49] Time model of data processing block in measurement system
    Bilski, Piotr
    Lukaszewski, Robert
    [J]. 2007 IEEE INSTRUMENTATION & MEASUREMENT TECHNOLOGY CONFERENCE, VOLS 1-5, 2007, : 1262 - +
  • [50] Wide azimuth seismic data processing for K Block
    Xia, Chang-Liang
    Zhang, Hong-Jun
    Hao, Jian-Bo
    Zhuang, Lin
    Wu, Lin
    Jiang, Hao
    [J]. Shiyou Diqiu Wuli Kantan/Oil Geophysical Prospecting, 2010, 45 (SUPPL. 1): : 74 - 79