High-Level Support for Pipeline Parallelism on Many-Core Architectures

被引:0
|
作者
Benkner, Siegfried [1 ]
Bajrovic, Enes [1 ]
Marth, Erich [1 ]
Sandrieser, Martin [1 ]
Namyst, Raymond [2 ]
Thibault, Samuel [2 ]
机构
[1] Univ Vienna, Res Grp Sci Comp, A-1010 Vienna, Austria
[2] Univ Bordeaux, LaBRI, INRIA, Talence, France
来源
关键词
LANGUAGE; SYSTEMS;
D O I
暂无
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
With the increasing architectural diversity of many-core architectures the challenges of parallel programming and code portability will sharply rise. The EU project PEPPHER addresses these issues with a component-based approach to application development on top of a task-parallel execution model. Central to this approach are multi-architectural components which encapsulate different implementation variants of application functionality tailored for different core types. An intelligent runtime system selects and dynamically schedules component implementation variants for efficient parallel execution on heterogeneous many-core architectures. On top of this model we have developed language, compiler and runtime support for a specific class of applications that can be expressed using the pipeline pattern. We propose C/C++ language annotations for specifying pipeline patterns and describe the associated compilation and runtime infrastructure. Experimental results indicate that with our high-level approach performance comparable to manual parallelization can be achieved.
引用
下载
收藏
页码:614 / 625
页数:12
相关论文
共 50 条
  • [41] Accelerating Asian option pricing on many-core architectures
    Li, Shuo
    Lin, James
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2016, 28 (03): : 848 - 865
  • [42] Benchmarking Molecular Dynamics with OpenCL on Many-Core Architectures
    Halver, Rene
    Homberg, Wilhelm
    Sutmann, Godehard
    PARALLEL PROCESSING AND APPLIED MATHEMATICS (PPAM 2017), PT II, 2018, 10778 : 244 - 253
  • [43] TOOLS AND ENVIRONMENTS FOR MULTICORE AND MANY-CORE ARCHITECTURES INTRODUCTION
    Feng, Wu-Chun
    Balaji, Pavan
    COMPUTER, 2009, 42 (12) : 26 - 27
  • [44] Exploiting memory allocations in clusterised many-core architectures
    Garibotti, Rafael
    Ost, Luciano
    Butko, Anastasiia
    Reis, Ricardo
    Gamatie, Abdoulaye
    Sassatelli, Gilles
    IET COMPUTERS AND DIGITAL TECHNIQUES, 2019, 13 (04): : 302 - 311
  • [45] Vectorizing unstructured mesh computations for many-core architectures
    Reguly, Istvan Z.
    Laszlo, Endre
    Mudalige, Gihan R.
    Giles, Mike B.
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2016, 28 (02): : 557 - 577
  • [46] Power Efficient Photonic Networks for Many-Core Architectures
    Neel, Brian
    Morris, Randy
    Ditomaso, Dominic
    Kodi, Avinash
    2012 INTERNATIONAL GREEN COMPUTING CONFERENCE (IGCC), 2012,
  • [47] Adapting Particle Filter Algorithms to Many-Core Architectures
    Chitchian, Mehdi
    van Amesfoort, Alexander S.
    Simonetto, Andrea
    Keviczky, Tamas
    Sips, Henk J.
    IEEE 27TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2013), 2013, : 427 - 438
  • [48] Hybrid Coarrays: a PGAS Feature for Many-Core Architectures
    Cardellini, Valeria
    Fanfarillo, Alessandro
    Filippone, Salvatore
    Rouson, Damian
    PARALLEL COMPUTING: ON THE ROAD TO EXASCALE, 2016, 27 : 175 - 184
  • [49] Performance Assessment of Hybrid Parallelism for Large-Scale Reservoir Simulation on Multi- and Many-core Architectures
    AlOnazi, Amani
    Rogowski, Marcin
    Al-Zawawi, Ahmed
    Keyes, David
    2018 IEEE HIGH PERFORMANCE EXTREME COMPUTING CONFERENCE (HPEC), 2018,
  • [50] Scalable Parallel Flash Firmware for Many-core Architectures
    Zhang, Jie
    Kwon, Miryeong
    Swift, Michael
    Jung, Myoungsoo
    PROCEEDINGS OF THE 18TH USENIX CONFERENCE ON FILE AND STORAGE TECHNOLOGIES, 2020, : 121 - 136