ATF: A Generic Auto-Tuning Framework

被引:0
|
作者
Rasch, Ari [1 ]
Gorlatch, Sergei [1 ]
机构
[1] Univ Munster, Munster, Germany
关键词
D O I
10.1145/3220192.3220194
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
We describe the Auto-Tuning Framework (ATF)-a simple-to-use, generic framework for automatic program optimization by choosing the most suitable values of program parameters, such as number of parallel threads, tile sizes, etc. ATF combines four major advantages over the state-of-the-art auto-tuners: i) it is generic regarding the programming language, application domain, tuning objective, and search technique; ii) it can auto-tune a broader class of applications by allowing tuning parameters to be interdependent, e.g., when a parameter is divisible by another parameter; iii) it allows tuning parameters to have substantially larger ranges by implementing an optimized search space generation process; and iv) it is arguably simpler to use: the ATF user prepares an application for auto-tuning by annotating its source code with simple tuning directives. Our experimental results demonstrate that ATF shows significantly better tuning results as compared to the state-of-the-art auto-tuners OpenTuner and CLTune.
引用
收藏
页码:3 / 4
页数:2
相关论文
共 50 条
  • [1] ATF: A Generic Auto-Tuning Framework
    Rasch, Ari
    Haidl, Michael
    Gorlatch, Sergei
    2017 19TH IEEE INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING AND COMMUNICATIONS (HPCC) / 2017 15TH IEEE INTERNATIONAL CONFERENCE ON SMART CITY (SMARTCITY) / 2017 3RD IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND SYSTEMS (DSS), 2017, : 64 - 71
  • [2] ATF: A generic directive-based auto-tuning framework
    Rasch, Ari
    Gorlatch, Sergei
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2019, 31 (05):
  • [3] Efficient Auto-Tuning of Parallel Programs with Interdependent Tuning Parameters via Auto-Tuning Framework (ATF)
    Rasch, Ari
    Schulze, Richard
    Steuwer, Michel
    Gorlatch, Sergei
    ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION, 2021, 18 (01)
  • [4] FIBER: A generalized framework for auto-tuning software
    Katagiri, T
    Kise, K
    Honda, H
    Yuba, T
    HIGH PERFORMANCE COMPUTING, 2003, 2858 : 146 - 159
  • [5] A Scalable Auto-tuning Framework for Compiler Optimization
    Tiwari, Ananta
    Chen, Chun
    Chame, Jacqueline
    Hall, Mary
    Hollingsworth, Jeffrey K.
    2009 IEEE INTERNATIONAL SYMPOSIUM ON PARALLEL & DISTRIBUTED PROCESSING, VOLS 1-5, 2009, : 796 - +
  • [6] A Verification Framework for Streamlining Empirical Auto-tuning
    Hirasawa, Shoichi
    Takizawa, Hiroyuki
    Kobayashi, Hiroaki
    PROCEEDINGS OF 2015 THIRD INTERNATIONAL SYMPOSIUM ON COMPUTING AND NETWORKING (CANDAR), 2015, : 508 - 514
  • [7] An Architecture for Flexible Auto-Tuning: The Periscope Tuning Framework 2.0
    Mijakovic, Robert
    Firbach, Michael
    Gerndt, Michael
    2016 2ND INTERNATIONAL CONFERENCE ON GREEN HIGH PERFORMANCE COMPUTING (ICGHPC), 2016,
  • [8] Shaman: An Intelligent Framework For Auto-Tuning Hpc Systems
    Robert, Sophie
    Zertal, Soraya
    Goret, Gael
    Couvee, Philippe
    International Journal of Computer Science and Applications, 2021, 18 (01) : 45 - 68
  • [9] GeST: Generalized Stencil Auto-tuning Framework on GPUs
    Sun, Qingxiao
    PROCEEDINGS OF THE ACM TURING AWARD CELEBRATION CONFERENCE-CHINA 2024, ACM-TURC 2024, 2024, : 199 - 200
  • [10] PERI Auto-Tuning
    Bailey, David H.
    Chame, Jacqueline
    Chen, Chun
    Dongarra, Jack
    Hall, Mary
    Hollingsworth, Jeffrey K.
    Hovland, Paul
    Moore, Shirley
    Seymour, Keith
    Shin, Jaewook
    Tiwari, Ananta
    Williams, Sam
    You, Haihang
    SCIDAC 2008: SCIENTIFIC DISCOVERY THROUGH ADVANCED COMPUTING, 2008, 125