ZEN: A directive-based language for automatic experiment management of distributed and parallel programs

被引:2
|
作者
Prodan, R [1 ]
Fahringer, T [1 ]
机构
[1] Univ Vienna, Inst Software Sci, A-1090 Vienna, Austria
关键词
D O I
10.1109/ICPP.2002.1040863
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
So far there exists very little support to specify and to control execution of a large number of experiments on distributed and parallel architectures. This paper describes ZEN, a directive-based language for the specification of arbitrarily complex program executions by varying problem, system, or machine parameters for parallel and distributed applications. ZEN introduces directives to substitute strings and to insert assignment statements inside arbitrary files, such as program, input, script, or make files. The programmer thus can invoke experiments for arbitrary value ranges of any problem parameter, including program variables, file names, compiler options, target machines, machine sizes, scheduling strategies, data distributions, etc. The number of experiments can be controlled through ZEN constraint directives. Finally, the programmer may request a large set of performance metrics to be computed for any code region of interest. The scope of ZEN directives can be restricted to arbitrary file or code regions. We have implemented a prototype tool for automatic experiment management that is based on ZEN. We will report results for performance analysis of an ocean simulation application and for parameter study of a computational finance code.
引用
收藏
页码:93 / 100
页数:8
相关论文
共 49 条
  • [1] A Compiler translate Directive-based Language to Optimized CUDA
    Li, Feng
    An, Hong
    Liang, Weihao
    Li, Xiaoqiang
    Cheng, Yichao
    Jiang, Xia
    2014 IEEE INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING AND COMMUNICATIONS, 2014 IEEE 6TH INTL SYMP ON CYBERSPACE SAFETY AND SECURITY, 2014 IEEE 11TH INTL CONF ON EMBEDDED SOFTWARE AND SYST (HPCC,CSS,ICESS), 2014, : 982 - 989
  • [2] HeteroPP: A directive-based heterogeneous cooperative parallel programming framework
    Wan, Lanjun
    Cui, Xueyan
    Li, Yuanyuan
    Zheng, Weihua
    Yuan, Xinpan
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2024, 36 (11):
  • [3] HSTREAM: A directive-based language extension for heterogeneous stream computing
    Memeti, Suejb
    Pllana, Sabri
    2018 21ST IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE 2018), 2018, : 138 - 145
  • [4] NAS Parallel Benchmarks for GPGPUs Using a Directive-Based Programming Model
    Xu, Rengan
    Tian, Xiaonan
    Chandrasekaran, Sunita
    Yan, Yonghong
    Chapman, Barbara
    LANGUAGES AND COMPILERS FOR PARALLEL COMPUTING (LCPC 2014), 2015, 8967 : 67 - 81
  • [5] A Type System for Data Independence of Loop Iterations in a Directive-Based PGAS Language
    Abe, Tatsuya
    PROCEEDINGS OF THE 16TH ACM SIGPLAN INTERNATIONAL CONFERENCE ON MANAGED PROGRAMMING LANGUAGES AND RUNTIMES (MPLR '19), 2019, : 50 - 62
  • [6] The Scalable Modeling System: directive-based code parallelization for distributed and shared memory computers
    Govett, M
    Hart, L
    Henderson, T
    Middlecoff, J
    Schaffer, D
    PARALLEL COMPUTING, 2003, 29 (08) : 995 - 1020
  • [7] Automatic search for performance problems-in parallel and distributed programs by using multi-experiment analysis
    Fahringer, T
    Seragiotto, C
    HIGH PERFORMANCE COMPUTING - HIPC 2002, PROCEEDINGS, 2002, 2552 : 151 - 162
  • [9] Automatic identification of parallel units and synchronisation points in programs for parallel execution on a distributed system
    Evans, DJV
    Goscinski, AM
    COMPUTER SYSTEMS SCIENCE AND ENGINEERING, 1997, 12 (05): : 307 - 315
  • [10] PERFORMANCE-MEASUREMENT FOR PARALLEL AND DISTRIBUTED PROGRAMS - A STRUCTURED AND AUTOMATIC APPROACH
    YANG, CQ
    MILLER, BP
    IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 1989, 15 (12) : 1615 - 1629