Parallelization of a quantum scattering code using P-grade: A case study

被引:0
|
作者
Bencsura, A [1 ]
Lendvay, G [1 ]
机构
[1] Hungarian Acad Sci, Chem Res Ctr, Inst Chem, H-1525 Budapest, Hungary
关键词
P-GRADE; quantum scattering; parallelization;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
We used P-GRADE, a graphical tool and programming environment to parallelize atomic level reaction dynamics codes, In the present case study ABC, a quantum reactive scattering code written in FORTRAN has been parallelized. We used the possibly coarsest grain parallelization, i.e. a complete calculation at each total energy is performed on a node. From the automatic schemes offered by P-GRADE, the task farm was selected. The FORTRAN code was separated into an input/output and a working section. The former, enhanced by a data transfer section operates on the master, the latter on the slaves. Small sections for data transfer were written in C language, The P-GRADE environment offers a user-friendly way of monitoring the efficiency of the parallelization. On a 20-processor NPACI Rocks cluster the speed-up is 99 percent proportional to the number of processors. P-GRADE proved to be user-friendly and made the programmer's work very efficient.
引用
收藏
页码:121 / 128
页数:8
相关论文
共 50 条
  • [1] Parallelization of reaction dynamics codes using P-GRADE: A case study
    Bencsura, A
    Lendvay, G
    [J]. COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2004, PT 2, 2004, 3044 : 290 - 299
  • [2] Using P-GRADE for Monte Carlo computations in a distributed environment
    Alexandrov, VN
    Thandavan, A
    Kacsuk, P
    [J]. COMPUTATIONAL SCIENCE - ICCS 2004, PROCEEDINGS, 2004, 3039 : 475 - 482
  • [3] Supporting workflow-level parameter study applications by the P-GRADE grid portal
    Kacsuk, Peter
    Farkas, Zoltan
    Sipos, Gergely
    Hermann, Gabor
    Kiss, Tamas
    [J]. TOWARDS NEXT GENERATION GRIDS, 2007, : 253 - +
  • [4] Simulation of the EMMIL e-marketplace model on SEE-GRID using the P-GRADE portal
    Kacslik, Peter
    Hermann, Gabor
    Balasko, Akos
    Bruckner, Livia Kacsukne
    [J]. EUROPEAN SIMULATION AND MODELLING CONFERENCE 2007, 2007, : 569 - +
  • [5] Graphical design of parallel programs with control based on global application states using an extended P-grade system
    Tudruj, M
    Borkowski, J
    Kopanski, D
    [J]. DISTRIBUTED AND PARALLEL SYSTEMS: CLUSTER AND GRID COMPUTING, 2005, 777 : 113 - 120
  • [6] Incremental parallelization using navigational programming: A case study
    Pan, L
    Zhang, WH
    Asuncion, A
    Lai, MK
    Dillencourt, MB
    Bic, LF
    [J]. 2005 INTERNATIONAL CONFERENCE ON PARALLEL PROCESSSING, PROCEEDINGS, 2005, : 611 - 620
  • [7] Using Amdahl's law as a metric to drive code parallelization: Two case studies
    Horoi, M
    Enbody, RJ
    [J]. INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2001, 15 (01): : 75 - 80
  • [8] An Efficient Method for Testing Source Code by Using Test Case Reduction, Prioritization and Prioritized Parallelization
    Udupa, Pradeep
    Nithyanandam, S.
    [J]. 2019 5TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTING & COMMUNICATION SYSTEMS (ICACCS), 2019, : 1192 - 1196
  • [9] A Framework for Auto-Parallelization and Code Generation: An Integrative Case Study with Legacy FORTRAN Codes
    Krommydas, Konstantinos
    Sathre, Paul
    Sasanka, Ruchira
    Feng, Wu-chun
    [J]. PROCEEDINGS OF THE 47TH INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING, 2018,
  • [10] Algorithm Parallelization using Software Design Patterns, an Embedded Case Study Approach
    Vincke, Robbie
    Van Landschoot, Sille
    Cordemans, Piet
    Peuteman, Joan
    Steegmans, Eric
    Boydens, Jeroen
    [J]. 2013 EIGHTH INTERNATIONAL CONFERENCE ON P2P, PARALLEL, GRID, CLOUD AND INTERNET COMPUTING (3PGCIC 2013), 2013, : 470 - 473