国产bbaaaaa片,成年美女黄网站色视频免费,成年黄大片,а天堂中文最新一区二区三区,成人精品视频一区二区三区尤物

首頁> 外文期刊>Parallel Computing >A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence
【24h】

A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence

機(jī)譯：混合MPI-OpenMP方案用于流體湍流的可擴(kuò)展并行偽譜計(jì)算

獲取原文
獲取原文并翻譯 | 示例
  • 摘要
  • 著錄項(xiàng)
  • 相似文獻(xiàn)
  • 相關(guān)主題

摘要

A hybrid scheme that utilizes MPI for distributed memory parallelism and OpenMP for shared memory parallelism is presented. The work is motivated by the desire to achieve exceptionally high Reynolds numbers in pseudospectral computations of fluid turbulence on emerging petascale, high core-count, massively parallel processing systems. The hybrid implementation derives from and augments a well-tested scalable MPI-parallelized pseudospectral code. The hybrid paradigm leads to a new picture for the domain decomposition of the pseudospectral grids, which is helpful in understanding, among other things, the 3D transpose of the global data that is necessary for the parallel fast Fourier transforms that are the central component of the numerical discretizations. Details of the hybrid implementation are provided, and performance tests illustrate the utility of the method. It is shown that the hybrid scheme achieves good scalability up to ~20,000 compute cores with a maximum efficiency of 89%, and a mean of 79%. Data are presented that help guide the choice of the optimal number of MPI tasks and OpenMP threads in order to maximize code performance on two different platforms.
機(jī)譯：提出了一種混合方案，該方案利用MPI進(jìn)行分布式內(nèi)存并行處理，并使用OpenMP進(jìn)行共享內(nèi)存并行處理。這項(xiàng)工作的動(dòng)機(jī)是希望在新興的petascale，高核數(shù)，大規(guī)模并行處理系統(tǒng)的流體湍流的偽譜計(jì)算中獲得異常高的雷諾數(shù)。混合實(shí)現(xiàn)從經(jīng)過良好測(cè)試的可擴(kuò)展MPI并行偽譜代碼派生并增強(qiáng)。混合范式為偽光譜網(wǎng)格的域分解帶來了新的圖景，這尤其有助于理解全局?jǐn)?shù)據(jù)的3D轉(zhuǎn)置，這是并行快速傅里葉變換所必需的，而并行快速傅里葉變換是該結(jié)構(gòu)的核心部分。數(shù)值離散化。提供了混合實(shí)現(xiàn)的詳細(xì)信息，性能測(cè)試說明了該方法的實(shí)用性。結(jié)果表明，混合方案可在高達(dá)約20,000個(gè)計(jì)算內(nèi)核的情況下實(shí)現(xiàn)良好的可伸縮性，最大效率為89％，平均效率為79％。提供的數(shù)據(jù)可幫助指導(dǎo)最佳數(shù)量的MPI任務(wù)和OpenMP線程的選擇，以便在兩個(gè)不同平臺(tái)上最大化代碼性能。

著錄項(xiàng)

  • 來源
    《Parallel Computing》 |2011年第7期|p.316-326|共11頁
  • 作者單位

    Institute for Mathematics Applied to Geosciences. National Center for Atmospheric Research, P.O. Box 3000, Boulder, CO 80307-3000, USA,Departamento de Fisica, Facultad de Ciencias Exactas y Naturales & IFIBA, CONICET, Ciudad Universitaria, 1428 Buenos Aires, Argentina;

    Institute for Mathematics Applied to Geosciences. National Center for Atmospheric Research, P.O. Box 3000, Boulder, CO 80307-3000, USA;

    Pittsburgh Supercomputing Center, 300 S. Craig Street, Pittsburgh, PA 15213. USA;

    Institute for Mathematics Applied to Geosciences. National Center for Atmospheric Research, P.O. Box 3000, Boulder, CO 80307-3000, USA;

  • 收錄信息 美國(guó)《科學(xué)引文索引》(SCI);美國(guó)《工程索引》(EI);
  • 原文格式 PDF
  • 正文語種 eng
  • 中圖分類
  • 關(guān)鍵詞

    computational fluids; numerical simulation; mpi; openmp; parallel scalability;

    機(jī)譯：計(jì)算流體;數(shù)值模擬mpi;openmp;并行可伸縮性;

相似文獻(xiàn)

  • 外文文獻(xiàn)
  • 中文文獻(xiàn)
  • 專利
獲取原文

客服郵箱：kefu@zhangqiaokeyan.com

京公網(wǎng)安備：11010802029741號(hào) ICP備案號(hào)：京ICP備15016152號(hào)-6 六維聯(lián)合信息科技 (北京) 有限公司?版權(quán)所有

  • 客服微信

  • 服務(wù)號(hào)