...
首页> 外文期刊>Scientific programming >Performance Optimization of 3D Lattice Boltzmann Flow Solver on a GPU
【24h】

Performance Optimization of 3D Lattice Boltzmann Flow Solver on a GPU

机译:GPU上3D格子Boltzmann流量求解器的性能优化

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       

摘要

Lattice Boltzmann Method (LBM) is a powerful numerical simulation method of the fluid flow. With its data parallel nature, it is a promising candidate for a parallel implementation on a GPU. The LBM, however, is heavily data intensive and memory bound. In particular, moving the data to the adjacent cells in the streaming computation phase incurs a lot of uncoalesced accesses on the GPU which affects the overall performance. Furthermore, the main computation kernels of the LBM use a large number of registers per thread which limits the thread parallelism available at the run time due to the fixed number of registers on the GPU. In this paper, we develop high performance parallelization of the LBM on a GPU by minimizing the overheads associated with the uncoalesced memory accesses while improving the cache locality using the tiling optimization with the data layout change. Furthermore, we aggressively reduce the register uses for the LBM kernels in order to increase the run-time thread parallelism. Experimental results on the Nvidia Tesla K20 GPU show that our approach delivers impressive throughput performance: 1210.63 Million Lattice Updates Per Second (MLUPS).
机译:格子玻尔兹曼法(LBM)是一种强大的流体流动数值模拟方法。凭借其数据并行性,它是在GPU上并行实现的有希望的候选者。但是,LBM占用大量数据,并且内存受限。特别是,在流计算阶段将数据移动到相邻的单元会导致GPU上发生许多未经事先告知的访问,这会影响整体性能。此外,LBM的主要计算内核在每个线程中使用大量寄存器,由于GPU上的寄存器数量固定,这限制了运行时可用的线程并行性。在本文中,我们通过最小化与未分批处理的内存访问相关的开销,同时通过使用带有数据布局更改的切片优化来改善缓存局部性,来开发LBM在GPU上的高性能并行化。此外,我们积极减少LBM内核的寄存器使用量,以增加运行时线程并行度。在Nvidia Tesla K20 GPU上的实验结果表明,我们的方法可提供令人印象深刻的吞吐性能:每秒121063万个晶格更新(MLUPS)。

著录项

  • 来源
    《Scientific programming》 |2017年第1期|1205892.1-1205892.16|共16页
  • 作者单位

    Myongji Univ, Dept Comp Sci & Engn, 116 Myongji Ro, Yongin, Gyeonggi Do, South Korea;

    Myongji Univ, Dept Comp Sci & Engn, 116 Myongji Ro, Yongin, Gyeonggi Do, South Korea;

    Myongji Univ, Dept Comp Sci & Engn, 116 Myongji Ro, Yongin, Gyeonggi Do, South Korea;

  • 收录信息 美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号