期刊
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
卷 29, 期 8, 页码 1865-1878出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPDS.2018.2810237
关键词
GPU; CUDA; LBM; CFD; parallel computing
资金
- National Science Centre [N N501 042140]
- Chair of Computer Engineering, Faculty of Electronics, Wroclaw University of Science and Technology
We describe a high-performance implementation of the lattice Boltzmann method (LBM) for sparse geometries on graphic processors. In our implementation we cover the whole geometry with a uniform mesh of small tiles and carry out calculations for each tile independently with proper data synchronization at the tile edges. For this method, we provide both a theoretical analysis of complexity and the results for real implementations involving two-dimensional (2D) and three-dimensional (3D) geometries. Based on the theoretical model, we show that tiles offer significantly smaller bandwidth overheads than solutions based on indirect addressing. For 2D lattice arrangements, a reduction in memory usage is also possible, although at the cost of diminished performance. We achieved a performance of 682 MLUPS on GTX Titan (72 percent of peak theoretical memory bandwidth) for the D3Q19 lattice arrangement and double-precision data.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据