期刊
IEEE ACCESS
卷 9, 期 -, 页码 61224-61236出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3073667
关键词
GPU computing; high-performance computing; lattice Boltzmann method; vascular flow
资金
- National Science Foundation [CNS-1725573]
This study presents the implementation and scaling analysis of a GPU-accelerated kernel for HemeLB, a high-performance Lattice Boltzmann code designed for sparse complex geometries. The research shows significant speedups in single-GPU performance for HemeLB-GPU compared to a single CPU core, with good scalability up to 32 GPUs. Strategies to improve kernel performance and scalability for a larger number of GPUs are also discussed, aiming to enable better utilization of heterogeneous high-performance computing systems for large-scale lattice Boltzmann simulations.
We present an implementation and scaling analysis of a GPU-accelerated kernel for HemeLB, a high-performance Lattice Boltzmann code for sparse complex geometries. We describe the structure of the GPU implementation and we study the scalability of HemeLB on a GPU cluster under normal operating conditions and with real-world application cases. We investigate the effect of CUDA block size and GPU over-subscription on the single-GPU performance, and we present a strong-scaling analysis of multi-GPU parallel simulations using two different hardware models (P100 and V100) and a variety of large cerebral aneurysm geometries. We find that HemeLB-GPU achieves single-GPU speedups of 50x (P100) and $100x (V100) compared to a single CPU core, with good scalability up to 32 GPUs. We also discuss strategies to improve both the kernel performance as well as the scalability of HemeLB-GPU to a larger number of GPUs. The GPU implementation supports the LBGK collision kernel, boundary conditions for walls and inlets/outlets, and several lattice types (D3Q15, D3Q19, D3Q27), and it integrates seamlessly with the existing infrastructure in HemeLB for graph partitioning and parallelization via MPI. It is expected that the GPU implementation will enable users of the HemeLB code to make better utilization of heterogeneous high-performance computing systems for large-scale lattice Boltzmann simulations.
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