arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1010.4834hep-latphysics.comp-ph
收藏

SU(2)格点规范理论在Fermi GPU上的模拟

SU(2) Lattice Gauge Theory Simulations on Fermi GPUs

Nuno Cardoso, Pedro Bicudo

摘要:

在这项工作中,我们探讨了淬火格SU(2)模拟的CUDA的性能。CUDA(NVIDIA Compute Unified Device Architecture,NVIDIA计算统一设备架构)是NVIDIA为GPU上的计算开发的硬件和软件架构。我们提出了一个分析和性能比较GPU和CPU之间的单精度和双精度。分析了多个GPU和两种不同的架构(G200和费米架构)。为了获得高性能,代码必须针对GPU架构进行优化,即,一种利用CUDA编程模型的内存层次结构的实现。我们为SU(2)格点规范组态的Monte Carlo生成、平均格元、有限T下的Polyakov环和威尔逊圈产生了程序。我们还提出了使用许多配置($50\ 000$)的潜力,没有涂抹和几乎$2\ 000$配置APE涂抹的结果。通过两个Fermi GPU,我们实现了$200 \times$的出色性能,速度超过一个CPU,单精度约为110 Gflops/s。我们还发现,使用费米体系结构,双精度计算的静态夸克-反夸克势并不比单精度计算慢(小于$2 \times$慢)。

英文摘要:

In this work we explore the performance of CUDA in quenched lattice SU(2) simulations. CUDA, NVIDIA Compute Unified Device Architecture, is a hardware and software architecture developed by NVIDIA for computing on the GPU. We present an analysis and performance comparison between the GPU and CPU in single and double precision. Analyses with multiple GPUs and two different architectures (G200 and Fermi architectures) are also presented. In order to obtain a high performance, the code must be optimized for the GPU architecture, i.e., an implementation that exploits the memory hierarchy of the CUDA programming model. We produce codes for the Monte Carlo generation of SU(2) lattice gauge configurations, for the mean plaquette, for the Polyakov Loop at finite T and for the Wilson loop. We also present results for the potential using many configurations ($50\ 000$) without smearing and almost $2\ 000$ configurations with APE smearing. With two Fermi GPUs we have achieved an excellent performance of $200 \times$ the speed over one CPU, in single precision, around 110 Gflops/s. We also find that, using the Fermi architecture, double precision computations for the static quark-antiquark potential are not much slower (less than $2 \times$ slower) than single precision computations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑