文献类型：期刊文献

英文题名：Clustered cell parallelization for GPU computing of silicon anisotropic etching simulation

作者：Li, Jianhua[1]; Chen, Jingyuan[1]; Wang, Yan[2]; Huang, Jianhua[1]

机构：[1] Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai 200237, China; [2] Georgia Institute of Technology, Woodruff School of Mechanical Engineering, Atlanta, GA, 30332, United States

年份：2013

卷号：2 A

外文期刊名：Proceedings of the ASME Design Engineering Technical Conference

收录：EI(收录号：20141417531368)

语种：英文

外文关键词：Application programming interfaces (API) - Atoms - Cells - Computer aided design - Silicon - Cellular automata - Computer graphics - Cytology - Anisotropy - Program processors

摘要：The parallelization of silicon anisotropic etching simulation with the cellular automata (CA) model on graphics processing units (GPUs) is challenging, because the numbers of computational tasks in etching simulation dynamically change and the existing parallel CA mechanisms do not fit in GPU computation well. In this paper, an improved CA model, called clustered cell model, is proposed for GPU-based etching simulation. The model consists of clustered cells, each of which manages a scalable number of atoms. In this model, only the etching and update of states for the atoms on the etching surface and their unexposed neighbors are performed at each CA time step, whereas the clustered cells are reclassified in a longer time step. With this model, a crystal cell parallelization method is given, where clustered cells are allocated to threads on GPUs in the simulation. With the optimizations from the spatial and temporal aspects as well as a proper granularity, this method provides a faster process simulation. The proposed simulation method is implemented with the Compute Unified Device Architecture (CUDA) application programming interface. Several computational experiments are taken to analyze the efficiency of the method. Copyright ? 2013 by ASME.