Parallel algorithms for structure transient analysis based on heterogeneous multi-core processor architecture

被引：0
作者：
Yu G. [1 ,2 ]
Lou Y. [1 ,2 ,3 ]
Li J. [1 ,2 ]
Jin X. [1 ,2 ]
机构：
[1] State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai
[2] School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai
[3] Aerospace System Engineering Shanghai, Shanghai
来源：
Zhendong yu Chongji/Journal of Vibration and Shock | 2023年 / 42卷 / 06期
关键词：
distributed memory parallel computer; heterogeneous multi-core; hierarchical communication; large-scale vibration analysis; parallel computation;
D O I：
10.13465/j.cnki.jvs.2023.06.018
中图分类号：
学科分类号：
摘要：
According to the architecture characteristics of the domestic heterogeneous multi-core processor, a hierarchical communication parallel computing algorithm for structural transient analysis was proposed, which had important significance for improving the parallel efficiency of the system transient analysis on the entire large structure under the domestic heterogeneous multi-core and distributed memory parallel computers. Based on hierarchical communication and the Newmark - HHT algorithm, a parallel computing system for a large-scale transient analysis was established, which could not only significantly improve the memory access rate through the distributed storage of a large amount of data, but also significantly improve the communication rate with the two-layer parallelization of the computational procedure. It is shown that the method can improve the efficiency rates of parallel computing of the large-scale transient analysis by fully exploiting the architecture characteristics of the domestic heterogeneous multi-core and distributed memory parallel computers. Finally, typical numerical experiments were used to validate the correctness and efficiency of the proposed method. Then，the parallel transient analysis of a high-rise building with over ten-million-DOF was performed and ten thousands of core processors were applied. © 2023 Chinese Vibration Engineering Society. All rights reserved.
引用
收藏
页码：152 / 158
页数：6
相关论文
共 23 条
[1]  
MIAO Xinqiang, JIN Xianlong, DING Junhong, A hierarchical parallel computing approach for structural static linite element analysis, Acta Mechanica Sinica, 46, 4, pp. 611-618, (2014)
[2]  
LI Yanbing, ZHAO Rongcai, HAN Lin, Et al., Parallelizing compilation framework for heterogeneous many-core processors [J], Journal of Software, 30, 4, pp. 981-1001, (2019)
[3]  
KORIC S, LU Q Y, CULERYUZ E M., Evaluation of massively parallel linear sparse solvers on unstructured finite element meshes[ J], Computers and Structures, 141, pp. 19-25, (2014)
[4]  
LIU Ying, HUANG Lei, LU Fang, Et al., Cross-platform data layout optimization based on relaxed reuse distance on heterogeneous architectures [ J], Journal of Software, 27, 8, pp. 2168-2184, (2016)
[5]  
DAGA M, AJI A M, FENG W C., On the efficacy of a fused CPU + GPU processor ( or APU ) for parallel computing [ C ], 2011 Symposium on Application Accelerators in High-Performance Computing, (2011)
[6]  
KECKLER S W, DALLY W J, KHAILANY B., CPUs and the future of parallel computing, IEEE Micro, 31, pp. 7-17, (2011)
[7]  
CARTER N P, AGRAWAL A, BORKAR S., Runnemede: an architecture for ubiquitous high-performance computing[ C], 2013 IEEE 19 th International Symposium on High Performance Computer Architecture, (2013)
[8]  
LIU Fangfng, YANG Chao, YUAN Xinhui, Et al., General SpMV implementation in many-core domestic Sunway 26010 processor [ J ], Journal of Software, 29, 12, pp. 3921-3932, (2018)
[9]  
TA T, CHOO K, TAN E, Et al., Accelerating DynEarthSol3D on tightly coupled CPU - GPLI heterogeneous processors [ J ], Computers & Geosciences, 79, pp. 27-37, (2015)
[10]  
CAI Y, LI G Y, LIU W Y., Parallelized implementation of an explicit linite element method in many integrated core ( MIC ) architecture [ J ], Advances in Engineering Software, 116, pp. 50-59, (2018)
123