A high performance crashworthiness simulation system based on GPU

A parallel crashworthiness simulation system based on GPU is developed.Contact-searching and contact force calculations are parallelized.Two novel strategies are proposed to improve the test pairs searching.A strategy is presented to realize coalesced access between different hierarchies. Crashworthiness simulation system is one of the key computer-aided engineering (CAE) tools for the automobile industry and implies two potential conflicting requirements: accuracy and efficiency. A parallel crashworthiness simulation system based on graphics processing unit (GPU) architecture and the explicit finite element (FE) method is developed in this work. Implementation details with compute unified device architecture (CUDA) are considered. The entire parallel simulation system involves a parallel hierarchy-territory contact-searching algorithm (HITA) and a parallel penalty contact force calculation algorithm. Three basic GPU-based parallel strategies are suggested to meet the natural parallelism of the explicit FE algorithm. Two free GPU-based numerical calculation libraries, cuBLAS and Thrust, are introduced to decrease the difficulty of programming. Furthermore, a mixed array and a thread map to element strategy are proposed to improve the performance of the test pairs searching. The outer loop of the nested loop through the mixed array is unrolled to realize parallel searching. An efficient storage strategy based on data sorting is presented to realize data transfer between different hierarchies with coalesced access during the contact pairs searching. A thread map to element pattern is implemented to calculate the penetrations and the penetration forces; a double float atomic operation is used to scatter contact forces. The simulation results of the three different models based on the Intel Core i7-930 and the NVIDIA GeForce GTX 580 demonstrate the precision and efficiency of this developed parallel crashworthiness simulation system.

[1]  Hu Wang,et al.  Time-based metamodeling technique for vehicle crashworthiness optimization , 2010 .

[2]  Thomas J. R. Hughes,et al.  Nonlinear finite element analysis of shells: Part I. three-dimensional shells , 1981 .

[3]  Dimitri Komatitsch,et al.  Fluid–solid coupling on a cluster of GPU graphics cards for seismic wave propagation , 2011 .

[4]  Hiroshi Okuda,et al.  GPU Acceleration for FEM-Based Structural Analysis , 2013 .

[5]  Kevin Skadron,et al.  A performance study of general-purpose applications on graphics processors using CUDA , 2008, J. Parallel Distributed Comput..

[6]  Krzysztof Banas,et al.  Numerical integration on GPUs for higher order finite elements , 2013, Comput. Math. Appl..

[7]  Robert Winter,et al.  Theory and application of finite element analysis to structural crash simulation , 1981 .

[8]  Ted Belytschko,et al.  Advances in one-point quadrature shell elements , 1992 .

[9]  Z. Zhong.  Finite Element Procedures for Contact-Impact Problems , 1993 .

[10]  Jie Cheng,et al.  Programming Massively Parallel Processors. A Hands-on Approach , 2010, Scalable Comput. Pract. Exp..

[11]  K. Y. Sze,et al.  Hybrid Stress Finite Element Methods for Plate and Shell Structures , 2001 .

[12]  Bruce Hendrickson,et al.  Parallel strategies for crash and impact simulations , 1998 .

[13]  M. W. Fahmy,et al.  A survey of parallel nonlinear dynamic analysis methodologies , 1994 .

[14]  Thomas J. R. Hughes,et al.  Nonlinear Dynamic Finite Element Analysis of Shells , 1981 .

[15]  Ulf Assarsson,et al.  Fast parallel GPU-sorting using a hybrid algorithm , 2008, J. Parallel Distributed Comput..

[16]  Wen-mei W. Hwu,et al.  Program optimization carving for GPU computing , 2008, J. Parallel Distributed Comput..

[17]  Shahin Sirouspour,et al.  GPU-based acceleration of computations in nonlinear finite element deformation analysis. , 2014, International journal for numerical methods in biomedical engineering.

[18]  Robert Strzodka,et al.  Exploring weak scalability for FEM calculations on a GPU-enhanced cluster , 2007, Parallel Comput..

[19]  Jerry I. Lin,et al.  Explicit algorithms for the nonlinear dynamics of shells , 1984 .

[20]  Mark O. Neal,et al.  Contact‐impact by the pinball algorithm with penalty and Lagrangian methods , 1991 .

[21]  T. Belytschko,et al.  Physical stabilization of the 4-node shell element with one point quadrature , 1994 .

[22]  R. Stocki,et al.  Stochastic simulation for crashworthiness , 2004 .

[23]  Kumar K. Tamma,et al.  An effective data parallel self‐starting explicit methodology for computational structural dynamics on the connection machine CM‐5 , 1995 .

[24]  Nathan Bell,et al.  Thrust: A Productivity-Oriented Library for CUDA , 2012 .

[25]  Masakazu Shibahara,et al.  Prediction of residual stresses in multi-pass welded joint using Idealized Explicit FEM accelerated by a GPU , 2014 .

[26]  Wang Hu,et al.  Parallel Computing of Central Difference Explicit Finite Element Based on GPU General Computing Platform , 2013 .

[27]  A. Curnier,et al.  A finite element method for a class of contact-impact problems , 1976 .

[28]  Seung Jo Kim,et al.  Parallel performance of large scale impact simulations on Linux cluster super computer , 2006 .

[29]  Ted Belytschko,et al.  Explicit finite element methods with contact-impact on SIMD computers , 1991 .

[30]  David W. Murray,et al.  Nonlinear Finite Element Analysis of Steel Frames , 1983 .

[31]  Nancy L. Johnson,et al.  A parallel finite element contact/impact algorithm for non‐linear explicit transient analysis: Part II—Parallel implementation , 1994 .

[32]  Ted Belytschko,et al.  Contact-impact simulations on massively parallel SIMD supercomputers , 1992 .

[33]  Guangyao Li,et al.  Development of parallel explicit finite element sheet forming simulation system based on GPU architecture , 2012, Adv. Eng. Softw..