GPU accelerated computational homogenization based on a variational approach in a reduced basis framework
GPU accelerated computational homogenization based on a variational approach in a reduced basis framework
复制标题
DOI：
10.1016/j.cma.2014.05.006
复制
发表时间：
2014-08-15
影响因子：
7.2
通讯作者：
Leuschner, Matthias
中科院分区：
文献类型：
--
作者：
Fritzen, Felix;Hodapp, Max;Leuschner, Matthias
计算多尺度方法，如Fe2技术(Feyel，1999)，对CPU时间和内存都有很大的要求。为了显著降低多尺度方法的计算成本，作者最近提出了一种粘塑性材料的混合计算均匀化方法，该方法使用混合变分公式中的减基方法(Fritzen和Leuschner，2013)。在本贡献中介绍了该方法的两个扩展：第一，通过允许不同的硬化变量而不是分段恒定场来扩展先前的建议。这提高了方法的精确度。其次，利用NVIDIA的CUDA框架，给出了该算法的大规模并行GPU实现。用于批处理线性代数运算的GPU子例程被集成到专用库中，以便于其使用。通过数值算例说明了不同硬化状态对专用GPU实现的精度和性能的影响。与高性能有限元实现相比，总体加速比达到10(4)数量级，同时保持了预测的非线性材料响应的良好精度。(C)2014爱思唯尔B.V.保留所有权利。
Computational multiscale methods such as the FE2 technique (Feyel, 1999) come along with large demands in both CPU time and memory. In order to significantly reduce the computational cost of multiscale methods the authors recently proposed a hybrid computational homogenization method for visco-plastic materials using a reduced basis approach in a mixed variational formulation (Fritzen and Leuschner, 2013). In the present contribution two extensions of the method are introduced: First, the previous proposal is extended by allowing for heterogeneous hardening variables instead of piecewise constant fields. This leads to an improved accuracy of the method. Second, a massively parallel GPU implementation of the algorithm using Nvidia's CUDA framework is presented. The GPU subroutines for the batched linear algebraic operations are integrated into a specialized library in order to facilitate its use. The impact of the heterogeneous hardening states on the accuracy and the performance gains obtained from the dedicated GPU implementation are illustrated by means of numerical examples. An overall speedup in the order of 10(4) with respect to a high performance finite element implementation is achieved while preserving good accuracy of the predicted nonlinear material response. (C) 2014 Elsevier B.V. All rights reserved.