Finite element numerical integration on Xeon Phi coprocessor
Finite element numerical integration on Xeon Phi coprocessor
复制标题
DOI：
10.15439/2014f222
复制
发表时间：
2014-10
期刊：
影响因子：
--
通讯作者：
Filip Kruzel;K. Banas
中科院分区：
文献类型：
--
作者：
Filip Kruzel;K. Banas
在本文中，我们描述了至强融核协处理器的有限元数值积分算法的实现。协处理器是用于计算的众核专用单元的思想的扩展，并且根据假设，其性能必须与当前的GPU家族竞争。它的主要优点是内置的512位向量寄存器集，并且易于从普通x86架构中传输现有代码。但是，标准x86架构和Xeon Phi之间的差异并不能保证性能的可移植性。我们选择了一种替代方法，而不是移植标准的多线程代码，我们适应至强融核以前开发的OpenCL算法有限元数值积分。该算法进行了测试，标准的有限元近似选定的问题。所获得的时序结果允许比较在Xeon Phi和当代GPU上执行的OpenCL内核的性能。
In the present article we describe the implementation of the finite element numerical integration algorithm for the Xeon Phi coprocessor. The coprocessor is an extension of the idea of the many-core specialized unit for calculations and, by assumption, its performance has to be competitive with the current families of GPUs. Its main advantage is the built-in set of 512-bit vector registers and the ease of transferring existing codes from normal x86 architectures. However, the differences between standard x86 architectures and Xeon Phi do not guarantee performance portability. We choose an alternative approach and, instead of porting standard multithreaded code, we adapt to Xeon Phi previously developed OpenCL algorithms for finite element numerical integration. The algorithm is tested for standard FEM approximations of selected problems. The obtained timing results allow to compare the performance of the OpenCL kernels executed on the Xeon Phi and the contemporary GPUs.