Memory Efficient Two-Pass 3D FFT Algorithm for Intel? Xeon Phi~(TM) Coprocessor

	Memory Efficient Two-Pass 3D FFT Algorithm for Intel? Xeon Phi~(TM) Coprocessor
	Liu Yiqun 1; Li Yan 2; Zhang Yunquan 3; Zhang Xianyi 1
	2014
发表期刊	Journal of Computer Science and Technology
ISSN	1000-9000
卷号	29 期号:6 页码:989
摘要	Equipped with 512-bit wide SIMD instructions and large numbers of computing cores, the emerging x86-based Intel? Many Integrated Core (MIC) Architecture provides not only high floating-point performance, but also substantial off-chip memory bandwidth. The 3D FFT (three-dimensional fast Fourier transform) is a widely-studied algorithm; however, the conventional algorithm needs to traverse the data array three times. In each pass, it computes multiple 1D FFTs along one of three dimensions, giving rise to plenty of non-unit strided memory accesses. In this paper, we propose a two-pass 3D FFT algorithm, which mainly aims to reduce the amount of explicit data transfer between the memory and the on-chip cache. The main idea is to split one dimension into two sub-dimensions, and then combine the transform along each sub-dimension with one of the rest dimensions respectively. The difference in amount of TLB misses resulting from decomposition along different dimensions is analyzed in detail. Multi-level parallelism is leveraged on the many-core system for a high degree of parallelism and better data reuse of local cache. On top of this, a number of optimization techniques, such as memory padding, loop transformation and vectorization, are employed in our implementation to further enhance the performance. We evaluate the algorithm on the Intel? Xeon Phi~(?) coprocessor 7110P, and achieve a maximum performance of 136 Gflops with 240 threads in offload mode, which beats the vendor-specific Intel? MKL library by a factor of up to 2.22X.
关键词	3D-FFT memory efficient many-core Many Integrated Core Intel? Xeon Phi~(TM)
语种	英语
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/34828
专题	中国科学院计算技术研究所期刊论文_中文
作者单位	1.中国科学院软件研究所 2.Department of Computer Science and Technology,Tsinghua University 3.中国科学院计算技术研究所
推荐引用方式 GB/T 7714	Liu Yiqun,Li Yan,Zhang Yunquan,et al. Memory Efficient Two-Pass 3D FFT Algorithm for Intel? Xeon Phi~(TM) Coprocessor[J]. Journal of Computer Science and Technology,2014,29(6):989.
APA	Liu Yiqun,Li Yan,Zhang Yunquan,&Zhang Xianyi.(2014).Memory Efficient Two-Pass 3D FFT Algorithm for Intel? Xeon Phi~(TM) Coprocessor.Journal of Computer Science and Technology,29(6),989.
MLA	Liu Yiqun,et al."Memory Efficient Two-Pass 3D FFT Algorithm for Intel? Xeon Phi~(TM) Coprocessor".Journal of Computer Science and Technology 29.6(2014):989.