MPFFT: An Auto-Tuning FFT Library for OpenCL GPUs

ISCAS OpenIR

	MPFFT: An Auto-Tuning FFT Library for OpenCL GPUs
	Li, Yan; Zhang, Yun-Quan; Liu, Yi-Qun; Long, Guo-Ping; Jia, Hai-Peng
	2013
发表期刊	JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
ISSN	1000-9000
卷号	28 期号:1 页码:90-105
摘要	Fourier methods have revolutionized many fields of science and engineering, such as astronomy, medical imaging, seismology and spectroscopy, and the fast Fourier transform (FFT) is a computationally efficient method of generating a Fourier transform. The emerging class of high performance computing architectures, such as CPU, seeks to achieve much higher performance and efficiency by exposing a hierarchy of distinct memories to software. However, the complexity of GPU programming poses a significant challenge to developers. In this paper, we propose an automatic performance tuning framework for FFT on various OpenCL GPUs, and implement a high performance library named MPFFT based on this framework. For power-of-two length FFTs, our library substantially outperforms the clAmdFft library on AMD GPUs and achieves comparable performance as the CUFFT library on NVIDIA GPUs. Furthermore, our library also supports non-power-of-two size. For 3D non-power-of-two FFTs, our library delivers 1.5x to 28x faster than FFTW with 4 threads and 20.01x average speedup over CUFFT 4.0 on Tesla C2050.; Fourier methods have revolutionized many fields of science and engineering, such as astronomy, medical imaging, seismology and spectroscopy, and the fast Fourier transform (FFT) is a computationally efficient method of generating a Fourier transform. The emerging class of high performance computing architectures, such as CPU, seeks to achieve much higher performance and efficiency by exposing a hierarchy of distinct memories to software. However, the complexity of GPU programming poses a significant challenge to developers. In this paper, we propose an automatic performance tuning framework for FFT on various OpenCL GPUs, and implement a high performance library named MPFFT based on this framework. For power-of-two length FFTs, our library substantially outperforms the clAmdFft library on AMD GPUs and achieves comparable performance as the CUFFT library on NVIDIA GPUs. Furthermore, our library also supports non-power-of-two size. For 3D non-power-of-two FFTs, our library delivers 1.5x to 28x faster than FFTW with 4 threads and 20.01x average speedup over CUFFT 4.0 on Tesla C2050.
收录类别	SCI
关键词	Fast Fourier Transform Gpu Opencl Auto-tuning
部门归属	[Li, Yan; Zhang, Yun-Quan; Liu, Yi-Qun; Long, Guo-Ping] Chinese Acad Sci, Inst Software, Beijing 100190, Peoples R China. [Li, Yan; Liu, Yi-Qun] Chinese Acad Sci, Grad Univ, Beijing 100049, Peoples R China. [Jia, Hai-Peng] Ocean Univ China, Sch Informat Sci & Engn, Qingdao 266000, Peoples R China.
语种	英语
内容类型	期刊论文
URI标识	http://ir.iscas.ac.cn/handle/311060/16959
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Li, Yan,Zhang, Yun-Quan,Liu, Yi-Qun,et al. MPFFT: An Auto-Tuning FFT Library for OpenCL GPUs[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2013,28(1):90-105.
APA	Li, Yan,Zhang, Yun-Quan,Liu, Yi-Qun,Long, Guo-Ping,&Jia, Hai-Peng.(2013).MPFFT: An Auto-Tuning FFT Library for OpenCL GPUs.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,28(1),90-105.
MLA	Li, Yan,et al."MPFFT: An Auto-Tuning FFT Library for OpenCL GPUs".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 28.1(2013):90-105.