A performance model for general-purpose computation on GPU

CORC > 北京大学 > 计算机科学技术研究所

	A performance model for general-purpose computation on GPU
	Han, Bo ; Zhou, Bingfeng
刊名	jisuanji fuzhu sheji yu tuxingxue xuebaojournal of computer aided design and computer graphics
	2009
英文摘要	We present an efficient model to analyze and improve the performance of general-purpose computation on graphics processing units (GPGPU). After analyzing the parallel architecture and massive-thread working mechanism of modern GPUs, we build a performance model on a four-level stream processing pipeline, including data input, computation, output and transfer. We further conclude two key factors for GPGPU applications to achieve high performance: high intensity in both computation and memory access. To demonstrate the effectiveness of our model, we highlight its performance on three typical image processing applications, including Gaussian convolution, DCT and motion estimation. Guided by our performance model, some techniques are put forward to remove the performance bottleneck and achieve 4~10 times performance improvement. In practice, the experimental results fit well with the estimations of our proposed model.; EI; 0; 9; 1219-1226; 21
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/321323]
专题	计算机科学技术研究所
推荐引用方式 GB/T 7714	Han, Bo,Zhou, Bingfeng. A performance model for general-purpose computation on GPU[J]. jisuanji fuzhu sheji yu tuxingxue xuebaojournal of computer aided design and computer graphics,2009.
APA	Han, Bo,&Zhou, Bingfeng.(2009).A performance model for general-purpose computation on GPU.jisuanji fuzhu sheji yu tuxingxue xuebaojournal of computer aided design and computer graphics.
MLA	Han, Bo,et al."A performance model for general-purpose computation on GPU".jisuanji fuzhu sheji yu tuxingxue xuebaojournal of computer aided design and computer graphics (2009).