CLSIFT: An optimization study of the scale invariance feature transform on GPUs

ISCAS OpenIR

	CLSIFT: An optimization study of the scale invariance feature transform on GPUs
	Wang, Weiyan (1); Zhang, Yunquan (1); Guoping, Long (1); Yan, Shengen (1); Jia, Haipeng (1)
	2014
会议名称	15th IEEE International Conference on High Performance Computing and Communications, HPCC 2013 and 11th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC 2013
页码	93-100
会议日期	November 13, 2013 - November 15, 2013
会议地点	Zhangjiajie, Hunan, China
收录类别	EI
出版地	IEEE Computer Society
ISBN	9780769550886
部门归属	(1) Lab. of Parallel Software and Computational Science, Institute of Software Chinese Academy of Sciences, China; (2) State Key Laboratory of Computing Science, Institute of Software Chinese Academy of Sciences, China; (3) School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China
摘要	Scale Invariance Feature Transform (SIFT) is quite suitable for image matching because of its invariance to image scaling, rotation and slight changes in illumination or viewpoint. However, due to high computation complexity it's technically challenging to deploy SIFT in real time application situations. To address this problem, we propose CLSIFT, an OpenCL based highly speeded up and performance portable SIFT solution. Important optimization techniques employed in CLSIFT such as: (1) For less global memory traffic, independent logical functions are merged into the same kernel to reuse data.(2) loop buffers are introduced in for data and intermediate results reusing.(3)Task queue used to schedule threads in the same branch to remove branch divergences. (4) Data partition is based on the statics patterns for workload balance among workgroups. (5) Overlap of CPU time and better parallel strategies are used too. With all mentioned efforts, CLSIFT processes lena. jpg at 74.2 FPS and 43.4FPS respectively on NVidia and AMD GPUS, much higher than CPU's nearly 10 FPS and the known fastest SIFTGPU's 39.8 FPS and 13FPS. Moreover in a quantitative comparison approach we analyze those successful strategies beating SIFTGPU, a famous existing GPU implementation. Additionally, we observe and conclude that NVidia GPU achieves better occupancy and performance due to some factors. Finally, we summarize some techniques and empirical guiding principles that may be shared by other applications on GPU. © 2013 IEEE.; Scale Invariance Feature Transform (SIFT) is quite suitable for image matching because of its invariance to image scaling, rotation and slight changes in illumination or viewpoint. However, due to high computation complexity it's technically challenging to deploy SIFT in real time application situations. To address this problem, we propose CLSIFT, an OpenCL based highly speeded up and performance portable SIFT solution. Important optimization techniques employed in CLSIFT such as: (1) For less global memory traffic, independent logical functions are merged into the same kernel to reuse data.(2) loop buffers are introduced in for data and intermediate results reusing.(3)Task queue used to schedule threads in the same branch to remove branch divergences. (4) Data partition is based on the statics patterns for workload balance among workgroups. (5) Overlap of CPU time and better parallel strategies are used too. With all mentioned efforts, CLSIFT processes lena. jpg at 74.2 FPS and 43.4FPS respectively on NVidia and AMD GPUS, much higher than CPU's nearly 10 FPS and the known fastest SIFTGPU's 39.8 FPS and 13FPS. Moreover in a quantitative comparison approach we analyze those successful strategies beating SIFTGPU, a famous existing GPU implementation. Additionally, we observe and conclude that NVidia GPU achieves better occupancy and performance due to some factors. Finally, we summarize some techniques and empirical guiding principles that may be shared by other applications on GPU. © 2013 IEEE.
语种	英语
内容类型	会议论文
URI标识	http://ir.iscas.ac.cn/handle/311060/16605
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Wang, Weiyan ,Zhang, Yunquan ,Guoping, Long ,et al. CLSIFT: An optimization study of the scale invariance feature transform on GPUs[C]. IEEE Computer Society,2014:93-100.