accelerating viola-jones facce detection algorithm on gpus

ISCAS OpenIR

	accelerating viola-jones facce detection algorithm on gpus
	Jia Haipeng; Zhang Yunquan; Wang Weiyan; Xu Jianliang
	2012
会议名称	IEEE 14th International Conference on High Performance Computing and Communications (HPCC) / IEEE 9th International Conference on Embedded Software and Systems (ICESS)
会议录名称	Proceedings of the 14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012
页码	396-403
会议日期	JUN 25-27, 2012
会议地点	Liverpool, ENGLAND
收录类别	ISTP ; EI
ISBN	978-0-7695-4749-7
部门归属	Jia Haipeng; Zhang Yunquan; Wang Weiyan Chinese Acad Sci Inst Software Lab Parallel Software & Computat Sci Beijing Peoples R China.
摘要	The Viola-Jones face detection algorithm represents a class of parallel algorithms that both memory accesses and work distributions are irregular, thereby hard to obtain high performance on GPUs. Furthermore, conventional GPU programming wisdom usually guides us on how to optimize data parallel workloads with regular inputs and outputs. While how to efficiently write task-level parallelism programs with irregular workloads have not much material to reference. In this paper, we present an OpenCL-implementation of Viola-Jones face detection algorithm with high performance on both NVIDIA and AMD GPUs through five main techniques: warp size work granularity, persistent threads, Uberkernel, local and global queues. We also demonstrate the high performance of our implementation by comparing it with a well-optimized CPU version from OpenCV library. Experiment results show that the speedup reaches up to 5.193 similar to 35.08 times (16.91 on average) and 5.85 similar to 32.641 times (17.535 on average) on AMD and NVIDIA GPU respectively.; The Viola-Jones face detection algorithm represents a class of parallel algorithms that both memory accesses and work distributions are irregular, thereby hard to obtain high performance on GPUs. Furthermore, conventional GPU programming wisdom usually guides us on how to optimize data parallel workloads with regular inputs and outputs. While how to efficiently write task-level parallelism programs with irregular workloads have not much material to reference. In this paper, we present an OpenCL-implementation of Viola-Jones face detection algorithm with high performance on both NVIDIA and AMD GPUs through five main techniques: warp size work granularity, persistent threads, Uberkernel, local and global queues. We also demonstrate the high performance of our implementation by comparing it with a well-optimized CPU version from OpenCV library. Experiment results show that the speedup reaches up to 5.193 similar to 35.08 times (16.91 on average) and 5.85 similar to 32.641 times (17.535 on average) on AMD and NVIDIA GPU respectively.
关键词	Viola-jones Imbalanced Computation Persistent Threads Local Queues Global Queues
主办者	IEEE, IEEE Comp Soc, Univ Bradford, IEEE Tech Comm Scalable Comp (TCSC)
语种	英语
内容类型	会议论文
URI标识	http://ir.iscas.ac.cn/handle/311060/15807
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Jia Haipeng,Zhang Yunquan,Wang Weiyan,et al. accelerating viola-jones facce detection algorithm on gpus[C],2012:396-403.