CORC  > 北京大学  > 信息科学技术学院
MrPhi: An Optimized MapReduce Framework on Intel Xeon Phi Coprocessors
Lu, Mian ; Liang, Yun ; Huynh Phung Huynh ; Ong, Zhongliang ; He, Bingsheng ; Goh, Rick Siow Mong
刊名IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
2015
关键词Xeon Phi Intel Many Integrated Core architecture (MIC) coprocessors MapReduce parallel programming high performance computing heterogeneous computing SYSTEMS
DOI10.1109/TPDS.2014.2365784
英文摘要In this work, we develop MrPhi, an optimized MapReduce framework on a heterogeneous computing platform, particularly equipped with multiple Intel Xeon Phi coprocessors. To the best of our knowledge, this is the first work to optimize the MapReduce framework on the Xeon Phi. We first focus on employing advanced features of the Xeon Phi to achieve high performance on a single coprocessor. We propose a vectorization friendly technique and SIMD hash computation algorithms to utilize the SIMD vectors. Then we pipeline the map and reduce phases to improve the resource utilization. Furthermore, we eliminate multiple local arrays but use low cost atomic operations on the global array to improve the thread scalability. For a given application, our framework is able to automatically detect suitable techniques to apply. Moreover, we extend our framework to a heterogeneous platform to utilize all hardware resource effectively. We adopt non-blocking data transfer to hide the communication overhead. We also adopt aligned memory transfer in order to fully utilize the PCIe bandwidth between the host and coprocessor. We conduct comprehensive experiments to benchmark the Xeon Phi and compare our optimized MapReduce framework with a state-of-the-art multi-core based MapReduce framework (Phoenix++). By evaluating six real-world applications, the experimental results show that our optimized framework is 1.2 to 38 x faster than Phoenix++ for various applications on a single Xeon Phi. Additionally, the performance of four applications is able to achieve linear scalability on a platform equipped with up to four Xeon Phi coprocessors.; National Natural Science Foundation of China [61300005]; MoE AcRF Tier 2 grant in Singapore [MOE2012-T2-2-067]; SCI(E); EI; ARTICLE; lum@ihpc.a-star.edu.sg; ericlyun@pku.edu.cn; huynhph@ihpc.a-star.edu.sg; ongzl@ihpc.a-star.edu.sg; bshe@ntu.edu.sg; gohsm@ihpc.a-star.edu.sg; 11; 3066-3078; 26
语种中文
内容类型期刊论文
源URL[http://ir.pku.edu.cn/handle/20.500.11897/415455]  
专题信息科学技术学院
推荐引用方式
GB/T 7714
Lu, Mian,Liang, Yun,Huynh Phung Huynh,et al. MrPhi: An Optimized MapReduce Framework on Intel Xeon Phi Coprocessors[J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS,2015.
APA Lu, Mian,Liang, Yun,Huynh Phung Huynh,Ong, Zhongliang,He, Bingsheng,&Goh, Rick Siow Mong.(2015).MrPhi: An Optimized MapReduce Framework on Intel Xeon Phi Coprocessors.IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS.
MLA Lu, Mian,et al."MrPhi: An Optimized MapReduce Framework on Intel Xeon Phi Coprocessors".IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS (2015).
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace