QQ客服 官方微博 反馈留言

	An Energy-Efficient Branch Prediction with Grouped Global History
	Huang, Mingkai ; He, Dan ; Liu, Xianhua ; Tan, Mingxing ; Cheng, Xu
	2015
英文摘要	Branch prediction has been playing an increasingly important role in improving the performance and energy efficiency for modern microprocessors. The state-of-the-art branch predictors, such as the perceptron and TAGE predictors, leverage novel prediction algorithms to explore longer branch history for higher prediction accuracy. We observe that as the branch history is becoming longer, the efficiency of global history is degraded by the interference of different branch instructions. In order to mitigate the excessive influence of the branch history interference, we propose the Grouped Global History (GGH) based branch predictor, a lightweight yet efficient branch predictor. Unlike existing branch predictors that make use of a unified global history for prediction, GGH divides the global history into a set of subgroups such that the interference resulted by frequently executed branch instructions could be restricted. With subgroups of global history, GGH also enables us to track even longer effective branch correlation without introducing hardware storage overhead. Our experimental results based on SPEC CINT 2006 workloads demonstrate that our approach can significantly reduce the branch mispredictions per kilo instructions (MPKI) by 4.76 over the baseline perceptron predictor, with a simple control logic extension.; EI; CPCI-S(ISTP); huangmingkai@mprc.pku.edu.cn; hedan@mprc.pku.edu.cn; liuxianhua@mprc.pku.edu.cn; mingxing.tan@cornell.edu; chengxu@mprc.pku.edu.cn; 140-149; 2015-December
语种	英语
出处	44th Annual International Conference on Parallel Processing Workshops (ICPPW)
DOI标识	10.1109/ICPP.2015.23
内容类型	其他
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/449543]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Huang, Mingkai,He, Dan,Liu, Xianhua,et al. An Energy-Efficient Branch Prediction with Grouped Global History. 2015-01-01.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

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。