Dynamic Resizing on Active Warps Scheduler to Hide Operation Stalls on GPUs.

IEEE Transactions on Parallel and Distributed Systems(2017)

引用 4|浏览58
暂无评分
摘要
This paper conducts a detailed study of the factors affecting the operation stalls in terms of the fetch group size on the warp scheduler of GPUs. Throughout this paper, we reveal that the size of a fetch group is highly involved for hiding various types of operation stalls: short latency stalls, long latency stalls, and Load/Store Unit (LSU) stalls. The scheduler with a small fetch group cannot h...
更多
查看译文
关键词
Graphics processing units,Message systems,Instruction sets,Registers,Scheduling,System-on-chip
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要