Hiding memory access latency in software pipelining | |
Liu Li ; Li Wen-Long ; Chen Yu ; Li Sheng-Mei ; Tang Zhi-Zhong | |
2010-05-06 ; 2010-05-06 | |
关键词 | Practical/ pipeline processing processor scheduling program control structures storage management/ hiding memory access latency software pipelining memory optimization technologies foresighted latency modulo scheduling load instructions/ C6150N Distributed systems software C6120 File organisation C6150C Compilers, interpreters and other processors |
中文摘要 | Software pipelining tries to improve the performance of a loop by overlapping the execution of several successive iterations. As processor gets much higher speed, the memory access latency becomes a bottleneck that restricts higher performance. Software pipelining has been combined with several memory optimization technologies for higher performance by hiding memory access latency. This paper presents a foresighted latency modulo scheduling (FLMS) algorithm which determines the latency of load instructions according to the feature of the loop. Experimental results show that FLMS decreases the stall time and improves the performance of programs. |
语种 | 中文 ; 中文 |
出版者 | Science Press ; China |
内容类型 | 期刊论文 |
源URL | [http://hdl.handle.net/123456789/10335] ![]() |
专题 | 清华大学 |
推荐引用方式 GB/T 7714 | Liu Li,Li Wen-Long,Chen Yu,et al. Hiding memory access latency in software pipelining[J],2010, 2010. |
APA | Liu Li,Li Wen-Long,Chen Yu,Li Sheng-Mei,&Tang Zhi-Zhong.(2010).Hiding memory access latency in software pipelining.. |
MLA | Liu Li,et al."Hiding memory access latency in software pipelining".(2010). |
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。
修改评论