Power Issues Related to Branch Prediction — University Of Virginia Tech
نویسندگان
چکیده
This paper explores the role of branch predictor organization in power/energy/performance tradeoffs for processor design. We find that as a general rule, to reduce overall energy consumption in the processor it is worthwhile to spend more power in the branch predictor if this results in more accurate predictions that improve running time. Two techniques, however, provide substantial reductions in power dissipation without harming accuracy. Banking reduces the portion of the branch predictor that is active at any one time. And a new on-chip structure, the prediction probe detector (PPD), can use pre-decode bits to entirely eliminate unnecessary predictor and BTB accesses. Despite the extra power that must be spent accessing the PPD, it reduces local predictor power and energy dissipation by about 45% and overall processor power and energy dissipation by 5–6%.
منابع مشابه
The Virginia Tech Scholarly Review
The Virginia Tech Scholarly Review was established to enhance the exchange of information within the university community about the scope and significance of scholarly activity at Virginia Tech. It is a forum that allows faculty members from diverse disciplines to share their excitement, methods, and achievements with their colleagues across the Virginia Tech community. Poets and playwrights ca...
متن کاملStudent reactions to the shootings at Virginia Tech and Northern Illinois University: Does sharing grief and support over the internet affect recovery?
After the shootings at Virginia Tech and Northern Illinois University, many students gravitated to the Internet for support. Despite the fact that the Internet plays a major role in how people live their lives in contemporary society, little is known about how people use the Internet in times of tragedy and whether this use affects well-being. To address these issues, the current study assessed...
متن کاملA INDEMICS: An Interactive High-Performance Computing Framework for Data Intensive Epidemic Modeling
Keith R. Bisset, NDSSL, Virginia Bioinformatics Institute, Virginia Tech Jiangzhuo Chen, NDSSL, Virginia Bioinformatics Institute, Virginia Tech Suruchi Deodhar, NDSSL, Virginia Bioinformatics Institute, Virginia Tech, Department of Computer Science, Virginia Tech Xizhou Feng, NDSSL, Virginia Bioinformatics Institute, Virginia Tech, Department of Mathematics, Statistics, and Computer Science, M...
متن کاملLayer-by-layer self-assembled conductor network composites in ionic polymer metal composite actuators with high strain response
polymer metal composite actuators with high strain response Sheng Liu, Reza Montazami, Yang Liu, Vaibhav Jain, Minren Lin, James R. Heflin, and Q. M. Zhang Department of Electrical Engineering, The Pennsylvania State University, University Park, Pennsylvania 16802, USA Department of Materials Science and Engineering, Virginia Tech, Blacksburg, Virginia 24061, USA Macromolecular Science and Engi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2001