By Topic

A behavior-based reconfigurable cache for the low-power embedded processor

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Jiongyao Ye ; Grad. Sch. of Inf., Productions & Syst., Waseda Univ., Kitakyushu, Japan ; Jiannan Jin ; Watanabe, T.

In embedded processor designs, a cache becomes the main contributor of the power consumption as it greatly improves the performance. The conventional low-power techniques of a cache based on a fixed hardware configuration cannot be configured and it is independent on the program behavior. Thus, a configurable cache is proposed to save energy and improve performance by dynamically adjusting the cache parameters for the code that is executing. However, most existing configurable caches explore and adapt the optimal configuration based on successive time-intervals, which presents efficiency only if the program can keep its execution phase for a number of intervals. In this paper, we propose a behavior-based configurable cache, which can be dynamically adjusted based on the program behavior. The design adds very little hardware complexity and commits most workload to the software, so that it is very effective for the embedded microprocessors design. Simulation by using Spec 2000 shows that our proposed configurable cache can reduce the power consumption by up to 60.6% and 22.3% compared to a conventional set-associative cache and a temporal-based configurable cache, respectively. At the same time, performance degradation is about 0.75%.

Published in:

ASIC (ASICON), 2011 IEEE 9th International Conference on

Date of Conference:

25-28 Oct. 2011