中文摘要：

这篇文章建议低开销和更少的运行时刻的机制，称为的动态缓存资源分配(DCRA ) ，它与要求的缓存资源分配每个应用程序。机制在运行时刻收集缓存点击失误信息然后分析信息并且决定资源多少缓存应该被分配到执行申请的水流。缓存资源的数量动态地变化减少失误和精力消费的全部的数字。从 SPEC2000 的几应用的学习证明节省的重要精力与 39% 积蓄的一般水准基于 DCRA 为申请被完成。

英文摘要：

This article proposes a mechanism of low overhead and less runtime, termed dynamic cache resources allocation （DCRA）, which allocates each application with required cache resources. The mechanism collects cache hit-miss information at runtime and then analyzes the information and decides how many cache resources should be allocated to the current executing application. The amount of cache resources varies dynamically to reduce the total number of misses and energy consumption. The study of several applications from SPEC2000 shows that significant energy saving is achieved for the application based on the DCRA with an average of 39% savings.