Abstract

The conventional way-predicting cache can effectively reduce power consumption, due to only speculatively selecting an MRU (most recently used) way before starting a normal cache access. However, for accessing the data within the same cache block, to fetch an MRU table and an MRU tag-subarray is unnecessary. Especially for executing a program with good locality, the probability to access the intrablock data in the cache is more significant. Focusing on the way-predicting cache based on intrablock data access, we propose a new cache scheme that can judge if the present cache access is an intrablock, and then only directly enable one data-subarray. By this approach the proposed scheme is a further improvement on average energy savings over the conventional way-predicting cache, especially for large block sizes and good program locality. Therefore, such a way-predicting cache based on intrablock access indeed provides another solution for the design of low-power caches.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.