Abstract

Three-dimensional (3-D) integration technology provides various architectural opportunities including huge memory bandwidth. This paper proposes versatile stream buffer architecture to work as a secondary victim cache as well as the conventional stream buffer. The versatile stream buffer utilizes empty spaces to exploit massive memory bandwidth provided by 3-D integration technology and to reduce memory access frequency. Performance evaluation results show that the proposed mechanism with a 16KB stream buffer and a 4KB victim cache can achieve better performance than the conventional L2 cache with the capacity of 256KB and 2MB by 10% and 3%, respectively. The proposed mechanism reduces the miss rate by about 12% more than the conventional L2 cache with the capacity of 256KB.

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.