DocumentCode :
2903475
Title :
Fixed Segmented LRU cache replacement scheme with selective caching
Author :
Morales, K. ; Byeong Kil Lee
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Texas at San Antonio, San Antonio, TX, USA
fYear :
2012
fDate :
1-3 Dec. 2012
Firstpage :
199
Lastpage :
200
Abstract :
Cache replacement policies are an essential part of the memory hierarchy used to bridge the gap in speed between CPU and memory. Most of the cache replacement algorithms that can perform significantly better than LRU (Least Recently Used) replacement policy come at the cost of large hardware requirements [1][3]. With the rise of mobile computing and system-on-chip technology, these hardware costs are not acceptable. The goal of this research is to design a low cost cache replacement algorithm that achieves comparable performance to existing scheme. In this paper, we propose two enhancements to the SLRU (Segmented LRU) algorithm: (i) fixing the number of protected and probationary segments based on effective segmentation ratio with increasing the protected segments, and (ii) implementing selective caching, to achieve more effective eviction, based on preventing dead blocks from entering the cache. Our experiment results show that we achieve a speed up to 14.0% over LRU and up to 12.5% over standard SLRU.
Keywords :
cache storage; CPU; SLRU; fixed segmented LRU cache replacement scheme; hardware requirements; least recently used; memory hierarchy; mobile computing; segmented LRU; selective caching; system-on-chip technology; Algorithm design and analysis; Benchmark testing; Hardware; Hidden Markov models; Prediction algorithms; Standards; System-on-a-chip; cache; cache bypassing; dead blocks; replacement policy; segmented LRU;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Performance Computing and Communications Conference (IPCCC), 2012 IEEE 31st International
Conference_Location :
Austin, TX
ISSN :
1097-2641
Print_ISBN :
978-1-4673-4881-2
Type :
conf
DOI :
10.1109/PCCC.2012.6407712
Filename :
6407712
Link To Document :
بازگشت