1. Dept. of Microelectronic Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China;
2. School of Electronic Engineering, Heilongjiang University, Harbin, Heilongjiang 150080, China
Abstract：NTS cache augments the direct-mapped main cache with a small fully-associative cache that holds those blocks predicted as holding non-temporal locality characteristics.The most outstanding difference of the NTS cache from the victim cache lies in the NTS cache doesn't have direct data path between the two caches,so its advantages are lower power and easier structure design.In this paper,an improvement of the NTS cache scheme,called Selective Conflict Prediction cache (SCP cache),is proposed.In this scheme,incoming blocks into the cache are placed selectively in the direct-mapped cache or the fully-associative cache by the use of a conflict prediction algorithm which detects the locality of data blocks in the cache.Simulation results show that the performance of SCP cache is always better than that of NTS cache with similar area.
[1] Tyson G,Farrens M,et al.A modified approach to data cache management[A].Proceedings of the 28th Annual IEEE/ACM International Symposium on Microarchitecture(MICRO-28)[C].Ann Arbor,USA,1995.93-103.
[2] Rivers J A,Tam E S,Davidson E S.On effective data supply for multi-issue processors[A].Proceedings of the 1997 International Conference on Computer Design(ICCD'97)[C].Austin,USA,1997.519-528.
[3] Rivers J A,Tam E S,et al.Evaluating the performance of active cache management schemes[A].Proceedings of the 1998 International Conference on Computer Design (ICCD'98)[C].Austin,USA,1998.368-375.
[4] Jouppi N P.Improving direct mapping cache performance by the addition of a small full associative cache and prefetch buffers[A].Proceedings of 17th Annual International Symposium on Computer Architecture(ISCA 1990)[C].Seattle,USA,1990.364-373.
[5] Tse J,Smith A J.CPU prefetching:timing evaluation of hardware implementations[J].IEEE Transaction on Computers,1998,47(5):509-526.
[6] Rotenberg E,Bennett S,Smith J E.A trace cache micro-architecture and evaluation[J].IEEE Transaction on Computers,1999,48(2):111-120.
[7] Kharbutli M,Solihin Y.Counter-based cache replacement and bypassing algorithms[J].IEEE Transaction on Computers,2008,57(4):433-447.
[8] Davanam N,Lee B K.Towards smaller-sized cache for mobile processors using shared set-associativity[A].Proceedings of the 7th International Conference on Information Technology[C].Las Vegas,USA,2010.1-6.
[9] Qureshi M K,Thompson D,Patt Y N.The VWay cache:demand based associativity via global replacement[A].Proceedings of 32nd Annual International Symposium on Computer Architecture (ISCA'05)[C].Madison,USA,2005.544-555.
[10] Tam E S,Rivers J A,et al.Active management of data caches by exploiting reuse information[J].IEEE Transaction on Computers,1999,48(11):1244-1258.
[11] 李晓明,鲍东星,喻明艳,叶以正.利用冲突预测方法的高缓组织方案[J].电子学报,2003,31(5):724-727. Li Xiao-ming,Bao Dong-xing,Yu Ming-yan,Ye Yi-zheng.Cache management by using conflict prediction method[J].Acta Electronica Sinica,2003,31(5):724-727.(in Chinese)
[12] Burger D,Austin T M.Evaluating future processors:the SimpleScalar tool set.Technical Report #1342[R].University of Wisconsin,1997.
[13] Tam E S,Rivers J A,et al.Mlcache:a flexible multilateral cache simulater[A].Proceedings of the 6th International Symposium on Modeling,Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS'98)[C].Montreal,Canada,1998.19-26.
2018, Vol. 46 
