Research Paper on Cache Memory

Author(s)

Pooja Agarwal , Prerna Mangla , Preeti Kumari ,

Download Full PDF Pages: 06-13 | Views: 1146 | Downloads: 233 | DOI: 10.5281/zenodo.3427906

Volume 4 - February 2015 (02)

Abstract

Cache memory is a memory which is used by the central processing unit in a computer to reduce the burden on the main access memory. Cache memory stores all the recent instructions and this is the only reason it is nearest to CPU. It lies in the path between processor and memory and this is the only reason why it use less time to access memory than main memory. Ere cache uses 100ns speed main memory uses 700 ns speed. The subject of using the data is displayed by a factor that is named hit ratio. In this paper, a new process for increasing the hit ratio is introduced which is referred to as the programmable cache memory. This method is a grouping of both the physical and logical approach, i.e., in adding together to use a high speed SRAM, a programmable logical circuit is added to the cache manager in order to increase the hit ratio. In the paper we have thrown light on cache working that the very basic functioning of the processor. We have also reached the topic discussing the cache memories in uniprocessors.  Besides we have discussed the directory protocols used in cache where main protocol is snoopy protocol. And at last we have gone through cache consistencies that is how it works in tough times. And at last we have concluded with some important points.

Keywords

Hit Ratio, Locality Of Reference, Programmable Cache Memory, Snoopy Protocols, Cache Coherence, Cache Consistency

References

        i.         RUSSELL R. ATKINSON AND EDWARD M. MCCREIGHT. “The Dragon Processor”. Proceedings Second International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS II), Palo Alto, California, IEEE Computer Society Press, October 5–8, 1987,pages 65–69

ii.        JAMES K. ARCHIBALD. “A Cache Coherence Approach For Large Multiprocessor Systems”. 1988 International Conference on Supercomputing, St. Malo, France, ACM Press, July 4–8, 1988, pages 337–345.

iii.      C. GORDON BELL. “Multis: A New Class of Multiprocessor Computers”. Science, volume 228, number 4698, April 26, 1985, pages 462–467.

iv.      PAUL L. BORRILL. “MicroStandards Special Feature: A Comparison of 32-Bit Buses”. IEEE Micro, IEEE Computer Society, volume 5, number 6, December 1985, pages 71–79.

v.       REED BOWLBY. “The DIP may take its final bows”. IEEE Spectrum, volume 22, number 6, June 1985, pages 37–42.

vi.      KHALED A. EL-AYAT AND RAKESH K. AGARWAL. “The Intel 80386 — Architecture and Implementation”. IEEE Micro, IEEE Computer Society, volume 5, number 6, December 1985, pages 4–22.

vii.    JAMES R. GOODMAN. “Using Cache Memory to Reduce Processor–Memory Traffic”. The 10th Annual International Symposium on Computer Architecture Conference Proceedings, Stockholm, Sweden, IEEE Computer Society Press, June 13–17, 1983, pages 124–131

viii.   HUMOUD B. HUMOUD. A Study in Memory Interference Models. Ph.D. dissertation, The University of Michigan Computing Research Laboratory, Ann Arbor, Michigan, April 1985.

ix.      TOM´AS LANG, MATEO VALERO, AND IGNACIO ALEGRE. “Bandwidth of Crossbar and Multiple-Bus Connections for Multiprocessors”. IEEE Transactions on Computers, volume C-31, number 12, December 1982, pages 1227–1234.

x.       ALAN JAY SMITH. “Cache Memories”. Computing Surveys, Association for Computing Machinery,volume 14, number 3, September 1982, pages 473–530.

Cite this Article: