期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2013
卷号：4
期号：6
DOI：10.14569/IJACSA.2013.040622
出版社：Science and Information Society (SAI)
摘要：The processor-memory speed gap referred to as memory wall, has become much wider in multi core processors due to a number of cores sharing the processor-memory interface. In addition to other cache optimization techniques, the mechanism of prefetching instructions and data has been used effectively to close the processor-memory speed gap and lower the memory wall. A number of issues have emerged when prefetching is used aggressively in multicore processors. The results presented in this paper are an indicator of the problems that need to be taken into consideration while using prefetching as a default technique. This paper also quantifies the amount of degradation that applications face with the aggressive use of prefetching. Another aspect that is investigated is the performance of multicore processors using a multiprogram workload as compared to a single program workload while varying the configuration of the built-in hardware prefetchers. Parallel workloads are also investigated to estimate the speedup and the effect of hardware prefetchers. This paper is the outcome of work that forms a part of the PhD research project currently in progress at NED University of Engineering and Technology, Karachi.
