Performance of LRU Block Replacement Algorithm with Pre-Fetching

  • Authors:
  • Ravi Pendse;Ravi Bhagavathula

  • Affiliations:
  • -;-

  • Venue:
  • MWSCAS '98 Proceedings of the 1998 Midwest Symposium on Systems and Circuits
  • Year:
  • 1998

Quantified Score

Hi-index 0.00

Visualization

Abstract

An economical solution to the need for unlimited amounts of fast memo? is a memo? hierarchy, which takes advantage of locality and cost/performance of memoy technologies. Most of the advanced block replacement algorithms exploit the presence of temporal local@ in programs to achieve a better performing cache. A direct fallout of this approach is the increased overhead involved due to the complexiy of the algorithm without any significant improvement in the cache performance. The petjormance of the cache could be improved if spatial locality present in the programs is flirther exploited. This paper presents the results of the investigation of the impact of preyfetching techniques on the miss rates due to the basic Least Recently Used (LRU) block replacement algorithm. Simulations reveal an improvement of about 609 in the miss rates for instruction caches due to pre-fetching and a corresponding improvement of about 1070 for data caches.