A Cache Memory System based on a Dynamic/Adaptive Replacement Approach

  title={A Cache Memory System based on a Dynamic/Adaptive Replacement Approach},
  author={Jos{\'e} Aguilar and Ernst L. Leiss},
  journal={Rev. Colomb. de Computaci{\'o}n},
In this work we propose a cache memory system based on an adaptive cache replacement scheme, as part of the virtual memory system of an operating system. We use a sequential discrete-event simulator of a distributed system to compare our approach with previous work. Our adaptive cache replacement scheme is based on several criteria about the system and applications with the objective being to estimate/choose the best replacement policy. We assign a replacement priority value to each cache block… 

Figures from this paper

Cache memory coherence protocol for distributed systems

This work proposes a protocol which man ages the coherence in the cache memory in systems with distributed memory, and was proved using a methodology based on the formal description using a finites states ma chine and the Spin tool.



The effect of using state-based priority information in a shared-memory multiprocessor cache replacement policy

  • F. Mounes-ToussiD. Lilja
  • Computer Science
    Proceedings. 1998 International Conference on Parallel Processing (Cat. No.98EX205)
  • 1998
This work studies the impact of incorporating the cache block coherence state information in the random replacement policy in a shared memory multiprocessor and indicates that, with the appropriate priority assignment and a set associativity size less than 16, the proposed policy can outperforms the Random and Random & Invalid policies and, in some cases, can even outperform the LRU policy.

Coherence and Replacement Protocol of DICE-A Bus-Based COMA Multiprocessor

This paper presents the coherence and replacement protocol of the DICE multiprocessor and its design trade-offs, and describes a four-state write-invalidate coherence protocol in detail.

Analysis of cache replacement-algorithms

The model shows that the majority of the cache misses that OPT avoids over LRU come from the most-recently-discarded lines of the LRU cache, which leads to three realizable near-optimal replacement algorithms that try to duplicate the replacement decisions made by OPT.

EELRU: simple and effective adaptive page replacement

Early Eviction LRU (EELRU) is presented: an adaptive replacement algorithm based on the principle of detecting when the LRU algorithm underperforms (i.e., when the fetched memory pages are often the ones evicted lately).

Estimating neural networks-based algorithm for adaptive cache replacement

Simulation results for a wide spectrum of cache configurations indicate that the estimating neural network based replacement scheme provides significant performance advantage over existing policies.

On the existence of a spectrum of policies that subsumes the least recently used (LRU) and least frequently used (LFU) policies

The L RFU policy is applied to buffer caching, and results from trace-driven simulations show that the LRFU performs better than previously known policies for the workloads the authors considered.

“A Proposal for a Consistent Framework of Dynamic/Adaptive Policies for Cache Memory Management”

  • Technical Report, Department of Computer Sciences,
  • 2000

“Estimating NN-Based Algorithm for Adaptive Cache Replacement”

  • IEEE Transaction on System, Man and Cybernetic,
  • 1998

“Analysis of Cache Replacement Algorithms”, Ph.D dissertation

  • Dept. Elect. Compt. Eng., Univ. Mass
  • 1985