An optimal replacement algorithm for balancing multi-module caches

نویسندگان

  • Hans Vandierendonck
  • Koen De Bosschere
چکیده

Multi-module caches consist of multiple parallel caches. Their goal is to increase level 1 data cache hit ratios by allowing more freedom in placing blocks in the cache. Balancing multi-module caches provide the opportunity to reorganise blocks by moving them between the cache modules, in an attempt to balance the amount of data stored in each module. This capability allows for even higher hit ratios. We present an algorithm to simulate optimal replacement in balancing multi-module caches. This algorithm is optimal since it minimizes the number of cache misses However, it is infeasible to implement it in hardware. We discuss the effects of the set index functions used in the modules and the ways they interact. The algorithm is used to investigate three cache configurations and provide some performance limits for balancing multimodule caches. Keywords— cache memory, multi-module cache, optimal replacement algorithm

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Pareto Optimal Balancing of Four-bar Mechanisms Using Multi-Objective Differential Evolution Algorithm

Four-bar mechanisms are widely used in the industry especially in rotary engines. These mechanisms are usually applied for attaining a special motion duty like path generation; their high speeds in the industry cause an unbalancing problem. Hence, dynamic balancing is essential for their greater efficiency. In this research study, a multi-objective differential evolution algorithm is used for P...

متن کامل

Pareto Optimal Multi-Objective Dynamical Balancing of a Slider-Crank Mechanism Using Differential Evolution Algorithm

The present paper aims to improve the dynamical balancing of a slider-crank mechanism. This mechanism has been widely used in internal combustion engines, especially vehicle engines; hence, its dynamical balancing is important significantly. To have a full balance mechanism, the shaking forces and shaking moment of foundations should be eliminated completely. However, this elimination is usuall...

متن کامل

A Multi-Objective Particle Swarm Optimization for Mixed-Model Assembly Line Balancing with Different Skilled Workers

This paper presents a multi-objective Particle Swarm Optimization (PSO) algorithm for worker assignment and mixed-model assembly line balancing problem when task times depend on the worker’s skill level. The objectives of this model are minimization of the number of stations (equivalent to the maximization of the weighted line efficiency), minimization of the weighted smoothness index and minim...

متن کامل

Development of Model and Algorithm for Depot Balancing Multi-Depot Vehicle Scheduling Problem Considering Depot Balancing

The main of multi-depot vehicle scheduling problem (MDVSP) is to schedule the timetabled trips using limited resources, optimally. The problem is very important in the management of the transportation systems. One of the most useful ways to better manage these systems is to consider the real conditions including depot balancing constraints. To normalize the number of vehicles departed from each...

متن کامل

Coordinated Placement and Replacement for Large-Scale Distributed Caches

In a large-scale information system such as a digital library or the web, a set of distributed caches can improve their eeectiveness by coordinating their data placement decisions. Using simulation, we examine three practical cooperative placement algorithms including one that is provably close to optimal, and we compare these algorithms to the optimal placement algorithm and several cooperativ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007