Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

Using dynamic, full cache locking and genetic algorithms for cache size minimization in multitasking, preemptive, real-time systems

  • Martí-Campoy, Antonio|||0000-0002-6009-8703
  • Rodríguez-Ballester, Francisco|||0000-0002-4087-5077
  • Ors Carot, Rafael|||0000-0003-2787-4683
Cache locking have shown during the last years their usefulness easing the schedulability analysis of multitasking, preemptive, real-time systems. Cache locking provides a high degree of predictability while system performance is maintained at a similar level to that provided by regular, highly unpredictable, non-locked cache. Cache locking may also be useful to reduce hardware costs by means of reducing the size of the cache memory needed to make a real-time system schedulable.This work shows how full, dynamic cache locking may help to reduce the size of the cache memory versus a regular cache. This reduction is possible thanks to a genetic algorithm that selects the set of instructions that have to be locked in cache to provide the maximum cache size minimization while keeping the system schedulable., This work is partially supported by PAID-06-11/2055 of Universitat Politècnica de València and TIN2011-28435-C03-01 of Ministerio de Ciencia e Innovación.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

LUT saving in embedded FPGAs for cache locking in real-time systems

  • Martí-Campoy, Antonio|||0000-0002-6009-8703
  • Rodríguez-Ballester, Francisco|||0000-0002-4087-5077
  • Ors Carot, Rafael|||0000-0003-2787-4683
[EN] In recent years, cache locking have appeared as a solution to ease the schedulability analysis of real-time systems using cache memories maintaining, at the same time, similar performance improvements than regular cache memories. New devices for the embedded market couple a processor and a programmable logic device designed to enhance system flexibility and increase the possibilities of customisation in the field. This arrangement may help to improve the use of cache locking in real-time systems. This work proposes the use of this embedded programmable logic device to implement a logic function that provides the cache controller the information it needs in order to determine if a referenced main memory block has to be loaded and locked into the cache; we have called this circuit a Locking State Generator. Experiments show the requirements in terms of number of hardware resources and a way to reduce them and the circuit complexity. This reduction ranges from 50% up to 80% of the number of hardware resources originally needed to build the Locking State Generator circuit., This work has been partially supported by PAID-06-11/2055 of Universitat Politecnica de València and TIN2011-28435- C03-01 of Ministerio de Ciencia e Innovacion.