• English
    • Ελληνικά
    • Deutsch
    • français
    • italiano
    • español
  • français 
    • English
    • Ελληνικά
    • Deutsch
    • français
    • italiano
    • español
  • Ouvrir une session
Voir le document 
  •   Accueil de DSpace
  • Επιστημονικές Δημοσιεύσεις Μελών ΠΘ (ΕΔΠΘ)
  • Δημοσιεύσεις σε περιοδικά, συνέδρια, κεφάλαια βιβλίων κλπ.
  • Voir le document
  •   Accueil de DSpace
  • Επιστημονικές Δημοσιεύσεις Μελών ΠΘ (ΕΔΠΘ)
  • Δημοσιεύσεις σε περιοδικά, συνέδρια, κεφάλαια βιβλίων κλπ.
  • Voir le document
JavaScript is disabled for your browser. Some features of this site may not work without it.
Tout DSpace
  • Communautés & Collections
  • Par date de publication
  • Auteurs
  • Titres
  • Sujets

An optically-enabled chip-multiprocessor architecture using a single-level shared optical cache memory

Thumbnail
Auteur
Maniotis P., Gitzenis S., Tassiulas L., Pleros N.
Date
2016
Language
en
DOI
10.1016/j.osn.2016.05.001
Sujet
Adaptive systems
Buses
Dynamic random access storage
Image coding
Memory architecture
Multiplexing
Multiprocessing systems
Program processors
Random access storage
Wavelength division multiplexing
Cache architecture
Chip Multiprocessor
Dynamic random access memory
In-chip
Interconnection systems
Shared cache
System level simulation
Wavelength division multiplexed
Cache memory
Elsevier B.V.
Afficher la notice complète
Résumé
We present an optical bus-based chip-multiprocessor architecture where the processing cores share an optical single-level cache implemented in a separate chip next to the Central-Processing-Unit (CPU) die. The interconnection system is realized through Wavelength-Division-Multiplexed optical interfaces connecting the shared cache with the cores and the Main-Memory via spatial-multiplexed waveguides. Evaluating the proposed approach, we realize system-level simulations of a wide-range parallel workloads using Gem5. Optical cache architecture is compared against the conventional one that uses dedicated on-chip Level-1 electronic caches and a shared Level-2 cache. Results show significant Level-1 miss rate reduction of up to 96% for certain cases; on average, a performance speed-up of 19.4% or cache capacity requirements reduction of 63% is attained. Combined with high-bandwidth CPU-Dynamic Random Access Memory (DRAM) bus solutions based on optical interconnects, the proposed design is a promising architecture bridging the gap between high-speed optically connected CPU-DRAM schemes and high-speed optical memory technologies. © 2016 Elsevier B.V.
URI
http://hdl.handle.net/11615/76275
Collections
  • Δημοσιεύσεις σε περιοδικά, συνέδρια, κεφάλαια βιβλίων κλπ. [19735]
htmlmap 

 

Parcourir

Tout DSpaceCommunautés & CollectionsPar date de publicationAuteursTitresSujetsCette collectionPar date de publicationAuteursTitresSujets

Mon compte

Ouvrir une sessionS'inscrire
Help Contact
DepositionAboutHelpContactez-nous
Choose LanguageTout DSpace
EnglishΕλληνικά
htmlmap