• DocumentCode
    639329
  • Title

    Vectorization past dependent branches through speculation

  • Author

    Menezo, Lucia G. ; Puente, Valentin ; Gregorio, Jose Angel

  • Author_Institution
    Univ. of Cantabria, Santander, Spain
  • fYear
    2013
  • fDate
    7-11 Sept. 2013
  • Firstpage
    353
  • Lastpage
    362
  • Abstract
    This paper introduces a new coherence protocol that addresses the challenges of complex multilevel cache hierarchies in future many-core systems. In order to keep coherence protocol complexity bounded, inclusiveness is required to track coherence information across levels in this type of systems, but this might introduce unsustainable costs for directory structures. Cost reduction decisions taken to reduce this complexity may introduce artificial inefficiencies in the on-chip cache hierarchy, especially when the number of cores and private caches size is large. The coherence protocol presented in this work, denoted MOSAIC, introduces a new approach to tackle this problem. In energy terms, the protocol scales like a conventional directory coherence protocol, but relaxes the shared information inclusiveness. This allows the performance implications of directory size and associativity reduction to be overcome. Contrary to the common belief that inclusiveness is inescapable when attempting to maintain complexity constrained, MOSAIC is even simpler than a conventional directory. The results of our evaluation show that the approach is quite insensitive, in terms of performance and energy expenditure, to the size and associativity of the directory.
  • Keywords
    cache storage; multiprocessing systems; MOSAIC; associativity reduction; complex multilevel cache hierarchy; complex on-chip cache hierarchy; conventional directory coherence protocol; cost reduction; directory size; many-core systems; scalable coherence protocol; Bandwidth; Coherence; Complexity theory; Proposals; Protocols; System-on-chip; Vectors; IFKO; SIMD vectorization; atlas; compiler optimization; iterative compilation; speculation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Parallel Architectures and Compilation Techniques (PACT), 2013 22nd International Conference on
  • Conference_Location
    Edinburgh
  • ISSN
    1089-795X
  • Print_ISBN
    978-1-4799-1018-2
  • Type

    conf

  • DOI
    10.1109/PACT.2013.6618824
  • Filename
    6618824