Texas A&M University LibrariesTexas A&M University LibrariesTexas A&M University Libraries
    • Help
    • Login
    OAKTrust
    View Item 
    •   OAKTrust Home
    • Colleges and Schools
    • Office of Graduate and Professional Studies
    • Electronic Theses, Dissertations, and Records of Study (2002– )
    • View Item
    •   OAKTrust Home
    • Colleges and Schools
    • Office of Graduate and Professional Studies
    • Electronic Theses, Dissertations, and Records of Study (2002– )
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Multithreading Aware Hardware Prefetching for Chip Multiprocessors

    Thumbnail
    View/Open
    ALBARAKAT-THESIS-2017.pdf (858.6Kb)
    Date
    2017-07-28
    Author
    Albarakat, Laith Mohammad
    Metadata
    Show full item record
    Abstract
    To take advantage of the processing power in the Chip Multiprocessors design, applications must be divided into semi-independent processes that can run concur- rently on multiple cores within a system. Therefore, programmers must insert thread synchronization semantics (i.e. locks, barriers, and condition variables) to synchro- nize data access between processes. Indeed, threads spend long time waiting to acquire the lock of a critical section. In addition, a processor has to stall execution to wait for load data accesses to complete. Furthermore, there are often independent instructions which include load instructions beyond synchronization semantics that could be executed in parallel while a thread waits on the synchronization semantics. The conveniences of the cache memories come with some extra cost in Chip Multiprocessors. Cache Coherence mechanisms address the Memory Consistency problem. However, Cache Coherence adds considerable overhead to memory accesses. Having aggressive prefetcher on different cores of a Chip Multiprocessor can definitely lead to significant system performance degradation when running multi-threaded applications. This result of prefetch-demand interference when a prefetcher in one core ends up pulling shared data from a producing core before it has been written, the cache block will end up transitioning back and forth between the cores and result in useless prefetch, saturating the memory bandwidth and substantially increase the latency to critical shared data. We present a hardware prefetcher that enables large performance improvements from prefetching in Chip Multiprocessors by significantly reducing prefetch-demand interference. Furthermore, it will utilize the time that a thread spends waiting on syn- chronization semantics to run ahead of the critical section to speculate and prefetch independent load instruction data beyond the synchronization semantics.
    URI
    http://hdl.handle.net/1969.1/165781
    Subject
    prefetcher
    Collections
    • Electronic Theses, Dissertations, and Records of Study (2002– )
    Citation
    Albarakat, Laith Mohammad (2017). Multithreading Aware Hardware Prefetching for Chip Multiprocessors. Master's thesis, Texas A & M University. Available electronically from http : / /hdl .handle .net /1969 .1 /165781.

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Advanced Search

    Browse

    All of OAKTrustCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsDepartmentThis CollectionBy Issue DateAuthorsTitlesSubjectsDepartment

    My Account

    LoginRegister

    Statistics

    View Usage Statistics
    Help and Documentation

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV