Changeset 1360 for docs/HPCA2012


Ignore:
Timestamp:
Aug 23, 2011, 6:16:40 PM (8 years ago)
Author:
cameron
Message:

More abstract changes.

Location:
docs/HPCA2012
Files:
2 edited

Legend:

Unmodified
Added
Removed
  • docs/HPCA2012/00-abstract.tex

    r1358 r1360  
    11In modern applications text files are employed widely. For example,
    2 XML files provide data storage in human readable format and are widely
    3 used in applications ranging from database systems to mobile phone
     2XML files provide data storage in human readable format and are
     3ubiquitous in applications ranging from database systems to mobile phone
    44SDKs.  Traditional text processing tools are built around a
    55byte-at-a-time processing model where each character token of a
     
    2121In this paper, we enable text processing applications to effectively
    2222use commodity processors. We introduce Parabix (Parallel Bitstream)
    23 technology, a software runtime and execution model that allows
     23technology, a software toolkit and execution framework that allows
    2424applications to exploit modern SIMD instructions extensions for high
    2525performance text processing. Parabix enables the application developer
     
    3131then enables us to operate on multiple characters with single
    3232bit-parallel SIMD operators. We demonstrate the features and
    33 efficiency of parabix with a XML parsing application. We evaluate a
     33efficiency of Parabix with a XML parsing application. We evaluate a
    3434Parabix-based XML parser against two widely used XML parsers, Expat
    3535and Apache's Xerces, and across three generations of x86 processors,
     
    4141improvements across Intel processor generations, culminating with a
    4242look at the latest 256-bit AVX technology in \SB{} versus the now
    43 legacy 128-bit SSE technology. Finally, we partition the XML
     43legacy 128-bit SSE technology. We also examine Parabix on mobile platforms
     44using ARM processors with Neon SIMD extensions.  Finally, we partition the XML
    4445program into pipeline stages and demonstrate that thread-level
    4546parallelism exploits SIMD units scattered across the different cores
Note: See TracChangeset for help on using the changeset viewer.