Changeset 1088 for docs/PACT2011


Ignore:
Timestamp:
Apr 8, 2011, 5:36:57 PM (8 years ago)
Author:
ksherdy
Message:

Minor edits.

File:
1 edited

Legend:

Unmodified
Added
Removed
  • docs/PACT2011/00-abstract.tex

    r1040 r1088  
    11XML is a data format designed for documents as well as the
    2 representation of data structures. The simplicity and generality of
     2representation of data structures.  The simplicity and generality of
    33the rules make it widely used in web services and database
    4 systems. Traditional XML parsers have been built around the
     4systems.  Traditional XML parsers have been built around the
    55byte-at-a-time model, in which they process every character token in
    66the file in a sequential fashion.  Unfortunately, the byte-at-time
     
    1515The first generation Parabix1 parser then uses bit-scan instructions
    1616over these streams to make multibyte moves in an otherwise sequential
    17 approach.   The second generation Parabix2 technology adds further
     17approach.  The second generation Parabix2 technology adds further
    1818parallelism by replacing much of the sequential
    1919bit scanning with a parallel scanning approach based on bit-stream
    20 addition.    We evaluate Parabix1 and Parabix2
    21 against two widely-used XML parsers, James Clark's Expat and Apache's Xerces-C
     20addition.  We evaluate Parabix1 and Parabix2
     21against two widely-used XML parsers, James Clark's Expat and Apache's Xerces
    2222on three generations of x86 machines, including the new Intel
    23 \SB{}.    We show that Parabix2's speedup is 2$\times$--7$\times$
     23\SB{}.  We show that Parabix2's speedup is 2$\times$--7$\times$
    2424over Expat and Xerces.  In stark contrast to the energy expenditures necessary
    2525to realize performance gains through multicore parallelism, we also show
    2626that our Parabix parsers deliver energy savings directly in proportion
    27 to performance gains.   We also assess the scalability advantages
     27to performance gains.  We also assess the scalability advantages
    2828of SIMD processor improvements the different Intel machine generations,
    2929culminating with an evaluation of the 256-bit AVX technology in
Note: See TracChangeset for help on using the changeset viewer.