Ignore:
Timestamp:
Nov 2, 2011, 8:32:44 PM (7 years ago)
Author:
ksherdy
Message:

Minor edit. Prefer 128-bit over 128 bit, 256-bit over 256 bit.

File:
1 edited

Legend:

Unmodified
Added
Removed
  • docs/HPCA2012/11-conclusions.tex

    r1421 r1652  
    1515parallelism in their application assuming an infinite resource
    1616abstract SIMD machine without worrying about or having to change code
    17 to handle processor specifics (e.g., 128 bit SIMD SSE vs 256 bit SIMD
     17to handle processor specifics (e.g., 128-bit SIMD SSE vs 256-bit SIMD
    1818on AVX). We applied Parabix technology to a widely deployed
    1919application; XML parsing and demonstrate the efficiency gains that can
     
    29293-operand instructions deliver significant benefit the wider
    3030operations in some cases have higher overheads compared to the
    31 existing 128 bit SSE operations. We also compare Intel's SIMD
     31existing 128-bit SSE operations. We also compare Intel's SIMD
    3232extensions against the ARM \NEON{}. Note that Parabix allowed us to
    3333perform these studies without having to change the application source.
Note: See TracChangeset for help on using the changeset viewer.