Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Skew-Resistant Parallel Processing of Feature-Extracting Scientific User-Defined Functions
 

Summary: Skew-Resistant Parallel Processing of Feature-Extracting
Scientific User-Defined Functions
YongChul Kwon, Magdalena Balazinska,
Bill Howe
University of Washington
{yongchul,magda,billhowe}@cs.washington.edu
Jerome Rolia
HP Labs
jerry.rolia@hp.com
ABSTRACT
Scientists today have the ability to generate data at an un-
precedented scale and rate and, as a result, they must in-
creasingly turn to parallel data processing engines to per-
form their analyses. However, the simple execution model
of these engines can make it difficult to implement efficient
algorithms for scientific analytics. In particular, many sci-
entific analytics require the extraction of features from data
represented as either a multidimensional array or points in
a multidimensional space. These applications exhibit sig-
nificant computational skew, where the runtime of different

  

Source: Anderson, Richard - Department of Computer Science and Engineering, University of Washington at Seattle

 

Collections: Computer Technologies and Information Sciences