For the current REF see the REF 2021 website REF 2021 logo

Output details

11 - Computer Science and Informatics

Queen Mary University of London

Return to search Previous output Next output
Output 29 of 83 in the submission
Output title

HAWKEYE: effective discovery of dataflow impediments to parallelization.

Type
E - Conference contribution
Name of conference/published proceedings
OOPSLA
Volume number
-
Issue number
-
First page of article
207
ISSN of proceedings
-
Year of publication
2011
Number of additional authors
3
Additional information

<10>This paper presents a mechanism that can significantly speed up programs that depend heavily on access to remote data. The system works by rewriting Java bytecode to produce a related program that executes in parallel to the original, prefetching and caching remote data that might be required. Sprint system that implements this mechanism was applied to automatically improve the performance of several real-world Java programs that access remote databases (MySQL, DB2) and web services (Facebook, IBM’s Yellow Pages). IBM filed a US Patent Application (USSN: 13/645,032) to cover this work.

Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
3
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-