Output details
11 - Computer Science and Informatics
Lancaster University
Output title
Mapping parallelism to multi-cores: a machine learning based approach
Type
E - Conference contribution
Name of conference/published proceedings
Proceedings of the 14th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming (PPoPP '09)
Volume number
-
Issue number
-
First page of article
75
ISSN of proceedings
-
Year of publication
2009
Number of additional authors
1
Additional information
<08> First work world-wide to show how machine learning can determine scheduling policies that can both port automatically across different multi-core platforms and outperform all existing prior work. Published in PPoPP, a world-leading venue in parallel computing, as one of only 26 papers accepted from 109 submissions (23.8%). Significant influence in the field as reflected in citations, and also taught in compiler courses at top universities including Carnegie Mellon University.
Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
25
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-