Applying Skeletal Parallel Programming to Non-numeric Computation on Unstructured Data

2014 Fiscal Year Final Research Report

• Project/Area Number: 24700025
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Software
• Research Institution: Kyushu Institute of Technology (2013-2014); The University of Tokyo (2012)
• Principal Investigator: EMOTO Kento 九州工業大学, 大学院情報工学研究院, 助教 (00587470)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 並列プログラミング / スケルトン / グラフ

Outline of Final Research Achievements

This research developed programming methods to ease making efficient programs dealing with large data such as road networks and social networks, in which, for example, programs will find (the best) portions that match with given conditions. The main results of this research are the extension of the Generate-Test-Aggregate programming paradigm to more general data structures, the development of framework for mechanical proof of correctness of the programming transformations via proof assistant software, and the combination of existing different methods for flexibility and performance improvements for shortest-path problems.

Free Research Field

計算機科学