Structural Recursion on Bulk Synchronous Parallelism for Efficient Large-Graph Querying

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K12011
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Multi-year Fund
• Research Field: Software
• Research Institution: National Institute of Informatics
• Principal Investigator: HU Zhenjiang 国立情報学研究所, アーキテクチャ科学研究系, 教授 (50292769)
• Co-Investigator(Kenkyū-buntansha): LI CHONG 国立情報学研究所, 大学共同利用機関等の部局等, 特任研究員 (50745312)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 大規模グラフ / 構造的再帰 / グラフ問い合わせ / 並列プログラミング

Outline of Final Research Achievements

The ever-increasing size of graph data today creates a critical need for programming models that can deal with large graph efficiently. In this research, we proposed a novel solution to efficient large-graph querying, by combining the expressive power of structural recursion with Pregel, a popular system based on Bulk Synchronous Parallelism for large scale graph processing. We showed that any decomposible structural recursion can be efficiently mapped to Pregel, based on which, we succeeded in parallelization of UnQL, a declarative graph query language. Moreover, we designed and implemented a new domain specific language, called Palgel, which can support both remote reads and writes, allow programmers to use a more declarative syntax called chain access to directly read data on remote vertices, and be efficiently implemented over Pregel.

Free Research Field

計算機科学、プログラミング言語、関数プログラミング、並列プログラミング、双方向変換