GRAPE: Conducting Parallel Graph Computations without Developing Parallel Algorithms

Wenfei Fan, Jingbo Xu, Xiaojian Luo, Yinghui Wu, Wenyuan Yu, Ruiqi Xu

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

Developing parallel graph algorithms with correctness guarantees is nontrivial even for experienced programmers. Is it possible to parallelize existing sequential graph algorithms, without recasting the algorithms into a parallel model? Better yet, can the parallelization guarantee to converge at correct answers as long as the sequential algorithms provided are correct? GRAPE tackles these questions, to make parallel graph computations accessible to a large group of users. This paper presents (a) the parallel model of GRAPE, based on partial evaluation and incremental computation, and (b) a performance study, showing that GRAPE achieves performance comparable to the state-of-the-art systems.
Original languageEnglish
Pages (from-to)30-41
Number of pages12
JournalIEEE Data Engineering Bulletin
Issue number3
Publication statusPublished - 30 Sept 2017


Dive into the research topics of 'GRAPE: Conducting Parallel Graph Computations without Developing Parallel Algorithms'. Together they form a unique fingerprint.

Cite this