Horizon: A Multi-abstraction Framework for Graph Analytics
Authors: A. Haider, F. Checconi, X. Que, L. Schneidenbach, D. Buono, X.-H. Sun
Date: May, 2018
Venue: The ACM International Conference on Computing Frontiers 2018 (CF'18), Italy, 2018. pp. 252-255
Type: Workshop
Abstract
In this paper we present Horizon, a distributed graph processing framework achieving close to native performance without penal- izing productivity by providing a multi-layer, multi-abstraction model of computation. Compared to current frameworks, Horizon extends the scope of computation by exposing two notions usually relegated to implementations: graph data models and communica- tion models. Horizon can reduce execution time by an average of 5.3× across different applications and datasets and process an order of magnitude larger graphs when compared to the state of the art.