HyPar: A divide-and-conquer model for hybrid CPU-GPU graph processing

Panja, Rintu and Vadhiyar, Sathish S (2019) HyPar: A divide-and-conquer model for hybrid CPU-GPU graph processing. In: JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 132 . pp. 8-20.

PDF Jou_par_dis_com_132_8_2019.pdf - Published Version Restricted to Registered users only Download (828kB) | Request a copy

Abstract

Efficient processing of graph applications on heterogeneous CPU-GPU systems require effectively harnessing the combined power of both the CPU and GPU devices. This paper presents HyPar, a divide-and-conquer model for processing graph applications on hybrid CPU-GPU systems. Our strategy partitions the given graph across the devices and performs simultaneous independent computations on both the devices. The model provides a simple and generic API, supported with efficient runtime strategies for hybrid executions. The divide-and-conquer model is demonstrated with five graph applications and using experiments with these applications on a heterogeneous system it is shown that our HyPar strategy provides equivalent performance to the state-of-art, optimized CPU-only and GPU-only implementations of the corresponding applications. When compared to the prevalent BSP approach for multi-device executions of graphs, our HyPar method yields 74%-92% average performance improvements.

Item Type:	Journal Article
Publication:	JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING
Publisher:	ACADEMIC PRESS INC ELSEVIER SCIENCE
Additional Information:	copyright for this article belongs to ACADEMIC PRESS INC ELSEVIER SCIENCE
Keywords:	Graph algorithms; Hybrid CPU-GPU; Divide-and-conquer
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	12 Sep 2019 10:38
Last Modified:	12 Sep 2019 10:38
URI:	http://eprints.iisc.ac.in/id/eprint/63389

Actions (login required)

View Item