HLognGP: A parallel computation model for GPU clusters. (8th April 2015)

• Record Type: Journal Article
• Authors: Lu, Fengshun; Song, Junqiang; Pang, Yufei
• Is Part Of: Concurrency and computation. Volume 27:Number 17(2015:Dec.)
• Page Start: 4880
• Page End: 4896
• Publication Date: 2015-04-08
• Subjects: parallel computation model -- GPU cluster -- heterogeneous system -- performance evaluation -- LogGP -- TH‐1A -- NPB; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.3475
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: Parallel computation model is an abstraction for the performance characteristics of parallel computers, and should evolve with the development of computational infrastructure. The heterogeneous CPU/Graphics Processing Unit (GPU) systems have been and will be important platforms for scientific computing, which introduces an urgent demand for new parallel computation models targeting this kind of supercomputers. In this research, we propose a parallel computation model called HLogn GP to abstract the computation and communication features of heterogeneous platforms like TH‐1A. All the substantial parameters of HLogn GP are in vector form and deal with the new features in GPU clusters. A simplified version HLog3 GP of the proposed model is mapped to a specific GPU cluster and verified with two typical benchmarks. Experimental results show that HLog3 GP outperforms the other two evaluated models and can well model the new particularities of GPU clusters. Copyright © 2015 John Wiley & Sons, Ltd.