Parallel Pairwise Correlation Computation On Intel Xeon Phi Clusters
School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, GA, USA
arXiv:1605.01584 [cs.DC], (5 May 2016)
@article{liu2016parallel,
title={Parallel Pairwise Correlation Computation On Intel Xeon Phi Clusters},
author={Liu, Yongchao and Pan, Tony and Aluru, Srinivas},
year={2016},
month={may},
archivePrefix={"arXiv"},
primaryClass={cs.DC}
}
Co-expression network is a critical technique for the identification of inter-gene interactions, which usually relies on all-pairs correlation (or similar measure) computation between gene expression profiles across multiple samples. Pearson’s correlation coefficient (PCC) is one widely used technique for gene co-expression network construction. However, all-pairs PCC computation is computationally demanding for large numbers of gene expression profiles, thus motivating our acceleration of its execution using high-performance computing. In this paper, we present LightPCC, the first parallel and distributed all-pairs PCC computation on Intel Xeon Phi clusters. It achieves high speed by exploring the SIMD-instruction-level and thread-level parallelism within Xeon Phis as well as accelerator-level parallelism among multiple Xeon Phis. To facilitate balanced workload distribution, we have proposed a general framework for symmetric all-pairs computation by building bijective functions between job identifier and coordinate space for the first time. We have evaluated LightPCC and compared it to the sequential C++ implementation in ALGLIB (both use double-precision floating point) using a set of gene expression datasets. Performance evaluation revealed that LightPCC runs up to 20.6 and 218.2 faster than ALGLIB by using one and 16 Xeon Phi 5110P coprocesssors, respectively. In addition, LightPCC demonstrated good parallel scalability in terms of number of Xeon Phis.
May 7, 2016 by hgpu
