用于在高性能集群上进行双向上位性检验的快速线性混合模型（FaST-LMM）

FaST-LMM for Two-Way Epistasis Tests on High-Performance Clusters.

作者信息

Martínez Héctor, Barrachina Sergio, Castillo Maribel, Quintana-OrtÍ Enrique S, Rambla de Argila Jordi, Farré Xavier, Navarro Arcadi

机构信息

1 Department of Computer Science and Engineering, Jaume I University , Castellón, Spain .

2 Department of Experimental and Health Sciences, Pompeu Fabra University , Barcelona, Spain .

出版信息

J Comput Biol. 2018 Aug;25(8):862-870. doi: 10.1089/cmb.2018.0087. Epub 2018 Jul 18.

DOI:10.1089/cmb.2018.0087

PMID:30020811

Abstract

We introduce a version of the epistasis test in FaST-LMM for clusters of multithreaded processors. This new software maintains the sensitivity of the original FaST-LMM while delivering acceleration that is close to linear on 12-16 nodes of two recent platforms, with respect to improved implementation of FaST-LMM presented in an earlier work. This efficiency is attained through several enhancements on the original single-node version of FaST-LMM, together with the development of a message passing interface (MPI)-based version that ensures a balanced distribution of the workload as well as a multigraphics processing unit (GPU) module that can exploit the presence of multiple GPUs per node.

摘要

我们在适用于多线程处理器集群的FaST-LMM中引入了一种上位性测试版本。这个新软件在保持原始FaST-LMM灵敏度的同时，在两个最新平台的12至16个节点上实现了接近线性的加速，这得益于早期工作中对FaST-LMM的改进实现。这种效率是通过对原始单节点版本的FaST-LMM进行多项改进，以及开发基于消息传递接口（MPI）的版本（确保工作负载均衡分配）和一个能够利用每个节点多个图形处理单元（GPU）的多GPU模块来实现的。