A GPU-Based Gibbs Sampler for a Unidimensional IRT Model. (30th October 2014)

• Record Type: Journal Article
• Authors: Sheng, Yanyan; Welling, William S.; Zhu, Michelle M.
• Other Names: Tohka Jussi Academic Editor.
• Is Part Of: ISRN obstetrics and gynecology. Volume 2014(2014)
• Publication Date: 2014-10-30
• Subjects: Obstetrics -- Periodicals; Gynecology -- Periodicals; Pregnancy Complications; Genital Diseases, Female; Gynecology; Obstetrics; Electronic journals; Periodical; Periodicals; Fulltext; Internet Resources; Periodicals; 618.2
• DOI: 10.1155/2014/368149
• Languages: English
• ISSNs: 2090-4436

Abstract

Abstract : Item response theory (IRT) is a popular approach used for addressing large-scale statistical problems in psychometrics as well as in other fields. The fully Bayesian approach for estimating IRT models is usually memory and computationally expensive due to the large number of iterations. This limits the use of the procedure in many applications. In an effort to overcome such restraint, previous studies focused on utilizing the message passing interface (MPI) in a distributed memory-based Linux cluster to achieve certain speedups. However, given the high data dependencies in a single Markov chain for IRT models, the communication overhead rapidly grows as the number of cluster nodes increases. This makes it difficult to further improve the performance under such a parallel framework. This study aims to tackle the problem using massive core-based graphic processing units (GPU), which is practical, cost-effective, and convenient in actual applications. The performance comparisons among serial CPU, MPI, and compute unified device architecture (CUDA) programs demonstrate that the CUDA GPU approach has many advantages over the CPU-based approach and therefore is preferred.