CISUC

GPUMLib: An Efficient Open-Source GPU Machine Learning Library

Authors

Abstract

Graphics Processing Units (GPUs) placed at our disposal an unprecedented computational-power that largely surpasses the performance of cutting-edge CPUs (Central Processing Units). The high-parallelism inherent to the GPU makes this device especially well-suited to address Machine Learning (ML) problems with prohibitively computational intensive tasks. Nevertheless, few ML algorithms have been implemented on the GPU and most are not openly shared, posing difficulties to researchers and engineers aiming to develop GPU-based systems. To
mitigate this problem, we propose the creation of an open source GPU Machine Learning Library (GPUMLib) that aims to provide the building blocks for the development of efficient GPU ML software. Experimental results on benchmark datasets show that the algorithms already implemented yield significant time savings over CPU counterparts.

Journal

International Journal of Computer Information Systems and Industrial Management Applications, Vol. 3, pp. 355-362, K. Saeed, A. Abraham, February 2011

Cited by

Year 2016 : 2 citations

 Huang, W. B., & Sun, F. C. (2016). Building feature space of extreme learning machine with sparse denoising stacked-autoencoder. Neurocomputing, 174, 60-71.

 Mi, P. (2016). GPU Based Methods for Interactive Information Visualization of Big Data (Doctoral dissertation, Virginia Tech).

Year 2015 : 4 citations

 Dong, Y., Xue, M., Zheng, X., Wang, J., Qi, Z., & Guan, H. (2015). Boosting GPU virtualization performance with hybrid shadow page tables. In 2015 USENIX Annual Technical Conference (USENIX ATC 15) (pp. 517-528).

 Smithrud, J. M., McElroy, P., & Andonie, R. (2015). Massively Parallel kNN using CUDA on Spam-Classification. In MAICS (pp. 175-180).

 Ashari, A., Tatikonda, S., Boehm, M., Reinwald, B., Campbell, K., Keenleyside, J., & Sadayappan, P. (2015, January). On optimizing machine learning workloads via kernel fusion. In ACM SIGPLAN Notices (Vol. 50, No. 8, pp. 173-182). ACM.

 Huang, Wen-bing, and Fu-chun Sun. "A Deep and Stable Extreme Learning Approach for Classification and Regression." Proceedings of ELM-2014 Volume 1. Springer International Publishing, 2015. 141-150.

Year 2014 : 3 citations

 Wu, Zheng Yi, "Portable GPU-Based Artificial Neural Networks For Data-Driven Modeling" (2014). Proceedings of the 11th International Conference on Hydroinformatics. CUNY Academic Works.

 Le-le Cao, W. B. H., & Sun, F. C. (2014). A Deep and Stable Extreme Learning Approach for Classification and Regression?. Proceedings of ELM-2014 Volume 1: Algorithms and Theories, 3, 141.

 Codreanu, Valeriu, et al. "Evaluating automatically parallelized versions of the support vector machine." Concurrency and Computation: Practice and Experience (2014).

Year 2013 : 1 citations

 Kumar, D. P. (2013). Intra Frame Luma Prediction using Neural Networks in HEVC (Doctoral dissertation, UNIVERSITY OF TEXAS AT ARLINGTON).

Year 2012 : 4 citations

 Comparative Study on Use of Mobile Videos in Elementary and Middle School
P Tuomi, J Multisilta - mirlabs.org

 A Distributed Data Mining Framework Accelerated with Graphics Processing Units
NL Tran, Q Dugauthier, S Skhiri - euranova.eu

 Generalized GPU-based Artificial Neural Network Surrogate Model for Extended Period Hydraulic Simulation
M Behandish, ZY Wu - ascelibrary.org

 Jansson, Karl. "Performance study of using the Direct Compute API for implementing Support vector machines on GPUs." (2012).