This Title All WIREs
How to cite this WIREs title:
WIREs Data Mining Knowl Discov
Impact Factor: 7.250

A survey on graphic processing unit computing for large‐scale data mining

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

General purpose computation using Graphic Processing Units (GPUs) is a well‐established research area focusing on high‐performance computing solutions for massively parallelizable and time‐consuming problems. Classical methodologies in machine learning and data mining cannot handle processing of massive and high‐speed volumes of information in the context of the big data era. GPUs have successfully improved the scalability of data mining algorithms to address significantly larger dataset sizes in many application areas. The popularization of distributed computing frameworks for big data mining opens up new opportunities for transformative solutions combining GPUs and distributed frameworks. This survey analyzes current trends in the use of GPU computing for large‐scale data mining, discusses GPU architecture advantages for handling volume and velocity of data, identifies limitation factors hampering the scalability of the problems, and discusses open issues and future directions. WIREs Data Mining Knowl Discov 2018, 8:e1232. doi: 10.1002/widm.1232 This article is categorized under: Technologies > Computer Architectures for Data Mining Technologies > Machine Learning Technologies > Computational Intelligence
Graphic processing unit (GPU) architecture, multi‐GPU, and distributed‐GPU scalability.
[ Normal View | Magnified View ]
MapReduce architecture in a multi‐graphic processing unit (GPU) system.
[ Normal View | Magnified View ]
Summary performance chart for techniques and applications.
[ Normal View | Magnified View ]
Model and data parallelism in deep learning.
[ Normal View | Magnified View ]
Neural network architecture, activation function, and neuron weight updates.
[ Normal View | Magnified View ]
Support vector machine (SVM) formulation and matrix vector multiplication.
[ Normal View | Magnified View ]
Decision tree encoding in graphic processing unit linear memory.
[ Normal View | Magnified View ]
Intrarule parallelization in genetic programming.
[ Normal View | Magnified View ]
Distance matrices for k nearest neighbor (KNN) local and incremental neighborhood selection.
[ Normal View | Magnified View ]
(a) Binary radix tree and (b) parallel support reduction.
[ Normal View | Magnified View ]
Parallel pairwise distance computation and centroid‐based clustering.
[ Normal View | Magnified View ]
Compute unified device architecture (CUDA) example for pairwise Euclidean distances computation on graphic processing units.
[ Normal View | Magnified View ]
Compute unified device architecture (CUDA) threads and blocks multidimensional programming model.
[ Normal View | Magnified View ]

Related Articles

Top Ten WIDM Articles

Browse by Topic

Technologies > Computational Intelligence
Technologies > Machine Learning
Technologies > Computer Architectures for Data Mining

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts