k-NN Text Classification using an FPGA-Based Sparse Matrix Vector Multiplication Accelerator
| Authors | Kevin Townsend, Song Sun, Tyler Johnson, Osama Attia, Phillip Jones, and Joseph Zambreno |
|---|---|
| Type | Conference Paper |
| Published in | Proceedings of the IEEE International Conference on Electro/Information Technology (EIT) |
| Date | May 2015 |
Abstract
Text classification is an important enabling technology for a wide range of applications such as Internet search, email filtering, network intrusion detection, and data mining electronic documents in general. The k Nearest Neighbors (k-NN) text classification algorithm is among the most accurate classification approaches, but is also among the most computationally expensive. In this paper, we propose accelerating k-NN using a novel reconfigurable hardware based architecture. More specifically, we accelerate a k-NN application’s core with an FPGA-based sparse matrix vector multiplication coprocessor. On average our implementation shows a speed up factor of 15 over a naive single threaded CPU implementation of k-NN text classification for our datasets, and a speed up factor of 1.5 over a 32-threaded parallelized CPU implementation.
BibTeX
@conference{TowSun15A,
title = {k-NN Text Classification using an FPGA-Based Sparse Matrix Vector Multiplication Accelerator},
booktitle = {Proceedings of the IEEE International Conference on Electro/Information Technology (EIT)},
year = {2015},
month = may,
author = {Townsend, Kevin and Sun, Song and Johnson, Tyler and Attia, Osama and Jones, Phillip and Zambreno, Joseph}
}