A Fully-Pipelined Hardware Design for Gaussian Mixture Models

File Description SizeFormat 
tc17ch.pdfAccepted version794.74 kBAdobe PDFView/Open
Title: A Fully-Pipelined Hardware Design for Gaussian Mixture Models
Authors: He, C
Fu, H
Guo, C
Luk, W
Yang, G
Item Type: Journal Article
Abstract: Gaussian Mixture Models (GMMs) are widely used in many applications such as data mining, signal processing and computer vision, for probability density modeling and soft clustering. However, the parameters of a GMM need to be estimated from data by, for example, the Expectation-Maximization algorithm for Gaussian Mixture Models (EM-GMM), which is computationally demanding. This paper presents a novel design for the EM-GMM algorithm targeting reconfigurable platforms, with five main contributions. First, a pipeline-friendly EM-GMM with diagonal covariance matrices that can easily be mapped to hardware architectures. Second, a function evaluation unit for Gaussian probability density based on fixed-point arithmetic. Third, our approach is extended to support a wide range of dimensions or/and components by fitting multiple pieces of smaller dimensions onto an FPGA chip. Fourth, we derive a cost and performance model that estimates logic resources. Fifth, our dataflow design targeting the Maxeler MPCX2000 with a Stratix-5SGSD8 FPGA can run over 200 times faster than a 6-core Xeon E5645 processor, and over 39 times faster than a Pascal TITAN-X GPU. Our design provides a practical solution to applications for training and explores better parameters for GMMs with hundreds of millions of high dimensional input instances, for low-latency and high-performance applications.
Issue Date: 5-Jun-2017
Date of Acceptance: 1-May-2017
URI: http://hdl.handle.net/10044/1/56380
DOI: https://dx.doi.org/10.1109/TC.2017.2712152
ISSN: 0018-9340
Publisher: Institute of Electrical and Electronics Engineers
Start Page: 1837
End Page: 1850
Journal / Book Title: IEEE Transactions on Computers
Volume: 66
Issue: 11
Copyright Statement: © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Engineering & Physical Science Research Council (EPSRC)
Engineering & Physical Science Research Council (E
Commission of the European Communities
Engineering & Physical Science Research Council (E
Funder's Grant Number: EP/I012036/1
PO 1553380
671653
516075101 (EP/N031768/1)
Keywords: Science & Technology
Technology
Computer Science, Hardware & Architecture
Engineering, Electrical & Electronic
Computer Science
Engineering
Gaussian mixture model
expectation maximization
high performance computing
data flow engine
reconfigurable hardware
algorithms implemented in hardware
INDEPENDENT SPEAKER IDENTIFICATION
SEGMENTATION
ALGORITHM
Science & Technology
Technology
Computer Science, Hardware & Architecture
Engineering, Electrical & Electronic
Computer Science
Engineering
Gaussian mixture model
expectation maximization
high performance computing
data flow engine
reconfigurable hardware
algorithms implemented in hardware
INDEPENDENT SPEAKER IDENTIFICATION
SEGMENTATION
ALGORITHM
0803 Computer Software
0805 Distributed Computing
1006 Computer Hardware
Computer Hardware & Architecture
Publication Status: Published
Appears in Collections:Faculty of Engineering
Computing



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx