Handling large-size discrete wavelet transform on network-based computing systems - parallelization via divisible load paradigm

Authors:
Teo Tse Chin;Bharadwaj Veeravalli;Jingxi Jia
Affiliations:
DSO National Laboratories, 20 Science Park Drive, Singapore;Computer Networks and Distributed Systems (CNDS) Laboratory, Department ECE, The National University of Singapore, 4 Engineering Drive 3, Singapore;Computer Networks and Distributed Systems (CNDS) Laboratory, Department ECE, The National University of Singapore, 4 Engineering Drive 3, Singapore
Venue:
Journal of Parallel and Distributed Computing
Year:
2009

Citing 8
Cited 0

Divisible task scheduling — concept and verification

Parallel Computing - Special issue on task scheduling problems for parallel and distributed systems
Large matrix-vector products on distributed bus networks with communication delays using the divisable load paradigm: performance analysis and simulaton

Mathematics and Computers in Simulation
Scheduling Divisible Loads in Parallel and Distributed Systems

Scheduling Divisible Loads in Parallel and Distributed Systems
Ten Reasons to Use Divisible Load Theory

Computer
Scheduling Divisible Loads on Star and Tree Networks: Results and Open Problems

IEEE Transactions on Parallel and Distributed Systems
Discrete wavelet transform: data dependence analysis and synthesisof distributed memory and control array architectures

IEEE Transactions on Signal Processing
A parallel implementation of the 2-D discrete wavelet transformwithout interprocessor communications

IEEE Transactions on Signal Processing
Computing BLAS level-2 operations on workstation clusters using the divisible load paradigm

Mathematical and Computer Modelling: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

The discrete wavelet transform (DWT) is a powerful signal processing tool, but comes with a considerable computation cost. In this paper, we consider the problem of parallelizing the DWT computation on loosely-coupled networked systems. We first systematically analyze the data dependencies among DWT computations, identify the partitionable portions and then by applying the divisible load theory (DLT), we derive a novel scheduling strategy to schedule DWT computation onto bus networks. Our study is first of its kind in the DLT literature to demonstrate handling a highly coupled recursive computational nature of this problem towards gaining a significant speed-up. We conduct a wide variety of rigorous simulation experiments to quantify the performance of our strategy. Results demonstrate that using the proposed method of scheduling, the parallel DWT computation scales significantly with respect to the input signal size, with no compromise in performance observed when the input size was increased. However, the algorithm is shown to be sensitive to the speed (delay) of the communication channel.