Parallel visual data restoration on multi-GPGPUs using stencil-reduce pattern
- 17 February 2015
- journal article
- research article
- Published by SAGE Publications in The International Journal of High Performance Computing Applications
- Vol. 29 (4) , 461-472
Abstract
In this paper, a highly effective parallel filter for visual data restoration is presented. The filter is designed following a skeletal approach, using a newly proposed stencil-reduce, and has been implemented by way of the FastFlow parallel programming library. As a result of its high-level design, it is possible to run the filter seamlessly on a multicore machine, on multi-GPGPUs, or on both. The design and implementation of the filter are discussed, and an experimental evaluation is presented.Keywords
This publication has 23 references indexed in Scilit:
- StarPU: a unified platform for task scheduling on heterogeneous multicore architecturesConcurrency and Computation: Practice and Experience, 2010
- A survey of algorithmic skeleton frameworks: high‐level structured parallel programming enablersSoftware: Practice and Experience, 2010
- Fast Two-Phase Image Deblurring Under Impulse NoiseJournal of Mathematical Imaging and Vision, 2009
- Minimization of a Detail-Preserving Regularization Functional for Impulse Noise RemovalJournal of Mathematical Imaging and Vision, 2007
- A Variational Method with a Noise Detector for Impulse Noise Removal2007
- A new adaptive center weighted median filter for suppressing impulsive noise in imagesInformation Sciences, 2007
- Regularizing Flows for Constrained Matrix-Valued ImagesJournal of Mathematical Imaging and Vision, 2004
- Fast, robust total variation-based reconstruction of noisy, blurred imagesIEEE Transactions on Image Processing, 1998
- Weighted median filters: a tutorialIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1996
- A fast two-dimensional median filtering algorithmIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979