Abstract
Many big data applications need to process massive images and videos, while the performance of image processing is far from reaching requirements. This paper proposes the SunwayImg, a parallel image processing library, to support image-related applications on the Sunway many-core processor as well as the Sunway TaihuLight supercomputer. The SunwayImg integrates three kinds of image algorithms: fundamental algorithms to support basic image operations on the Sunway processor, widely used image feature extraction algorithms and a typical neural network model DBN. In addition, to parallelize various kinds of image algorithms efficiently on the Sunway processor, we propose a three-tier parallelization strategy as well as fine-grained parallelization inside core-groups. Finally, we accomplish implementation of the SunwayImg and evaluate it on the Sunway TaihuLight supercomputer to verify its effectiveness and performance.
Highlights
Image processing plays an essential role in image-related applications, such as pattern recognition, content-based image retrieval, etc
1) RESTRICTED BOLTZMANN MACHINES AND DEEP BELIEF NETWORKS In order to process images in artificial neural networks, each binary image is treated as a training set which can be modeled as a two-layer network called Restricted Boltzmann Machine (RBM), in which binary pixels are connected to stochastic binary feature detectors using symmetrically weighted connections
EXPERIMENT SETUP We evaluate our SunwayImg library on the Sunway TaihuLight supercomputer and compare the performance of Deep Belief Networks (DBNs), SIFT, SURF, LBP, and SIFT algorithms with their original sequential version on CPU
Summary
Image processing plays an essential role in image-related applications, such as pattern recognition, content-based image retrieval, etc. R. Liu et al.: SunwayImg: A Parallel Image Processing Library for the Sunway Many-Core Processor has a 64KB local device memory for software management. The Sunway processor provides a different parallel programming model for the massive parallelism of the CPEs. the limitation of Sunway hardware and software environment prevents the naive adoption of an existing image library to Sunway. To overcome the above challenge, this paper proposes the SunwayImg, a parallel image processing library, to support image-related applications on the Sunway many-core processors as well as the TaihuLight supercomputer. Main characteristics of the SunwayImg are as follows: The SunwayImg is the first image processing library for the Sunway processors, which provides various kinds of image processing algorithms to upper-level applications and accelerates compute-intensive algorithms using many-core resources.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
