Abstract
AbstractCone‐beam X‐ray computed tomography (CT) is attracting increasing attention due to its applications in medicine, biomedical sciences, material engineering, and non‐destructive industrial evaluation. Rapid volumetric image reconstruction is highly desirable in all these fields for prompt visualization and analysis of complex structures of interest. However, in most applications, volumetric image reconstruction is still a very demanding computational task. The Cell Broadband Engine architecture (CBEA) is a novel microprocessor architecture designed to provide power‐efficient and cost‐effective high‐performance processing for some of the world's most demanding applications, including next generation game consoles. Applications that show special promise of benefiting from CBEA are medical imaging, security and surveillance, digital media, entertainment, communications, and certain scientific workloads. We believe that the CBEA is a good vehicle for processing 3D CT image reconstructions because it has the capability of reaching 200 Gfps. We implemented 3D CT image reconstruction on the CBEA. However, the programming scheme of the CBEA is different from single‐core architectures. To archive peak performance on the CBEA, coding optimizations are needed to exploit the unique features of the hardware. In this paper, we describe the parallelization of the 3D image reconstruction algorithm on the CBEA. The results show that the CBEA can achieve significant run time savings. Copyright © 2009 John Wiley & Sons, Ltd.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: International Journal of Adaptive Control and Signal Processing
Disclaimer: 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.