Paper
17 February 2012 Quantitative comparison of hardware architectures for high-speed processing in optical coherence tomography
Brian E. Applegate, Jesung Park, Esteban Carbajal, Darren Schmidt, Kalyanramu Vemishetty
Author Affiliations +
Abstract
Several factors are spurring the development of hardware and software to accomplish high-speed processing for Optical Coherence Tomography (OCT). The two most prevalent architectures incorporate either an FPGA or a GPU. While GPUs have faster clock-speed the fact an FPGA can be pipelined makes a direct comparison based simply on system specifications difficult. We have undertaken an effort to make a direct comparison on the same host and consider the total time from digitization to rendering of the image. In addition to making quantitative comparisons between the two architectures we hope to derive useful benchmarks that will inform the design of an optimal high-speed processing system.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Brian E. Applegate, Jesung Park, Esteban Carbajal, Darren Schmidt, and Kalyanramu Vemishetty "Quantitative comparison of hardware architectures for high-speed processing in optical coherence tomography", Proc. SPIE 8213, Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XVI, 821332 (17 February 2012); https://doi.org/10.1117/12.911755
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Field programmable gate arrays

Optical coherence tomography

Computing systems

Data conversion

Software development

Clocks

Computer architecture

Back to Top