Abstract
Microwave Imaging (MI) for biomedical applications has attracted attention due to its harmless radiation compared to X-ray or MRI. One of the commonly used computing methods in MI is Finite Difference Time Domain (FDTD), which is executed several times in iterative loops, hence resulting in a high execution time. Although several hardware accelerators for FDTD have been recently introduced, they are not specifically designed for MI applications. In particular, only simple absorbing boundary conditions have been investigated, and the impact of dispersive materials on FDTD has not been considered. In this paper, we propose a multi-FPGA accelerator for 3D FDTD that is integrated in an MI algorithm, with Convolutional Perfectly Matched Layer (CPML) boundary conditions and an exact model for dispersive materials. By using High Level Synthesis (HLS), we obtain an optimized hardware accelerator that uses an efficient blocking method to reduce the data transfer time between external and local memories. We propose two alternative architectures that trade off performance and resource usage. In addition, our code, being developed at a high level, can also be run on GPUs whenever necessary. The results show that our multi-FPGA accelerator is superior to three similar GPU-based designs in terms of execution time and power consumption.
Highlights
M ICROWAVE Imaging (MI) uses microwaves emitted and captured by several antennas to create an image of the inner dielectric profile of an object
We developed a 3D Finite Difference Time Domain (FDTD) accelerator using a high-level approach, so that the code can be both implemented in FPGA using a High-Level Synthesis (HLS) flow, or changed to be executed in a GPU
Before reporting the performance results obtained on this FPGA, we briefly discuss the accuracy of the C++ code in comparison to the Acceleware code
Summary
M ICROWAVE Imaging (MI) uses microwaves emitted and captured by several antennas to create an image of the inner dielectric profile of an object. It has attracted attention among biomedical researchers due to its low-cost, non-ionizing and non-invasive characteristics. Non-linear approaches solve the inverse problem by updating the dielectric estimation iteratively, which results in a high execution time. Starting from an initial guess of the dielectric profile, the forward solver, often implemented using the Finite Difference Time Domain (FDTD) approach [5], computes the electromagnetic fields. The output of the forward solver is compared with the actual microwave measurements and, based on the error, the dielectric profile is updated with a specific inverse scattering algorithm.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
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.