X-ray tomography reconstruction accelerated on FPGA through High-Level Synthesis tools - Pôle Signaux Access content directly
Journal Articles IEEE Transactions on Biomedical Circuits and Systems Year : 2023

X-ray tomography reconstruction accelerated on FPGA through High-Level Synthesis tools

Daouda Diakite
Nicolas Gac

Abstract

Model-Based Iterative Reconstruction (MBIR) algorithms iteratively use expensive computational operators of forward and backward projections. The irregular memory access pattern of these operators makes them a memory-bound application. Their computation time must be reduced to meet clinical routine constraints. This paper proposes a hardware accelerator architecture based on Field Programmable Gate Arrays (FPGAs) through high-level language, as an alternative to GPU architecture. This acceleration is based on an offline memory access analysis to address the main bottleneck of the algorithm and maximize the data reuse rate. The offline analysis allows for the tuning of the architecture parameters so that they converge to an optimal solution. Then, the Berkeley Roofline model guides our optimization steps by iteratively analyzing the design performance. Our design flow significantly improved the algorithm's computational intensity and overcame the memory bottleneck. Thus, our architecture takes advantage of the FPGA local memory to achieve significant memory bandwidth and efficiently harness the pipeline without stalling the computation. Furthermore, we present the scaling-up strategy from mid-range FPGA to high-end FPGA and any concerns of portability. We used two Intel FPGA devices to implement the algorithm, and then we compared the results with our GPU implementation in terms of speedup and energy efficiency. Our experimental results show that our design has achieved better computational throughput than the works on FPGA architectures reported in the literature.
Fichier principal
Vignette du fichier
IEEE-TBSC-2023.pdf (3.11 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04021970 , version 1 (19-03-2023)

Identifiers

Cite

Daouda Diakite, Nicolas Gac. X-ray tomography reconstruction accelerated on FPGA through High-Level Synthesis tools. IEEE Transactions on Biomedical Circuits and Systems, 2023, pp.1-14. ⟨10.1109/TBCAS.2023.3258879⟩. ⟨hal-04021970⟩
113 View
54 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More