2/5/2025 | 11:00 AM - 12:20 PM | Regency A

High-performance tomographic imaging powered by tensor-core and PTX assembly

Author(s)

Du Wu | RIKEN-CCS
Peng Chen | National Institute of Advanced Industrial Science and Technology
Xiao Wang | Oak Ridge National Laboratory
Issac Lyngaas | Oak Ridge National Laboratory
Takaaki Miyajima | Meiji University
Toshio Endo | Tokyo Institute of Technology
Satoshi Matsuoka | RIKEN-CCS
Mohamed Wahib | RIKEN-CCS

Abstract

Computed Tomography (CT) serves as a key imaging technology that relies on computationally intensive filtering and back-projection algorithms for 3D image reconstruction. While conventional high-resolution image reconstruction (> 2𝐾³) solutions provide quick results, they typically treat reconstruction as an offline workload to be performed remotely on large-scale HPC systems. The growing demand for post-construction AI-driven analytics and the need for real-time adjustments call for high-resolution reconstruction solutions that are feasible on local computing resources, i.e. on a single GPU server. In this paper, we propose a novel approach that utilizes Tensor Cores to optimize image reconstruction without sacrificing precision. Evaluations conducted on a single Nvidia A100 and H100 GPU show performance improvements of 1.91× and 2.15× compared to highly optimized production libraries.