A study by LightSolver, a subsidiary of CollPlant Biotechnologies Ltd., has shown the potential for photonic computing to accelerate sparse linear solvers. The research, published in the proceedings of the 23rd ACM International Conference on Computing Frontiers, titled "Accelerating Sparse Linear Solvers with an Optical Laser Processing Unit," is available via the ACM Digital Library.
The study used an emulator of LightSolver's Laser Processing Unit (LPU) architecture to project performance against established iterative algorithms running on a GPU. The research projected time-to-solution acceleration ranging from approximately 40 times to more than 80,000 times, depending on the algorithm and problem evaluated.
The joint research, conducted with the High-Performance Computing Center Stuttgart (HLRS), examined photonic computing performance for solving large-scale sparse systems of linear equations. These systems are utilized in scientific and engineering simulations, including computational fluid dynamics, structural mechanics, electromagnetics, molecular dynamics, and materials science.
Prof. Michael Resch, Director of HLRS, stated: "This joint work demonstrates how an emerging photonic computing architecture can be evaluated against established numerical methods and modern GPU platforms. The results provide valuable insight into where photonic computing may offer advantages for high-performance computing workloads and how it could be integrated into future hybrid computing systems."
Dr. Ruti Ben-Shlomi, CEO and Co-Founder of LightSolver, noted that the research marks a milestone in validating the LPU as a computing layer alongside traditional CPUs and GPUs. CollPlant operates in deep-tech computing via LightSolver and in regenerative medicine through plant-derived recombinant human collagen technologies.
