Chinese algorithm claimed to boost Nvidia GPU performance by up to 800X for advanced science applications | Tom’s Hardware

Researchers from Shenzhen MSU-BIT University developed a new computational algorithm that significantly enhances the efficiency of peridynamics simulations, a non-local theory used to model fractures and material damage. The algorithm, implemented on Nvidia GPUs, achieves up to 800x speed gains, enabling faster and more accessible simulations for material science, engineering, and defense applications. This breakthrough reduces reliance on foreign technology and has broad implications for industries requiring detailed material analysis.

*****
Written on