Analysis, optimization and application of GPGPU-accelerated high-intensity focused ultrasound simulations including heterogeneous tissue properties

NVIDIA has incorporated Tensor Cores into its newer generations of graphics cards. These enable the acceleration of matrix-matrix multiplications, which are popular in data science and simulation applications. We are using this technology to accelerate an interactive HIFU simulation software to minimize treatment time for patients under anaesthesia. HIFU is a new, modern, and non-invasive therapeutic approach for treating a variety of pathologies. Many of these applications require simulation to avoid risks and unnecessary damage. We implement our improvements in C++ using CUDA and measure up to a halving of runtime. Additionally, we find numerous difficulties such as limited memory and memory bandwidth and try to work around them.