Accelerating Stencil Computations on a GPU by Combining Using Tensor Cores and Temporal Blocking
Futa Kambe, Toshio Endo · 2024
Stencil computations, which approximate differential equations in simulations, are important computations in high-performance computing. One of speed-up techniques is called temporal blocking, which reduces memory access by advancing computations of several time steps locally at a time. In addition, recent GPUs are equipped with units such as tensor cores that specialize in matrix operations, and there is a research project TCStencil, which applies them to stencil computations.