Technical Papers Archive

Do We Need Tensor Cores for Stencil Computations?


Authors: Qiqi Gu and Chenpeng Wu (Shanghai Jiao Tong University); Heng Shi (Shanghai Enflame Technology Co., Ltd.; Shanghai Jiao Tong University); and Jianguo Yao and Haibing Guan (Shanghai Jiao Tong University)

Abstract: Stencil computation is a fundamental kernel in scientific computing, widely used in applications such as fluid dynamics and weather simulation. Although stencils are traditionally considered memory-bound and thus ill-suited for compute-oriented Tensor Cores, recent studies report substantial acceleration, creating an apparent contradiction. This paper resolves this discrepancy through a systematic performance analysis of stencil computations on Tensor Cores. We revisit stencil-to-Tensor-Core mappings, quantify the computational redundancy introduced by hardware-driven transformations, and develop an enhanced performance model that captures arithmetic-intensity shifts under temporal fusion. From this model, we derive analytical criteria that provide a first-order estimate of whether Tensor Cores will outperform, match, or underperform CUDA Cores for a given stencil and hardware setting. Our analysis identifies the performance sweet spot for Tensor Core acceleration. Evaluations on NVIDIA GPUs with state-of-the-art implementations, including EBISU, ConvStencil, and SPIDER, validate our criteria and show its value for guiding stencil optimization.


Presentation: file

Back to Technical Papers Archive Listing