ConvStencil: Transform Stencil Computation to Matrix Multiplication on Tensor Cores

Abstract

Tensor Core Unit (TCU) is increasingly integrated into modern high-performance processors to enhance matrix multiplication performance. However, constrained to its over-specification, its potential for improving other critical scientific operations like stencil computations remains untapped. This paper presents ConvStencil 1 , a novel stencil computing system designed to efficiently transform stencil computation to matrix multiplication on Tensor Cores. We first develop a performance model for ConvStencil to guide al-gorithm design and optimization on TCUs. Based on this model, we propose three techniques: (1) Memory-efficient Layout Transformation using the stencil2row method; (2)