Mapping Stencils on Coarse-grained Reconfigurable Spatial Architecture

TL;DR

This paper presents novel methods for mapping stencil computations onto coarse-grained reconfigurable spatial architectures (CGRA), leveraging data reuse and parallelism to outperform GPUs in scientific computing tasks.

Contribution

It introduces new mapping techniques for stencil computations on CGRA, fully exploiting data reuse and parallelism for enhanced performance.

Findings

Mappings are efficient and outperform GPUs in simulations.

Data reuse significantly improves performance.

Parallelism in CGRA benefits stencil computations.

Abstract

Stencils represent a class of computational patterns where an output grid point depends on a fixed shape of neighboring points in an input grid. Stencil computations are prevalent in scientific applications engaging a significant portion of supercomputing resources. Therefore, it has been always important to optimize stencil programs for the best performance. A rich body of research has focused on optimizing stencil computations on almost all parallel architectures. Stencil applications have regular dependency patterns, inherent pipeline-parallelism, and plenty of data reuse. This makes these applications a perfect match for a coarse-grained reconfigurable spatial architecture (CGRA). A CGRA consists of many simple, small processing elements (PEs) connected with an on-chip network. Each PE can be configured to execute part of a stencil computation and all PEs run in parallel; the network can also be configured so that data loaded can be passed from a PE to a neighbor PE directly and thus reused by many PEs without register spilling and memory traffic. How to efficiently map a stencil computation to a CGRA is the key to performance. In this paper, we show a few unique and generalizable ways of mapping one- and multidimensional stencil computations to a CGRA, fully exploiting the data reuse opportunities and parallelism. Our simulation experiments demonstrate that these mappings are efficient and enable the CGRA to outperform state-of-the-art GPUs.