Copyright Notice:

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Publications of SPCL

J. de Fine Licht, A. Kuster, T. De Matteis, T. Ben-Nun, D. Hofer, T. Hoefler:

 StencilFlow: Mapping Large Stencil Programs to Distributed Spatial Computing Systems

(In Proceedings of the 19th ACM/IEEE International Symposium on Code Generation and Optimization (CGO'21), 2021)

Abstract

Spatial computing devices have been shown to significantly accelerate stencil computations, but have so far relied on unrolling the iterative dimension of a single stencil operation to increase temporal locality. This work considers the general case of mapping directed acyclic graphs of heterogeneous stencil computations to spatial computing systems, assuming large input programs without an iterative component. StencilFlow maximizes temporal locality and ensures deadlock freedom in this setting, providing end-to-end analysis and mapping from a high-level program description to distributed hardware. We evaluate our generated architectures on a Stratix 10 FPGA testbed, yielding 1.31 TOp/s and 4.18 TOp/s on single-device and multi-device, respectively, demonstrating the highest performance recorded for stencil programs on FPGAs to date. We then leverage the framework to study a complex stencil program from a production weather simulation application. Our work enables productively targeting distributed spatial computing systems with large stencil programs, and offers insight into architecture characteristics required for their efficient execution in practice.

Documents

download article:
access preprint on arxiv:


Recorded talk (best effort)

 

BibTeX

@article{stencilflow,
  author={Johannes de Fine Licht and Andreas Kuster and Tiziano De Matteis and Tal Ben-Nun and Dominic Hofer and Torsten Hoefler},
  title={{StencilFlow: Mapping Large Stencil Programs to Distributed Spatial Computing Systems}},
  year={2021},
  booktitle={Proceedings of the 19th ACM/IEEE International Symposium on Code Generation and Optimization (CGO'21)},
  doi={https://doi.org/10.1109/CGO51591.2021.9370315},
}