Quantitative Economics

Journal Of The Econometric Society

Edited by: Stéphane Bonhomme • Print ISSN: 1759-7323 • Online ISSN: 1759-7331

Quantitative Economics: Jan, 2025, Volume 16, Issue 1

Programming FPGAs for Economics: An Introduction to Electrical Engineering Economics

https://doi.org/10.3982/QE2344
p. 49-87

Bhagath Cheela|André DeHon|Jesús Fernández‐Villaverde|Alessandro Peri

We show how to use field‐programmable gate arrays (FPGAs) and their associated high‐level synthesis (HLS) compilers to solve heterogeneous agent models with incomplete markets and aggregate uncertainty (Krusell and Smith (1998)). We document that the acceleration delivered by one single FPGA is comparable to that provided by using 69 CPU cores in a conventional cluster. The time to solve 1200 versions of the model drops from 8 hours to 7 minutes, illustrating a great potential for structural estimation. We describe how to achieve multiple acceleration opportunities—pipeline, data‐level parallelism, and data precision—with minimal modification of the C/C++ code written for a traditional sequential processor, which we then deploy on FPGAs easily available at Amazon Web Services. We quantify the speedup and cost of these accelerations. Our paper is the first step toward a new field, electrical engineering economics, focused on designing computational accelerators for economics to tackle challenging quantitative models. Replication code is available on Github.


Full Content: Print

Supplemental Material

Supplement to "Programming FPGAs for Economics: An Introduction to Electrical Engineering Economics"

Bhagath Cheela, André DeHon, Jesús Fernández-Villaverde, and Alessandro Peri

Supplemental Appendix

Supplement to "Programming FPGAs for Economics: An Introduction to Electrical Engineering Economics"

Bhagath Cheela, André DeHon, Jesús Fernández-Villaverde, and Alessandro Peri

The replication package for this paper is available at https://doi.org/10.5281/zenodo.14013936. The Journal checked the data and codes included in the package for their ability to reproduce the results in the paper and approved online appendices. Given the highly demanding nature of the algorithms, the reproducibility checks were run on a simplified version of the code, which is also available in the replication package.

Journal News

View