Field-programmable gate arrays and quantum Monte Carlo: Power efficient coprocessing for scalable high-performance computing
View / Open Files
Publication Date
2019-06-15Journal Title
International Journal of Quantum Chemistry
ISSN
0020-7608
Publisher
Wiley-Blackwell
Volume
119
Issue
12
Type
Article
This Version
AM
Metadata
Show full item recordCitation
Cardamone, S., Kimmitt, J., Burton, H., Todman, T., Li, S., Luk, W., & Thom, A. (2019). Field-programmable gate arrays and quantum Monte Carlo: Power efficient coprocessing for scalable high-performance computing. International Journal of Quantum Chemistry, 119 (12)https://doi.org/10.1002/qua.25853
Abstract
Massively parallel architectures offer the potential to significantly accelerate an application relative to their
serial counterparts. However, not all applications exhibit an adequate level of data and/or task parallelism to
exploit such platforms. Furthermore, the power consumption associated with these forms of computation renders
"scaling out" for exascale levels of performance incompatible with modern sustainable energy policies. In this
work, we investigate the potential for field-programmable gate arrays (FPGAs) to feature in future exascale
platforms, and their capacity to improve performance per unit power measurements for the purposes of scientific
computing. We have focussed our efforts on Variational Monte Carlo, and report on the benefits of co-processing with
a FPGA relative to a purely multicore system.
Sponsorship
Royal Society
Horizon 2020
Hartree Centre
Funder references
Royal Society (uf110161)
European Commission Horizon 2020 (H2020) Future and Emerging Technologies (FET) (671653)
Royal Society (UF160398)
Identifiers
External DOI: https://doi.org/10.1002/qua.25853
This record's URL: https://www.repository.cam.ac.uk/handle/1810/288200
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved