DOE OSTI · 3015375
Fiats: Functional inference and training for surrogates
Abstract
Fiats provides a platform for research on the training and deployment of neural-network surrogate models for computational science. Fiats also supports exploring, advancing, and combining functional, object-oriented, and parallel programming patterns in Fortran 2023. As such, the Fiats name has dual expansions: “Functional Inference And Training for Surrogates” or “Fortran Inference And Training for Science.” Fiats inference and training procedures are pure and therefore satisfy a language constraint imposed on procedure invocations inside Fortran’s parallel loop construct: do concurrent. Furthermore, the Fiats training procedures are built around a do concurrent parallel reduction. Several compilers can automatically parallelize do concurrent on Central Processing Units (CPUs) or Graphics Processing Units (GPUs). Fiats thus aims to achieve performance portability through standard language mechanisms.
Keep this discovery
Explore connections, maps & timelines
Rouson, Damian [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:000000022344868X), Bonachea, Dan [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0000000207249349), Richardson, Brad [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0000000232052169), Welsman, Jordan A. [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:000000022882594X), Bailey, Jeremiah [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0000000204369118), Gutmann, Ethan D [NSF National Center for Atmospheric Research, Boulder, CO (United States)] (ORCID:0000000340773430), Torres, David [Northern New Mexico College, Espanola, NM (United States)] (ORCID:0000000324695284), Rasmussen, Katherine [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0000000179741853), Dibba, Baboucarr [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0009000804793948), Zhang, Yunhao [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0009000931829296), Weaver, Kareem [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0009000938466248), Bai, Zhe [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0000000230920903), Nguyen, Tan [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:000000033748403X). 2025-12-06. Fiats: Functional inference and training for surrogates. https://doi.org/10.21105/joss.08785
Cite the original work for its findings. Save a collection to share your selection of sources.