FEREBUS: A High-Performance Modern Gaussian Process Regression Engine

Matthew J. Burn, Paul L. A. Popelier

Research output: Contribution to journalArticlepeer-review


FEREBUS is a highly optimised Gaussian process regression (GPR) engine, which provides both model and optimiser flexibility to produce tailored models designed for domain specific applications. FEREBUS provides the user with the necessary tools to decide on the trade-off between time and accuracy, in order to produce adequately accurate machine learnt models. FEREBUS has been designed from the ground up, for deep integration in the file management pipeline (ICHOR) of the multipolar, machine learned, polarisable force field FFLUX. As such it can produce accurate atomistic models for molecular dynamics simulations as efficiently as possible. FEREBUS utilises both OpenMP and OpenAcc technologies for parallel execution of optimisation routines and offloading computation to GPU accelerator devices with high efficiency, reaching parallel efficiency of 99%. The FORTRAN90 program FEREBUS embodies a modern approach to a high performance GPR engine providing both flexibility and performance in a single package.
Original languageEnglish
JournalDigital Discovery
Publication statusAccepted/In press - 27 Nov 2022


Dive into the research topics of 'FEREBUS: A High-Performance Modern Gaussian Process Regression Engine'. Together they form a unique fingerprint.

Cite this