Accurate Simulation of Neutrons in Less Than One Minute Pt. 2: Sandman—GPU-Accelerated Adjoint Monte-Carlo Sampled Acceptance Diagrams

Abstract

A computational method in the modelling of neutron beams is described that blends neutron acceptance diagrams, GPU-based Monte-Carlo sampling, and a Bayesian approach to efficiency. The resulting code reaches orders of magnitude improvement in performance relative to existing methods. For example, data rates similar to world-leading, real instruments can be achieved on a 2017 laptop, generating 10 6 neutrons per second at the sample position of a high-resolution small angle scattering instrument. The method is benchmarked, and is shown to be in agreement with previous work. Finally, the method is demonstrated on a mature instrument design, where a sub-second turnaround in an interactive simulation process allows the rapid exploration of a wide range of options. This results in a doubling of the design performance, at the same time as reducing the hardware cost by 40%.