arXiv2023
The Event Horizon Telescope (EHT) has recently released high-resolution images of accretion flows onto two supermassive black holes. Our physical understanding of these images depends on accuracy and precision of numerical models of plasma and radiation around compact objects. The goal of this work is to speed up radiative-transfer simulations used to create mock images of black holes for comparison with the EHT observations. A ray-tracing code for general relativistic and fully polarized radiative transfer through plasma in strong gravity is ported onto a graphics processing unit (GPU). We describe our GPU implementation and carry out speedup tests using models of optically thin advection-dominated accretion flow (ADAF) onto a black hole realised semi-analytically and in 3D general relativistic magnetohydrodynamics simulations, low and very high image pixel resolutions, and two different sets of CPU+GPUs. We show that a GPU with high double precision computing capability can significantly reduce the image production computational time, with a speedup factor of up to approximately 1200. The significant speedup facilitates, e.g., dynamic model fitting to the EHT data, including polarimetric data. The method extension may enable studies of emission from plasma with nonthermal particle distribution functions for which accurate approximate synchrotron emissivities are not available. The significant speedup reduces the carbon footprint of the generation of the EHT image libraries by at least an order of magnitude.