Utilizing dynamic parallelism in CUDA to accelerate a 3D red-black successive over relaxation wind-field solver. (March 2021)

• Record Type: Journal Article
• Authors: Bozorgmehr, Behnam; Willemsen, Pete; Gibbs, Jeremy A.; Stoll, Rob; Kim, Jae-Jin; Pardyjak, Eric R.
• Is Part Of: Environmental modelling & software. Volume 137(2021)
• Publication Date: 2021-03
• Subjects: QES-Winds -- Poisson equation -- Fast-response -- Wind modeling -- Iterative method -- Staggered grid; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2021.104958
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: QES-Winds is a fast-response wind modeling platform for simulating high-resolution mean wind fields for optimization and prediction. The code uses a variational analysis technique to solve the Poisson equation for Lagrange multipliers to obtain a mean wind field and GPU parallelization to accelerate the numerical solution of the Poisson equation. QES-Winds benefits from CUDA dynamic parallelism (launching the kernel from the GPU) to speed up calculations by a factor of 128 compared to the serial solver for a domain with 145 million cells. The dynamic parallelism enables QES-Winds to calculate mean velocity fields for domains with sizes of 10 km 2 and horizontal resolutions of 1 - 3 m in under 1 min. As a result, QES-Winds is a numerical code suitable for computing high-resolution wind fields on large domains in real time, which can be used to model a wide range of real-world problems including wildfires and urban air quality. Highlights: Fast-response wind modeling platform that solves the Poisson equation for Lagrange multipliers. Three GPU-solver implementations: dynamic-parallel, global memory, and shared memory. All GPU solvers are faster than the CPU (serial) solver because of parallelization benefits. The dynamic-parallel solver has improved data security compared to other GPU solvers. Optimization and prediction for modeling winds for environmental applications is possible.