What is the best approach for conducting parallel simulations in EnergyPlus on an HPC cluster? In BEopt, users can specify the number of cores for parallel simulation, but how does one achieve this on an HPC?

Is it feasible to submit all simulation jobs at once and call EnergyPlus concurrently on different nodes/CPUs/Cores for simultaneous execution (e.g., using SLURM) rather than serial processing? If not, what alternative methods can be employed to achieve parallel simulation on an HPC cluster?