In the documentation it seems as if there is no need to write parallel = 'mpi' when creating an SCE-UA sampler. I'm guessing this part is simply missing? And if yes, would the cores assigned in mpirun have to match the ngs parameter in some way? Thanks a lot!
In the documentation it seems as if there is no need to write
parallel = 'mpi'
when creating an SCE-UA sampler. I'm guessing this part is simply missing? And if yes, would the cores assigned inmpirun
have to match thengs
parameter in some way? Thanks a lot!