Maybe put it in a singularity/shifter/charliecloud container and hope for the best? That seems to work reasonable well for python.
Todd. > On Mar 11, 2019, at 9:45 PM, Smith, Barry F. <bsm...@mcs.anl.gov> wrote: > > > Hmm, actually I may be wrong. The just in time compile approach may require > some attention since the nodes might require access to compiler > infrastructure. Doable, of course, but the vendors could make it easier or > more difficult. I don't know enough but to speculate. > > >> On Mar 11, 2019, at 9:37 PM, Smith, Barry F. via petsc-dev >> <petsc-dev@mcs.anl.gov> wrote: >> >> >> There is no particular reason they shouldn't. >> >> In fact, we should ask for an uplift to prepare Julia for exascale if >> someone hasn't already ;) >> >> Barry >> >> >>> On Mar 11, 2019, at 9:35 PM, Munson, Todd <tmun...@mcs.anl.gov> wrote: >>> >>> >>> One question from me would be, will any of the exascale machines support >>> Julia >>> when they are delivered? >>> >>> Todd. >>> >>>> On Mar 11, 2019, at 9:28 PM, Smith, Barry F. via petsc-dev >>>> <petsc-dev@mcs.anl.gov> wrote: >>>> >>>> >>>> PETSc source code is becoming an unmaintainable, unextendable monstrosity. >>>> How long until Julia is mature enough that we can (re)implement PETSc in >>>> it? >>>> >>>> Barry >>>> >>> >> >