[petsc-dev] Kokkos initialize
bsmith at petsc.dev
Thu Oct 15 19:34:21 CDT 2020
I thought the plan was that Kokkos also had a lazy initialization but perhaps it does not and needs to be fixed.
> On Oct 15, 2020, at 6:49 PM, Mark Adams <mfadams at lbl.gov> wrote:
> I am running a on SUMMIt with a Kokkos cuda configuration and while debugging with ddt I noticed that it spent a long time in KokkosInit, but I was not using Kokkos. KokkosInit was call in PETSc's GPU init, which seems logical enough, but it would be better if it is not called if you are not using Kokkos.
> I recall seeing places where Kokkos is checked when calling a Kokkos method (ie, lazy initialization). Do we have policy on whether we are being lazy with KokkosInit or not?
More information about the petsc-dev