Jeremy L Thompson
Jeremy L Thompson
I'm just commenting that I would find it easier to see what's going if all this from our current yaml ``` # Compilers - export COVERAGE=1 CC=gcc CXX=g++ FC=gfortran HIPCC=hipcc...
This is looking pretty good overall. This is marked draft. What's left before it's ready for review? I'd like to migrate it over to Ratel when this branch is ready.
@LeilaGhaffari, this sounds pretty close to ready. I'd like to add this work to Ratel. It think it will take a bit of effort to adapt, but it shouldn't be...
Note - this branch needs the updates in main for the latest development version of PETSc: #940
I think a smaller first step could be refactoring the code generation backends to share the kernels that other backends use. Currently there are some minor differences, but I don't...
For the long term health of these backends, I think we should do a cleanup and refactor in the near term. Combining kernels across the CUDA and HIP backends should...
Side note, using `-dm_plex_box_bd periodic,periodic,periodic` sets the boundary *cells* as periodic rather than the faces, which is annoying when paired with the fact that for `bps.c` we removed the ability...
Really, I should have said *element* instead of *cell*. But I think I was misunderstanding the information I was seeing.
I think this might be easier to get to with #1050?
This now compiles and passes the t3 tests on Ookami. ToDo: - [ ] Performance comparisons - [x] Makefile flag fix (not sure how the AVX one even works) -...