Dan Ibanez
Dan Ibanez
@tawiesn a while back I found that Kokkos didn't quite have a general enough sorting interface and put together something of my own that either calls Thrust or an OpenMP...
Edit: I typed out a repeat of my comment at the top, I had forgotten I already commented on this.
From a design perspective, I don't think this belongs in the mesh reading API. There should be a separate helper function `scale(Mesh*, Few)`.
I suspect the phi field has become very non-smooth in some part of the mesh... it would be interesting to look more closely at it. Typically gradation becomes slow when...
Unless its trivial, I don't think so. I have lots of travel in April.
I have no problem with supporting it, but so far the projects I work on either use structured meshes or use the SNL mesh generator (CUBIT), not Gmsh, so I...
@smelchio I would personally do the first option, the "duplicate" one. This allows users to read the format without building Gmsh on the same machine, and it also avoids issues...
You'd need to form a different communication pattern (underlying Dist object). It can be done, but is more expensive and isn't something you can do with existing `sync*` APIs
In general, the two-array CRS approach is the most efficient general way to store varying size data. If the variance is less than 2X, using a fixed size could be...
This API: ```cpp void build_from_elems2verts(Mesh* mesh, CommPtr comm, Omega_h_Family, Int edim, LOs ev2v, Read vert_globals); ``` If called on all processors with consistent vertex global IDs (each processor gives the...