Teleconference 2016-12-07

From VTKM
Revision as of 13:52, 7 December 2016 by Kmorel (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Attendees: Ken Moreland (SNL), Matt Larsen (LLNL), Tom Otahal (SNL), Dave Pugmire (ORNL), Chris Sewell (LANL), Olie Lo (LANL), Berk Geveci (Kitware), Mark Kim (ORNL), Dongliang Chu (ORNL), Tom Fogal (NVIDIA)

Chris working with unified memory on Pascal architecture. Comparing streaming vs. paging. Hope for concrete results soon.

Bug found and fixed in contour tree fixed. Open sourcing of that code is progressing.

Looking at extract arbitrary subset.

Flexi project is working with VTK-m to integrate with Catalyst for in situ processing.

Olie extending atomic array to floating points.

There is an issue with the unit tests where they are not creating threads because the amount of work is too small.

Dongliang Chu is new post-doc working at ORNL.

Putting together a stand alone VTK-m streamline and contour algorithm to measure with Oxbow.

Added VTK-m rectilinear grid reader.

We need a way to get data sets for tests in VTK-m. We decided to use the same mechanism in VTK and ParaView. Berk will coordinate setting that up.

Mark working on CSG miniapp. Hacked into VTK-m ray caster.

Retrieved from "https://m-old.vtk.org/index.php?title=Teleconference_2016-12-07&oldid=386"