Teleconference 2024-01-29

Attendees: Ken Moreland (ORNL), Mark Bolstad (SNL), Silvio Rizzi (ANL), Dave Pugmire (ORNL), Nicole Marsaglia (LLNL), Jefferson Amstutz (Nvidia)

OASIS Deliverables

The following items are proposed for FY25 (which will end at the end of the fiscal year)

• Address requests for support, improvement, and new features by current and potential applications such as XGC and WarpX as well as other users of ParaView, VisIt, and Ascent.
• Strengthen operation of VTK-m on Aurora.
• Improve documentation with automatic generation and web deployment.
• Integrate into High Performance Software Foundation (HPSF) as Viskores.
• Improve integration between VTK-m/Viskores and VTK.

In the future, we will have to think about how to highlight VTK-m/Viskores. Our most visible deployment is usually through Ascent, but we don't want to take Ascent's thunder. I think Ascent gets its main funding through a different stream, so perhaps we could submit complementary highlights through SciDAC and NNSA.

Viskores / HPSF

The HPSF has granted us some funding to transition our software from VTK-m to Viskores. This funding is provided to Kitware, and the contract is in place.

Vicente cannot be here today to talk about it, but the work will start shortly. You should still be able to make contributions to VTK-m until about March. At the end of the transition, we plan to do the final tagging and switch over completely to Viskores.

There will be an HPSF Conference in Chicago May 5 - 8. Viskores will be part of that. I encourage VTK-m/Viskores TAC, developers, and users to attend. In the future, we can leverage the HPSF conference for user group meetings and/or hackathons if there is enough interest.

Roundtable

Ken has made progress on adding Marching Cells cases for polygonal elements. He has case tables that work. Unfortunately, his first implementation caused a performance degradation in the contour filter (picked up by the the benchmarking CI). Ken is going to move to a different approach that should be as fast but won't work with mixed dimensions by default.

Silvio has compiled VTK-m on Aurora with the new compiler. It fixes a priority bug that we had and some tests now pass because of it. However, there are still some failures to look into. This compiler should be available for use some time in February.

Silvio tried building ParaView with SYCL with CMake settings that Abhishek gave him. The build works, but testing is forthcoming.

Nicole has mesh with structured cells and explicit coordinates. External faces is throwing exceptions about a bad cast and call.

Ascent getting weird ray culling issue.