Attendees: Ken Moreland (SNL), Ollie Lo (LANL), Nick Davis (SNL), Matt Larsen (LLNL), Allie Vacanti (Kitware), Sujin Philip (Kitware), Berk Geveci (Kitware)
- Planning work detail for FY20 and beyond
- Will have a meeting next month to solidify FY20Q1 plans
- All PI's: edit https://confluence.exascaleproject.org/display/STDA05/FY20-FY23+Activities+WorkSheet
- Needs to be completed before our meeting
- End of Q3 fast approaching
- Need all updates by next Wednesday.
- Will subsequently be unavailable the rest of the month
ECP deliverable updates
- [MS-19/08] Point Movement 2
- Rob has a merge request for the documentation. Ken will look into that.
- [MS-19/09] Path Geometry
- Added polyline support to VTK-m explicit cell sets
- [MS-20/01] Lightweight Cell Library
- Have implementation for Quad and implementing some tests using random cell generation.
- Other cells will be implemented similarly.
- [MS-20/02] Specialized Data Models
- Mark Kim working on this.
- [MS-20/03] Feature-Sensitive Surface Norm
- Allie getting back on that after being out of the office for a while
- [MS-20/04] VTK-m Release 3
- On track
- Probably June would be a good time for a release.
- [MS-20/05] Cell Metrics
- Brent and Daniel are working on an MR.
- Steven Walton is getting engaged on this.
- Initial MR will only be about 1/3 of the metrics.
- First MR is moving forward
- Will advance after that.
- Hank might have to jump in during the summer.
- [MS-20/06] Contouring
- Will model the problem after triangulation. Have different contouring for each cell type.
- Ollie looking into VTK implementation and flying edge paper.
- [MS-20/07] Advanced Flow Algorithms
- Abhishek and Dave have been working on performance fixes for unstructured grids.
- James and Dave have been fixing bugs for distributed memory and for unstructured grids.
The hackathon will be held in Albuquerque starting July 30. Everyone planning on attending should register. Go to Hackathon 2019-07-30 for details.
We should try to collect some ECP data so that as we do reporting we can quickly generate relevant images. It would be great if we could also share across ALPINE and other vis projects.
- Terry Turton has collected some stuff from LANL. Not sure if can be sent out.
- She might have a list of distributed data in different places
Ken tried compiling VTK-m with Spack on Stampede2. After some issues, version 1.3 compiled OK. There were several issues with compiling Ascent with Spack. It didn't work because the version dependencies are not set up correctly.
Matt helped Steven at UO with extract structured. It now uses global point indices rather than just local point indices.
There is an issue where if compiling VTK-m with CUDA into static libraries, any executable has to use nvcc for linking whether or not it uses CUDA itself.
Looking for the ability to get information from VTK-m canvases other than color and depth. For example, it would be helpful to get a scalar value at the surface at that point.
No meeting two weeks from now.