ParaView 3 Telecon 09-23-2009

Item	People	Description
1	Moreland	Project Randy
2	Moreland	SC Tutorial
3	Geveci	ParaView + ADIOS
4	Moreland	Ultrascale Workshop
5	Ayachit	ParaView 3.8.1 Release
6	Moreland	Non-breaking python client tests
7	Moreland	Documenting Plugins
8	Moreland	Warning when ProcessRequests modifies itself
9	Moreland	Book omissions and errata
10	Utkarsh	Transition to git
11	Moreland	Stronger Dashboard Test consolidation Boiling the frog coverage

Project Randy

Previously:

Alan is still having problems scaling up past 5.5K cores or so, but this might be caused by the Red Sky system itself. Nathan reports similar problems using solvers without ParaView at all.

Ken got timings from Pat for running on Intrepid up to 32K cores. Pat has mentioned that might be some issues with the timings, possibly the job size being too big for the problem size.

In two weeks, Pat is going to Argonne and working with Vankate, who has been doing research on moving data quickly from computation platforms to visualization clusters. Going to integrate that into the coprocessing library.

We talked a bit about data staging. Everyone's doing it. Ken and Scott Klasky have had talked in the past about combining the paraview server with ADIOS data staging. Ken has an action item to send an email to Scott to perhaps organize a meeting at SC between Scott, Ken, and Berk.

Need good I/O comparisons between solver output and coprocessing output.

Can we distribute PHASTA with coprocessing adapter?

Today:

Pat's trip to Argonne: "It was a very productive visit." Working on using Vankate's library to deliver data from the supercomputer to the vis cluster. Made some good progress but has not finished. Still moving forward.

Nathan has been able to compile coprocessing static with CTH on XTP (small Cielo clone). With the AMR dual grid filter, there is some odd MPI abort with a tag value. Works fine on point contouring.

Call to everyone: a list of features to put in a comparative matrix between ParaView Coprocessing and other solutions.

Supercomputing Tutorial

We got permission to distribute PHASTA as an example for integration. However, the only compelling use cases use a commercial solver. There is some completely open solver, but it has no real compelling use case.

ParaView + ADIOS

Sebastian is writing a reader for ADIOS. Once that works, ADIOS guys should have enough to get data delivered from stage. From there, there only thing we need is the fancy Pat Marion stuff to detect when new stuff shows up.

Initial implementation revealed a bug. That's been fixed. Going to move to Jaguar.

ParaView 3.8.1 Release

Finial builds for release are being made.

Documenting Plugins

The new rule should be that if a plugin is distributed with the ParaView binaries, it must have a wiki page documenting it. These wiki pages will then be integerated in the new ParaView electronic book.

Warning when ProcessRequest modifies itself

Previously:

A while ago we talked about adding a check to the executive that issues a warning if it detects that its MTime changes during a call to ProcessRequest. Whatever happened to that? I just spent 2 days tracking down a parallel pipeline update problem that would have been quickly alerted had this been in place (and was easily fixed once I put my own check in place).

Berk suggested first adding the check only to ParaView. We will see how that works, and then possibly move to VTK. Kitware will take care of that.

On Berk's todo list. Berk is working on proposals for the ARB. One is to change the modularization of VTK. The other is to yank out VTK 4.0 compatibility, which will allow us to clean up vtkExecutive change.

Book omissions and errata

Previously:

Lisa is going to create a bug-tracker like functionality for the Kitware books.

Transition to git

Branchy workflow. Tie in to stronger dashboard.