ParaView 3 Telecon 07-30-2009: Difference between revisions
(Created page with '{| cellpadding="2" cellspacing="4" |- ! style="background:#abcdef" | Item ! style="background:#abcdef" | People ! style="background:#abcdef" | Description |- | 1 || Ice || MARS/V…') |
No edit summary |
||
| (2 intermediate revisions by the same user not shown) | |||
| Line 9: | Line 9: | ||
| 2 || Scott || Select block from (Exodus/global) id quickly | | 2 || Scott || Select block from (Exodus/global) id quickly | ||
|- | |- | ||
| 3 || Moreland || Stronger Dashboard | | 3 || Scott || Exodus implied node index | ||
|- | |||
| 4 || Moreland || Stronger Dashboard | |||
* Boiling the frog coverage | * Boiling the frog coverage | ||
|- | |- | ||
| | | 5 || Thompson || Statistics Update | ||
|- | |- | ||
| | | 6 || Moreland || In-situ paper | ||
|} | |} | ||
== MARS Milestone == | |||
The scaling studies have stalled. Kitware does not have any CTH simulation that makes sense to scale past about 500 processors. Thus, the fraction of time spent in fragment analysis is not representative (the entire dataset is replicated in ghost cells. | |||
As an action, someone at Sandia needs to work with someone in 1500 to get some reasonable scaling numbers. | |||
== Select block from (Exodus/global) id quickly == | |||
Another problem users are having is trying to quickly find an element with a particular id. Our best suggestion so far is to have another toolbar with more selection operations that are common and hard to do. Operations that came up: quickly selecting a node with a particular id/field value, in one click bring up a spreadsheet showing selected stuff, quickly toggle selected point/cell labels (how do you select the field to show?). | |||
== Exodus implied node index == | |||
There is an implied index number in Exodus on the numbering of points per file. Need to be able to search on these. Probably build a new array, much like objectid and fileid to represent the original ids. | |||
== Stronger Dashboard == | |||
Dave P. is now monitoring the dashboard. | |||
Utkarsh is still going to think about how to run more tests faster. | |||
Latest revision as of 13:05, 30 July 2009
| Item | People | Description |
|---|---|---|
| 1 | Ice | MARS/V&V Milestone issues |
| 2 | Scott | Select block from (Exodus/global) id quickly |
| 3 | Scott | Exodus implied node index |
| 4 | Moreland | Stronger Dashboard
|
| 5 | Thompson | Statistics Update |
| 6 | Moreland | In-situ paper |
MARS Milestone
The scaling studies have stalled. Kitware does not have any CTH simulation that makes sense to scale past about 500 processors. Thus, the fraction of time spent in fragment analysis is not representative (the entire dataset is replicated in ghost cells.
As an action, someone at Sandia needs to work with someone in 1500 to get some reasonable scaling numbers.
Select block from (Exodus/global) id quickly
Another problem users are having is trying to quickly find an element with a particular id. Our best suggestion so far is to have another toolbar with more selection operations that are common and hard to do. Operations that came up: quickly selecting a node with a particular id/field value, in one click bring up a spreadsheet showing selected stuff, quickly toggle selected point/cell labels (how do you select the field to show?).
Exodus implied node index
There is an implied index number in Exodus on the numbering of points per file. Need to be able to search on these. Probably build a new array, much like objectid and fileid to represent the original ids.
Stronger Dashboard
Dave P. is now monitoring the dashboard.
Utkarsh is still going to think about how to run more tests faster.
