Marek,

2016-07-22 2:42 GMT-04:00 Vinetou Incucuna <[email protected]>:
> Therefore ad1)  is split into small subsystems (approximately 2000
> unknowns for each core) and therefore the Amesos_Superludis should
> have worked nicely?
Yes SuperLU should work on this problem but I think that there is some
confusion here. When you use more cores the system is not split into
small systems. Each processor will get a bunch of rows of the global
matrix. If it takes 1 seconds to invert a 1000 x 1000 matrix using one
processor, you cannot expect that will takes 1 seconds to solve a 2000
x 2000 matrix using four processors. It will take longer.

Best,

Bruno

-- 
The deal.II project is located at http://www.dealii.org/
For mailing list/forum options, see 
https://groups.google.com/d/forum/dealii?hl=en
--- 
You received this message because you are subscribed to the Google Groups 
"deal.II User Group" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
For more options, visit https://groups.google.com/d/optout.

Reply via email to