Here is a data point:
```
pkrysl@firenze:~/dealii-9.5.2/examples/step-3$ make
Consolidate compiler generated dependencies of target step-3
[ 50%] Building CXX object CMakeFiles/step-3.dir/step-3.cc.o
[100%] Linking CXX executable step-3
[100%] Built target step-3
Thank you. I have actually no complaints about the performance.
I just want to know what is going on in deal.ii for a paper I am working on.
On Tuesday, March 12, 2024 at 6:59:19 PM UTC-7 bruno.t...@gmail.com wrote:
> If building the sparsity pattern is the bottleneck in your code, feel free
>
If building the sparsity pattern is the bottleneck in your code, feel free
to open an issue and we can take a look at how we can improve it. Though if
the assembly of the matrix is performance critical, using the MatrixFree
class is the way to go.
Bruno
Le mar. 12 mars 2024 à 20:38, Petr Krysl
In Matlab calling sparse() is equivalent to building a sparsity pattern
(just forget about the actual values)
from the I, J row and column indices. And that is NOT a negligible expense.
It is a sizeable fraction of
the cost of building a Laplacian matrix on triangles, for instance.
On Tuesday,
I am not sure why but I need to approve all of your messages. Usually we
only need to approve the first time someone posts. Not sure what's going on
here.
I don't remember how long the computation of the sparsity pattern took but
it was small. The reason this part is not parallelized in deal.II
Oops. I was wondering what happened to my response, and I did not realize
it was subject to approval and posted another
attempt at framing the answer. Sorry.
On Tuesday, March 12, 2024 at 2:15:22 PM UTC-7 Petr Krysl wrote:
> Good point about Tpetra: I will check it out.
>
> > SparsityPattern
That is a good point about Tpetra: I will check it out.
> SparsityPattern is usually extremely fast
It can still become a bottleneck, provided everything else runs in
parallel. ;-)
Which reminds me: I wanted to ask you about the WorkStream paper: The
sparsity pattern computation was not
Good point about Tpetra: I will check it out.
> SparsityPattern is usually extremely fast
If it is the only sequential of a program executed with multiple threads,
it can still control the scalability.
Which reminds me: In your WorkStream paper, you do not report the time
taken to construct
In Trilinos, the Tpetra library has Graph which is basically a
SparsityPattern. Tpetra uses Kokkos (which abstracts multithreading and GPU
support) everywhere so I would expect that they use Kokkos to build the
Graph too. Multithreading for dealii's SparsityPattern is not planned so
far. It could
Thanks, that is a helpful confirmation.
Would you know if there is any multithreading sparsity pattern computation
available anywhere?
Is something like this planned for dealii?
On Tuesday, March 12, 2024 at 10:39:22 AM UTC-7 bruno.t...@gmail.com wrote:
> Hello,
>
> SparsityPattern is used for
Hello,
SparsityPattern is used for deal.II own matrices which do not support MPI.
As far as I can tell, SparsityPattern does not use multithreading and I
don't think adding elements is threadsafe. So you are right.
Best,
Bruno
On Tuesday, March 12, 2024 at 12:58:37 PM UTC-4
It would appear that the sparsity pattern is not (and cannot be) computed
in parallel. That is my reading of the code. Am I wrong?
--
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
Thank you for the hints. It works now.
Best regards,
Paras
On Wed, Mar 6, 2024 at 12:36 AM Wolfgang Bangerth
wrote:
> On 3/5/24 09:59, Paras Kumar wrote:
> >
> > Thank you for your response. That is exactly what I am trying to do via
> the
> > deserialize function. I build an object of the
13 matches
Mail list logo