Thanks Barry and Sherry, it works like a charm :)
Best regards,
Felix
Zitat von Barry Smith :
Good. I have cleaned up the code and rebased the branch so if you
use it in the future you need to do
git fetch
git checkout master
git branch -D barry/2020-07-28/superlu_dist-single
git chec
See case '"-num_rhs" in petsc/src/ksp/ksp/tests/ex30.c
Hong
From: petsc-users on behalf of Matthew
Knepley
Sent: Tuesday, August 4, 2020 7:29 PM
To: Anthony Paul Haas
Cc: petsc-users
Subject: Re: [petsc-users] reuse Mumps factorization for multiple RHS
On
On Tue, Aug 4, 2020 at 7:57 PM Anthony Paul Haas
wrote:
> Hello,
>
> When using Mumps to solve a linear system of equations (see below), can I
> reuse the factorization to solve for multiple RHS, ie, can I use KSPSolve
> multiple
> times while only building a different RHS in between the calls t
Yes, it automatically uses the same factorization.
> On Aug 4, 2020, at 6:55 PM, Anthony Paul Haas wrote:
>
> Hello,
>
> When using Mumps to solve a linear system of equations (see below), can I
> reuse the factorization to solve for multiple RHS, ie, can I use KSPSolve
> multiple times w
Hello,
When using Mumps to solve a linear system of equations (see below), can I
reuse the factorization to solve for multiple RHS, ie, can I use
KSPSolve multiple
times while only building a different RHS in between the calls to KSPSolve?
Thanks,
Anthony
call KSPSetType(self%ksp,KSPPREONLY,sel
On Tue, Aug 4, 2020 at 6:35 AM Stefano Zampini
wrote:
> Nicola,
>
> You are actually not using the GPU properly, since you use HYPRE
> preconditioning, which is CPU only. One of your solvers is actually slower
> on “GPU”.
> For a full AMG GPU, you can use PCGAMG, with cheby smoothers and with
> J
On Tue, Aug 4, 2020 at 6:04 AM nicola varini
wrote:
> Dear all, thanks for your replies. The reason why I've asked if it is
> possible to overlap poisson and ampere is because they roughly
> take the same amount of time. Please find in attachment the profiling logs
> for only CPU and only GPU.
>
Good. I have cleaned up the code and rebased the branch so if you use it in
the future you need to do
git fetch
git checkout master
git branch -D barry/2020-07-28/superlu_dist-single
git checkout barry/2020-07-28/superlu_dist-single
Do not just do a git pull in barry/2020-07-28/sup
EventCount Time (sec) Flop
--- Global --- --- Stage Total GPU- CpuToGpu - - GpuToCpu - GPU
PS:
I saw you committed a new version for the SUPERLU_DIST installer.
There is a missing ")" at the end of line 42.
Also I think one also has to add
self.addToArgs(args,'-DCMAKE_CXX_FLAGS:STRING','-I'+self.blasLapack.include)
as well (for me only adding the C flag raised the same error as
befor
Yep, when I assign the mkl include directory to CPATH, it works :)
Best regards,
Felix
Zitat von Barry Smith :
On some systems, like my Mac, the environmental variable CPATH is
set to the appropriate directory for mkl.h when MKL is initialized
with
source /opt/intel/compilers_and_libraries
Thanks for your reply Stefano. I know that HYPRE is not ported on GPU, but
the Solver is running on GPU and is taking ~9s and is showing 100% of GPU
utilization.
Il giorno mar 4 ago 2020 alle ore 12:35 Stefano Zampini <
stefano.zamp...@gmail.com> ha scritto:
> Nicola,
>
> You are actually not usi
Nicola,
You are actually not using the GPU properly, since you use HYPRE
preconditioning, which is CPU only. One of your solvers is actually slower on
“GPU”.
For a full AMG GPU, you can use PCGAMG, with cheby smoothers and with Jacobi
preconditioning. Mark can help you out with the specific com
13 matches
Mail list logo
