Thanks Mark and Matt for the comments.
From: Mark Adams
Sent: Saturday, April 13, 2024 12:53 PM
To: Matthew Knepley
Cc: Ng, Cho-Kuen ; Barry Smith ;
petsc-users ; Jacob Faibussowitsch
Subject: Re: [petsc-users] Using PETSc GPU backend
As Matt said, high
,
>> Cho
>> --
>> *From:* Mark Adams
>> *Sent:* Friday, April 12, 2024 4:52 PM
>> *To:* Barry Smith
>> *Cc:* Ng, Cho-Kuen ; petsc-users <
>> petsc-users@mcs.anl.gov>; Jacob Faibussowitsch
>> *Subject:* Re:
rom:* Mark Adams
> *Sent:* Friday, April 12, 2024 4:52 PM
> *To:* Barry Smith
> *Cc:* Ng, Cho-Kuen ; petsc-users <
> petsc-users@mcs.anl.gov>; Jacob Faibussowitsch
> *Subject:* Re: [petsc-users] Using PETSc GPU backend
>
> As Barry said, this is a bit small but the perfor
en ; petsc-users
; Jacob Faibussowitsch
Subject: Re: [petsc-users] Using PETSc GPU backend
As Barry said, this is a bit small but the performance looks reasonable.
The solver does very badly, mathematically.
I would try hypre to get another data point.
You could also try 'cg' to check that the
n
> *Sent:* Saturday, August 12, 2023 8:08 AM
> *To:* Jacob Faibussowitsch
> *Cc:* Barry Smith ; petsc-users >
> *Subject:* Re: [petsc-users] Using PETSc GPU backend
>
> Thanks Jacob.
> --
> *From:* Jacob Faibussowitsch
> *Sent:* Saturday,
ry Smith mailto:bsm...@petsc.dev>>; petsc-users
> mailto:petsc-users@mcs.anl.gov>>
> Subject: Re: [petsc-users] Using PETSc GPU backend
>
> Thanks Jacob.
> From: Jacob Faibussowitsch mailto:jacob@gmail.com>>
> Sent: Saturday, August 12, 2023 5:02 AM
&g
] Using PETSc GPU backend
Thanks Jacob.
From: Jacob Faibussowitsch
Sent: Saturday, August 12, 2023 5:02 AM
To: Ng, Cho-Kuen
Cc: Barry Smith ; petsc-users
Subject: Re: [petsc-users] Using PETSc GPU backend
> Can petsc show the number of GPUs used?
-device_view
B
Thanks Jacob.
From: Jacob Faibussowitsch
Sent: Saturday, August 12, 2023 5:02 AM
To: Ng, Cho-Kuen
Cc: Barry Smith ; petsc-users
Subject: Re: [petsc-users] Using PETSc GPU backend
> Can petsc show the number of GPUs used?
-device_view
Best regards,
Ja
gt; Thanks,
> Cho
>
> From: Barry Smith
> Sent: Wednesday, August 9, 2023 4:09 PM
> To: Ng, Cho-Kuen
> Cc: petsc-users@mcs.anl.gov
> Subject: Re: [petsc-users] Using PETSc GPU backend
>
> We would need more information about "hanging". Do PETSc examples a
show the number of GPUs used?
Thanks,
Cho
From: Barry Smith
Sent: Wednesday, August 9, 2023 4:09 PM
To: Ng, Cho-Kuen
Cc: petsc-users@mcs.anl.gov
Subject: Re: [petsc-users] Using PETSc GPU backend
We would need more information about "hanging"
>
> Best,
> Cho
>
> From: Barry Smith mailto:bsm...@petsc.dev>>
> Sent: Monday, July 17, 2023 6:58 AM
> To: Ng, Cho-Kuen mailto:c...@slac.stanford.edu>>
> Cc: petsc-users@mcs.anl.gov <mailto:petsc-users@mcs.anl.gov>
> mailto:petsc-users@mcs.a
: Barry Smith
Sent: Monday, July 17, 2023 6:58 AM
To: Ng, Cho-Kuen
Cc: petsc-users@mcs.anl.gov
Subject: Re: [petsc-users] Using PETSc GPU backend
The examples that use DM, in particular DMDA all trivially support using the
GPU with -dm_mat_type aijcusparse -dm_vec_type cuda
On Jul 17, 2023
etsc-users@mcs.anl.gov>
> mailto:petsc-users@mcs.anl.gov>>
> Subject: Re: [petsc-users] Using PETSc GPU backend
>
>
>
>Cho,
>
> We currently have a crappy API for turning on GPU support, and our
> documentation is misleading in places.
>
&g
Subject: Re: [petsc-users] Using PETSc GPU backend
Cho,
We currently have a crappy API for turning on GPU support, and our
documentation is misleading in places.
People constantly say "to use GPU's with PETSc you only need to use
-mat_type aijcusparse (for example)" This is
tthew Knepley mailto:knep...@gmail.com>>
>> Sent: Friday, July 14, 2023 5:57 PM
>> To: Ng, Cho-Kuen mailto:c...@slac.stanford.edu>>
>> Cc: Barry Smith mailto:bsm...@petsc.dev>>; Mark Adams
>> mailto:mfad...@lbl.gov>>; petsc-users@mcs.anl.gov
>> <mai
c:* Barry Smith ; Mark Adams ;
> petsc-users@mcs.anl.gov
> *Subject:* Re: [petsc-users] Using PETSc GPU backend
>
> On Fri, Jul 14, 2023 at 7:57 PM Ng, Cho-Kuen
> wrote:
>
> I managed to pass the following options to PETSc using a GPU node on
> Perlmutter.
>
> -mat
nused options." However, there is no improvement on the GPU
performance.
Thanks,
Cho
From: Matthew Knepley
Sent: Friday, July 14, 2023 5:57 PM
To: Ng, Cho-Kuen
Cc: Barry Smith ; Mark Adams ;
petsc-users@mcs.anl.gov
Subject: Re: [petsc-users] Using PETSc G
r
> of magnitude slower. How can I improve the GPU performance?
>
> Thanks,
> Cho
> --
> *From:* Ng, Cho-Kuen
> *Sent:* Friday, June 30, 2023 7:57 AM
> *To:* Barry Smith ; Mark Adams
> *Cc:* Matthew Knepley ; petsc-users@mcs.anl.gov <
> p
slower. How can I improve the GPU performance?
Thanks,
Cho
From: Ng, Cho-Kuen
Sent: Friday, June 30, 2023 7:57 AM
To: Barry Smith ; Mark Adams
Cc: Matthew Knepley ; petsc-users@mcs.anl.gov
Subject: Re: [petsc-users] Using PETSc GPU backend
Barry, Mark and Matt
Paul,
Thank you for your suggestion. I will try different spack install
specifications.
Cho
From: Grosse-Bley, Paul Leonard
Sent: Friday, June 30, 2023 4:07 AM
To: Ng, Cho-Kuen
Cc: petsc-users@mcs.anl.gov
Subject: Re: [petsc-users] Using PETSc GPU backend
Hi
: [petsc-users] Using PETSc GPU backend
Note that options like -mat_type aijcusparse -vec_type cuda only work if the
program is set up to allow runtime swapping of matrix and vector types. If you
have a call to MatCreateMPIAIJ() or other specific types then then these
options do nothing
ialize()
>> unless you shut it off.
>>
>> Thanks,
>>
>> Matt
>>
>>> Cho
>>> From: Ng, Cho-Kuen mailto:c...@slac.stanford.edu>>
>>> Sent: Thursday, June 29, 2023 8:32 PM
>>> To: Mark Adams mailto:mfad...@lbl.gov
line argument automatically in PetscInitialize()
> unless you shut it off.
>
> Thanks,
>
> Matt
>
>
>> Cho
>> --
>> *From:* Ng, Cho-Kuen
>> *Sent:* Thursday, June 29, 2023 8:32 PM
>> *To:* Mark Adams
>&g
users@mcs.anl.gov
> *Subject:* Re: [petsc-users] Using PETSc GPU backend
>
> Mark,
>
> Thanks for the information. How do I put the runtime options for the
> executable, say, a.out, which does not have the provision to append
> arguments? Do I need to change the C++ main to read i
Cc: petsc-users@mcs.anl.gov
Subject: Re: [petsc-users] Using PETSc GPU backend
Mark,
Thanks for the information. How do I put the runtime options for the
executable, say, a.out, which does not have the provision to append arguments?
Do I need to change the C++ main to read in the options
, 2023 5:55 PM
To: Ng, Cho-Kuen
Cc: petsc-users@mcs.anl.gov
Subject: Re: [petsc-users] Using PETSc GPU backend
Run with options: -mat_type aijcusparse -vec_type cuda -log_view -options_left
The last column of the performance data (from -log_view) will be the percent
flops on the GPU. Check
Run with options: -mat_type aijcusparse -vec_type cuda -log_view
-options_left
The last column of the performance data (from -log_view) will be the
percent flops on the GPU. Check that that is > 0.
The end of the output will list the options that were used and options that
were _not_ used (if
I installed PETSc on Perlmutter using "spack install petsc+cuda+zoltan" and
used it by "spack load petsc/fwge6pf". Then I compiled the application code
(purely CPU code) linking to the petsc package, hoping that I can get
performance improvement using the petsc GPU backend. However, the timing
28 matches
Mail list logo
