On Sun, May 31, 2020 at 10:33 AM Drew Parsons wrote:
> On 2020-05-27 22:00, Junchao Zhang wrote:
> > On Wed, May 27, 2020 at 12:09 AM Drew Parsons
> > wrote:
> >
> >> On 2020-05-24 10:01, Drew Parsons wrote:
> >>> On 2020-05-23 23:45, Satish Balay wrote:
>
> One more issue: Most
On 2020-05-27 22:00, Junchao Zhang wrote:
On Wed, May 27, 2020 at 12:09 AM Drew Parsons
wrote:
On 2020-05-24 10:01, Drew Parsons wrote:
On 2020-05-23 23:45, Satish Balay wrote:
One more issue: Most externalpackages don't support
64bit-indices.
...
We haven't tried using MUMPS in this
On Wed, May 27, 2020 at 12:09 AM Drew Parsons wrote:
> On 2020-05-24 10:01, Drew Parsons wrote:
> > On 2020-05-23 23:45, Satish Balay wrote:
> >>
> >> One more issue: Most externalpackages don't support 64bit-indices.
> ...
> >> We haven't tried using MUMPS in this mode with PETSc
> >
> > This
On 2020-05-24 10:01, Drew Parsons wrote:
On 2020-05-23 23:45, Satish Balay wrote:
One more issue: Most externalpackages don't support 64bit-indices.
...
We haven't tried using MUMPS in this mode with PETSc
This will be the interesting test. I'll start with the 64-bit build of
MUMPS and see
Drew Parsons writes:
> On 2020-05-23 14:49, Drew Parsons wrote:
>> On 2020-05-23 14:18, Jed Brown wrote:
>>
>>> I wonder if you are aware of any static analysis tools that can
>>> flag implicit conversions of this sort:
>>>
>>> int64_t n = ...;
>>> for (int32_t i=0; i>> ...
>>> }
>>>
>>>
On 2020-05-23 14:49, Drew Parsons wrote:
On 2020-05-23 14:18, Jed Brown wrote:
I wonder if you are aware of any static analysis tools that can
flag implicit conversions of this sort:
int64_t n = ...;
for (int32_t i=0; i
I'll ask the Debian gcc team and the Science team if they have ideas
On 2020-05-23 23:45, Satish Balay wrote:
One more issue: Most externalpackages don't support 64bit-indices.
Note: OpenBLAS supports 64bit indices. MKL has bunch of packages built
as ILP64
[MPICH/OpenMPI - as far as I know is LP64]
The primary reason PETSc defaults to 32bit indices is -
On 2020-05-23 20:27, Junchao Zhang wrote:
On Sat, May 23, 2020 at 1:49 AM Drew Parsons
wrote:
On 2020-05-23 14:18, Jed Brown wrote:
You don't need to change BLAS or MPI.
I see, the PETSc API allows for PetscBLASInt and PetscMPIInt
distinct
from PetscInt. That gives us more flexibility.
On Sat, 23 May 2020, Junchao Zhang wrote:
> On Sat, May 23, 2020 at 1:49 AM Drew Parsons wrote:
>
> > On 2020-05-23 14:18, Jed Brown wrote:
> > > Drew Parsons writes:
> > >
> > >> Hi, the Debian project is discussing whether we should start providing
> > >> a
> > >> 64 bit build of PETSc
On Sat, 23 May 2020, Drew Parsons wrote:
> On 2020-05-23 14:18, Jed Brown wrote:
> > Drew Parsons writes:
> >
> >> Hi, the Debian project is discussing whether we should start providing a
> >> 64 bit build of PETSc (which means we'd have to upgrade our entire
> >> computational library stack,
On Sat, May 23, 2020 at 1:49 AM Drew Parsons wrote:
> On 2020-05-23 14:18, Jed Brown wrote:
> > Drew Parsons writes:
> >
> >> Hi, the Debian project is discussing whether we should start providing
> >> a
> >> 64 bit build of PETSc (which means we'd have to upgrade our entire
> >> computational
On 2020-05-23 14:18, Jed Brown wrote:
Drew Parsons writes:
Hi, the Debian project is discussing whether we should start providing
a
64 bit build of PETSc (which means we'd have to upgrade our entire
computational library stack, starting from BLAS and going through MPI,
MUMPS, etc).
You
Drew Parsons writes:
> Hi, the Debian project is discussing whether we should start providing a
> 64 bit build of PETSc (which means we'd have to upgrade our entire
> computational library stack, starting from BLAS and going through MPI,
> MUMPS, etc).
You don't need to change BLAS or MPI.
13 matches
Mail list logo
