I would start at a lower level. Clear your error counters then run some
fabric over the network, maybe using an IMB or OSU benchmark.
Then look to see if any ports are very noisy - that usually indicates a
cable needing a reseat or replacement.
Now start at a low level. Run IMB or OSU bandwidth o
Hi,
I'm trying to compile the latest OpenMPI version with Infiniband support
in our local cluster, but didn't get very far (since I'm installing this
via Spack, I also asked in their support group).
I'm doing the installation via Spack, which is issuing the following
.configure step (see the opti
Hi all,
Say I have some int `x`. I want to check if all MPI ranks get the same
value for `x`. What's a good way to achieve this using MPI collectives?
The simplest I could think of is, broadcast rank0's `x`, do the comparison,
and allreduce-LAND the comparison result. This requires two collective
Hi Niranda,
A pattern I have seen in several places is to allreduce the pair p =
{-x,x} with MPI_MIN or MPI_MAX. If in the resulting pair p[0] == -p[1],
then everyone has the same value. If not, at least one rank had a
different value. Example:
```
bool is_same(int x) {
int p[2];
p[0] =
Thanks Joseph! I think that's a nifty trick! :-)
On Thu, Feb 17, 2022 at 4:57 PM Joseph Schuchart via users <
users@lists.open-mpi.org> wrote:
> Hi Niranda,
>
> A pattern I have seen in several places is to allreduce the pair p =
> {-x,x} with MPI_MIN or MPI_MAX. If in the resulting pair p[0] ==
Angel,
Infiniband detection likely fails before checking expanded verbs.
Please compress and post the full configure output
Cheers,
Gilles
On Fri, Feb 18, 2022 at 12:02 AM Angel de Vicente via users <
users@lists.open-mpi.org> wrote:
> Hi,
>
> I'm trying to compile the latest OpenMPI version
