On 09/02/2017 09:51, Santiago Vila wrote:
> On Thu, Feb 09, 2017 at 09:28:45AM +0100, Ansgar Burchardt wrote:
>> On Thu, 2017-02-09 at 00:05 +0100, Santiago Vila wrote:
>>> In either case I'm setting this to serious again because it makes
>>> packages to fail on single-CPU systems, and having
On Thu, Feb 09, 2017 at 09:28:45AM +0100, Ansgar Burchardt wrote:
> On Thu, 2017-02-09 at 00:05 +0100, Santiago Vila wrote:
> > In either case I'm setting this to serious again because it makes
> > packages to fail on single-CPU systems, and having more than one CPU
> > is
> > definitely *not*
On Thu, 2017-02-09 at 00:05 +0100, Santiago Vila wrote:
> In either case I'm setting this to serious again because it makes
> packages to fail on single-CPU systems, and having more than one CPU
> is
> definitely *not* part of the build-essential definition.
It is not, but trying to build
severity 850559 serious
thanks
On Thu, 19 Jan 2017, Graham Inggs wrote:
> On 19/01/2017 13:59, Santiago Vila wrote:
> > That would be somewhere in debian/rules (in dh_auto_build) for the affected
> > packages?
> > Or somewhere else?
>
> Yes, just add 'export OMPI_MCA_rmaps_base_oversubscribe=1'
On 19/01/2017 13:59, Santiago Vila wrote:
That would be somewhere in debian/rules (in dh_auto_build) for the affected
packages?
Or somewhere else?
Yes, just add 'export OMPI_MCA_rmaps_base_oversubscribe=1' near the top
of debian/rules.
Most MPI programs should already have 'export
On Thu, Jan 19, 2017 at 01:55:18PM +0200, Graham Inggs wrote:
> It looks like setting the environment variable
> 'OMPI_MCA_rmaps_base_oversubscribe=1' does the trick, and shouldn't break
> other MPI implementations. It's also less intrusive than patching in
> '--oversubscribe' everywhere.
That
It looks like setting the environment variable
'OMPI_MCA_rmaps_base_oversubscribe=1' does the trick, and shouldn't
break other MPI implementations. It's also less intrusive than patching
in '--oversubscribe' everywhere.
7 matches
Mail list logo
