WHAT: Add -DOPEN_MPI=1 to the mpif77 and mpif90 command lines
WHY: Parity with mpi.h's "#define OPEN_MPI 1"
WHERE: ompi/config/ompi_setup_wrappers.m4
WHEN: v1.5.1
TIMEOUT: Friday, Feb 19
We've long-since had "#define OPEN_MPI 1" in mpi.h for anyone
In not throwing my $.02 cent on this discussion ;)
On Feb 10, 2010, at 12:50 , Lisandro Dalcin wrote:
> PS: The following question is unrelated to this thread, but my
> curiosity+laziness cannot resist... Does Open MPI has some MCA
> parameter to add a synchronization at every collective call?
Y
On 10 February 2010 14:19, Jeff Squyres wrote:
> On Feb 10, 2010, at 11:59 AM, Lisandro Dalcin wrote:
>
>> > If I remember correctly, the HPCC pingpong test synchronizes occasionally
>> > by
>> > having one process send a zero-byte broadcast to all other processes.
>> > What's a zero-byte broadc
On Feb 10, 2010, at 11:59 AM, Lisandro Dalcin wrote:
> > If I remember correctly, the HPCC pingpong test synchronizes occasionally by
> > having one process send a zero-byte broadcast to all other processes.
> > What's a zero-byte broadcast? Well, some MPIs apparently send no data, but
> > do ha
On 10 February 2010 13:42, Eugene Loh wrote:
> Here is a related case.
>
> If I remember correctly, the HPCC pingpong test synchronizes occasionally by
> having one process send a zero-byte broadcast to all other processes.
> What's a zero-byte broadcast? Well, some MPIs apparently send no data,
On 10 February 2010 11:48, Jeff Squyres wrote:
> On Feb 10, 2010, at 8:40 AM, Lisandro Dalcín wrote:
>
>> > Note that from a standards perspective, note that MPI_REDUCE *does*
>> > require at least one element -- MPI-2.2 p163:34-35:
>> >
>> > "Each process can provide one element, or a sequence
Here is a related case.
If I remember correctly, the HPCC pingpong test synchronizes
occasionally by having one process send a zero-byte broadcast to all
other processes. What's a zero-byte broadcast? Well, some MPIs
apparently send no data, but do have synchronization semantics. (No
non-r
On Feb 10, 2010, at 8:40 AM, Lisandro Dalcín wrote:
> > Note that from a standards perspective, note that MPI_REDUCE *does* require
> > at least one element -- MPI-2.2 p163:34-35:
> >
> > "Each process can provide one element, or a sequence of elements..."
>
> Are you really convinced that suc
On 10 February 2010 09:31, Jeff Squyres wrote:
> Thanks for the reminder.
>
> Note that from a standards perspective, note that MPI_REDUCE *does* require
> at least one element -- MPI-2.2 p163:34-35:
>
> "Each process can provide one element, or a sequence of elements..."
>
Are you really conv
Thanks for the reminder.
Note that from a standards perspective, note that MPI_REDUCE *does* require at
least one element -- MPI-2.2 p163:34-35:
"Each process can provide one element, or a sequence of elements..."
So I think that George's assertion is correct: your test code is incorrect.
B
10 matches
Mail list logo
