Hi,
Adding the following rules to openmpi-valgrind.supp removes all
warnings from valgrind about memory leaks and incorrect reads (at
least for the MPI programs I tried it on). Posting them in the mailing
list in case someone wants to add them to the default suppression
file:
{
writev suppressi
Patrik Jonsson wrote:
Hi all,
I'm seeing performance issues I don't understand in my multithreaded
MPI code, and I was hoping someone could shed some light on this.
The code structure is as follows: A computational domain is decomposed
into MPI tasks. Each MPI task has a "master thread" that re
On Fri, Dec 17, 2010 at 5:43 PM, Sashi Balasingam wrote:
> Hi,
> I recently started on an MPI-based, 'real-time', pipelined-processing
> application, and the application fails due to large time-jitter in sending
> and receiving messages. Here are related info -
>
> 1) Platform:
> a) Intel Box: Two
different machines?
>
>
> On Nov 10, 2010, at 12:29 AM, Yiannis Papadopoulos wrote:
>
>> Hello,
>>
>> I am using OpenMPI 1.4.1. I have a small test case that calls
>> MPI_Test() too many times. I see one or two random time spikes when
>> this happens. On the othe
Hello,
I am using OpenMPI 1.4.1. I have a small test case that calls
MPI_Test() too many times. I see one or two random time spikes when
this happens. On the other hand, if I avoid calling MPI_Test() based
on a timeout, this problem disappears.
For example, with no timeout, the results I'm gettin
Hi,
In my code I need to specify for some processes to create a group.
Now, in general the way of doing that is (correct me if I'm wrong):
int ranks[] = { 1,2,3 };
int rank;
MPI_Group world_group = MPI_GROUP_NULL;
MPI_Group subgroup = MPI_GROUP_NULL;
MPI_Comm subcomm = MPI_COMM_NULL;
MPI_Comm_ra