Usually ... I would say no. But this is a special case (of
course :)). In order to get better performances we align some fields
in our TCP header. As a result there is a small gap in the TCP
headers, which of course don't get initialized. Valgrind detect it
and complain, but it's harmless.
I was wondering if it is expected to have error messages from valgrind
when checking openmpi code?
For instance, I have following trivial code:
#include
#include
template
void distribute_val(T& val, int _procid, int _np)
{
MPI_Bcast(&val, sizeof(T), MPI_CHAR, 0, MPI_COMM_WORLD);
}
On Thu, May 03, 2007 at 01:57:27PM +0200, Chaloupka Zden?k wrote:
> Hello,
Hi!
> MPI_Init(&argv, &argc);
>
> [chaloz@chaloupka src]$ mpicc main.cc
> /tmp/ccBJb7ZI.o: In function
> `__static_initialization_and_destruction_0(int,
> int)':main.cc:(.text+0x23): undefined reference to
> `std::io
Hello,
Chaloupka Zdenìk wrote:
> Hello,
> I tried to compile following code:
>
> #include
> #include "mpi.h"
> int main(int argv, char *argc[])
> {
> int rank;
>
> MPI_Init(&argv, &argc);
> MPI_Comm_rank(MPI_COMM_WORLD, &rank);
> if (rank == 0) printf("Starting program\n");
>
Hello,
I tried to compile following code:
#include
#include "mpi.h"
int main(int argv, char *argc[])
{
int rank;
MPI_Init(&argv, &argc);
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
if (rank == 0) printf("Starting program\n");
printf("Pocet vstupnich parametru: %d a argumenty: %s\n", ar
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hello,
I forgot to attach the sample code.
Regards,
Harald Servat wrote:
> Hello,
>
> I'm using the PERUSE API from OpenMPI in order to know when messages
> arrive. I've executed some simple tests in three different machines
> (FreeBSD/x86 1cpu
