Open MPI logo

PLPA Users' Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all PLPA Users mailing list

From: Jeff Squyres (jsquyres_at_[hidden])
Date: 2007-04-23 12:20:43


Fixed -- thanks.

On Apr 22, 2007, at 2:34 PM, Bert Wesarg wrote:

> The loop end condition for max_processor should always be '<=' no '<'.
>
> Bert Wesarg
>
> PS: sorry for the '1/3' counter in the last mail, there is no order
> here
> ---
>
> src/libplpa/plpa_map.c | 2 +-
> 1 files changed, 1 insertion(+), 1 deletion(-)
>
> diff --quilt old/src/libplpa/plpa_map.c new/src/libplpa/plpa_map.c
> --- old/src/libplpa/plpa_map.c
> +++ new/src/libplpa/plpa_map.c
> @@ -280,11 +280,11 @@ static void load_cache(void)
> &map_processor_id_to_tuple[invalid_entry];
>
> /* See if this (socket,core) tuple exists in the other
> map. If so, set this entry to point to it (overriding
> the invalid entry default). */
> - for (k = 0; k < max_processor; ++k) {
> + for (k = 0; k <= max_processor; ++k) {
> if (map_processor_id_to_tuple[k].socket == i &&
> map_processor_id_to_tuple[k].core == j) {
> map_tuple_to_processor_id[i][j] =
> &map_processor_id_to_tuple[k];
> break;
> _______________________________________________
> plpa-users mailing list
> plpa-users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/plpa-users

-- 
Jeff Squyres
Cisco Systems