Brice Goglin, le Tue 29 Jun 2010 11:26:52 +0200, a écrit :
> * The matrix that I keep inside the topology is ordered by os_indexes
> since logical indexes may change later in the discovery (depending on
> the matrix itself, when we group according to distances)
> * I wonder if the current code works if the NUMA physical indexes are
That might pose problem: you never know whether an OS will have
(potentially very) sparse indexes.