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 > non-contigous That might pose problem: you never know whether an OS will have (potentially very) sparse indexes. Samuel
