I’m no expert here, but here’s something: Box 1, no NUMA: ~$ dmesg | grep -i numa [ 0.000000] No NUMA configuration found Box 2, some NUMA: ~$ dmesg | grep -i numa [ 0.000000] NUMA: Initialized distance table, cnt=8 [ 0.000000] NUMA: Node 4 [0,80000000) + [100000000,280000000) -> [0,280000000)
The first thing I want to point out is that you might want to double-check which cores are on each node. I don’t recall cores and nodes being interleaved like that. Also, you should have 16 threads due to HT. (unless you disabled it) Another thing: The socket 1366 Xeon machines are only slightly NUMA. … Read more
[I would make this a comment, but do not have enough reputation to do so.] I have a similar system and see similar results, but can add a few data points: If you reverse the direction of your naive memcpy (i.e. convert to *p_dest– = *p_src–), then you may get much worse performance than for … Read more