[OMPI users] What causes the pingpong bandwidth "hump" on SM?

[BRADLEY, PETER C PW]

I'm curious what causes the hump in the pingpong bandwidth curve when running 
on shared memory.  Here's an example running on a fairly antiquated 
single-socket 4 core laptop with linux (2.6.32 kernel).  Is this a cache 
effect?  Something in OpenMPI itself, or a combination?


[Macintosh HD:Users:up:Pictures:bandwidth_onepair_onenode.png]

Pete