Cunning Idea: do (almost) all the above at the same time
Eg IBM SP/Power4: 2 CPUs/chip sharing L2, multichip module
packages/links 4 chips/node, with L3 and DRAM for each CPU on
same board, with high-speed (ccNUMA) link to other nodes (see
http://www.rs6000.ibm.com/resource/features/1999/power4.html)
Advanced Computer Architecture Chapter 7.67