3D scaling could be important if there is high interdependence between the operations of each CPU, but I maintain that we may have to build new computing models to really take advantage of systems built around CPUs like this. Separate memory for each processor is a good start, since it relieves the bottleneck of access to shared memory. Data centers are a good application for this, because they often work on large numbers of independent transactions. By the way, we may also have to look at the nomenclature. I just realized that this isn't really a Central Processing Unit (CPU). It's more like a Central Processing Pool (CPP?). For that matter, is the 'processor' the chip or each of the sections of it? The same word is used for both in this article.