Sebastian Soeiro (sebastian_2896.delete@this.hotmail.com) on July 31, 2013 2:15 pm wrote:
> rwessel (robertwessel.delete@this.yahoo.com) on July 30, 2013 7:01 pm wrote:
> - The TLB lies in the store components of a core. (I know you said one TLB per CPU... but then
> you said that the TLB lies in the store components, so you must've meant core, correct?)


The term CPU has been slightly ambiguous for a long time. In the early days there were no multi-processor machines, and the term CPU was fairly unambiguous (although sometimes people made a distinction between the whole box, and the processor portion of the box - excluding memory, I/O channels, etc.). With multi-processor machines, you sometime saw references to the whole box as the CPU, or the collection of individual processors, although the individual "core" (although that term had yet to be invented) was the most common usage.

With the advent of multi-core chips, you have a marketing term "CPU" applied to the thing you buy in a box marked "Intel" that you put in the socket on the motherboard. And we've started to call the individual items inside that thing "cores". Although cores are still individual processor (or CPUs).

So yes, for clarity I should have probably said "core", but in a microarchitecturally context core and CPU are pretty synonymous.

And don't get me started on Ethernet "switches". We had a perfectly good name for those ("bridges"), and switches performed an similar function but for circuit switched networks (as opposed to packet switched networks like Ethernet). But noooo... The marketing types decided they needed a "better" name... Than that nonsense got extended to other parts of the networking hierarchy. “Level 4 switches”?! You mean a *router*?

Hmmm... Too late, I'm already started...