<p>As it will come to be known</p>
Shortly after the formation of the universe, Gordon Moore climbed to the top of the world’s highest mountain whilst carrying two stone tablets, and upon reaching the top, violently threw them from the mountain, screaming:
Take that, bitch. I will be your servant no longer...
The tablets had nothing on them. He appeared to have them more for effect than for a practical purpose. He continued:
I decree, the complexity for minimum component costs has increased at a rate of roughly a factor of two per year ... Certainly over the short term this rate can be expected to continue, if not to increase...
OK so Moore’s statement is a lot less heretical than I make it sound. Let me re-write history a little so I can move forward with disparaging Moore:
I decree, the complexity for minimum component costs has increased at a rate of roughly a factor of two per year ... [This] rate can be expected to continue, if not to increase [FOREVER... MWAAAHAHAHAHAHHAAAA. PHYSICS, I WILL MAKE YOU MY BITCH!!!]
Moore’s law (as stated with the evil laughter) never sat well with me. First, it’s not a law in the Mathematical sense. It’s not even a conjecture. In fact, it’s not even a law of physics. Is it a law of economics? Of capitalism? Is it even a law? Well, no! There are significant difficulties in making increasingly smaller components. The first is more obvious, and a hard limitation: You cannot make a sub-atomic transistor. Even if you could, you can’t make a sub-sub-atomic transistor.
The second is less obvious, and deals with Moore’s Second Law (as defined in Wikipedia, which I will term “Moore's Wall”, because it’s such a great pun). For each new generation of technology, that technology will cost twice as much as the previous generation. This is fine, except you need people to buy twice as many processors. This is possible, but that’s gotta stop at some point.
Moore’s Wall is also bigger than this, though. If you double the complexity of the circuit, this does not mean that the speed will double. In many cases it does double, but often it does not. In short, we have to start looking at Moore’s Law as it was originally stated, as not a law, but the prediction of a trend. Hell, the prediction only went onto 1975, so we really should stop talking about it.