Slashdot Mirror
Forty Years of Moore's Law
kjh1 writes "CNET is running a great article on how the past 40 years of integrated chip design and growth has followed [Gordon] Moore's law. The article also discusses how long Moore's law may remain pertinent, as well as new technologies like carbon nanotube transistors, silicon nanowire transistors, molecular crossbars, phase change materials and spintronics. My favorite data point has to be this: in 1965, chips contained about 60 distinct devices; Intel's latest Itanium chip has 1.7 billion transistors!"
In 2003, I purchased a P4 3.06ghz, which I'm using right now to type this message. 2005-2003 = 2 years. Where are the 6.12ghz machines?
I was wondering the same thing. I just bought two new machines and was doing price/performance considerations of the Xeon processors that were available, and I decided on the 3.0 GHz. I don't have the prices handy but here are the percent increase in at least clockspeed for two years of processors
3.0->3.2 _6.67%
3.0->3.4 13.33% 3.2->3.4 6.25%
3.0->3.6 20.00% 3.4->3.6 5.88%
3.0->3.8 26.67% 3.6->3.8 5.56%
Yet (I dont have them handy) the prices go up substantially for each 0.2 GHz increase. I don't consider the difference between 3.0 and 3.4 to even be significant. So many other variables like software optimization or whatever could easily account for 13% difference. Even 26% is not that exciting to me either.
So yeah, is Moore's theory holding true? If the # of transistors are still being increased 2x every 18 months, I'm not seeing anything near that in performance.