Gordon Moore’s original graph, showing projected transistor counts, long before the term “Moore’s law” was coined. Moore’s original observation was that transistor density doubled every year; in 1975, this was revised to doubling every two years. (credit: Intel)
Intel took half a day this week to talk about processor manufacturing technology.

The company still believes in Moore’s Law and says the principle will continue to guide and shape the microchip industry.

But the way the law works is changing.

The company also wants to change how people talk about manufacturing processes, because current terminology—wherein the node size is used to characterize a particular process—no longer serves as a good guide to how many transistors can be packed into a chip.
Moore’s Law—the observation by Intel co-founder Gordon Moore that the number of transistors in an integrated circuit would double every two years, and correspondingly, the cost per transistor would halve over the same timeframe—guided microchip manufacturing for around three decades.

During that period, process node shrinks, each one bringing a doubling of the number of transistors by making everything 0.7 times smaller, were all it took to fulfill Moore’s Law.

Backed by this easy scaling, computer performance increased at a rate unrivaled by any other human technological innovation.
This scaling started to falter in the 2000s when it became increasingly difficult to shrink integrated circuits simply by switching to a smaller process node.

But this didn’t bring about an end to Moore’s Law; instead, the industry used additional techniques, such as strained silicon, high-κ metal gates, and FinFETs.

The doubling of transistor density or halving of transistor cost continued to take place every two or so years.
Read 8 remaining paragraphs

Leave a Reply