This article is more than 1 year old
The huge flaw in Moore’s Law? It's NOT a law after all
From homemade nitroglycerine to Intel: Meet Gordon Moore
Running out of steam
Realistically, Moore’s Law as specifically applied to microprocessors is now seriously running out of steam, and most industry observers feel that without excessive stoking by Intel itself, it may have hit the buffers much sooner.
Physical limits have now come into play. In January Intel announced the Broadwell processors that it would be putting in mainstream PCs in 2015.
At just 14nm these chips were built to fit into the very thinnest and lightest devices, and the new die-size should accommodate performance increases for another few years yet. Intel may push on through 10nm, even 7nm, but sooner or later heat dissipation issues in such tiny form factors will force the issue.
Radical data transmission methods, coupled with new active physical compounds supplementing current silicon substrates, will need to be pulled out of the hat to uphold the law.
In 2005, on the 40th anniversary of his law, Moore himself conceded that his early projections could not last. "It can't continue forever. The nature of exponentials is that you push them out and eventually disaster happens," he said.
"In terms of size [of transistors] you can see that we're approaching the size of atoms which is a fundamental barrier, but it'll be two or three generations before we get that far," he added.
“That's as far out as we've ever been able to see. We have another 10 to 20 years before we reach a fundamental limit. By then they'll be able to make bigger chips and have transistor budgets in the billions."
Whether or not Moore’s Law is still credible in its original or revised forms, its broader legacy is undeniable.
In many ways it became a self-fulfilling prophecy in the computing industry for much of the past 50 years, and that influence has branched into many other scientific fields in which measurable progress can be observed to be moving more forward or less exponentially – the speed of genome modelling, nanotechnology miniaturisation, solar power efficiency, digital photography pixel density and so on.
Moore’s idea not only predicted the development rate of computing power, it set an ambitious pace for all IC manufacturers to maintain. Moore inadvertently drove the global race for miniaturization in the semiconductor industry, and provided clear if somewhat arbitrary annual targets.
As a result business computing innovation and consumer electronic production were each propelled at breakneck pace.
It may or may not be at the end of its life, but its legacy is undoubted. As Moore himself has noted, semiconductor technology has been the key to modern electronics, changing the way the world works.
“It has allowed us to make more and more high-performance circuits. They were the key product in making computers relatively ubiquitous. Places that were completely isolated recently now are connected to the rest of the world."
“And of course it is the technology that has enabled all of the internet applications that consume people today.”
It laid the runway for Intel, too. ®