A technological phenomenon that has played a role in just about every major advance in engineering and technology for decades states that “number of electronic components which could be crammed into an integrated circuit would double every year”.
That continual shrinking has helped make computers more powerful, compact, and energy-efficient. It has moved computers from entire basements to desks to laps and hence to pockets. And Moore’s Law has become shorthand for the idea that anything involving computing gets more capable over time.
With a little more data and some simplification, this observation became “Moore’s law: the number of transistors per chip would double once every two years”. Even so, you would have to be very brave to believe that such a law would continue for 44 years, meaning double something 22 times and you have 4M times more of it, or perhaps something 4M times better.
That fulfillment was made possible largely because transistors have the unusual quality of getting better as they get smaller; a small transistor can be turned on and off with less power and at greater speeds than a larger one. This meant that you could use more and faster transistors without needing more power or generating more waste heat, and thus that chips could get bigger as well as better.
Hitting this target didn’t happen by accident. There were lots of complex processes, machinery, software and raw materials indirectly making chips much more expensive. In the early 2000s, when the features began to shrink below about 90 nanometers, that automatic benefit began to fail. As electrons had to move faster and faster through silicon circuits that were smaller and smaller, the chips began to get too hot. So manufacturers seized on solution like not increasing more clock speed and using multi-core designs.
There is a tech joke saying suppose you purchase a new PC and within taking it home and unwrapping it, you would be witnessing a TV ad showing better specs and improvised PC, such was the pace of technology.
But can this continue till next ages, the demise of this virtuous circle has been predicted many times. Now the computer industry is increasingly aware that the jig will soon be up. And while the benefits of making things smaller have been decreasing, the costs have been rising.
This brings us to a new thought.
Are the chips down for Moore’s Law? [Double, double, toil and trouble]
And the law about Moore’s law is “The number of people predicting the death of Moore’s law doubles every two years”
Moore’s law has not hit a brick wall. Chip makers are spending billions on new designs and materials that may make transistors amenable to a bit more shrinkage and allow another few turns of the exponential crank. They are also exploring ways in which performance can be improved with customized designs and cleverer programming. In the past the relentless doubling and redoubling of computing power meant there was less of an incentive to experiment with other sorts of improvement.
Chip makers are trying various methods to avoid this like “Strained Silicon”, finFET, gate-all-around” transistors. Beyond this, more exotic solutions may be needed. But will this really help us to develop what we want? Rather than focus on the technology used in the chips, the new road map will take an approach it describes as “More than Moore.”
The move is thought to be a reflection that companies are struggling to keep up with the pace of innovation required to cram ever more transistors onto a finite space. Among the most limiting issues has still been the heat generated as more and more circuitry is jammed onto a silicon chip.
While some companies have attempted to overcome this with new approaches like integrating microscopic channels to circulate water through the chip (micro-pump), progress has been slow. Other problems like the quirky way particles behave on the extremely small quantum scale will also start to become a growing problem as circuits continue to decrease in size.
Will the semiconductor industry rise again?
The end of Moore’s law will make the computer industry a much more complicated place.
The industry is hoping that they will now carry on to everything from clothes to smart homes to self-driving cars. Many of those applications demand things other than raw performance. The highly integrated chips used in these devices mean that it’s desirable to build processors that aren’t just logic and cache, but which also include RAM, power regulation, analog components for GPS, cellular, and Wi-Fi radios, or even micro electro-mechanical components such as gyroscopes and accelerometers.
The industry has essentially experienced a split into two segments. “more Moore” and “more than Moore”.
“more Moore” still exists, IC designs still move to 14nm.
”more than Moore” requires putting some smarts into play.
We can compare the future of the microchip to the airline industry, where rather than getting faster, passenger jets made use of new materials to make flying cheaper and more comfortable. A Boeing 787 doesn’t go any faster than a 707 did in the 1950s – but they are very different airplanes.
The biggest market of all is expected to be the “internet of things”—in which cheap chips and sensors will be attached to everything, from fridges that order food or washing machines that ask clothes for laundering instructions to paving slabs in cities to monitor traffic or pollution.
Consumers do not care about Moore’s law per se: “Most of the people who buy computers don’t even know what a transistor does.” They simply want the products they buy to keep getting ever better and more useful. In the past, that meant mostly going for exponential growth in speed. That road is beginning to run out. But there will still be plenty of other ways to make better computers or devices and build according to the environment/surrounding.
‘For every End, there is a new Beginning. Innovation will absolutely continue – but it will be more nuanced and complicated’
Author: Shekhar S Kulkarni, Design Engineer at CoreEL