What is the law of moore and what is it for?

Moore's Law refers to an observation made by Intel co-founder Gordon Moore in 1965, in which he discovered that the number of transistors per square inch in integrated circuits had been doubling year after year since its invention.

Moore's Law predicts that this trend will remain intact for years to come. Although the rate has decreased, the number of transistors per square inch doubled approximately every year and a half. This is used as the current definition of Moore's Law.

Index of contents

The simplified version of this law states that processor speeds or overall computing power for computers will double every two years. A quick check between technicians from different computer companies shows that the term is not very popular, but the rule is still accepted.

If we examined processor speeds from 1970 to 2018 and then again in 2019, we might think that the law has reached its limit or is approaching. In the 1970s, processor speeds ranged from 740 KHz to 8 MHz. However, the law is actually more accurate to apply to transistors than to speed.

The amount of computing power that we can now use on the smallest devices is somewhat remarkable compared to what could be achieved, say, a decade ago.

Looking back, even five years or so, a PC that was the best at the time would be considered outdated if compared to a current PC.

This is possible simply because chip manufacturers are able to increase the number of transistors on a chip significantly each year, as advances in chip research improve.

The extension of Moore's Law is that computers, computer-powered components, and computing power become smaller and faster over time, as transistors in integrated circuits become more efficient.

Transistors are simple electronic on-off switches integrated into microchips, processors, and small electrical circuits. The faster they process electrical signals, the more efficient a computer becomes.

The costs of these higher-powered computers also decreased over time, generally around 30 percent a year. When hardware designers increased the performance of computers with better integrated circuits, manufacturers were able to create better machines that could automate certain processes. This automation created lower-priced products for consumers, as hardware created lower labor costs.

Moore's Law in today's society

Fifty years after Moore's Law, contemporary society sees dozens of benefits exposed by this law. Mobile devices, such as smartphones and desktop computers, would not work without very small processors. Smaller, faster computers improve transportation, healthcare, education, and energy production. Almost every facet of a high-tech society benefits from the Moore's Law concept put into practice.

Today, all consumer processors are made of silicon, the second most abundant element in the Earth's crust, after oxygen. But silicon is not a perfect conductor, and the limits to the mobility of electrons it carries place a hard limit on how thickly you can pack silicon transistors.

But not only is power consumption a huge problem, but also an effect called a quantum tunnel can cause problems keeping electrons contained beyond a certain thickness threshold.

Silicon transistors currently reach 14 nanometers, and while some 10-nanometer chip designs will hit the market soon, it has been concluded that to comply with Moore's Law for a long period of time, companies will have to create newer and better materials to be the foundation of next-generation computers.

Moore's Law in the future

Thanks to nanotechnology, some transistors are smaller than a virus. These microscopic structures contain perfectly aligned silicon and carbon molecules that help move electricity along the circuit faster.

Eventually, the temperature of the transistors makes it impossible to create smaller circuits, because cooling the transistors requires more energy than what passes through the transistors. Experts show that computers should reach the physical limits of Moore's Law sometime in the next few years. When that happens, computer scientists will have to examine completely new ways of creating computers.

Applications and software could improve the speed and efficiency of computers in the future, rather than physical processes. Cloud technology, wireless communication, the Internet of Things, and quantum physics could also play an important role in information technology innovation.

Progress toward doubling the number of circuits has slowed down, and integrated circuits can't get much smaller as transistors get closer to the size of an atom.

At some point in the future, advances in software or hardware may keep the dream of Moore's Law alive. However, the computer industry seems to be ready to turn to another course that will advance in a few years.

The progress of Moore's Law

Although Moore's Law had said it every two years, this rapid increase in technological production has shortened the period in the minds of technicians and users alike.

The limitation that exists is that once transistors can be created as small as atomic particles, then there will be no more room for growth in the CPU market when it comes to speeds.

Moore noted that the total number of components in these circuits had approximately doubled each year, so he extrapolated this annual duplication to the following decade, estimating that the 1975 microcircuits would contain a staggering 65, 000 components per chip.

In 1975, as the growth rate began to slow, Moore revised his two-year time frame. His revised law was a little pessimistic; About 50 years after 1961, the number of transistors doubled approximately every 18 months. Subsequently, magazines regularly referred to Moore's Law as if it were a technological law with the security of Newton's laws of motion.

What made this dramatic explosion in circuit complexity possible was the shrinking size of transistors over decades.

Transistor characteristics that measure less than a micron were achieved during the 1980s, when dynamic random access memory (DRAM) chips began to offer megabyte storage capabilities.

At the dawn of the 21st century, these features approached 0.1 microns wide, enabling the manufacture of gigabyte memory chips and microprocessors operating at gigahertz frequencies. Moore's Law continued in the second decade of the 21st century with the introduction of tens- nanometer three-dimensional transistors.

The near end of Moore's Law

Because Moore's Law suggests exponential growth, it is unlikely to continue indefinitely. Most experts expect Moore's Law to last another two decades. Some studies have shown that physical limitations could be reached in 2018.

According to a recent report from the International Technology Roadmap for Semiconductors (ITRS), which includes chip giants like Intel and Samsung itself, the transistors could reach a point where they couldn't be further reduced by 2021. The companies allege that, in order to then, it will no longer be economically feasible to make them smaller, finally ending Moore's Law.

This means that although they could physically get smaller, in theory they would achieve what the ITRS calls its “economic minimum”, which means that doing so would only make costs prohibitive.

This is not the first time that Moore's theory has been questioned. Last year, Intel Chief Executive Brian Krzanich announced that resizing from one transistor to another is taking two to two and a half years. Krzanich questioned this during an earnings call from Intel, saying that manufacturing processes have not progressed at the same rate as in the past.

However, the ITRS believes that this does not mean the end of the concept behind the Act, as manufacturers find increasingly innovative ways to introduce more switches in a given space. Take for example Intel's 3D NAND technology, which involves stacking 32 layers of memory on top of each other to create huge storage capacities.

Final words and conclusion

Until now, Moore's Law has proven correct, over and over again, and as a result has long been said to be responsible for most advancements in the digital age, from PCs to supercomputers, due to its Use in the semiconductor industry to guide long-term planning and set goals for research and development.

Moore's Law is a law of economics, not a physical one. It indicates that each new chip will have twice as many transistors and will therefore calculate the capacity of the previous generation for the same production cost.

This simple rule of thumb has fueled all advances in the technological revolution for over half a century and continues to define the ever-widening limits of today's technology, allowing us to take concepts like artificial intelligence and autonomous vehicles - and make them happen.

This law gained notoriety because people like laws that allow them to predict the future of one of the world's largest industries, but the physical basis of this principle means that it is slightly different, and less reliable, than many people believe.

The physical limitations in making these chips could easily push that number back to five years or more, effectively invalidating Moore's Law forever.

Source Images Wikimedia Commons