Several high tech gurus are quite adamant about how chip design is going to evolve in the near future. In order to continue the high tech progression we have been seeing, they tend to agree on one thing in regards to predictions about future computers.
“Moore’s Law is dead. Moore’s Law is over.”
This is what Mike Muller now believes, who is the chief technology officer from major chip designer Arm, which is a Japanese-owned company who manufactures processor cores for mobile phones.
Dealing With Increased Information Speeds
Those of us who follow technology pretty much know that Moore’s Law has cranking along at a breakneck speed. This pace has made some people worry about the industry.
“On one level it’s true, but I’d say, certainly from my perspective and Arm’s perspective, we don’t care,” Muller said, as he spoke during the Arm Research Summit 2018.
Muller and his associates have very sound reasons for being indifferent about the end of Moore’s Law, which was the famous prediction claiming that the given number of transistors on a computer processor is going to double every 2 years.
To begin with, most of these Arm-based processors that are being sold in the computer market, there is still lots of room for transistors to become smaller and for chips to get much faster.
But most importantly, Arm fully believes that routine bumps in computing power which are used to affect Moore’s Law is going to continue, and will actually stem from alterations as to how these chips are designed.
3 Predictions about Future Computers
- 3D chips will keep on improving the performance of processors.
Muller thinks that chip designers will keep squeezing power from processors as they stack more processor dies and transistors on top of one another.
“There’s a whole bunch of stuff happening in 3D, whether that’s within the silicon and 3D transistors stacking within a die, [or] stacking dies together,” he noted.
“It’s become a reality in how you manufacture Flash chips, it’s a reality in what you do in servers now, where you take your large multi-core CPU and cut it up into four smaller ones and stack them.
“The yields go up and you actually have better performance and higher yield by starting to stack those processors with memory.”
- Computers will rely more on specialized chips
The systems of today already pass off workloads to processors that design to accelerate such tasks. For example, the 3D rendering to running trained machine-learning models or GPUs to Google’s TPUs, Muller is predicting that systems of the future will need to have a wider assortment of these specialized chips.
“You have to step back and say ‘What are some of the tasks we’re doing? How can we architect better accelerators to solve specific tasks? And how do we build accelerators?’” he pointed out.
“It’s a way of putting brain cycles into solving computational problems that isn’t just brute force and transistors.”
Greg Yeric, who is the director of Future Silicon Technology from Arm Research, believe that there is plenty of room to keep improving accelerators.
“For the next three to five years there’s a lot to be gained just by making better CMOS-based machine learning,” he said.
“The Google TPU is a great example. You don’t need massive amounts of accuracy to do these calculations. You can cut back on power and delay by not counting as many bits in the decimal points. Simple things like that.”
- Computers are going to move beyond silicon chips
In the very near future, it is very possible that we’ll reach the limits of conventional technologies and materials that are used to create processors, like the CMOS (Complementary metal-oxide-semiconductor) chips that are being used today.
The chips that will be installed inside systems are going to be more diverse, and the traditional CMOS chips will actually sit beside much more exotic types of processors.
“We’re going to start to see accelerators that are hardware differentiated,” says Yeric.
“So, you can have a special kind of transistor that does one thing really well, [which] doesn’t necessarily do all compute well, and you can have a chip that bolts onto a regular CMOS chip.
“We have widgets that vastly outperform CMOS on certain things. It could be photonics , it could be spintronics , it could be new memory.
“Architecting those systems is going to be a bit more of a challenge, however, I really don’t see that we’re going to have a slowdown at the system level, it’s just that the systems won’t look like a big monolithic piece of CMOS.”
Muller is saying that we should expect spintronics, neuromorphic , and quantum photonic chips to be a part of future systems.
“There is going to be, in the 10-15 year timeframe, new technology to take us beyond CMOS,” he urged.
“Products as bought by people like you and me are just going to keep getting better and better.
“Our jobs [chip designers] might be getting harder and harder, but from a consumer’s perspective there isn’t going to be a slowing down,” he points out.