The Chip Shortage, Giant Chips, and the Future of Moore’s Law

IEEE Spectrum’s biggest semiconductor headlines of 2021

6 min read
The Chip Shortage, Giant Chips, and the Future of Moore’s Law

Employees work on the production line at the Volkswagen Autoeuropa car factory in Palmela, Spain on May 13, 2020.

Carlos Costa/AFP/Getty Images

With COVID-19 shaking the global supply chain like an angry toddler with a box of jelly beans, the average person had to take a crash course in the semiconductor industry. And many of them didn't like what they learned. Want a new car? Tough luck, not enough chips. A new gaming system? Same. But you are not the average person, dear reader. So, in addition to learning why there was a chip shortage in the first place, you also discovered that you can—with considerable effort—fit more than 2 trillion transistors on a single chip. You also found that the future of Moore's Law depends as much on where you put the wires as how small you make the transistors, among many other things.

So to recap the semiconductor stories you read most this year, we've put together this set of highlights:


How and When the Chip Shortage Will End, in 4 Charts

This year you learned the same thing that some carmakers did: Even if you think you've hedged your bets by having a diverse set of suppliers, those suppliers—or the suppliers of those suppliers—might all be using the output of the same small set of semiconductor fabs.

To recap: Carmakers panicked and canceled orders at the outset of the pandemic. Then when it seemed people still wanted cars, they discovered that all of the display drivers, power-management chips, and other low-margin stuff they needed had already been sucked up into the work/learn/live-from-home consumer frenzy. By the time they got back in line to buy chips, that line was nearly a year long, and it was time to panic again.

Chipmakers worked flat out to meet demand and have unleashed a blitz of expansion, though most of that is aimed at higher-margin chips than those that clogged the engine of the automotive sector. The latest numbers, from the chip manufacturing equipment industry association SEMI, show sales of equipment set to cross US $100 billion in 2021—a mark never before reached.

As for carmakers, they may have learned their lesson. At a gathering of stakeholders in the automotive electronics supply chain this summer at GlobalFoundries Fab 8 in Malta, N.Y., there was enthusiastic agreement that carmakers and chip makers needed to get cozy with each other. The result? GlobalFoundries has already inked agreements with both Ford and BMW.

Next-Gen Chips Will Be Powered From Below Transistors

You can make transistors as small as you want, but if you can't connect them to each other, there's no point. So Arm and the Belgian research institute Imec spent a few years finding room for those connections. The best scheme they found was to take the interconnects that carry power to logic circuits (as opposed to data) and bury them under the surface of the silicon, linking them to a power-delivery network built on the backside of the chip. This research trend suddenly became news when Intel said what sounded like "Oh yeah. We're definitely doing that in 2025."

Cerebras’s New Monster AI Chip Adds 1.4 Trillion Transistors

What has 2.6 trillion transistors, consumes 20 kilowatts, and carries enough internal bandwidth to stream a billion Netflix movies? It's generation 2 of the biggest chip ever made, of course! (And yes, I know that's not how streaming works, but how else do you describe 220 petabits per second of bandwidth?) Last April, Cerebras Systems topped its original, history-making AI processor with a version built using a more advanced chipmaking technology. The result was a more than doubling of the on-chip memory to an impressive 40 gigabytes, an increase in the number of processor cores from the previous 400,000 to a speech-stopping 850,000, and a mind-boggling boost of 1.4 trillion additional transistors.

Gob-smacking as all that is, what you can do with it is really what's important. And later in the year, Cerebras showed a way for the computer that houses its Wafer Scale Engine 2 to train neural networks with as many as 120 trillion parameters. For reference, the massive—and occasionally foul-mouthed—GPT-3 natural-language processor has 175 billion. What's more, you can now link up to 192 of these computers together.

Of course, Cerebras's computers aren't the only ones meant to tackle absolutely huge AI training jobs. SambaNova is after the same title, and clearly Google has its eye on some awfully big neural networks, too.

IBM Introduces the World’s First 2-nm Node Chip

IBM claimed to have developed what it called a 2-nanometer node chip and expects to see it in production in 2024. To put that in context, leading chipmakers TSMC and Samsung are going full-bore on 5 nm, with a possible cautious start for 3 nm in 2022. As we reminded you last year, what you call a technology process node has absolutely no relation to the size of any part of the transistors it constructs. So whether IBM's process is any better than rivals will really come down to the combination of density, power consumption, and performance.

The real importance is that IBM's process is another endorsement of nanosheet transistors as the future of silicon. While each big chipmaker is moving from today's FinFET design to nanosheets attheir own pace, nanosheets are inevitable.

RISC-V Star Rises Among Chip Developers Worldwide

The news hasn't all been about transistors. Processor architecture is increasingly important. Your smartphones' brains are probably based on an Arm architecture, your laptop and the servers it's so attached to are likely based on the x86 architecture. But a fast-growing cadre of companies, particularly in Asia, are looking to an open-source chip architecture called RISC-V. The attraction is to allow startups to design custom chips without the costly licensing fees for proprietary architectures.

Even big companies like Nvidia are incorporating it, and Intel expects RISC-V to boost its foundry business. Seeing RISC-V as a possible path to independence in an increasingly polarized technology landscape, Chinese firms are particularly bullish on RISC-V. Only last month, Alibaba said it would make the source code available for its RISC-V core.

New Optical Switch Up to 1,000x Faster Than Transistors

Although certain types of optical computing are getting closer, the switch researchers in Russia and at IBM described in October is likely for a computer that's far in the future. Relying on exotic stuff like exciton-polaritons and Bose-Einstein condensates, the device switched at about 1 trillion times per second. That's so fast that light would manage only about one third of a millimeter before the device switches again.

New Type of DRAM Could Accelerate AI

One of AI's big problems is that its data is so far away. Sure, that distance is measured in millimeters, but these days that's a long way. (Somewhere there's an Intel 4004 saying, "Back in my day, data had to go 30 centimeters, uphill, in a snowstorm.") There are lots of ways engineers are coming up with to shorten that distance. But this one really caught your attention:

Instead of building DRAM from silicon transistors and a metal capacitor built above it, use a second transistor as the capacitor and build them both above the silicon from oxide semiconductors. Two research groups showed that these transistors could keep their data way longer than ordinary DRAM, and they could be stacked in layers above the silicon, giving a much shorter path between the processor an its precious data.

Intel Unveils Big Processor Architecture Changes

In August Intel unveiled what it called the company's biggest processor architecture advances in a decade. They included two new x86 CPU core architectures—the straightforwardly named Performance-core (P-core) and Efficient-core (E-core). The cores are integrated into Alder Lake, a "performance hybrid" family of processors that includes new tech to let the upcoming Windows 11 OS run CPUs more efficiently.

"This is an awesome time to be a computer architect," senior vice president and general manager Raja Koduri said at the time. The new architectures and SoCs Intel unveiled "demonstrate how architecture will satisfy the crushing demand for more compute performance as workloads from the desktop to the data center become larger, more complex, and more diverse than ever."

If you want, you could translate that as: "In your face, process technology and device scaling! It's all about the architecture now!" But I don't think Koduri would take it that far.

U.S. Takes Strategic Step to Onshore Electronics Manufacturing

A bit alarmed by just how geographically close China is to Taiwan and Samsung, the only two countries capable of making the most advanced logic chips, U.S. lawmakers got the ball rolling on an effort to boost cutting-edge chipmaking in the United States. Some of that has already started with TSMC, Samsung, and Intel making major fab investments. Of course, Taiwan and South Korea are also making major domestic investments, as are Europe and Japan.

It’s all part of a broader economic and technological nationalism playing out across the world, notes geopolitical futurist Abishur Prakash, with the Center for Innovating the Future, in Toronto. Some see these “shifts in geopolitics as short term, as if they’re by-products of the pandemic and that things on a certain timeline will calm down if not return to normal,” he told IEEE Spectrum in May. “That’s wrong. The direction that nations are moving in now is the new permanent North Star.”

Event-Based Camera Chips Are Here. What’s Next?

Hey, remember all that brain-based processing stuff we've been banging on about for decades? Well, it's here now, in the form of a camera chip made by French startup Prophesee and major imager manufacturer Sony. Unlike a regular imager, this chip doesn't capture frame after frame with each tick of the clock. Instead it notes only the changes in a scene. That means both much lower power—when there's nothing happening, there's nothing to see—and faster response times.

The Conversation (3)
Jason Sachs29 Dec, 2021
M

"A bit alarmed by just how geographically close China is to Taiwan and Samsung," -- Samsung isn't a country.

Buddy Nguyen28 Dec, 2021

Carmakers jumped out of line for their chips during the pandemic but they're mostly using this excuse cause ICE is their bread and butter. They have nothing pure EV the public wants while Tesla and the Chinese EVs who seem to have no problem getting chips even though they use many more chips than the ICE OEMs.

1 Reply
A robot suspended by red cables holding a drumstick descends towards a cymbal in a dramatically lit warehouse

Video Friday: Robots at Night

3 min read

The Inner Beauty of Basic Electronics

Open Circuits showcases the surprising complexity of passive components

5 min read
A photo of a high-stability film resistor with the letters "MIS" in yellow.
All photos by Eric Schlaepfer & Windell H. Oskay
Blue

Eric Schlaepfer was trying to fix a broken piece of test equipment when he came across the cause of the problem—a troubled tantalum capacitor. The component had somehow shorted out, and he wanted to know why. So he polished it down for a look inside. He never found the source of the short, but he and his collaborator, Windell H. Oskay, discovered something even better: a breathtaking hidden world inside electronics. What followed were hours and hours of polishing, cleaning, and photography that resulted in Open Circuits: The Inner Beauty of Electronic Components (No Starch Press, 2022), an excerpt of which follows. As the authors write, everything about these components is deliberately designed to meet specific technical needs, but that design leads to “accidental beauty: the emergent aesthetics of things you were never expected to see.”

From a book that spans the wide world of electronics, what we at IEEE Spectrum found surprisingly compelling were the insides of things we don’t spend much time thinking about, passive components. Transistors, LEDs, and other semiconductors may be where the action is, but the simple physics of resistors, capacitors, and inductors have their own sort of splendor.

High-Stability Film Resistor

A photo of a high-stability film resistor with the letters "MIS" in yellow.

All photos by Eric Schlaepfer & Windell H. Oskay

This high-stability film resistor, about 4 millimeters in diameter, is made in much the same way as its inexpensive carbon-film cousin, but with exacting precision. A ceramic rod is coated with a fine layer of resistive film (thin metal, metal oxide, or carbon) and then a perfectly uniform helical groove is machined into the film.

Instead of coating the resistor with an epoxy, it’s hermetically sealed in a lustrous little glass envelope. This makes the resistor more robust, ideal for specialized cases such as precision reference instrumentation, where long-term stability of the resistor is critical. The glass envelope provides better isolation against moisture and other environmental changes than standard coatings like epoxy.

15-Turn Trimmer Potentiometer

A photo of a blue chip
A photo of a blue chip on a circuit board.

It takes 15 rotations of an adjustment screw to move a 15-turn trimmer potentiometer from one end of its resistive range to the other. Circuits that need to be adjusted with fine resolution control use this type of trimmer pot instead of the single-turn variety.

The resistive element in this trimmer is a strip of cermet—a composite of ceramic and metal—silk-screened on a white ceramic substrate. Screen-printed metal links each end of the strip to the connecting wires. It’s a flattened, linear version of the horseshoe-shaped resistive element in single-turn trimmers.

Turning the adjustment screw moves a plastic slider along a track. The wiper is a spring finger, a spring-loaded metal contact, attached to the slider. It makes contact between a metal strip and the selected point on the strip of resistive film.

Ceramic Disc Capacitor

A cutaway of a Ceramic Disc Capacitor
A photo of a Ceramic Disc Capacitor

Capacitors are fundamental electronic components that store energy in the form of static electricity. They’re used in countless ways, including for bulk energy storage, to smooth out electronic signals, and as computer memory cells. The simplest capacitor consists of two parallel metal plates with a gap between them, but capacitors can take many forms so long as there are two conductive surfaces, called electrodes, separated by an insulator.

A ceramic disc capacitor is a low-cost capacitor that is frequently found in appliances and toys. Its insulator is a ceramic disc, and its two parallel plates are extremely thin metal coatings that are evaporated or sputtered onto the disc’s outer surfaces. Connecting wires are attached using solder, and the whole assembly is dipped into a porous coating material that dries hard and protects the capacitor from damage.

Film Capacitor

An image of a cut away of a capacitor
A photo of a green capacitor.

Film capacitors are frequently found in high-quality audio equipment, such as headphone amplifiers, record players, graphic equalizers, and radio tuners. Their key feature is that the dielectric material is a plastic film, such as polyester or polypropylene.

The metal electrodes of this film capacitor are vacuum-deposited on the surfaces of long strips of plastic film. After the leads are attached, the films are rolled up and dipped into an epoxy that binds the assembly together. Then the completed assembly is dipped in a tough outer coating and marked with its value.

Other types of film capacitors are made by stacking flat layers of metallized plastic film, rather than rolling up layers of film.

Dipped Tantalum Capacitor

A photo of a cutaway of a Dipped Tantalum Capacitor

At the core of this capacitor is a porous pellet of tantalum metal. The pellet is made from tantalum powder and sintered, or compressed at a high temperature, into a dense, spongelike solid.

Just like a kitchen sponge, the resulting pellet has a high surface area per unit volume. The pellet is then anodized, creating an insulating oxide layer with an equally high surface area. This process packs a lot of capacitance into a compact device, using spongelike geometry rather than the stacked or rolled layers that most other capacitors use.

The device’s positive terminal, or anode, is connected directly to the tantalum metal. The negative terminal, or cathode, is formed by a thin layer of conductive manganese dioxide coating the pellet.

Axial Inductor

An image of a cutaway of a Axial Inductor
A photo of a collection of cut wires

Inductors are fundamental electronic components that store energy in the form of a magnetic field. They’re used, for example, in some types of power supplies to convert between voltages by alternately storing and releasing energy. This energy-efficient design helps maximize the battery life of cellphones and other portable electronics.

Inductors typically consist of a coil of insulated wire wrapped around a core of magnetic material like iron or ferrite, a ceramic filled with iron oxide. Current flowing around the core produces a magnetic field that acts as a sort of flywheel for current, smoothing out changes in the current as it flows through the inductor.

This axial inductor has a number of turns of varnished copper wire wrapped around a ferrite form and soldered to copper leads on its two ends. It has several layers of protection: a clear varnish over the windings, a light-green coating around the solder joints, and a striking green outer coating to protect the whole component and provide a surface for the colorful stripes that indicate its inductance value.

Power Supply Transformer

A photo of a collection of cut wires
A photo of a yellow element on a circuit board.

This transformer has multiple sets of windings and is used in a power supply to create multiple output AC voltages from a single AC input such as a wall outlet.

The small wires nearer the center are “high impedance” turns of magnet wire. These windings carry a higher voltage but a lower current. They’re protected by several layers of tape, a copper-foil electrostatic shield, and more tape.

The outer “low impedance” windings are made with thicker insulated wire and fewer turns. They handle a lower voltage but a higher current.

All of the windings are wrapped around a black plastic bobbin. Two pieces of ferrite ceramic are bonded together to form the magnetic core at the heart of the transformer.

{"imageShortcodeIds":[]}