The Switch

Pick up a modern graphics card and the first thing you notice is the weight. An RTX 4090 is over two kilograms of aluminium fins, copper pipes, and three fans. Almost none of that is the computer. The computer is a square of silicon about 2.5 cm on a side, hidden under the middle of the heatsink, and on that square sit 76.3 billion transistors. The rest of the card exists to feed it power and carry away the heat it makes.

Part 1 ended in 1959 with two inventions: a way to print many transistors onto one piece of silicon, and a new kind of transistor, the MOSFET, that switched by electric field rather than by current. Those two are what the 76.3 billion are made of. This part is about the switch itself: how it works, why it can only be on or off, how it got from one to 76 billion, what "4 nanometres" does and does not mean, and the physical limit that decided, twenty years ago, that the future of computing would be wide rather than fast.

A switch you flip with electricity

A light switch is a gap in a wire. Close the gap with your finger and current flows, open it and the current stops. That is the whole idea of a switch, and it is the most important idea in computing, because a switch has exactly two states and you can tell them apart from a mile away. Part 1 showed the two ways of flipping one without a finger that came before the transistor: a magnet moving an arm, and a grid throttling a stream of electrons in a vacuum.

The kind of transistor used in every modern chip is called a MOSFET (metal-oxide-semiconductor field-effect transistor, and you will never need the long form again). It is the triode with the vacuum, the glass, and the heater taken away, and the three parts renamed. It has three terminals. Current wants to flow from the source to the drain, but between them sits a thin strip of silicon that normally does not conduct. Above that strip, separated by an insulating layer only a few atoms thick, sits the gate. Put a voltage on the gate and its electric field pulls charge into the strip underneath, turning it into a conductor. Take the voltage away and the strip goes back to being an insulator. The gate never touches the channel. It flips the switch by influence alone, which is why it is called a field-effect transistor, and it is why the switch can flip billions of times a second with nothing wearing out.

The garden tap from Part 1 carries straight over. The handle is the gate, water enters at the source and leaves at the drain, and turning the handle does not itself move any water, it just opens the path. The analogy breaks in two honest places. First, a tap has a range of positions, whereas we will use the transistor at only two: fully open and fully shut. Second, a tap handle takes a second to turn, while a transistor's gate switches in a few picoseconds, a trillionth of a second. Try it below.

Why two states and not ten

Nothing about a transistor forces you to use only two states. Put a middle voltage on the gate and the channel half-conducts. Early on, some engineers built machines that used several voltage levels per wire, and there are still specialised chips today that do, including the memory in your phone. For a processor, though, two states won out, and the reason is noise.

Every wire in a chip picks up interference from its neighbours, from heat, from the power supply wobbling. If you try to carry the number 7 as "0.7 volts", a little noise turns it into 0.65 and the machine reads 6. If you carry only two values, fully on and fully off, the noise has to be enormous before anyone gets confused, and every transistor cleans the signal up again as it passes through. Two states is not a limitation, it is a design decision that buys reliability. We name the states 0 and 1, call one of them a bit, and from there on the machine counts in twos. Part 3 shows how you add and multiply with nothing but bits and switches, which is the part I found hardest to believe when I first learned it.

From one to 76 billion

The first transistor at Bell Labs was the size of a fingernail, held together with a paperclip and some wax, and for a decade transistors were made and soldered one at a time, which merely moved the tyranny of numbers from the tubes to the joints. The step that made modern computing possible was the one Part 1 ended on: Jack Kilby at Texas Instruments and Robert Noyce at Fairchild independently worked out how to make many transistors, and the wires between them, on a single piece of silicon in one manufacturing process. That is the integrated circuit, and the important word is process. You do not build a chip one transistor at a time. You draw the pattern once and then print it, in layers, using light, onto a wafer. Printing a billion transistors costs about the same as printing a thousand, which is the economic fact behind everything else in this series.

The trend that followed has a famous name. In 1965 Gordon Moore observed that the number of transistors that could economically be put on a chip was doubling roughly every year, later revised to every two years, and it kept doing so for half a century. A few points on that curve:

Notice the last line. Blackwell did not get its transistors by shrinking them further. It got them by gluing two chips together, and the reason is the subject of the next section.

What "4 nanometres" means, and what it doesn't

You will see Ada and Hopper described as "4 nm" chips, and Blackwell as "4NP". A nanometre is a billionth of a metre. A human hair is about 80,000 nm across, a virus is around 100 nm, and the spacing between atoms in silicon is about 0.5 nm. So "4 nm" sounds like a physical measurement, and it once was: the node name used to be the length of the transistor's gate. It is not any more. Somewhere around the 22 nm generation, fifteen years ago, the names came unstuck from any physical dimension and turned into marketing labels for successive generations of manufacturing. TSMC's "4N", the process Nvidia uses for Ada and Hopper, is a tuned version of TSMC's 5 nm-class family, and the TechInsights editorial Nanometer Nonsense is a good read on how little the number now tells you.

What is real is density. Divide the AD102's 76.3 billion transistors by its 608.5 mm² and you get about 125 million transistors per square millimetre. That is the number to keep in your head, because it sets a hard limit. The machines that print chips can only expose an area of roughly 850 mm² in one shot, called the reticle limit. Hopper's 814 mm² die sits right against it. If you want more transistors than the reticle allows at a given density, you have exactly one option: use more than one die. That is Blackwell's story, and it is why "how many dies per package" becomes a headline number by the end of this series.

Speed, and the price of speed

Every time a gate flips, it has to be charged up or drained, and that costs a tiny amount of energy. Tiny, but a modern chip flips billions of gates a few billion times a second. Multiply it out and you get the 450 W that an RTX 4090 draws under load, and the heatsink that outweighs the chip a thousand times over.

For decades this was manageable because of a happy accident of physics called Dennard scaling, described by Robert Dennard and colleagues at IBM in a 1974 paper: when you shrank a transistor, it also got faster and used proportionally less power, so a new generation of chips could run at a higher clock speed for the same heat. Around 2005 that stopped working. Transistors kept shrinking, but leakage current and the difficulty of lowering the voltage further meant that pushing the clock higher just made the chip hotter. The Pentium 4 hit 3.8 GHz in 2004, and twenty years later consumer chips are still in the 5 GHz range.

This one fact reshaped the industry. If you cannot make one switch flip faster, the only way to do more work is to have more switches flipping at once. CPUs went from one core to a handful. GPUs, as we will see in Part 6, took that idea to the extreme, and the end of Dennard scaling is the reason their design bet paid off.

Where this leaves us

A graphics processor is 76 billion switches, each flipped by an electric field rather than a finger, printed onto a square of silicon by light, and cooled by two kilograms of metal. Every one of those switches can only be on or off. There is nothing else in there. No numbers, no pictures, no neural network, just switches and the wires between them.

Everything from here on is about the arrangement. A few dozen switches, arranged one way, add two numbers. A few thousand multiply them. Wrap those in some memory and a clock and you have a processor. Copy that processor thousands of times, give the copies a clever way to share work, and you have a GPU. Put 72 of those in a rack and you have the machine that trains a language model. Same switch all the way up. Next, we arrange a handful of them to do the first half of w × x + b.

Next: From Switches to Sums: how switches become logic gates, how gates add and multiply, and why a multiplier that uses fewer bits is smaller, faster, and cooler, which turns out to be the whole plot of modern AI hardware.