Shouldn't that be tunneling?

Intel to start shipping a quantum processor

The 12-qubit device will go out to a few academic research labs.

John Timmer – Jun 15, 2023 9:35 PM | 53

The Tunnel Falls chip in its natural habitat (dilution refrigeration hardware not shown). Credit: Intel

Intel does a lot of things, but it's mostly noted for making and shipping a lot of processors, many of which have been named after bodies of water. So, saying that the company is set to start sending out a processor called Tunnel Falls would seem unsurprising if it weren't for some key details. Among them: The processor's functional units are qubits, and you shouldn't expect to be able to pick one up on New Egg. Ever.

Tunnel Falls appears to be named after a waterfall near Intel's Oregon facility, where the company's quantum research team does much of its work. It's a 12-qubit chip, which places it well behind the qubit count of many of Intel's competitors—all of which are making processors available via cloud services. But Jim Clarke, who heads Intel's quantum efforts, said these differences were due to the company's distinct approach to developing quantum computers.

Intel being Intel

So far, both the large companies and startups that are developing quantum computers have been focused on a single technology (transmons, trapped ions, etc.) that they're betting they can be the first to scale to useful qubit counts and error rates. To the extent that they have customers, those customers are simply developing the expertise needed to use the processors should they ever become viable. That can easily be achieved by accessing the hardware via a cloud service and using a software developer's kit instead of directly controlling the hardware. So, that's what nearly everyone other than Intel has been focused on providing.

Intel, by contrast, is attempting to build silicon-based qubits that can benefit from the developments that most of the rest of the company is working on. The company hopes to "ride the coattails of what the CMOS industry has been doing for years," Clarke said in a call with the press and analysts. The goal, according to Clarke, is to make sure the answer to "what do we have to change from our silicon chip in order to make it?" is "as little as possible."

The qubits are based on quantum dots, structures that are smaller than the wavelength of an electron in the material. Quantum dots can be used to trap individual electrons, and the properties of the electron can then be addressed to store quantum information. Intel uses its fabrication expertise to craft the quantum dot and create all the neighboring features needed to set and read its state and perform manipulations.

However, Clarke said there are different ways of encoding a qubit in a quantum dot (Loss-DiVincenzo, singlet-triplet, and exchange-only, for those curious). This gets at another key difference with Intel's efforts: While most of its competitors are focused solely on fostering a software developer community, Intel is simultaneously trying to develop a community that will help it improve its hardware. (For software developers, the company also released a software developer kit.)

To help get this community going, Intel will send Tunnel Falls processors out to a few universities: The Universities of Maryland, Rochester, Wisconsin, and Sandia National Lab will be the first to receive the new chip, and the company is interested in signing up others. The hope is that researchers at these sites will help Intel characterize sources of error and which forms of qubits provide the best performance.

Not quite a road map

That said, Intel plans to make many improvements on its own. Clarke described how the company is fabricating entire wafers filled with quantum chips, with a yield rate of over 95 percent on the individual processors on the wafer. The company has also developed hardware that allows it to cool entire wafers and test hundreds of individual chips overnight. This technology should help it figure out what works in terms of fabrication and what features are associated with better performance.

Using the chip, however, still requires hooking individual chips up to a PCB and getting it down to near absolute zero degrees in a dilution refrigeration system. This may ultimately place a bottleneck on testing, given that Intel can likely manufacture a lot more devices than it can possibly put to use—another reason why shipping them to others makes sense for the company.

While Tunnel Falls only has a dozen qubits, Clarke is confident enough in the company's fabrication capabilities that he foresees being able to have thousands of qubits with a quality sufficient to enable error correction by 2027—not too far off the expectations of the company that currently has the lead in qubit counts, IBM. Unlike IBM's transmons, however, Intel's qubits are small enough that it may be able to fit all of these on a single chip, saving the need to figure out how to entangle hardware across multiple chips. A key measure of progress here may come as early as next year when Intel promises the successor to Tunnel Falls; the number of qubits in that chip should give us a greater sense of whether things are scaling quickly enough.

Somewhere in between, the company will offer the software community access to its systems via a cloud service, but Clarke says that's not ready yet.

Overall, Intel has made a daring choice for its quantum strategy. Electron-based qubits have been more difficult to work with than many other technologies because they tend to have shorter life spans before they decohere and lose the information they should be holding. Intel is counting on rapid iteration, a large manufacturing capacity, and a large community to help it figure out how to overcome this. But testing quantum computing chips and understanding why their qubits sometimes go wrong is not an easy process; it requires highly specialized refrigeration hardware that takes roughly a day to get the chips down to a temperature where they can be used.

The company seems to be doing what it needs to do to overcome that bottleneck, but it's likely to need more than three universities to sign up if the strategy is going to work.

Listing image: Intel

John Timmer Senior Science Editor

John is Ars Technica's science editor. He has a Bachelor of Arts in Biochemistry from Columbia University, and a Ph.D. in Molecular and Cell Biology from the University of California, Berkeley. When physically separated from his keyboard, he tends to seek out a bicycle, or a scenic location for communing with his hiking boots.

53 Comments