On Tuesday, the quantum computing startup Quera laid out a road map that will bring error correction to quantum computing in only two years and enable useful computations using it by 2026, years ahead of when IBM plans to offer the equivalent. Normally, this sort of thing should be dismissed as hype. Except the company is Quera, which is a spinoff of the Harvard Universeity lab that demonstrated the ability to identify and manage errors using hardware that’s similar in design to what Quera is building.
Also notable: Quera uses the same type of qubit that a rival startup, Atom Computing, has already scaled up to over 1,000 qubits. So, while the announcement should be viewed cautiously—several companies have promised rapid scaling and then failed to deliver—there are some reasons it should be viewed seriously as well.
It’s a trap!
Current qubits, regardless of their design, are prone to errors during measurements, operations, or even when simply sitting there. While it’s possible to improve these error rates so that simple calculations can be done, most people in the field are skeptical it will ever be possible to drop these rates enough to do the elaborate calculations that would fulfill the promise of quantum computing. The consensus seems to be that, outside of a few edge cases, useful computation will require error-corrected qubits.
Error-corrected qubits spread individual bits of quantum information across several hardware qubits and connect these with additional qubits that allow identification and correction of errors. As a result, these “logical qubits” may require a dozen or more hardware qubits to function well enough to be useful. So, enabling that means generating hardware with thousands or tens of thousands of qubits, each with a sufficiently low error rate to ensure we can catch and correct any glitches before they ruin calculations.
IBM and several of its competitors are using electronic devices called transmons as their hardware qubits. Transmons are relatively simple to control, and their quality has been improving iteratively as companies get experience with fabricating devices. But they require bulky wiring to control and are large enough that any useful quantum processor will require integrating multiple transmon-containing chips.
Quera and some other companies have opted for qubits based on neutral atoms, with individual atoms held in traps formed by laser beams. These have several advantages. Unlike transmons, atoms do not suffer from device-to-device variations, and they’re incredibly compact—many thousands can potentially be held in a square centimeter. Qubits based on the spin of an atomic nucleus also hold its information for a relatively long time before suffering an error (with “long time” meaning more than a second here). Operations and readouts can also be performed using lasers, eliminating any wiring challenges.
Finally, the atoms can be moved around, potentially allowing any atom to be entangled with any other. This provides a degree of flexibility that’s impossible with the permanent wiring used to connect transmons.
Scaling challenges
The main challenge at this point appears to be scaling the number of atoms available. “we need about a milliwatt of laser power to hold each qubit,” Quera’s Yuval Boger told Ars. “So if you have 10,000 qubits, you need 10 watts, and this is 10 watts that’s available for the optical tweezers [that trap the atoms].” That laser also has to be relatively low noise for everything to work properly.
That will mean a significant jump in laser power compared to the 250 milliwatts or so needed for Quera’s current hardware. But, as noted earlier, one of its competitors has already scaled up a trapped atom system to over 1,000 qubits, so Quera will not run into problems immediately. But the company plans to hit the 10,000-qubit mark by 2026, so it doesn’t have much time before it will face larger challenges.
Another issue is that moving the atoms is relatively slow compared to other operations. That’s not an issue on Quera’s existing hardware; it might become more of a factor when thousands of atoms have to be moved around a much larger grid. Atom Computing, which also uses trapped atoms, isn’t convinced this is manageable and is considering keeping its grid of atoms static.
Quera, in contrast, makes moving atoms central to its machine’s architecture. While the company plans on storing its atoms in a two-dimensional grid, actual operations and measurements require that the atoms be moved into a separate area that the company calls an “entanglement zone.”
The physical and conceptual separation has advantages. But, once performing error correction on a hundred logical qubits, it will likely require thousands of qubits to be regularly shuffled in and out of the entanglement zone simply to get error correction to work—and that’s without any computation being attempted.
A logical road map
As our earlier coverage described, the Harvard lab where the technology behind Quera’s hardware was developed has already demonstrated a key step toward error correction. It created logical qubits from small collections of atoms, performed operations on them, and determined when errors occurred (those errors were not corrected in these experiments).
But that work relied on operations that are relatively easy to perform with trapped atoms: two qubits were superimposed, and both were exposed to the same combination of laser lights, essentially performing the same manipulation on both simultaneously. Unfortunately, only a subset of the operations that are likely to be desired for a calculation can be done that way. So, the road map includes a demonstration of additional types of operations in 2024 and 2025.
At the same time, the company plans to rapidly scale the number of qubits. Its goal for 2024 hasn’t been settled on yet, but Boger indicated that the goal is unlikely to be much more than double the current 256. By 2025, however, the road map calls for over 3,000 qubits and over 10,000 a year later. This year’s small step will add pressure to the need for progress in the ensuing years.
If things go according to plan, the 3,000-plus qubits of 2025 can be combined to produce 30 logical qubits, meaning about 100 physical qubits per logical one. This allows fairly robust error correction schemes and has undoubtedly been influenced by Quera’s understanding of the error rate of its current atomic qubits. That’s not enough to perform any algorithms that can’t be simulated on today’s hardware, but it would be more than sufficient to allow people to get experience with developing software using the technology. (The company will also release a logical qubit simulator to help here.)
Quera will undoubtedly use this system to develop its error correction process—Boger indicated that the company expected it would be transparent to the user. In other words, people running operations on Quera’s hardware can submit jobs knowing that, while they’re running, the system will be handling the error correction for them.
Finally, the 2026 machine will enable up to 100 logical qubits, which is expected to be sufficient to perform useful calculations, such as the simulation of small molecules. More general-purpose quantum computing will need to wait for higher qubit counts still.
It’s probably a measure of quantum computing’s progress that, while this road map seems optimistic and aggressive, it doesn’t seem completely ludicrous. A few years ago, logical qubits were a theoretical construct; their basics have now been demonstrated. Two companies already have hardware with over 1,000 qubits. Quera might face challenges—many companies in this space have found that their tech has failed to scale as expected. But the field as a whole appears to be moving steadily toward making logical qubits a reality.