Intel Bets Big on 2-Track Quantum Strategy

By Doug Black

January 15, 2019

Quantum computing has lived so long in the future it’s taken on a futuristic life of its own, with a Gartner-style hype cycle that includes triggers of innovation, inflated expectations and – though a useful quantum system is still years away – anticipatory troughs of disillusionment.

To wit, there’s Mikhail Dyakonov in the November IEEE Spectrum, who, even as investors, companies and countries pour billions into quantum, says it will never work. The theoretical physicist at the Université de Montpellier, France, contends that error correction (monitoring variables and correcting errors) isn’t possible at quantum scale. “A useful quantum computer needs to process a set of continuous parameters,” Dyakonov wrote, “…larger than the number of subatomic particles in the observable universe.”

Maybe. But betting against quantum flies in the face of centuries of technological breakthroughs reinforcing the maxim: what we can conceive we can achieve. At a technical level, countering Dyakonov is a post-doctoral researcher at QuTech, part of the Delft University of Technology in the Netherlands (see his rebuttal in HPCwire), who writes, “No computer, classical or quantum, ever has to process even a single continuous parameter. In classical computers, we can use floating-point arithmetic to approximate continuous parameters using a finite number of bits.”

Intel’s Jim Clarke

Also at odds with Dyakonov is Jim Clarke, director of quantum hardware at Intel Labs, who told us during a recent interview that, daunting as quantum error correction may be, there are tougher quantum challenges to overcome, beginning with scale – which in the quantum world is otherworldly.

This is because, as described in a recent MIT Technology Review article, “The fundamental units of computation…are qubits, which — unlike bits — can occupy a quantum state of 1 and 0 simultaneously. By linking qubits through an almost mystical phenomenon known as entanglement, quantum computers can generate exponential increases in processing power.”

Leaving aside the headsplitting notion that qubits can be both 1 and 0 (University of Nottingham professor Phil Moriarty: “As a quantum physicist, it’s not that you understand it, you just get used to it.”), in Clarke’s explanation, a qubit is like a spinning coin – it’s both heads and tails. This is the principal of “quantum superposition.”

“So if I get two coins spinning at the same time, I’d simultaneously have four states; with three coins, eight states,” Clarke said. “With 300 spinning coins, how many states can I have? That’s two to the 300th, which is more states than there are in the universe. At 50 you can represent more states than any supercomputer could do.”

This brings us to Clarke’s biggest quantum worry: interconnection. Holding a superconducting qubit processing unit (QPU – see left), Clarke said, “If you take this chip, I’ve got 49 qubits and 108 coaxial connectors to the outside world. What would it look if I had a million qubits? I can’t have 2 million coax cables to the outside world. Maybe that’s what an ENIAC system looked like in the 1940s, but that’s not what conventional system looks like. So what worries me most is wiring your interconnects.”

By comparison, Clarke said, an Intel Xeon server chip has 7 billion transistors and only 2000 connectors, mostly for power and ground.

The wiring problem is a factor contributing to Intel’s two-track quantum strategy – one track is development of a “mainstream” (in the quantum world)  superconducting qubit, which most companies (IBM, Google, Rigetti and others) are attempting to perfect; Intel’s other development track is the silicon spin qubit (SSQ), which Intel is pursuing along with Delft University, the University of New South Wales and Princeton and which looks like a transistor.

While developmentally less mature than the superconducting qubit (which have reached about 50 entangled qubits), the SSQ (now at about 23 entangled qubits) may tap more readily into Intel’s chip heritage.

“When you think of Intel, you probably think of it as a transistor company,” Clarke said, “and you’d be right. (SSQ’s)…look a lot like a transistor. I’d describe it as a single electron transistor.”

Intel is the only large company investigating SSQ’s, according to Clarke.

“Our thought is to look at similar (superconducting qubit) technologies as some of our competitors, but we’re also looking at a novel technology that resembles our transistors in the infrastructure we have,” Clarke said. “We can build on our multi-billion dollar infrastructure to make these devices. So that’s a big bet we’re making…. We’re doing both, we’re basically hedging out bet.”

A potential advantage of the SSQ (picture at right) is that it’s “a million times smaller than the superconducting qubit,” said Clarke. “…. just from a real estate perspective, if this has 49 (coax cables), then I have to wonder what a million would look like. It would be huge. But with silicon spin, there’s no reason we can’t have a density similar to our advanced logic or advanced memory, so there’s no reason we couldn’t get into the millions easily… We’re hoping to accelerate that technology and make it competitive with superconducting qubits and then, hopefully, it will be the technology that will scale.”

Intel’s two-track strategy poses another challenge for Clarke: how to accelerate the development of one versus the other. “But it’s hard for me to imagine that we’d give up early on the technology that looks like transistors, being a transistor company,” he said.

Clarke concedes that IBM, Google and others have been working on quantum longer than Intel, but he argues that Intel has advantages the others can’t match, notably Intel’s architecture and process expertise.

“We can tap into state-of-the-art fabrication facilities,” Clarke said, citing research the quantum group has done jointly with Intel’s packaging group in Arizona aimed at improving performance and reliability.

“We have our fabrication engineers working on the chip, we have folks working on control electronics for the QPU, we have people developing architectures for the QPU,” Clarke said. “They’re all working based on the background of Intel’s experience. We’re trying to put together a complete system.”

Companies without advanced fabrication, Clarke said, probably rely on “something that resembles a university lab. You can imagine that a university professor can make one good transistor. But can he build 7 billion of them all the same, and put them on a chip that you could buy for a server?”

He cited Intel’s 500-acre Romler Acres campus in Hillsboro, Ore., at which, though Intel’s quantum work is experimental, “we’re still running our material through the same factories that our advanced technologies are running on, and that has to be considered an advantage…. We get to use state-of-the-art tools with process controls, we take great care with our material deposition.”

With Quantum years away, quantum developers necessarily adopt long time horizons. Clarke estimates quantum is half a decade from a significant step in system performance.

“I think there’s a race to quantum supremacy,” he said. “At some number, 50 or 60 (qubits), someone will say we’ve contrived a problem that can’t be solved with a classical computer. That would be a milestone, but it’s not a practical milestone. I think being able to do an optimization problem or characterize the configuration of a molecule that can’t be done with a classical computer, that would be a first milestone. We’re probably five or six years away from that.”

Waiting that long for results runs counter to our impatient culture, but Clarke suggests quantum progress be put in historical perspective.

“In a field where computer advances are measured on the span of a year or two, then when you say something (quantum) is 10 years away, some will say it might as well be forever,” he said. “But if you look at the history of electronics, the first transistor was 1947, the first silicon transistor was 1954, the integrated circuit was 1958, and the first microprocessor was 1970. So these things don’t happen overnight. If you take a look at where we are, we’ve surpassed the equivalent of the first integrated circuit, and now we’re trying to get to a large enough size to do something useful. So…if we say we’re 10 years away from having a few thousand qubits to do something that cannot be done otherwise, it’s actually not so far of a stretch.”

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire