Dell is creating the building blocks to assimilate quantum computers into conventional IT infrastructures as it opens datacenters to new types of accelerated computers.
The server-maker has created a blueprint for conventional server infrastructure to interface with the unique demands of quantum systems, which are considered significantly faster and solve problems in a different way.
The hybrid classical-quantum computing model includes an adjusted hierarchy with conventional servers acting as hosts and managers of attached quantum computers, which compute differently.
The blueprint also includes a conventional computing layer so relevant results from quantum calculations – which aren’t straightforward answers – can be sent back to users within an IT infrastructure.
“We are already seeing those areas that we can optimize and make that intelligent interplay between the classical infrastructure and the quantum infrastructure even more powerful in order to do things that we even haven’t considered yet,” Ken Durazzo, vice president of research at Dell told HPCwire.
The hybrid computing blueprint, which includes hardware and software, is built around PowerEdge servers and quantum computing technologies from IonQ. The companies announced a hybrid system, Dell Quantum Computing Solution, based on the design at the SC22 conference. The system will be available in the U.S. and Canada.
Quantum computers are widely seen as one way to advance computing beyond today’s PCs and servers. Quantum computers perform significantly more calculations in parallel, which provides a vast increase in processing power compared to conventional servers.
“As we’ve seen on this journey with quantum, we realized that it’s not quantum computing as the future, it’s classical and quantum working together,” Durazzo said.
Durazzo said the top-end GPUs are being taxed by applications such as computational fluid dynamics and chemistry. Dell’s hybrid model involves running applications on the classical infrastructure, and algorithms from those applications being accelerated via quantum computing.
“We identified very early on … that there are clear roles for the classical infrastructure and then for the quantum infrastructure,” Durazzo said.
Dell’s hybrid model accounts for the vast amounts of data ingested by quantum computers, which runs calculations at breakneck speeds. The conventional infrastructure creates the conditions for quantum calculations before data is fed into quantum processors, which has its own quirks in the way it calculates and delivers results.
For example, conventional systems spit out answers resulting from calculations on circuits like CPUs and GPUs. By comparison, quantum computers don’t deliver answers, but instead send back probabilistic results. Those could be any number of results, which are delivered in some level of stack rank order.
“When the algorithm gets sent to the QPU [quantum processing unit], the QPU sends back results of the computation. They don’t send back an answer, they send back results of the computation. Those results will be taken into the classical system again, and will be formulated into a result that the end user could actually see coming from the application,” Durazzo said.
The foundation for the hybrid model is a set up of the server, networking and other components, where the program actually runs and initiates high-speed data transfers to quantum systems. The data has to pass through an intermediary host processor, which is more of an instruction layer for conventional systems to interface with the quantum systems.
“What the host processor in this case is actually doing is taking that circuit, compiling it into QASM, or the quantum assembly language, and then taking that to program the QPU. That host processor is an intermediary step in order to program the QPU and to provide the algorithm for the QPU to actually exercise,” Durazzo said.
Over time, the host processor will be able to do “very intelligent scheduling operations,” Durazzo said.
For example, instead of sending an entire quantum computing task to a physical quantum processor, the host processor will be able to decompose a quantum task and bifurcate its execution between a physical quantum hardware and software-based quantum simulator on GPUs.
“We’re going see more and more models of that interplay between classical simulation and actual physical quantum systems, where the intelligent orchestration and the ability to understand where to best run these particular functions or operations is going to become more critical,” Durazzo said, adding “We’re well positioned for that world as that emerges.”
A classical system will then try to make sense of the complicated quantum output and formulate a concrete answer from an application for end users. The classical system could be equipped with accelerators like GPUs, which could use AI techniques to crunch the quantum output to generate relevant answers. The hybrid model uses standard software stacks that includes Kubernetes for orchestration and QISKIT for quantum applications.
“We also designed it to enable an applications developer to write the application or the algorithm one time and then run it anywhere they need to,” such as on a physical quantum circuit or a quantum emulator on a GPU, Durazzo said.
Access to quantum computers are already available through Amazon and Google clouds. Dell hopes its managed services offering will make it easier for companies to smoothly transition to quantum systems, which could be a daunting task.
Dell’s partnership with IonQ is just the start of its quantum journey, and many partnerships with quantum computer providers could be on tap, Durazzo said.
Each quantum computer vendor offers its own type of qubit, and customers are eager to test different systems to find the right hardware that fits their infrastructure. IonQ offers the trapped-ion qubit, Google and IBM are working on superconducting qubits, and D-Wave offers a quantum annealing system for optimization tasks.
“In this case, we’re selling with IonQ, but we can easily add support … [from] multiple vendors to allow for investment protection as well as to allow for experimentation on these different quantum systems because they all behave just a little bit different,” Durazzo said.