Quantum computer startup SEEQC (Elmsford, New York) is partnering with Nvidia to develop an all-digital low-latency chip-to-chip interface between any quantum computing system and GPU chips.
When completed the interface will allow a multi-chip module quantum processor to be directly linked to both GPU- and CPU-based computers.
SEEQC’s quantum technology is entirely digital and so the direct interface will remove several analog hardware overheads that otherwise add noise and expense.
The efficient combination of classical and quantum computing will support quantum artificial intelligence and quantum machine learning and other applications in the data center, SEEQC said. Integrating quantum computing and GPUs will advance Nvidia’s CUDA quantum platform. This will enable “full-stack” quantum AI with real-time error correction powered by SEEQC’s single flux quantum (SFQ) technology.
Best of both
“The development we’re taking on with NVIDIA represents the best of breed in both quantum and classical; and, together, both core technologies create unprecedented compute power,” said John Levy, CEO and co-founder of SEEQC, in a statement.
Tim Costa, director of high-performance and quantum computing at NVIDIA, said: “Tight integration of quantum with GPU supercomputing is essential for progress toward useful quantum computing. Coupling the NVIDIA GH200 Grace Hopper Superchip with SEEQC’s digital chip architecture – tied together by the CUDA quantum programming model – will provide a major step toward that goal.”
Jean-François Bobier, quantum computing research lead for Boston Consulting Group (BCG), said: “With this collaboration, SEEQC and NVIDIA are paving the way for the enterprise-grade quantum computing era.” He added: “Low latency is the key to scalable applications and error correction, which will unlock 90 percent of quantum computing use cases in value.”