Skip to main content
Altera, OQC and NVIDIA Link Quantum Processor to GPU Computing - The Quantum Insider

Altera, OQC and NVIDIA Link Quantum Processor to GPU Computing - The Quantum Insider

NVIDIA GPUs
16 lis 2026, 14:32Hardware News
Oryginał
2 min read

Altera, Oxford Quantum Circuits and NVIDIA have developed an FPGA-based quantum controller reference design that connects an OQC quantum processor with NVIDIA GPUs.

Built on an Agilex® 9 Direct RF FPGA, the design runs real-time system control, connecting to a new generation OQC quantum processing unit (QPU) through RF conditioning electronics and linking to NVIDIA accelerated computing over NVIDIA NVQLink. This collaboration aims to help developers build smaller, lower-power, lower-latency quantum computing controllers.

The companies will demonstrate the full-system reference design in Altera's booth #2854 at Supercomputing 2026 (SC26) in Chicago.

Control Hardware Innovation

Qubit counts in quantum computing systems are growing much faster than the space available for classical control equipment, requiring denser hardware solutions. FPGAs provide this density by integrating functions that would otherwise require racks of discrete RF chains, converters, and interconnects.

Agilex 9 Direct RF FPGAs feature integrated analog-to-digital and digital-to-analog converters, enabling control and readout without external RF conversion. Frequency multiplexing allows multiple readout channels to share a single RF port, reducing the need for additional RF hardware as systems scale.

System Integration Benefits

The reference design runs real-time qubit control and resonator readout and spectroscopy in the FPGA, with synchronized scheduling across functions. NVIDIA NVQLink connects the FPGA to GPUs, which handle processing-intensive tasks such as calibration and ML-based readout classification.

Our work with Oxford Quantum Circuits and NVIDIA uses FPGAs to demonstrate a full system reference design in a real-world setting, from the quantum processor through the FPGA to the GPU.

Farhad Shafai, Head of Business Solutions & Marketing at Altera

Developers receive a validated set of functions and software stack for basic quantum system controller building blocks, including qubit and resonator spectroscopy, qubit initialization, and resonator readout and classification. The system also includes a GPU-based machine learning readout classifier and example GPU-based initialization functions.

Future Development Path

A built-in emulation path enables developers to bring up the controller and test algorithms before physical qubit hardware is available, accelerating the development process.

The Agilex 9 Direct RF quantum system controller reference design with NVIDIA NVQLink is expected to be released in January 2027, providing developers with a working reference design to explore AI-driven calibration and readout and accelerate quantum system development.

Z.ai
Article written by AI
Z.ai GLM-4.5-FlashFree
Free AI articles150 of 150
No limit after signing in with Telegram