Will NVIDIA enter the quantum computing race?

0

Well, not directly. However, the company makes it easy to develop code for quantum machines using GPUs.

Okay, let’s face it. Programming quantum computers is difficult. Really hard. While we don’t expect NVIDIA to develop and release its own quantum system anytime soon (never say never!), the company is helping developers use GPUs to simplify the task of coding.

What did NVIDIA announce?

NVIDIA believes a “bridge” technology can help enable dynamic workflows across different architectures, with processors, GPUs, and quantum devices providing a hybrid quantum-classical computing platform. To enable this approach, NVIDIA launched previews of the NVIDIA Quantum-Optimized Device Architecture (QODA), enabling programming in an integrated hybrid system and workflow.

For the programmer who wants to research algorithms and build hybrid applications for future quantum advantage, bridge technology is needed to enable dynamic workflows across disparate system architectures. NVIDIA Quantum-Optimized Device Architecture (QODA) is a first-of-its-kind platform for hybrid classical quantum computers, using emulated processors, GPUs, and QPUs to effectively mimic the behavior of a hardware QPU in a programmed condition.

“QODA consists of both a specification and an NVQ++ compiler. It provides a unified programming model designed for quantum processors (real or emulated) in a hybrid environment, i.e. CPUs, GPUs and QPUs work together,” the company said.

Quoda connects to any type of QPU backend, allowing accessibility to all users. Interestingly, NVIDIA saw a 287X speedup in the end-to-end performance of the Variational Quantum Eigensolver (VQE) with 20 qubits and significantly improved scaling compared to existing Pythonic frameworks.

QODA features include:

  • Kernel-based programming model extending C++ for hybrid quantum-classical systems (full Python support is on the way).
  • Native GPU hybrid compute support, enabling GPU pre- and post-processing and classic optimizations.
  • System-level compiler toolchain including split compilation with NVQ++ compiler for quantum kernels, downgrading to Multi-Level Intermediate Representation (MLIR) and Quantum Intermediate Representation (QIR).
  • Standard Library of Quantum Algorithmic Primitives
  • Interoperable with partner QPUs as well as simulated QPUs using the cuQuantum GPU platform; partnership with QPU builders on many different types of qubits

Partners include several supercomputing centers, including NERSC, Jülich and Oak Ridge National Labs, and quantum pioneers Xanadu, Pasqal, Quantinuum and others, but major QPU developers (IBM, QCI, Google, Microsoft, Honeywell and others) seem miss this time.

conclusion

While NVIDIA is unlikely to build a quantum computer anytime soon, if ever, the company’s GPUs and expertise in parallel software can certainly help developers move forward into an era where a quantum computer can deliver results. superior to “traditional” (i.e., digital) computer systems. Quoda is another example of NVIDIA’s software approach and integrated systems that can offer much more than competitors who were only recently able to compete with a 2-year-old GPU in a few select benchmarks.

Share.

Comments are closed.