Nvidia's QODA, a quantum-optimized device architecture, is unveiled today at the Q2B conference in Tokyo. Its purpose is (and title) to provide a single programming environment for hybrid classical-quantum computing.
A brave quantum world
Qubits are the loose equivalent of bits in classical computing, but while they may be read as having a value of zero or one, qubits can have many values simultaneously, making them and the hardware that instantiates them the essence of quantum computers.
All developers are invited to join QODA.
The QODAs credo is aimed at nonquantum-specialized developers who want to benefit from this industry advancement. Particular domains include drug discovery, chemistry, finance, and optimization (as a general computing technique), where quantum can accelerate things and make it possible to tackle problems that would otherwise be computationally impossible to deal with.
Transform 2022
Join us at the premier event on applied artificial intelligence for enterprise business and technology decision makers from July 19 to August 28.
Nvidia's GPU technology is already a dominant platform in the HPC world, of course. It turns out to have special application on the quantum side as well. That's because, while GPUs arent quantum hardware, they may be more suitable for quantum circuit simulations, because they can exploit state vector and tensor network methods, which accelerate quantum circuit simulations.
QODA provides a single platform for hybrid development that addresses the new split personality potential of GPUs. Nvidia's cuQuantum SDK includes connectivity with Qiskit, Pennylane and other quantum computing frameworks. The DGX Quantum Appliance is a software container that runs on any Nvidia hardware.
QODA provides two things to assist conventional scientists in making quantum computing more accessible to them:
Nvidia gives a hybrid coding example with a block of quantum code on the top and GPU-oriented code below.
Combining virtual and physical
QODA and cuQuantum work with GPU hardware, but they also work with physical QPUs, so code written on the platform is easily accessible in both virtual and physical environments. Hardware partners include IQM Quantum Computers, Pasqal, Quantum Brilliance, and Zapata Computing, as well as software/algorithm partners like NERSC/Lawrence Berkeley National Laboratory and Oak Ridge National Laboratory.
What's next for Nvidia and quantum?
Nvidia believes that QODAs purpose is to encourage innovators who are interested in a particular application (rather than quantum computing itself) to adopt quantum computing and to see it as a technology that can accelerate what they're already doing. This is a pragmatic approach to adopting quantum computing, which might be the largest development since the introduction of the microcomputer or even the mainframe.
Nvidia's aim with its QODA collaboration is to unite many businesses, with the aim of fostering cohesion and an ecosystem in the quantum arena. Doing so is crucial to helping the space mature and be more attractive for enterprise customers, as the QODA announcement should help make quantum computing more industrialized and commercially viable.
