Adapted by:
Juan Carlos López
Senior WriterAn engineer by training. A science and tech journalist by passion, vocation, and conviction. I've been writing professionally for over two decades, and I suspect I still have a long way to go. At Xataka, I write about many topics, but I mainly enjoy covering nuclear fusion, quantum physics, quantum computers, microprocessors, and TVs.
Alba Mora
WriterAn established tech journalist, I entered the world of consumer tech by chance in 2018. In my writing and translating career, I've also covered a diverse range of topics, including entertainment, travel, science, and the economy.
Nvidia’s commitment to quantum computing is becoming increasingly pronounced. At the company’s annual developer conference, co-founder and CEO Jensen Huang announced that Nvidia will open a dedicated quantum computing research lab in Boston. The lab will enable Nvidia engineers to collaborate closely with researchers at Harvard University and MIT. Operations are set to begin in late 2025.
This strategic move clearly indicates that Huang doesn’t want to miss out on a technology expected to create significant disruptions in the near future. Interestingly, before officially announcing the launch of the new lab, Huang had seemingly backtracked on earlier comments. In January, some of his statements led to a sharp decline in the shares of companies involved in quantum computing.
At that time, Huang said, “If you kind of said 15 years … that’d probably be on the early side. If you said 30 years, it’s probably on the late side. But if you picked 20 years, I think a whole bunch of us would believe it.” He was trying to predict when truly useful quantum computers would be ready, meaning capable of tackling a wide range of complex problems. However, just two and a half months later, the CEO of Nvidia seems to be convinced that these machines will be ready much sooner.
The Focus Is on Fixing Bugs in Quantum Computers
Nvidia’s interest in quantum computers isn’t a recent development. The company has been collaborating with Quantum Machines for over two years. Quantum Machines specializes in creating hardware and software for quantum systems. Together, both companies are working on DGX Quantum, a low-latency, high-performance architecture aimed at advancing quantum computing.
The DGX Quantum platform is designed to assist researchers in the field of quantum computing with the development of new quantum algorithms.
Nvidia provides its Grace Hopper CPU/GPU system, an advanced machine designed for AI applications and scalable high-performance computing. Additionally, Nvidia contributes its open-source CUDA Quantum programming model. Meanwhile, Quantum Machines takes charge of integrating and fine-tuning a quantum platform that’s specifically tailored for hybrid systems. This is where classical and quantum hardware can work together seamlessly.
The DGX Quantum platform aims to assist researchers in quantum computing in creating new quantum algorithms. While it may seem surprising that classical hardware can be used to develop quantum algorithms, it’s entirely feasible. This approach significantly broadens access to quantum computing, allowing more researchers to implement and test their ideas without needing direct access to a prototype quantum computer.
Additionally, Nvidia claims that the DGX Quantum platform helps calibrate and control quantum systems. It also aspires to play a pivotal role in the development of an error correction system that would enable quantum computers to rectify their own errors. Huang highlighted this concept at Nvidia’s GTC 2023, and it’s undoubtedly an intriguing possibility.
In the end, the advancement of error correction will position the scientific community to tackle truly significant problems using quantum computers.
Image | Nvidia
Log in to leave a comment