After triumphing with its chips for AI, Nvidia has set another disruptive technology: quantum computers

Nvidia’s bet for Quantum computers It is less and less shy. Jensen Huang, the co -founder and general director of this company, has announced A few hours ago at its annual developer conference that will open a laboratory expressly dedicated to Quantum computing research. It will be housed in Boston (Massachusetts) and will allow NVIDIA engineers to work side by side with the researchers at Harvard University and the Massachusetts Technology Institute (MIT). It will begin operating at the end of 2025.

This strategic movement puts on the table with absolute clarity that Huang does not want to stay out of technology that will presumably cause a medium -term disruption. The most curious thing is that before formalizing the implementation of its new quantum technologies development laboratory, this executive has not let out the opportunity to retract. At the beginning of last January A few statements They caused a very abrupt fall of the actions of some of the companies that are dedicated to the development of quantum computers.

“If you said 15 years you would probably be optimistic. And if you said 30 you would be pessimistic. But if you opt for 20 years I think many of us would believe it,” Jensen Huang argued At that time. With this reflection I tried to predict when the really useful quantum machines will be ready, and, therefore, capable of dealing with a very wide range of problems. But he has changed his mind. Just two and a half months later seems to be convinced that fully functional quantum computers will be ready much earlier.

With the correction of errors of quantum computers in the spotlight

Nvidia flirting with quantum computers is not really new. And is that He has been collaborating for more than two years With the Israeli company Quantum Machines. This company specialized in the development of hardware and software for quantum machines, and has been ready with NVIDIA a low -performance and high performance architecture that seeks to promote the progress of quantum computing.

NVIDIA has contributed its CPU/GPU grace hopper system, a beast that is designed to execute applications of artificial intelligence and offer productivity at high performance computer scenarios, and also its open source programming model CUDA QUANTUM. His partner in this project, Quantum Machines, has been in charge of the integration and set -up of a quantum platform that, according to these two companies, is specifically designed to work in hybrid systems in which classical hardware and quantum coexist in harmony.

The purpose of the DGX Quantum platform, which is what is called the hardware that these two companies have developed, is to help researchers who work in the field of quantum computing to develop new quantum algorithms. It may seem surprising that it is possible to use classic hardware to develop quantum algorithms, but it is something perfectly viable. In fact, this strategy helps to put quantum computing within the reach of many more researchers who can implement and test their ideas without having access to a quantum computer prototype.

However, the DGX quantum platform also serves, according to NVIDIA, to calibrate quantum systems, control them, and even aspires to have a prominent role in the tuning of a correction system that allows quantum computers amend your own mistakes. Jensen Huang emphasized this idea during his GTC 2023 conference, and there is no doubt that It is a very attractive possibility. Extraordinarily attractive. And is that, As Ignacio Cirac explained to us In the conversation we had with him, the correction of errors will give us the opportunity to solve with quantum computers really significant problems.

Image | Nvidia

More information | Reuters | SCMP

In Xataka | Quantum computers find it impossible to do nothing. It is a mystery that has scientists on alert