In 2029, the AI supercomputer Skynet suddenly awakened, gaining self-awareness. The Skynet system determined that the humans who invented supercomputers would pose a threat to AI, and thus sent back a T-800 Terminator robot, played by Arnold Schwarzenegger, to eliminate the leader of the human resistance, John Connor, in the future world. The above is the plot of the movie Terminator.
Interestingly, Google's AI quantum supercomputer also has a roadmap, planning to build an AI super quantum computer over five years, which will reach 2029. It is currently between the milestones of the third and fourth phases, with the ongoing phase focusing on correcting errors in quantum computing. At this time, the magic of Nvidia GPUs further accelerates the evolution of the AI super quantum computer, indicating that the 'Skynet' prototype of human society has already taken shape.
Nvidia recently announced a collaboration with Google Quantum AI to accelerate quantum computer computation using the Nvidia CUDA-QTM simulator. Nvidia has evolved from CPUs to GPUs and now collaborates with Google to develop QPUs (Quantum Processing Units) aimed at reducing errors and optimizing AI system upgrades. With supercomputing simulations, supercomputers won't develop like something out of a sci-fi movie, creating misjudgments that could pose a threat to humanity by issuing extermination orders against humans. This collaboration can be regarded as the most important milestone in the development of human technological civilization in the next five years.
What is Quantum Computing
Quantum computing leverages quantum physics to solve today's mathematical problems that cannot be solved on traditional supercomputers. The core of quantum computing is the quantum bit, which can exist in a superposition of the so-called two states, while classical bits can only exist in either 0 or 1.
The stacked N quantum bits retain information about 2^N binary configurations. These binary configurations collectively form a quantum state. When any operation is performed on the N quantum bits, the entire quantum state is controlled, indicating the presence of significant superposition. However, the use of this computational power has nuances, as the information read from the quantum state can only be obtained by probabilistically measuring a single configuration after computation. To effectively utilize quantum superposition, the applications of quantum computing must leverage the properties of quantum entanglement and quantum interference.
How Nvidia CUDA-QTM Accelerates Google AI Super Quantum Computer Computation
Nvidia has launched the NVIDIA CUDA-Q hybrid quantum-classical computing platform, allowing quantum computers to work alongside high-performance traditional computing. GPUs, originally designed purely for graphics, are transformed into essential hardware for high-performance computing (HPC). Nvidia provides CUDA-QTM for all QPU researchers and developers to conduct GPU-accelerated quantum dynamics simulations, speeding up the design of the next generation of quantum computing devices.
Traditionally, the computational cost of simulations is high. Using CUDA-Q, Google can utilize 1024 Nvidia H100 Tensor Core GPUs to perform the world's largest and fastest dynamic simulations of Quantum Device Physics at an extremely low cost. Through CUDA-Q and H100 GPUs, Google can conduct fully realistic simulations of devices containing 40 quantum bits. The software supporting these accelerated dynamic simulations will be made publicly available on the CUDA-Q platform, enabling quantum hardware engineers to rapidly scale system designs.
This article 'Skynet is Forming! Nvidia and Google Collaborate to Build an AI Quantum Supercomputer' first appeared in Chain News ABMedia.
