Key info:
-
Nvidia unveiled an replace to its GPU Hopper chips, known as the Nvidia H200.
-
24,000 of these chips will probably be utilized in Jupiter, an artificial intelligence supercomputer.
Nvidia, a number one producer in the market of video playing cards (GPU), laptop chips and computing {hardware}, introduced new developments at the Supercomputing 2023 occasion. Among them stands out JUPITER, described as “the most powerful artificial intelligence supercomputer in the world ».
JUPITER is a brand new class of supercomputers powered by the Nvidia Grace Hopper accelerated computing structure.whose first installations are projected for 2024. Specifically, the supercomputer will use 24,000 NVIDIA GH200 chips, one other of the merchandise that the firm unveiled at the occasion held in Denver, Colorado.
This will probably be the “most powerful artificial intelligence system in the world,” based on the firm, with a efficiency of greater than 90 exaflops for AI coaching and 1 exaflop for high-performance (HPC) purposes, consuming solely 18.2 megawatts of energy . An exaflop is a unit of measurement of computing efficiency, particularly in the area of supercomputing. It represents the skill to carry out one billion (10^18) floating level operations per second.
Nvidia emphasizes the potential use of this supercomputer to deal with scientific challenges in areas equivalent to local weather prediction, drug discovery, quantum computing applied sciences and industrial design.
The firm’s announcement, ratified and deepened in an official assertion later, confirms Nvidia’s orientation in direction of applied sciences equivalent to artificial intelligence and quantum computing. In latest years, the firm primarily based in California, United States, was a central participant in the area of GPUs used for mining cryptocurrencies, primarily Ethereum.
(*1*)(*2*)New Nvidia chips for high-performance computing
In addition to the JUPITER venture that can formally be launched subsequent 12 months, Nvidia introduced different developments centered on artificial intelligence and quantum computing. Quantum computing is a paradigm in laptop science that makes use of ideas of quantum mechanics to course of info in another way than classical computer systems. Unlike classical bits, that are binary and may be in a state of 0 or 1, quantum qubits can exist in a number of states concurrently due to quantum superposition.
Regarding Nvidia displays, we speak about the H200 chips, for instance. This is an improve to Nvidia’s GPU Hopper chips, with improved efficiency and higher value and energy effectivity. The Nvidia H200 chips introduce HBM3e reminiscence, which is quicker and better capability.
With 14 GB of reminiscence and the skill to course of 4.8 terabytes per second, the H200 chips intention to speed up industrial design, simulations and particularly generative artificial intelligence purposes and enormous language fashions.
On the different hand, the Grace Hopper Superchips had been unveiled, the results of the mixture of Nvidia’s Grace and Hopper applied sciences. The GH200, a part of the Grace Hopper collection, is utilized in analysis and computing-intensive duties, with a mixed efficiency of 200 exaflops of AI efficiency per second. These sorts of chips are utilized in supercomputers made by giant producers equivalent to Dell and HPE.
Finally, Nvidia announced the growth of quantum processing items (QPUs). In this sense, the open programming mannequin known as CUDA Quantum stands out, whose goal is to facilitate the integration of quantum processors in future supercomputers.
(*4*)Bitcoin mining pivots in direction of AI
The indisputable fact that Nvidia, as soon as a frontrunner in manufacturing {hardware} for cryptocurrency mining, focuses on artificial intelligence is one other instance of a pattern that was lately reported in CriptoNoticias. The factor is that artificial intelligence is an increasing enterprise, as had been cryptocurrency networks at the time. There, lInvestors see enterprise alternatives and supply them with processing energy for his or her operations.
An exemplary case is that of Hive Digital, one in all the principal Bitcoin mining corporations in the world. According to what its CEO, Frank Holmes, informed this newspaper, the funding in processing duties with artificial intelligence allowed the firm to earn greater than USD 250,000 in a single quarter with just some GPUs devoted to duties equivalent to coaching neural networks, calculations intensive or picture and video processing.
