The UK Government is developing the nation's most powerful AI supercomputer, featuring NVIDIA's GH200 Grace Hopper Superchips.
Isambard-AI Is Going To Deliver A Whopping 21 ExaFlops of AI Compute Horsepower, Courtesy of NVIDIA's GH200 Grace Hopper Superchips
Based on NVIDIA's announcement, the cost of the "Isambard-AI" supercomputer is expected to reach €225 million ($273 million). The primary reason behind the inauguration of such a capable product is the influence of AI in the UK since the market has exploded in the past months. The AI industry has contributed £3.7 billion to the U.K. economy and employs more than 50,000 people, which is why the advancement in computing is necessary to propel into the future.
Speaking of disclosed specifications, Isambard-AI has it all packed, featuring a whopping 5,448 NVIDIA GH200 "Grace Hopper" AI Superchips, which is a rather huge number considering the power it will potentially deliver. It is reported that the supercomputer will able to provide 2.7 petaflops of FP64 peak performance and consume less than 270 kilowatts of power, making it a power-efficient machine, and placing it amongst the industry's leading supercomputers.
Isambard-AI represents a huge leap forward for AI computational power in the U.K.
Today, Isambard-AI would rank within the top 10 fastest supercomputers in the world and, when in operation later in 2024, it will be one of the most powerful AI systems for open science anywhere.
- Simon McIntosh-Smith, a Bristol professor and director of the Isambard National Research Facility
The utilization of NVIDIA's AI chips such as Hopper H100 and GH200 Grace Hopper Superchips in the AI and supercomputing industry has been larger than ever. To manage the extreme workloads, the Isambard-AI will feature a direct-cooling technology, & to ensure longevity, the supercomputer will employ a thermal re-use mechanism as well that will significantly contribute towards the overall thermal dissipation.
AI developments have started to see a rise globally, especially in Europe, which has just unveiled its first ExaFLOPS supercomputer "Jupiter". The progression of genAI has resulted in an increased demand for high computing power, encouraging governments to act quickly in order to stay competitive.
News Source: NVIDIA Blog
About the author: Muhammad Zuhair is a hardware and technology reporter for Wccftech, specializing in the semiconductor industry and the complex interplay between technology, manufacturing, and geopolitics. His coverage focuses on the corporate strategies and technological roadmaps of industry giants like TSMC, NVIDIA, Samsung, and Intel. Zuhair's expertise lies in deconstructing complex topics such as fabrication nodes (e.g., 2nm process), the economic impact of policies like the CHIPS Act, and the strategic development of AI infrastructure from NVIDIA, AMD and Intel.
Follow Wccftech on Google to get more of our news coverage in your feeds.
