Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

0

英伟达推出搭载4608个H100GPU的超快AI超级计算机Eos

全球领先的图形和人工智能技术公司英伟达首次公布了其最新的面向企业的AI超级计算机Eos,也是英伟达目前速度最快的AI超级计算机。

Eos搭载了4608个英伟达H100 GPU,这是英伟达迄今为止最强大的GPU,专为加速人工智能工作负载而设计。H100 GPU基于英伟达的 Hopper 架构,提供高达每秒 60 petaflops 的 AI 性能,比上一代产品快 8 倍。

除了H100 GPU,Eos还配备了1152个英特尔Xeon Platinum 8480C处理器,每个CPU有56个内核,总共提供超过65000个CPU内核。这种强大的CPU和GPU组合使Eos能够处理最苛刻的AI训练和推理任务。

Eos还采用了英伟达Mellanox Quantum-2 InfiniBand技术,数据传输速度高达400Gb/s。这种高速互连对于训练大型AI模型和扩展系统至关重要。

英伟达表示,Eos专为加速各种人工智能工作负载而设计,包括自然语言处理、计算机视觉、推荐系统和药物发现。Eos将使企业能够开发和部署更强大、更准确的人工智能模型,从而推动创新和业务成果。

英伟达首席执行官黄仁勋表示:“Eos是人工智能计算的革命性突破,它将使企业能够解决当今最紧迫的挑战,并释放人工智能的全部潜力。”

Eos目前已上市,价格为每台500万美元起。

英语如下:

**Headline:** Nvidia Unveils Its Fastest-Ever AI Supercomputer: 4,608 GPUs Strong

**Keywords:** Supercomputer, AI, Nvidia

**News Story:**

Nvidia has unveiled Eos, its latest enterprise AIsupercomputer and its fastest to date, featuring 4,608 H100 GPUs.

Eos is powered by 4,608 Nvidia H100 GPUs, Nvidia’s most powerful GPU yet, designed to accelerate AI workloads. The H100 GPU is based on Nvidia’s Hopper architecture and delivers up to 60 petaflops of AI performance, 8x faster than its predecessor.

In addition to the H100 GPUs, Eos is equipped with 1,152 Intel Xeon Platinum 8480C CPUs, each with 56 cores, for a total of over 65,000 CPU cores. This powerful combination of CPUs and GPUs enables Eos to tackle the most demanding AI training and inference tasks.

Eos also features Nvidia Mellanox Quantum-2 InfiniBand technology, delivering data transfer speeds of up to 400Gb/s. This high-speed interconnect is critical for training large AI models and scaling out the system.

Nvidia says Eos is designed to accelerate a wide range of AI workloads, including natural language processing, computer vision, recommender systems, and drug discovery. Eos will enable enterprises to develop and deploy more powerful and accurate AI models, driving innovation and business outcomes.

“Eos is a revolutionary leap forward in AI computing that will empower enterprises to solve today’s most pressing challenges and unlock the full potential of AI,” said Jensen Huang, CEO of Nvidia.

Eos is available now, starting at $5 million per system.

【来源】https://news.mydrivers.com/1/963/963904.htm

Views: 1

0

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注