{"id":59126,"date":"2022-03-23T15:00:04","date_gmt":"2022-03-23T13:00:04","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=59126"},"modified":"2025-09-04T20:16:16","modified_gmt":"2025-09-04T17:16:16","slug":"nvidia-unveils-a-new-generation-of-server-ai-chips","status":"publish","type":"post","link":"https:\/\/u1f987.com\/en\/nvidia-unveils-a-new-generation-of-server-ai-chips\/","title":{"rendered":"Nvidia unveils a new generation of server AI chips"},"content":{"rendered":"

At the annual GTC 2022 conference, Nvidia \u0430\u043d\u043e\u043d\u0441\u0438\u0440\u043e\u0432\u0430\u043b\u0430<\/a> several new chips and technologies designed to accelerate the speed of artificial intelligence algorithm computations.<\/p>\n

The corporation \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430<\/a> architecture for next-generation Hopper GPUs and the H100 chip built on it, designed for machine-learning tasks.<\/p>\n

The device is manufactured on a 4-nm process and contains 80 billion transistors. It is the company’s first GPU to support PCIe Gen5 and to use HBM3, delivering memory bandwidth of 3 TB\/s.<\/p>\n

\"Nvidia
Hopper architecture H100 GPU. Data: Nvidia.<\/figcaption><\/figure>\n

The company stated that the H100 is three times faster than its predecessor A100 for FP16, FP32 and FP64 computations, and six times faster for 8-bit floating-point operations.<\/p>\n

\n

\u00abFor training giant transformers<\/a>, the H100 proved nine times more productive, training in just a few days rather than weeks\u00bb, said Paresh Hariya, Nvidia’s Senior Director of Product Management.<\/p>\n<\/blockquote>\n

The H100 will go on sale in the third quarter of 2022.<\/p>\n

Nvidia also \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430<\/a> the Grace CPU Superchip, based on the ARMv9 architecture. It comprises two Grace chips linked by NVLink, delivering data transfer speeds up to 900 GB\/s.<\/p>\n

\"Nvidia
Grace CPU Superchip. Data: Nvidia.<\/figcaption><\/figure>\n

Grace CPU Superchip contains 144 ARM cores and consumes around 500 W. The chip supports LPDDR5x memory, delivering up to 1 TB\/s bandwidth.<\/p>\n

Grace CPU Superchip will be available in the first half of 2023.<\/p>\n

In addition to hardware, Nvidia updated a range of AI software services, including the Maxine SDK for audio and video enhancement and the Rivay toolkit for developing natural-language processing systems.<\/p>\n

The company announced the creation of a new AI supercomputer, Eos. The installation will be equipped with 4,600 H100 GPUs, delivering 18.4 exaflops of performance. The system will be used solely for internal company research.<\/p>\n

Earlier, under regulatory pressure from the US, the EU and the UK, Nvidia abandoned the purchase of ARM for $40 billion.<\/p>\n

In the same month, the chipmaker reported a decline in revenue from selling GPUs<\/a> used for mining cryptocurrencies.<\/p>\n

In January, Meta announced the creation of the world’s largest AI supercomputer<\/a> based on Nvidia processors.<\/p>\n

Subscribe to ForkLog News on Telegram: ForkLog AI<\/a> \u2014 all the AI news!<\/p>\n","protected":false},"excerpt":{"rendered":"

At the annual GTC 2022 conference, Nvidia announced several new chips and technologies designed to accelerate the speed of AI algorithm computations.<\/p>\n","protected":false},"author":1,"featured_media":59127,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"1","news_style_id":"1","cryptorium_level":"","_short_excerpt_text":"","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438,1295,1294],"class_list":["post-59126","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-chips","tag-nvidia"],"aioseo_notices":[],"amp_enabled":true,"views":"71","promo_type":"1","layout_type":"1","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/59126","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/comments?post=59126"}],"version-history":[{"count":1,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/59126\/revisions"}],"predecessor-version":[{"id":59128,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/59126\/revisions\/59128"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media\/59127"}],"wp:attachment":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media?parent=59126"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/categories?post=59126"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/tags?post=59126"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}