{"id":41989,"date":"2021-04-13T09:58:43","date_gmt":"2021-04-13T09:58:43","guid":{"rendered":"http:\/\/icloud.pe\/blog\/?guid=e512c89ef79b02cbb8eb8cc98561cfb5"},"modified":"2021-04-13T09:58:43","modified_gmt":"2021-04-13T09:58:43","slug":"nvidia-takes-aim-at-intel-with-first-data-centre-cpu","status":"publish","type":"post","link":"https:\/\/icloud.pe\/blog\/nvidia-takes-aim-at-intel-with-first-data-centre-cpu\/","title":{"rendered":"Nvidia takes aim at Intel with first data centre CPU"},"content":{"rendered":"


\n Zach Marzouk<\/a><\/span>
\n <\/span><\/p>\n

\n
\n
13 Apr, 2021<\/span><\/div>\n<\/p><\/div>\n<\/div>\n

\n<\/a><\/p>\n

\n

Nvidia has unveiled Grace, an Arm-based\u00a0data centre CPU<\/a>\u00a0designed for giant-scale artificial intelligence (AI) and\u00a0high-performance computing<\/a>\u00a0(HPC) applications.\u00a0<\/p>\n

This new processor combines Arm\u00a0CPU cores with a low-power memory subsystem to help it analyse\u00a0enormous datasets requiring both ultra-fast compute performance and massive memory.<\/p>\n

<\/p>\n

\nNvidia Grace, named after US programming pioneer\u00a0Grace Hopper<\/a>, is a highly specialised processor that will target workloads such as training next-generation NLP models that have over 1 trillion parameters, according to the company.\u00a0<\/p>\n

Furthermore, Nvidia claims that a Grace CPU-based system will deliver 10x faster performance than the current Nvidia DGX-based systems that\u00a0run on x86 CPUs. Nvidia expects this\u00a0new processor<\/a>\u00a0to service a niche segment of computing.<\/p>\n

\u201cLeading-edge AI and data science are pushing today\u2019s computer architecture beyond its limits \u2013 processing unthinkable amounts of data,\u201d said Jensen Huang, founder and CEO of Nvidia.<\/p>\n

\u201cUsing licensed Arm IP, Nvidia has designed Grace as a CPU specifically for giant-scale AI and\u00a0HPC<\/a>. Coupled with the GPU and DPU, Grace gives us the third foundational technology for computing, and the ability to re-architect the data centre to advance AI. Nvidia is now a three-chip company.\u201d<\/p>\n

The Swiss National Supercomputing Centre (CSCS) and the US Department of Energy\u2019s Los Alamos National Laboratory have already announced plans to build Grace-powered\u00a0supercomputers<\/a>.<\/p>\n

This move could spell trouble for other chipmakers who already have a strong presence in the data centre market like Intel, which is currently dominating with a 90% share, and AMD. By promising a 10x increase in processing performance, it may cause some customers to take note of Grace. This was reflected in the markets where Intel and AMD are both down several percentage points following Nvidia’s announcement.<\/p>\n

Nvidia\u00a0also announced<\/a>\u00a0eight Nvidia Ampere architecture GPUs for next-generation laptops, desktops and servers.\u00a0<\/p>\n

The new Nvidia RTX A5000 and Nvidia RTX A4000 GPUs will help speed AI, graphics and real-time rendering up to 2x faster than previous generations in desktops. In laptops, the new Nvidia RTX A2000, Nvidia RTX A3000, RTX A4000 and RTX A5000 GPUs deliver accelerated performance without compromising mobility.\u00a0<\/p>\n

For\u00a0data centres<\/a>, the new Nvidia A10 GPU provides up to 2.5x the virtual workstation performance of the previous generation while the A16 GPU provides up to 2x user density with lower total cost of ownership and an enhanced virtual desktop infrastructure experience over the previous generation.<\/p>\n

In February, it emerged that\u00a0Nvidia had turned to some of its older graphic cards\u00a0<\/a>to meet the demand for GPUs during a global shortage of PC components and chipsets. Nvidia was going to re-release its old chips, such as the GTX 1050 Ti chip, which was meant to have been phased out two years ago, as well as the GeForce RTX 2060. <\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

Zach Marzouk<\/p>\n

13 Apr, 2021 <\/p>\n

Nvidia has unveiled Grace, an Arm-based\u00a0data centre CPU\u00a0designed for giant-scale artificial intelligence (AI) and\u00a0high-performance computing\u00a0(HPC) applications.\u00a0
\nThis new processor combines Arm\u00a0…<\/p>\n","protected":false},"author":654,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-41989","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/posts\/41989","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/users\/654"}],"replies":[{"embeddable":true,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/comments?post=41989"}],"version-history":[{"count":2,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/posts\/41989\/revisions"}],"predecessor-version":[{"id":41993,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/posts\/41989\/revisions\/41993"}],"wp:attachment":[{"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/media?parent=41989"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/categories?post=41989"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/tags?post=41989"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}