{"id":214651,"date":"2024-03-19T00:42:54","date_gmt":"2024-03-19T00:42:54","guid":{"rendered":"https:\/\/michigandigitalnews.com\/index.php\/2024\/03\/19\/jensen-huang-unveils-new-nvidia-super-chip-before-robots-come-onstage-everything-that-moves-in-the-future-will-be-robotic\/"},"modified":"2025-06-25T17:20:24","modified_gmt":"2025-06-25T17:20:24","slug":"jensen-huang-unveils-new-nvidia-super-chip-before-robots-come-onstage-everything-that-moves-in-the-future-will-be-robotic","status":"publish","type":"post","link":"https:\/\/michigandigitalnews.com\/index.php\/2024\/03\/19\/jensen-huang-unveils-new-nvidia-super-chip-before-robots-come-onstage-everything-that-moves-in-the-future-will-be-robotic\/","title":{"rendered":"Jensen Huang unveils new Nvidia super-chip before robots come onstage: \u2018Everything that moves in the future will be robotic\u2019"},"content":{"rendered":"

[ad_1]
\n
<\/p>\n

Nvidia<\/a> Corp. Chief Executive Officer Jensen Huang showed off new chips aimed at extending his company\u2019s dominance of artificial intelligence computing, a position that\u2019s already made it the world\u2019s third-most-valuable business.\u00a0<\/p>\n

\n

A new processor design called Blackwell is multiple times faster at handling the models that underpin AI, the company said at its GTC conference in San Jose, California. That includes the process of developing the technology \u2014 a stage known as training \u2013 and the running of it, which is called inference.<\/p>\n

The Blackwell chips, which are made up of 208 billion transistors, will be the basis of new computers and other products being deployed by the world\u2019s largest data center operators \u2014 a roster that includes Amazon<\/a>.com Inc., Microsoft<\/a> Corp., Alphabet Inc.\u2019s Google<\/a> and Oracle<\/a> Corp. Blackwell-based products will be available later this year, Nvidia said.<\/p>\n

Blackwell \u2014 named after David Blackwell, the first Black scholar inducted into the National Academy of Science \u2014 has a tough act to follow. Its predecessor, Hopper, fueled explosive sales at Nvidia by building up the field of AI accelerator chips. The flagship product from that lineup, the H100, has become one of the most prized commodities in the tech world \u2014 fetching tens of thousands of dollars per chip.<\/p>\n

The growth has sent Nvidia\u2019s valuation soaring as well. It is the first chipmaker to have a market capitalization of more than $2 trillion and trails only Microsoft Corp. and Apple<\/a> Inc. overall.<\/p>\n

The announcement of new chips was widely anticipated, and Nvidia\u2019s stock is up 79% this year through Monday\u2019s close. That made it hard for the presentation\u2019s details to impress investors, who sent the shares down about 1% in extended trading.<\/p>\n

Huang, Nvidia\u2019s co-founder, said AI is the driving force in a fundamental change in the economy and that Blackwell chips are \u201cthe engine to power this new industrial revolution.\u201d<\/p>\n

Nvidia is \u201cworking with the most dynamic companies in the world, we will realize the promise of AI for every industry,\u201d he said at Monday\u2019s conference, the company\u2019s first in-person event since the pandemic.\u00a0<\/p>\n

The new design has so many transistors \u2014 the tiny switches that give semiconductors their ability to store and process information \u2014 that it\u2019s too big for conventional production techniques. It\u2019s actually two chips married to each other through a connection that ensures they act seamlessly as one, the company said. Nvidia\u2019s manufacturing partner, Taiwan Semiconductor Manufacturing<\/a> Co., will use its 4NP technique to produce the product.\u00a0<\/p>\n

Blackwell will also have an improved ability to link with other chips and a new way of crunching AI-related data that speeds up the process. It\u2019s part of the next version of the company\u2019s \u201csuperchip\u201d lineup, meaning it\u2019s combined with Nvidia\u2019s central processing unit called Grace. Users will have the choice to pair those products with new networking chips \u2014 one that uses a proprietary InfiniBand standard and another that relies on the more common Ethernet protocol. Nvidia is also updating its HGX server machines with the new chip.<\/p>\n

The Santa Clara, California-based company got its start selling graphics cards that became popular among computer gamers. Nvidia\u2019s graphics processing units, or GPUs, ultimately proved successful in other areas because of their ability to divide up calculations into many simpler tasks and handle them in parallel. That technology is now graduating to more complex, multistage tasks, based on ever-growing sets of data.\u00a0<\/p>\n

Blackwell will help drive the transition beyond relatively simple AI jobs, such as recognizing speech or creating images, the company said. That might mean generating a three-dimensional video by simply speaking to a computer, relying on models that are have as many as 1 trillion parameters.<\/p>\n

For all its success, Nvidia\u2019s revenue has become highly dependent on a handful of cloud computing giants: Amazon, Microsoft, Google and Meta Platforms<\/a> Inc. Those companies are pouring cash into data centers, aiming to outdo their rivals with new AI-related services.\u00a0<\/p>\n

The challenge for Nvidia is broadening its technology to more customers. Huang aims to accomplish this by making it easier for corporations and governments to implement AI systems with their own software, hardware and services.<\/p>\n

Huang\u2019s speech kicks off a four-day GTC event that\u2019s been called a\u00a0\u201cWoodstock\u201d for AI developers<\/a>. Here are some of the highlights from the presentation:<\/p>\n