news

Nvidia's next-generation AI chip launch hits roadblock as engineering hurdles slow product launch

2024-08-06

한어Русский языкEnglishFrançaisIndonesianSanskrit日本語DeutschPortuguêsΕλληνικάespañolItalianoSuomalainenLatina

Source: Huanqiu.com

[Global Network Technology Comprehensive Report] On August 6, according to Bloomberg, Nvidia encountered engineering obstacles in the development of two new advanced chips, which slowed down the release of some products aimed at expanding the company's leading position in the artificial intelligence computing market. According to people familiar with the matter, the delay affected Nvidia's highly anticipated Blackwell product line, which was officially released by Nvidia in March this year. One version of the Blackwell product line, the AI ​​accelerator, is being redesigned to be more compatible with the data center infrastructure of the earlier chip Hopper H100.


Image source: IC photo

Nvidia declined to comment on "rumors" of recent engineering issues. The company said it has begun shipping Blackwell samples to a broad range of customers, and that demand for its Hopper products remains strong. Still, Nvidia said in a statement that "production is expected to ramp in the second half of the year."

However, Nvidia shares fell 6.4% on Monday, though a broader decline in technology stocks also weighed on the stock. Meanwhile, shares of rival Advanced Micro Devices Inc. rose 1.8%.

Nvidia supplies chips to Microsoft Corp., Alphabet Inc.’s Google and other companies that are spending billions of dollars to build data centers in anticipation of a surge in demand for artificial intelligence services.

Previously, in May, Nvidia's Huang Renxun said Blackwell was in full production and would be available to cloud computing providers later this year, and he predicted that demand for new and previous-generation products would continue to outstrip supply.