This approach is ingenious because rack space is less of a constraint for AI accelerators in data centers. Additionally, it allows Nvidia to continue using chips manufactured with the more mature 4NP technology rather than the latest 3nm technology. This results in better output rates and lower costs per unit.
Oh, the glue and spinal cord are patented! 😅😅
This is the check-mate moment. And not a surprise, AMD’s Lisa Su announced a few products line-up in Computex and AMD’s MI300x successor was not the key highlight.
Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.
