On the first day of NVIDIA’s GTC conference, CEO Huang Renxun delivered a keynote speech, introducing NVIDIA’s latest developments in AI, automotive, robotics, 5G, real-time graphics, collaboration, and data centers. progress.
In addition to introducing their latest developments in AI, data center, and other fields, and releasing Nvidia’s first data center CPU Grace, Huang Renxun also announced the roadmap of Nvidia’s data center chip in his speech.
Huang Renxun said in his speech that the data center roadmap includes three types of chips: CPU, GPU, and DPU, and Grace and BlueField are essential and key components.
Join us on Telegram
Among the three types of chips, CPU, GPU, and DPU, each chip architecture will undergo a two-year polishing cycle (changes may occur during the cycle), one year focusing on the x86 platform, and another year focusing on the Arm platform. They will be released every year Exciting new products, three types of chips, leap year by year, one architecture.
Judging from the roadmap announced by Huang Renxun in his speech, GPU and DPU will be updated in the same year, the next generation will be launched in 2022, and it is planned to be updated again in 2024.
In terms of CPU, the data center CPU Grace they released will not be officially launched until 2023, and the next generation will be launched in two years.
