Intel's Chen Liwu: As AI shifts from training to inference, the CPU-to-GPU ratio may reach 4:1

robot
Abstract generation in progress
Mars Finance News, May 20 — At the 54th Annual Global Technology, Media, and Telecommunications Conference hosted by JPMorgan Chase, Intel CEO Pat Gelsinger stated that Intel 18A has supported mass production of Panther Lake, with yield improving by about 7% per month, exceeding internal expectations. The 0.5 PDK for Intel 14A has been released, and a 0.9 PDK is planned to be offered to external customers in October. The team has already begun long-term planning for 10A and 7A process nodes. As AI shifts from training to inference, CPUs are becoming increasingly important and indispensable in the AI era, with the configuration ratio of CPUs to GPUs moving from 1:8 toward 1:1, and even reaching 4:1. Currently, efforts are being made to actively pursue ASIC business and provide customized solutions. (Wide-angle observation)
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned