Suqian Microelectronics releases the TUCA architecture and its GPGPU processor “Tianheng 1100”

robot
Abstract generation in progress
Domestic GPU chip and solution provider Suzhou Mingwei Microelectronics has recently released the “Thorsianway Unified Computing Architect-ure—TUCA” unified computing architecture for next-generation AI and heterogeneous computing, as well as the “Tianheng 1100” (TH1100) GPGPU processor for AI scenarios such as embodied intelligence. According to the announcement, the TUCA architecture can be combined with Suzhou Mingwei Microelectronics’ self-developed GPGPU, AI acceleration chips, and heterogeneous computing hardware to cover key computing links from application development, operator compilation, and runtime scheduling to hardware execution, thereby building a unified, efficient, and scalable heterogeneous computing software foundation. “Tianheng 1100” is the first GPGPU SoC chip independently developed by Suzhou Mingwei Microelectronics, designed for edge AI inference scenarios. (Sci-Tech Innovation Board Daily)
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