🟦Microsoft has announced its own chips for AI and cloud computing

Microsoft developed the Maia 100 AI Accelerator and the Cobalt 100 CPU.
With a systems approach to chips, Microsoft aims to tailor everything ‘from silicon to service’ to meet AI demand - Source
Microsoft unveils two custom chips, new industry partnerships and a systems approach to Azure hardware optimized for int...

🟦 Microsoft announces AI-specific Maia 100 and cloud Cobalt 100 proprietary chips

 Microsoft has developed its own chips, the Maia 100 AI Accelerator and the Cobalt 100 CPU. The chips will be manufactured using TSMC’s 5nm process technology.

  • “Maia”
    • Chips optimized to speed up generative AI operations
  • “Cobalt”
    • Chips aimed at providing high efficiency and performance for cloud-native products

🟦 Microsoft streamlines efficiency with AI semiconductors

 In response to the growing demand for processing power driven by the advancement of AI technology, our goal is to sustain competitiveness and minimize operating costs. By leveraging these semiconductors, Microsoft will optimize the operation of large-scale AI models, including GPT-4 Turbo. This approach will enable cost reduction while enhancing the quality and performance of AI services.


In order to take the lead in the AI market, Microsoft has developed the “Maia 100 AI Accelerator” and “Cobalt 100 CPU”. These chips are expected to contribute to high-speed AI processing and improved performance of cloud services, increasing the competitiveness of companies.

 The evolution of chips has progressed through repeated specialization and generalization. Currently, dedicated chips are popular in generative AI, but as time goes by, they will shift to general-purpose chips.

Copied title and URL