- Mediatek challenges Broadcom in the Hardware of the Evolution of Google
- The next generation TPU is aimed at a better processing of AI and lower costs
- Google diversifies the supply of AI chips, reducing the Broadcom dependence
MediaTak and Google will collaborate to develop next -generation tensioner processing units (TPU), a movement that means that Google will probably reduce its Broadcom dependence on its commercial hardware strategy of AI tools.
The objective of this collaboration is to design an affordable and efficient TPU in energy, produced by TSMC and will probably be launched as part of the 7th generation TPU series of Google.
Although Google will lead the general design, MediaTak will handle the input/output modules to facilitate communication between the processor and the peripherals, marking a change in the previous Broadcom paper in the development of the TPU nucleus, although Google is not reducing the broadcom ties completely.
Develop more efficient AI processors
According to reports, Google TPUs, designed to demand artificial and essential intelligence calculations to train the best LLM, will see better efficiency and performance, addressing the growing demand for powerful AI processing.
Google has been developing its own artificial intelligence server chips for internal use and cloud services to reduce the dependence of external suppliers such as NVIDIA, whose domain in AI Hardware contrasts with Google’s impulse for a more self -sufficient ecosystem through TPU investments.
Meanwhile, Mediatek has been expanding its presence in the development of AI chips, including associations in AI supercomputers.
INE Arly 2025, the company announced a collaboration of IA Supercomputer projects, with its last association with Google aligning with its broader strategy to strengthen its position in the AI industry.
If this collaboration is successful, it can influence the development of the best LLM models making IA processing more efficient.
Through you
