The Mountain View company Google has announced its latest and 6th generation Tensor Processing Unit with 4.7 times more computing power and the same is for data centres. Let’s get into the article to check out the full details.
As I mentioned above, it comes with 4.7 times more computing power and the company has achieved the boost by enhancing the chip’s matrix multiplication unit (MXU). It is very good for doubled memory bandwidth.
It comes with the third-generation SparseCore technology of Google and the same will enable Trillium TPUs to train models faster and deliver lower latency when serving those models.
The company offers the same with the most energy efficient setup and the company says that it can provide 67 percentage in energy efficiency compared to the previous generation.
Read interesting news, reviews as well as tips & tricks on TechnoBugg website, and stay updated with the latest happenings of the tech world on the go with Technobugg App. Also follow on Google News and join our Telegram channel as well as WhatsApp Channel for the latest updates.
