Google is Developing its Own Chip for Artificial Intelligence

Google is Developing its Own Chip for Artificial Intelligence

  • TPU is tailored to machine learning applications, allowing the chip to be more tolerant of reduced computational precision, which means it requires fewer transistors per operation.
  • A board with a TPU fits into a hard disk drive slot in our data center racks.
  • The Tensor Processing Unit (TPU) is a custom ASIC built specifically for machine learning.
  • Google just unveiled one of its hardware brainchilds: the Tensor Processing Unit (TPU).
  • The TPU is a custom ASIC created specifically for Google’s open source software library for machine learning, TensorFlow.

Read the full article, click here.


@futurism: “Google is Developing its Own Chip for Artificial Intelligence”


The Tensor Processing Unit (TPU) is a custom ASIC built specifically for machine learning. It was created for Google’s open source software library for machine learning, TensorFlow. It promises performance orders of magnitude above current chips, and is a seven-year leap forward for the technology.


Google is Developing its Own Chip for Artificial Intelligence

You might also like More from author

Comments are closed, but trackbacks and pingbacks are open.