Approximately a week ago, google built something called as a TPU (Tensor Processing Unit), an ASIC (Application Specific Integrated Circuit) for Machine Learning {TensorFlow is an Open Source Software Library for Machine Intelligence}.

TensorFlow™ is an open source software library for numerical computation using data flow graphs. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API. {But more about Tensor Flow in a later post…  }

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. Because of this, we can squeeze more operations per second into the silicon, use more sophisticated and powerful machine learning models and apply these models more quickly, so users get more intelligent results more rapidly. A board with a TPU fits into a hard disk drive slot in our data center racks.TPU is an example of how fast we turn research into practice — from first tested silicon, the team had them up and running applications at speed in our data centers within 22 days.

TPUs already power many applications at Google, including RankBrain, used to improve the relevancy of search results and Street View, to improve the accuracy and quality of their maps and navigation. AlphaGo was powered by TPUs in the matches against Go world champion, Lee Sedol, enabling it to “think” much faster and look farther ahead between moves.

 

Our goal is to lead the industry on machine learning and make that innovation available to our customers. Building TPUs into our infrastructure stack will allow us to bring the power of Google to developers across software like TensorFlow and Cloud Machine Learning with advanced acceleration capabilities. Machine Learning is transforming how developers build intelligent applications that benefit customers and consumers, and we’re excited to see the possibilities come to life.

One thing is sure, in the near future we can expect even more greater breakthroughs in Machine Learning using TPUs