Google last week announced the Tensor Processing Unit, a custom application-specific integrated circuit, at Google I/O. Built for machine learning applications, TPU has been running in Google’s data centers for more than a year. Google’s AlphaGo software, which thrashed an 18-time international Go champion in a match earlier this year, ran on servers using TPUs.
Wouldn’t it be cool if you could watch two, or even three, full-length movies on your laptop during a long flight without worrying about running out of battery? What if your laptop could display graphics well enough to play the most resource-intensive online games while you’re on the go? Thanks to the latest crop of Windows
Automated storage tiering boosts storage efficiency and saves money, but why is tiering different from caching, why is it suited to use with flash and how do suppliers differ? Implementing a successful storage solution is always a balance between capacity, performance and cost. Given unlimited resources, all data would be deployed on the fastest media
Microsoft says it is pulling support for a pared-down, IoT version of Windows 10 from the latest version of Intel’s Galileo board computer because it doesn’t have the hardware capabilities to support the OS. Intel’s Galileo is an uncased board being used by makers to build robots, appliances, wearable devices and other devices. The latest