{"id":9200,"date":"2023-08-02T20:49:00","date_gmt":"2023-08-03T03:49:00","guid":{"rendered":"https:\/\/mattfife.com\/?p=9200"},"modified":"2023-08-07T13:26:39","modified_gmt":"2023-08-07T20:26:39","slug":"google-tensor-processing-units-version-4","status":"publish","type":"post","link":"https:\/\/mattfife.com\/?p=9200","title":{"rendered":"Google Tensor Processing Units – version 4"},"content":{"rendered":"\n

I’ve written about Google’s custom silicon TPUs before (Google’s Tensor Processing Units – v1)<\/a>.<\/p>\n\n\n\n

One of the big reasons for Google and others web services to develop their own custom chips is that general purpose CPUs are flexible but typically need a lot of power. That power costs a lot of money in electricity bills and cooling costs in huge data centers. So, why buy chips with lots of stuff you don’t need when you can build your own – and save millions of dollars a year in a data center with lower cooling and power costs? <\/p>\n\n\n\n

In just a 6 years, Google has managed to design and build 4 ever increasingly capable AI data center chips. They had somewhat humble beginnings<\/a> – but they are becoming increasingly powerful. Now they have just published information about TPU version 4. <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

What is this new chip capable of?<\/a><\/p>\n\n\n\n