Google Brings Liquid Cooling to Data Centers to Cool Latest AI Chips

TPU 3.0 is 8x more powerful than last-year's chip

Alphabet CEO Sundar Pichai speaking at Google I/O 2018
Alphabet CEO Sundar Pichai speaking at Google I/O 2018Google I/O live stream

Alphabet’s Google has for the first time introduced liquid cooling in its data centers to cool the latest processors that underpin AI capabilities in everything from the latest Gmail updates to upcoming capabilities in Google Photos.

Alphabet CEO Sundar Pichai announced the next-generation TPU 3.0 chip in his keynote at the company’s annual I/O conference in Mountain View, California, Tuesday.

TPUs, or Tensor Processing Units, “are driving all the product improvements you’re seeing today,” Pichai said. “These chips are so powerful, that for the first time we’ve had to introduce liquid cooling in our data centers.”

The new chips are installed in “giant pods,” he said. “Each of these pods is now 8x more powerful than last year – it’s well over 100 petaflops, and this is what allows us to develop better [machine learning] models, larger models, more accurate models, and helps us tackle even bigger problems.”

Link_20-_20pichai_20tpu_203_20google_20io_20pod.jpg

Liquid-cooled TPU 3.0 pod inside a Google data center

Pichai announced first-generation custom TPUs at I/O in 2016. The company has since started offering access to TPUs as a cloud service for external customers, in addition to GPUs, which are commonly used to train neural networks for AI applications.

Google’s chief executive didn’t reveal much detail about the latest-generation TPUs or how the cooling systems for them are designed, but judging by the photo of TPU 3.0 he displayed during the keynote, the system brings chilled liquid directly to the chip via thin tubes.

Neural networks are trained using highly dense clusters of GPUs or, in Google’s case, TPUs. These are extremely powerful processors that consume a lot of power. Because the clusters are so power-dense, they require cooling approaches similar to those used in the supercomputer industry, such as bringing liquid directly to the chip, instead of the more traditional approach of cooling by pushing cold air through the servers.

Link_20-_20google_20tpu_203_20row_20of_20pods.jpg

Row of liquid-cooled TPU 3.0 pods inside a Google data center

About the Authors

Yevgeniy Sverdlik

Former editor in chief of Data Center Knowledge.

Data Center Knowledge

Data Center Knowledge, a sister site to ITPro Today, is a leading online source of daily news and analysis about the data center industry. Areas of coverage include power and cooling technology, processor and server architecture, networks, storage, the colocation industry, data center company stocks, cloud, the modern hyper-scale data center space, edge computing, infrastructure for machine learning, and virtual and augmented reality. Each month, hundreds of thousands of data center professionals (C-level, business, IT and facilities decision-makers) turn to DCK to help them develop data center strategies and/or design, build and manage world-class data centers. These buyers and decision-makers rely on DCK as a trusted source of breaking news and expertise on these specialized facilities.

Sign up for the ITPro Today newsletter
Stay on top of the IT universe with commentary, news analysis, how-to's, and tips delivered to your inbox daily.

You May Also Like