Google Tests AI Data Center in Space With TPU Satellite

The satellite, launched on October 1, is a prototype for Project Suncatcher. It contains four specialty chips called Tensor Processing Units, or TPUs, which Google designed for machine learning and has already deployed in data centers on Earth. A SpaceX rocket carried the satellite into orbit, and the company Planet will get it up and running, the report said.

Once operational, the TPUs will run a version of Google's Gemma AI model for 15 minutes at a time because of heat management constraints. The open-weight model will be used to answer simple queries. Google said in a blog post that the mission will gauge how the TPUs handle 'the physical stress of spaceflight and the radiation and thermal extremes of space.'

Travis Beals, senior director and lead of Project Suncatcher, called the satellite 'a very minimal test' to make sure the chips can run in space. Beals said Google will then fire up and test the TPUs. The goal is for the mission to be operational for a year.

The report was shared by longtime Slashdot reader Geoffrey.landis. It described the effort as part of a research project the company hopes can pave the way for orbiting AI data centers powered by the sun. The prototype satellite is designed to show whether TPUs can operate in the space environment.

Editor's Summary

Google has launched a prototype satellite carrying four TPUs to test whether its AI chips and Gemma model can run in orbit. The one-year mission, led by Project Suncatcher, will examine spaceflight stress, radiation and thermal extremes. Google hopes the research can pave the way for solar-powered orbiting AI data centers.