Google's AI Chips Blast Off into Space in Ambitious Computing Project

Google has successfully launched its custom Tensor Processing Units (TPUs) into space as part of its Project Suncatcher, a moonshot effort to test the feasibility of large-scale AI computing in low-Earth orbit. The TPUs were carried aboard SpaceX's Transporter-18 mission and will be tested against radiation, extreme heat, and launch conditions.

The project marks an important step towards Google's ambitious goal of powering computing infrastructure in space, which could potentially address one of the biggest constraints facing AI data centers: power. According to Planet Labs, the satellite carrying the TPUs can receive up to eight times more solar power than solar panels on Earth and has access to sunlight for much longer periods.

The economics of powering computing infrastructure in space still depend heavily on launch costs, which are currently high. However, Google's research suggests that if launch costs fall to around $200 per kilogram, the economics of powering computing infrastructure in space could begin to approach those of terrestrial data centers.