About Google (TPU)
The Tensor Processing Unit is a family of chips that Google designed for neural network workloads, with Broadcom helping turn the designs into manufacturable silicon. It is an ASIC, meaning a chip built for one job rather than general use, so it trades flexibility for efficiency on matrix maths. Google began using TPUs internally in 2015 and announced them in 2016. It now rents them to outside customers through Google Cloud. The seventh generation, Ironwood, was unveiled in April 2025 and can be linked in pods of up to 9,216 chips.
Google (TPU) was founded in 1998 and is based in Mountain View, CA, United States. It is listed under TPUs, Custom Silicon.
Compute Technologies
- TPUs
- Custom Silicon
What Google (TPU) works on
TPUs
A TPU, or tensor processing unit, is a chip designed by Google to run machine learning. A tensor is a grid of numbers, and neural networks are mostly built from multiplying such grids. A TPU is organised around doing that one operation very efficiently.
Custom Silicon
Custom silicon means a company designs its own chips for its own products or data centers instead of buying standard parts. The chip is made by a foundry such as TSMC, but the design belongs to the customer.
Also in United States
AWS Trainium/Inferentia, Oxmiq Labs, Applied Materials, Tesla Dojo, II-VI/Finisar (now Coherent)
