Tensor Processing Unit
The Tensor Processing Unit is an AI accelerator chip that Google designed in-house to speed up machine learning workloads.
The Tensor Processing Unit, usually called the TPU, is an application-specific integrated circuit built for the large matrix calculations at the heart of neural networks. Google first unveiled it in 2016. Google uses TPUs to train and run its own services and AI models and offers them to outside customers through Google Cloud.
Because it is purpose-built for specific workloads rather than general computing like a GPU, the TPU is often cited as a leading example of custom silicon designed by a large cloud provider.
This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.