![[Google Cloud Documentation]](https://www.gstatic.com/devrel-devsite/prod/v0f3a5b8b76e4a120372a69044e02756e703b6140f9f1812c6e4a0407b19864b7/clouddocs/images/lockup_full_color.svg){kind=link}
![[]](https://docs.cloud.google.com/_static/clouddocs/images/icons/categories/ai-and-machine-learning-color.svg){kind=link}
TPU v2
Caution: TPU v2 is only supported using the Cloud TPU API, which is no longer under active development. The Cloud TPU API will receive bug fixes and security updates only. You should migrate to a newer TPU version and use Compute Engine or Google Kubernetes Engine to manage TPU resources. For more information, see TPU resources in Compute Engine and About TPUs in GKE.This document describes the architecture and supported configurations of Cloud TPU v2.
System architecture
Architectural details and performance characteristics of TPU v2 are available in A Domain Specific Supercomputer for Training Deep Neural Networks.
Configurations
A TPU v2 slice is composed of 512 chips interconnected with reconfigurable
high-speed links. To create a TPU v2 slice, use the --accelerator-type
flag in the TPU creation command (gcloud compute tpus tpu-vm). You specify the
accelerator type by specifying the TPU version and the number of TPU cores. For
example, for a single v2 TPU, use --accelerator-type=v2-8. For a v2 slice
with 128 TensorCores, use --accelerator-type=v2-128.
The following command shows how to create a v2 TPU slice with 128 TensorCores:
$ gcloud compute tpus tpu-vm create tpu-name \ --zone=us-central1-a \ --accelerator-type=v2-128 \ --version=tpu-ubuntu2204-base
For more information about managing TPUs, see Manage TPUs. For more information about the TPU system architecture Cloud TPU, see System architecture.
The following table lists the supported v2 TPU types:
| TPU version | Support ends |
|---|---|
| v2-8 | (End date not yet set) |
| v2-32 | (End date not yet set) |
| v2-128 | (End date not yet set) |
| v2-256 | (End date not yet set) |
| v2-512 | (End date not yet set) |