Cloud TPU

Train and run machine learning models faster than ever before.

Empowering businesses with Google Cloud AI

Empowering businesses with Google Cloud AI

Machine learning has produced business and research breakthroughs ranging from network security to medical diagnoses. We built the Tensor Processing Unit (TPU) in order to make it possible for anyone to achieve similar breakthroughs. Cloud TPU is the custom-designed machine learning ASIC that powers Google products like Translate, Photos, Search, Assistant, and Gmail. Here’s how you can put the TPU and machine learning to work accelerating your company’s success, especially at scale.

Try the demo

Want to learn more about how the Cloud TPU is fine-tuned for your machine learning applications?
Give the demo a try or read the blog.
Try the demo

Machine learning performance and benchmarks

Machine learning performance and benchmarks

To see how Cloud TPU compares to other accelerators, read the blog or view the MLPerf benchmark results.

Benefits

Built for AI on Google Cloud

Built for AI on Google Cloud

Cloud TPU is designed to run cutting-edge machine learning models with AI services on Google Cloud. And its custom high-speed network offers up to 11.5 petaflops of performance in a single pod — enough computational power to transform your business or create the next research breakthrough.

Iterate faster on your ML solutions

Iterate faster on your ML solutions

Training machine learning models is like compiling code: you need to update often, and you want to do so as efficiently as possible. ML models need to be trained over and over as apps are built, deployed, and refined. Cloud TPU’s robust performance and low cost make it ideal for machine learning teams looking to iterate quickly and frequently on their solutions.

Proven, state-of-the-art models

Proven, state-of-the-art models

You can build your own machine learning-powered solutions for many real-world use cases. Just bring your data, download a Google-optimized reference model, and start training.

Cloud TPU offering

Cloud TPU v2

Cloud TPU v2

180 teraflops
64 GB High Bandwidth Memory (HBM)
Cloud TPU v3

Cloud TPU v3

420 teraflops
128 GB HBM
Cloud TPU v2 Pod alpha

Cloud TPU v2 Pod (alpha)

11.5 petaflops
4 TB HBM
2-D toroidal mesh network

Cloud TPU features

Model library

Get started immediately by leveraging our growing library of optimized models for Cloud TPU. These provide optimized performance, accuracy, and quality in image classification, object detection, language modeling, speech recognition, and more.

Connect Cloud TPUs to custom machine types

You can connect to Cloud TPUs from custom AI Platform Deep Learning VM Image types, which can help you optimally balance processor speeds, memory, and high-performance storage resources for your workloads.

Fully integrated with Google Cloud Platform

At their core, Cloud TPUs and Google Cloud’s data and analytics services are fully integrated with other Google Cloud Platform offerings, like Google Kubernetes Engine (GKE). So when you run machine learning workloads on Cloud TPUs, you benefit from GCP’s industry-leading storage, networking, and data analytics technologies.

Preemptible Cloud TPU

You can save money by using preemptible Cloud TPUs for fault-tolerant machine learning workloads, such as long training runs with checkpointing or batch prediction on large datasets. Preemptible Cloud TPUs are 70% cheaper than on-demand instances, making everything from your first experiments to large-scale hyperparameter searches more affordable than ever.

Pricing

Cloud TPU charges for using preemptible and non-preemptible (on-demand) Cloud TPU use to train machine learning models. For detailed pricing information, please view the pricing guide.

Single Cloud TPU v2 device pricing

The following table shows the pricing per region for using a single Cloud TPU v2 device.

Cloud TPU v2 $4.50 USD per TPU per hour.
Preemptible TPU v2 $1.35 USD per TPU per hour.

Single Cloud TPU v3 device pricing

The following table shows the pricing per region for using a single Cloud TPU v3 device.

Cloud TPU v3 $8.00 USD per TPU per hour.
Preemptible TPU v3 $2.40 USD per TPU per hour.

Cloud TPU Pods have transformed our approach to visual shopping by delivering a 10X speedup over our previous infrastructure. We used to spend months training a single image recognition model, whereas now we can train much more accurate models in a few days on Cloud TPU Pods. We’ve also been able to take advantage of the additional memory the TPU pods have, allowing us to process many more images at a time. This rapid turnaround time enables us to iterate faster and deliver improved experiences for both eBay customers and sellers.

Larry Colagiovanni, VP of New Product Development, eBay

Resources

Cloud TPU tutorials, quickstarts, and docs

Cloud TPU content from AI Hub

Start building with fully configured AI Platform Notebooks

What makes TPUs fine-tuned for deep learning?

Train TensorFlow ML models faster and at lower cost on Cloud TPU Pods

Cloud TPU v2 Pod is in alpha. For more information on our product launch stages, see here.

Skicka feedback om ...