Google Unveils Arm-Based Axion Processors for AI Model Training: Everything You Need to Know

Google Unveils Arm-Based Axion Processors for AI Model Training: Data centers can run a variety of workloads on Axion processors, including artificial intelligence training.

Google says Axion processors deliver up to 30% better performance than Arm-based processors.

Google Unveils Arm-Based Axion Processors for AI Model Training: Everything You Need to Know

Google Axion processors are up to 50% faster and 60% more energy efficient than comparable x86 chips.

The Axion processors already power Google Earth Engine and YouTube Ads platform, and the company plans to make them available to Cloud customers later this year.

Also Read: Automotive Giants Toyota, Honda, and Subaru Harness Generative AI for Car Design Innovation

Axion processors will be available in many Google Cloud services, including Google Compute Engine, Google Kubernetes Engine, Dataproc, Dataflow and Cloud Batch.

Google has a long history of designing silicon chips and deploying them at scale. So, what's next?

Introducing Google Cloud Axion—our new custom ArmⓇ-based CPU designed for the data center #GoogleCloudNext. pic.twitter.com/7eiXaPOh4P

— Google Cloud (@googlecloud) April 9, 2024

Since 2015, Google has released a series of five Tensor Processing Units (TPUs) designed specifically for AI and machine learning.

Google’s Tensor SoC powers the Pixel smartphone. CPUs based on Arm are Azure Cobalt 100 and Azure Maia 100.

In general computing, Cobalt is a custom Arm-based CPU, while Mia 100 runs AI models and language models.

Also Read: Top 6 Entertaining Prompts to Experiment with Copilot AI Chatbot