Google has introduced its initial Arm-based CPU for data centers today, likely in response to Amazon’s Arm chips powering the giant’s data centers.
The chip from Google is called Axion, designed using Arm’s Neoverse V2 CPU. It boasts a 30% performance improvement over the fastest general-purpose Arm-based instances currently available for cloud computing. Google claims Axion also outperforms “comparable current-generation x86-based instances” by 50% in performance and up to 60% in energy efficiency.
In the near future, services from Google such as BigTable, Spanner, BigQuery, Blobstore, Pub/Sub, Google Earth Engine, and the YouTube Ads platform will all implement Axion. The chip is particularly suited for web and app servers, containerized microservices, open-source databases, data analytics engines, media processing, CPU-based AI training, and inferencing, providing significant performance boosts, Google states.
Supporting Axion is Titanium, a system of purpose-built custom silicon microcontrollers and tiered scale-out offloads. This setup handles platform operations like networking and security, allowing Axion processors to operate with greater capacity and improved performance.
Arm CEO Rene Haas commented:
Google’s introduction of the new Axion CPU represents a major advancement in delivering custom silicon optimized for Google’s infrastructure and built on our high-performance Arm Neoverse V2 platform. Years of ecosystem investment, combined with Google’s ongoing innovation and open-source software contributions, ensure the best experience for customers utilizing Arm technology.
Google Cloud customers will have access to Axion in services such as Google Compute Engine, Google Kubernetes Engine, Dataproc, Dataflow, and Cloud Batch. Arm-compatible software and solutions are now available on the Google Cloud Marketplace. Axion is expected to be available “later this year”, with no specific date provided yet.
