Google Cloud unveils its first Arm-powered VMs

Google Cloud has announced its first line of ARM-based virtual machines (VMs).

The new Tau T2A chips (opens in new tab) will join Google’s existing line of Tau VMs, which were launched in June 2021.

Google says the new chips will be appropriate for scale-out workloads including web servers, containerized microservices, data-logging processing, media transcoding, and Java applications.

How much do they cost?

A 32vCPU VM with 128GB RAM will be priced at $1.232 per hour for on-demand usage in us-central1, and the entire new range is apparently price-performance optimized for cloud-native applications.

For your investment, you’ll get up to 48 vCPUs per VM, and 4GB of memory per vCPU, as well as 32 Gbps networking bandwidth, and a range of network-attached storage options, 

Google says the new T2A VMs support the most popular Linux operating systems including RHEL, CentOS, Ubuntu, and Rocky Linux. 

In addition, T2A VMs also support Google’s Container-optimized OS for Google Compute. 

Google is somewhat late to the party when it comes to rolling out VMs which support ARM.

Both Amazon Web Services (AWS), via its AWS Graviton processors, and Microsoft Azure have already rolled out Arm VMs.

Where can I sign up?

The T2A VMs are currently only available for preview in a select few Google Cloud regions, including Iowa, Netherlands, and Singapore, but they will enter General Availability in the coming months according to Google.

To get started, head to the Google Cloud Console (opens in new tab) and select T2A for your VMs.

If you’d like a more complete overview of what’s on offer or how much it costs before making a commitment, check out the guides which Google has pulled together here (opens in new tab) and here (opens in new tab).

“Our drug discovery research at Harvard includes several compute-intensive workloads that run on SLURM using VirtualFlow1,” said Christoph Gorgulla, research associate at Harvard University. “The ability to run our workloads on tens of thousands of VMs in parallel is critical to optimize compute time.”

“We ported our workload to the new T2A VM family from Google and were up and running with minimal effort.”

He added: “The improved price-performance of the T2A will help us screen more compounds and therefore discover more promising drug candidates.”