Google was among the first hyperscalers build custom silicon for its services, starting first with tensor processing units (TPUs) for its AI initiatives, and then video transcoding units (VCUs) for the YouTube service. But unlike its industry peers, the company has been slower to adopt custom CPU designs, prefering to stick to off-the-shelf chips from the major CPUs. This is finally changing at Google, with the announcement that the company has developed its own in-house datacenter CPU, the Axion.

Google's Axion processor is based on the Arm Neoverse V2 (Arm v9) platform, which is Arm's current-generation design for high-performance server CPUs, and is already employed in other chips such as NVIDIA's Grace and Amazon's Graviton4. Within Google, Axion is aimed at a wide variety of workloads, including web and app servers, data analytics, microservices, and AI training. Google claims that the Axion processors boast up to 50% higher performance and up to 60% better energy efficiency compared to current-generation x86-based processors, as well as offer a 30% higher performance compared to competing Arm-based CPUs for datacenters. Though as is increasingly common for the cryptic cloud side of Google's business, least for now the company isn't specifying what processors they're comparing Axion to in these metrics.

While Google is not disclosing core counts or the full specifications of its Axion CPUs, the company is revealing that they are incorporating their own secret sauce into the silicon in the form of the company's Titanium purpose-built microcontrollers. These microcontrollers are designed to handle basic operations like networking and security, as well as offload storage I/O processing to Hyperdisk block storage service. As a result of this offloading, virtually all of the CPU core resources should be available to actual workloads. As for the chip's memory subsystem, Axion uses conventional dual-rank DDR5 memory modules.

"Google's announcement of the new Axion CPU marks a significant milestone in delivering custom silicon that is optimized for Google's infrastructure, and built on our high-performance Arm Neoverse V2 platform," said Rene Haas, CEO of Arm. "Decades of ecosystem investment, combined with Google's ongoing innovation and open-source software contributions ensure the best experience for the workloads that matter most to customers running on Arm everywhere." 

Google has previously deployed Arm-based processors for its own services, including BigTable, Spanner, BigQuery, and YouTube Ads and is ready to offer instances based on its Armv9-based Axion CPUs to its customers that can use software developed for Arm architectures.

Sources: GoogleWall Street Journal

Comments Locked


View All Comments

  • ballsystemlord - Tuesday, April 9, 2024 - link

    This is all well and good, but how does it even matter? We can only even see one, let alone work with it, if we worked at some particular division of google. This isn't consumer, pro-sumer, or commercial, it's in house only.
  • bubblyboo - Tuesday, April 9, 2024 - link

    1st source, last sentence of 1st paragraph:

    "Axion delivers industry-leading performance and energy efficiency and will be available to Google Cloud customers later this year."
  • ballsystemlord - Wednesday, April 10, 2024 - link

    So they're basically saying that they have a new CPU for us to rent and isn't this wonderful...

    Forgive me if I am recalling incorrectly, but it seemed to me that in years gone by, companies would be very happy to talk about their new products, telling you why it was awesome instead of just being paid to say that it's awesome.
  • autarchprinceps - Wednesday, April 10, 2024 - link

    It's literally the same as with AWS Graviton. You can use them directly, when running VMs on the Google Cloud, or indirectly by using higher level services that run on those VMs.
    Obviously, this is only consumer for a very limited user circle, but going by Gravitons success it will be in wide use by enterprises.
  • autarchprinceps - Wednesday, April 10, 2024 - link

    If you are talking about running it in your own data center, AWS at least has the option the run individual servers or pre build rack units locally, including using Graviton. Quick google says Google might have something similar, but I personally have no experience with it.
  • Terry_Craig - Thursday, April 11, 2024 - link

    Extremely limited use.
  • mode_13h - Monday, April 15, 2024 - link

    Why do you find this so threatening?
  • Blastdoor - Wednesday, April 10, 2024 - link

    Is there any information about who is fabricating this for them?

    seems like this is an example of the kind of business that Intel needs to win
  • Terry_Craig - Thursday, April 11, 2024 - link

    Another wave of lies? EPYC has already been shown beating all ARM designs including Nvidia's pompous superchip, sometimes by such a huge margin that it's embarrassing. No one is stupid. Stop lying, Google.
  • Dante Verizon - Saturday, April 13, 2024 - link

    In some cases clients can work within the limitations and problems of the Arm design. But I agree that it's not the best option, especially with zen5 being released soon

Log in

Don't have an account? Sign up now