Google introduces Axion, the company's first custom Arm data center processor. The Axion is based on the Arm Neoverse V2 architecture and is said to be “thirty percent faster than current Arm competitors' chips.” The chip will be available to Google Cloud customers later this year.
Google writes In a blog post That Axion depends on Arm Neoverse V2 architecture. It is an Arm 2022 platform used for data centers and server chips and designed for cloud applications. high performance computing And machine learning. The chip also contains a system Google calls Titanium. This includes microcontrollers for specific tasks, such as networking and security. The CPU itself must have more computing capacity for general computing tasks.
The company also shared some concrete specifications about the chips. For example, it is not known how many cores the Neoverse V2 processor has. Google shares some performance claims based on its own tests. The technology company claims that Axion is up to 30 percent faster than “fastest.” General goal arm-Cases Currently available.” The company also says that the Axion's performance is up to 50 percent better and 60 percent more efficient than “similar x86-based instances.” However, the company does not share the data on which these numbers are based. Google also does not say which chips Competition was used in those comparisons.
Google wants to use Axion in its own cloud services soon. Customers should soon also be able to use the chip across Google Cloud applications like Compute Engine, Google Kubernetes Engine, Dataproc, Dataflow, and Cloudbarch.
With Axion, Google is following the lead of other cloud giants, which have been working on self-designed Arm processors for some time. For example, Amazon introduced the Graviton4 SoC with 96 Arm Neoverse V2 cores in November 2023. Microsoft also unveiled its first custom Arm chip last year, called the Cobalt 100. This chip should eventually become available to Azure customers. Axion is Google's first self-designed Arm chip for data centers, though the manufacturer has been around for years Development of TPU accelerators. They are used for specific AI computational tasks.
More Stories
Strong increase in gas export pipeline from Norway to Europe
George Louis Bouchez still puts Julie Tatton on the list.
Thai Air Force wants Swedish Gripen 39 fighter jets