You are currently offline

Google's Axion CPU outperforms competitors' Arm-based instances by 30% and offers 50% better performance and 60% energy efficiency than x86-based ones

Google has announced the development of its first custom Arm-based data center processor, named Axion, based on Arm's Neoverse 2 designs. The Axion instances are said to offer 30% better performance than other Arm-based instances from competitors like AWS and Microsoft and up to 50% better performance and 60% better energy efficiency than comparable X86-based instances.

Google's Axion instances are designed to support Google's AI workloads before they are rolled out to business customers of Google Cloud later this year. The Axion chips are already powering YouTube ads, the Google Earth Engine, and other Google services. Google is also updating its TPU AI chips, which are used as alternatives to Nvidia’s GPUs for AI acceleration tasks.

The Axion Arm-based CPU is built on Arm's Neoverse V2 technology and is designed to deliver strong vCPU performance for cloud-based workloads. It is expected to perform 30% faster than the leading Arm CPU and deliver 50% better performance and 60% better energy efficiency than comparable x86 CPUs. Google has invested significantly in optimizing its Go runtime language for Arm, and Axion is expected to support all general-purpose compute workloads such as Web serving, data analytics, containerized workloads, databases, and more.

Google's move to develop its own custom Arm-based data center processor follows similar actions by competitors such as Alibaba, Amazon, and Microsoft. The new processor, named Axion, is expected to become available later in 2024, and Google plans to utilize these Axion Arm chips for YouTube ad workloads once they become available.

Google's announcement of an Arm-based CPU comes months after Microsoft revealed its own custom silicon chips designed for its cloud infrastructure. Microsoft has built its own custom AI chip to train large language models and a custom Arm-based CPU for cloud and AI workloads. Amazon has also offered Arm-based servers for years through its own custom CPU, with the latest workloads able to use Graviton3 servers on AWS.

Google won't be selling these chips to customers, instead making them available for cloud services that businesses can rent and use. By developing its own custom Arm-based data center processor, Google is reducing its reliance on partners like Intel and Nvidia, while also competing with them on custom chips to power AI and cloud workloads.

Google won't be selling these chips to customers, instead making them available for cloud services that businesses can rent and use
Google won't be selling these chips to customers, instead making them available for cloud services that businesses can rent and use
blank

blank strive to empower readers with accurate insightful analysis and timely information on a wide range of topics related to technology & it's impact

Post a Comment (0)
Previous Post Next Post