Ampere Computing unveiled its AmpereOne Family of processors in 2023, boasting up to 192 single-threaded cores, which at the time was the highest in the industry.
Now, Ampere, founded in 2017 by Renée James, ex-President of Intel, is looking to push the boundaries further with its announcement of the AmpereOne Aurora, a 512-core CPU designed to cater to the evolving needs of cloud-native workloads.
Over the past few years, Ampere has focused on developing innovative technologies for cloud infrastructures. As general-purpose and AI workloads converge in the cloud, the need for a platform that is efficient, air-cooled, and integrated with AI acceleration has become apparent.
Addressing the global AI power challenge
AmpereOne Aurora integrates several of Ampere’s innovations, including custom cores, a proprietary mesh, and die-to-die interconnects across chiplets.
By adding Ampere’s own AI acceleration directly into the silicon hardware, the new processor aims to significantly enhance AI Compute capabilities. It offers up to 512 Ampere cores, delivering more than three times the performance of its predecessors.
The scalable AmpereOne mesh allows for seamless connection across various compute types, while the integrated Ampere AI IP and high-bandwidth memory further boost performance.
The new processor will be able to scale across a range of AI inference and training use cases, providing robust AI Compute capabilities for workloads like RAG and vector databases. Ampere says it will deliver leading performance per rack for AI Compute, and its air-cooling capability allows for deployment in any existing data center, including public clouds, enterprise settings, hyperscale data centers, and edge locations. This feature addresses the global AI power challenge by enabling efficient and versatile deployment.
Ampere’s collaborations with various partners and the AI Platform Alliance aim to create hardware solutions that deliver a full spectrum of AI Compute within an open and interoperable environment. Users can rely on accessible and affordable technologies to develop their own innovative AI products and services.
Despite these advancements, the market for cloud-native solutions is highly competitive. With established players continuously pushing the envelope, some industry analysts may question whether Ampere’s efforts might be too late for it to gain significant traction.
More from TechRadar Pro
https://cdn.mos.cms.futurecdn.net/PBqGFumDrnANLAa8Z5zZ7g-1200-80.jpg
Source link
waynewilliams@onmail.com (Wayne Williams)
