Published 20:25 IST, November 19th 2024
Microsoft Launches Two Data Centre Infrastructure Chips to Speed AI Applications
Microsoft has devoted significant resources to develop home-grown silicon for general purpose applications and artificial intelligence.
Advertisement
Microsoft has designed two ditional infrastructure chips for its data centres that will help speed artificial intelligence operations and increase data security, it said on Tuesday at its Ignite conference.
Microsoft has devoted significant resources to develop home-grown silicon for general purpose applications and artificial intelligence. Like rivals Amazon .com and Google, Microsoft's engineers say re is a performance and price benefit to designing chips that are customized for its needs.
Advertisement
Designing custom chips can reduce Microsoft's reliance on processors me by Intel and Nvidia.
Microsoft's two new chips are designed to be installed deep within company's data centre infrastructure. One chip is designed to increase security and or is for data processing.
Advertisement
company makes effort to design an array of data centre processors because it aims to "optimize every layer of infrastructure" and ensures that Microsoft's data centres crunch information at speed AI requires, said Rani Borkar, corporate vice president, Azure Hardware Systems and Infrastructure
Engineers will install new security chip called Azure Integrated HSM in every new server destined for a data centre beginning next year. chip aims to keep crucial encryption and or security data inside security module.
Advertisement
data processing unit, or DPU, aims to move multiple components of a server into a single chip that is focused on cloud storage data. company said it can run se specific tasks at three times less power and four times performance compared with its current hardware.
Microsoft also announced a new version of a cooling system for data centre servers that relies on liquid to reduce temperature of nearby components. cooling unit can be used to support large-scale AI systems.
Advertisement
20:24 IST, November 19th 2024