The big motion picture: Facebook is adding to a growing listing of companies that are rushing to develop their own chips. Apple, Microsoft, Google, Amazon, Tesla, and Baidu are all looking to cut their reliance on silicon giants like Intel, AMD, Nvidia, and Qualcomm. The principal reason is that custom silicon designed for specific workloads needs less power to run and can be more than scalable than general-purpose hardware. The latter has go a commodity that any competitors can apply and doesn't let for tight integration with the software.

Facebook is one of several companies jumping on the custom Arm-based silicon railroad train and condign more cocky-reliant. Co-ordinate to a report from The Information, the social giant has been developing a family of special chipsets for accelerating auto learning tasks. One of these will be used in grooming the AI that handles content recommendations.

This try dates back to 2022 when information technology transpired that Facebook was looking to rent engineers with feel in designing FPGAs and ASICs. I year subsequently, the company revealed plans to create an AI pipeline for its data centers with the help of partners like Intel, Qualcomm, Marvell, Esperanto, and Habana -- which is now endemic by Intel.

Image: Facebook's Zion pipeline for AI training

Yet, the new report suggests the social giant has changed its listen and is developing the new chips completely in-business firm. A company spokesperson clarified to us that "Facebook is e'er exploring ways to drive greater levels of compute performance and power efficiency with our silicon partners and through our own internal efforts." This suggests the company plans to practice the transition in small steps over the coming years, equally the new chips aren't meant to completely replace tertiary-political party solutions just still.

The company is also developing a chip for video transcoding to improve the infrastructure that delivers videos and livestreams in its apps. This is similar to what Google has been doing with its "Argos" Video Coding Units (VCUs) to accelerate the transcoding of videos uploaded to YouTube.