Google is reportedly designing its own Arm-based system-on-chips for Chromebook laptops and tablets to be launched in 2023.
The internet search giant appears to be following the same path as Apple by developing its own line of processors for client devices, according to Nikkei Asia.
Google earlier said its latest Pixel 6 and Pixel 6 Pro Android smartphones will be powered by a homegrown system-on-chip named Tensor. This component will be made up of CPUs and GPU cores licensed from other designers as well as Google’s own AI acceleration engine to boost machine-learning-based features, such as image processing and speech recognition.
The Chocolate Factory also launched its homemade Tensor Processing Units (TPUs) in 2016, aimed at training and running machine learning workloads on its cloud servers. Google’s CEO Sundar Pichai announced the fourth-generation of TPUs in May at the web titan's annual IO conference. Google also has a collection of its own Titan chips.
The rumored processors for its laptops and fondleslabs use Arm CPU cores, meaning Google will pay licensing fees to use the British chip designer’s blueprints. The chips will be manufactured elsewhere by fabrication plants, probably TSMC or Samsung. Technical specifications are hush-hush right now; The Register has asked Google for comment.
- Chip world veterans gather to design customizable, chiplet-based RISC-V server chips
- Pick a core, any core, says Intel – we'll magically put the right workload onto one in a hybrid SoC or accelerator
- EU to formally probe Nvidia's $54bn takeover over British chip designer Arm – report
- Boffins find if you torture AMD Zen+, Zen 2 CPUs enough, they are vulnerable to Meltdown-like attack
It’s beneficial for tech companies to develop their own chips as they, for one thing, roll out AI algorithms in their products. Custom accelerators can be optimized to run their makers' software stacks more efficiently, enabling more real-time intelligent decision-making by devices, whether that's in facial recognition or machine-learning-powered smartphone apps.
Apple’s iPhone 12 handsets, for example, contain the iGiant's 5nm 64-bit Arm-compatible A14 bionic SoC that's capable of accelerating computer-vision code and the processing of data from its sensors. Amazon also has custom processors available for its cloud customers on AWS, such as Inferentia and Graviton.
There are reportedly other in-house chip projects underway at Facebook for its Oculus VR headsets and at Microsoft for its servers and laptops. ®