Arm, a chip technology supplier, has released instruction set architecture targeting data centers — ahead of its planned $40 billion merger with Nvidia.
The new architecture called V9, the first new Arm architecture in a decade, aims to counter Intel in two areas: Security and artificial intelligence.
The number of Arm-based chips shipped reached more than 100 billion devices over the last five years. At the current rate, 100 percent of the world’s shared data will soon be processed on Arm; either at the endpoint, in the data networks or the cloud.
The chipset company said new capabilities in Armv9 will accelerate the move from general-purpose to more specialized compute across every application as AI, the Internet of Things (IoT) and 5G gain momentum.
Arm said the Armv9’s CPU performance increases by more than 30 percent over the next two generations of mobile and infrastructure CPUs.
One of the major advances for Intel and AMD chips was the ability for cloud computing providers to use software to split chips up into “virtual machines” that could run applications from multiple customers, which in turn helped firms such as Amazon Web Services (AWS) and Microsoft’s Azure to generate billions of dollars in profits, Reuters reported.
Arm also introduced a concept called “Realms” that will accomplish a similar task in the hardware of chips.
“We see no reason why the Realm technology cannot scale up to provide security in the most high-performance systems that are out there,” Arm Chief Executive Simon Segars said during a news briefing.
Arm is adding features for artificial intelligence chips for tasks like image and speech recognition, a field where Nvidia Corp’s chips have outperformed Intel’s and helped it exceed Intel by market capitalization.
“We’re excited by the prospect of combining with Nvidia and the enhanced engineering capabilities that we’ll be able to bring marrying our pervasive compute platform with their deep, deep expertise in AI,” Segars said.
