Arm has introduced new versions of its designs for heavy-duty central processing units (CPUs), graphics chips, and machine learning chips. The company made the announcement at the Computex tech trade show in Taiwan.
The Cambridge, England-based company announced the Arm Cortex-A77 CPU, the Arm Mali-G77 graphics processing unit (GPU), and the Arm Machine Learning processor. Those new chips will help the company prepare for the 5G wireless networking era.
“We’ve followed 5G for a number of years, and we are excited to see [what] is happening this year in the smartphone space,” said Ian Smythe, Arm’s VP of marketing for the client line, in a press briefing.
Above: 5G means computing everywhere.
The chips are aimed at scaling from the edge of the network to the cloud, and they are getting ready for the convergence of 5G, internet of things, and AI.
June 5th: The AI Audit in NYC
Join us next week in NYC to engage with top executive leaders, delving into strategies for auditing AI models to ensure fairness, optimal performance, and ethical compliance across diverse organizations. Secure your attendance for this exclusive invite-only event.
The Arm Cortex-A77 is a successor to the Cortex-A76, but it has about 20% more instructions per clock. It also has area efficiency, which results in lower costs, and offers a roughly 4 times improvement over the Cortex-A15 from 2013.
Arm said these devices can be used in always-connected laptops or more secure computing devices with machine learning. The Arm Mali-G77 has 40% better performance, thanks to its Valhall architecture. The Arm Cortex-A77 can be used in machine learning or augmented reality/virtual reality experiences.
The Arm Mali-G77 also boasts key microarchitecture enhancements — including engine, texture pipes, and load store caches — which achieve 30% better energy efficiency and 30% more performance density.
On top of that, Mali-G77 brings a 60% improvement to machine learning performance, which significantly boosts inference and neural net (NN) performance for advanced on-device intelligence. These generational enhancements provide developers with greater performance
capability to design more immersive games for the mobile app ecosystem.
