Arm's Cortex-M52 is a powerful compact processor for low-cost AIoT development

Arm has announced the launch of its new Cortex-M52 processor as part of a bid to enhance low-cost AI capabilities for enterprise IoT device users. 

The chipmaker unveiled the launch of its newest processor, which it described as the smallest, most area and cost efficient processor to date, on 22 November.

The Cortex-M52 uses Arm Helium technology, which the firm said will deliver “enhanced AI capabilities for lower cost IoT devices” and accelerate simplified development.

Using Helium, the processor provides significant performance improvements in both digital signal processing (DSP) and machine learning applications, and is targeted specifically for use in “small, low power” devices.

“The Cortex-M52 includes Arm Helium technology, providing a significant performance uplift in DSP and ML applications for small, low power embedded devices, making it possible to deploy more compute intensive ML inference algorithms in endpoints without a dedicated NPU ,” the firm said.

“Helium technology has already been implemented successfully in products at the far edge of the network, but the Cortex-M52 now enables Arm partners to take this capability into lower cost more power constrained devices.”

All told, Arm said developers can benefit from a 5.6x performance uplift for machine learning, as well as a 2.7x performance boost for DSP compared to previous generations of the Cortex-M range.

Paul Williamson, SVP and GM for Arm’s IoT wing, said the launch of the new processor comes in direct response to demand for AI integration with IoT devices to deliver more granular data insights.

“Generative Artificial Intelligence (AI) and Large Language Models (LLMs) are grabbing headlines, but many don’t realize how much AI is already deployed in embedded devices and impacting applications across our homes, cities and in industry,” he said.

“AI is critical to understanding data and enabling more seamless interactions between the physical and digital world,” Williamson added.

“As this technology advances, on-device intelligence is being deployed in smaller, more cost-sensitive and often battery powered devices at the lowest cost points, with greater privacy and reliability due to less reliance on the cloud.”

Arm Cortex-M52: Simplified migration paths

Arm said the Cortex-M52 provides a “simplified migration path” from previous lines, such as the Cortex-M33 and Cortex-M4, and will target a wide range of AIoT applications. 

This includes creating richer UI, voice, and vision experiences for use in the automotive and industrial control spaces.

Williamson noted that embedded device developers have traditionally grappled with the mathematical, data analysis, toolchain expertise, and programming skills required for AI.

He added that developer enablement in this space is “critical if we are to see an increase in artificial intelligence of things (AIoT) shipments”.

“Historically, to achieve the ML and DSP performance Cortex-M52 delivers would have required the combination of a CPU, a DSP and an NPU, meaning that once the hardware is built, developers would need to write, debug and tune code for chips with three separate tool chains, three compilers, three debuggers, and so on.”

The Cortex-M52, however, simplifies development processes for AI within a “single toolchain and single proven architecture”.

This, he said, ensures a unified development flow” for traditional, DSP, and ML workloads.