Second generation ST 64bit processor for edge AI

Second generation ST 64bit processor for edge AI

New Products |
By Nick Flaherty

Cette publication existe aussi en Français

STMicroelectronics has shown its second generation 64bit processor for Linux-based edge AI applications.

The STM32MP2 64bit processor series is aimed at smart factories, smart healthcare, smart buildings, and smart infrastructure that needs to run Linux with edge AI acceleration.

The 64bit Cortex-A35 core runs at up to 1.5GHz alongside a Cortex-M33 core, in-house graphics processor (GPU), neural processor (NPU) and video processor (VPU). AI workloads can run on the CPU, GPU, or NPU depending on processor loading and application demands, for optimal performance and energy efficiency.

This allows system designs to avoid active cooling, eliminating the need for fans to give smaller size, silent operation, greater reliability, and reduced power consumption.

The 3D GPU supports up to 1080p displays and the powerful multimedia features also include a full-HD video pipeline with parallel LVDS and DSI interfaces. Together with a MIPI CSI-2 camera interface with ISP, these enhance support for cutting-edge machine-vision applications. 

There are up to three Gigabit Ethernet ports with a 2-port switch and support for Ethernet time-sensitive networking (TSN). There are also PCIe Gen2, USB 3.0, and three CAN-FD interfaces.

ST is also pushing its security credentials in its second generation 64bit processor, with proprietary secure hardware, anti-tamper controls, protected firmware, and secure provisioning, working with ARM’s TrustZone architecture, to keep sensitive data and keys safe. The family is certified to SESIP Level 3 for the coming US CyberTrust mark and stipulations in the EU’s Radio Equipment Directive that are due to become mandatory in 2025. 

“Our embedded MPUs address the trend that’s pushing more workloads and greater demands to smart devices, often deployed at the IoT edge, for faster response and increased efficiency,” said Stephane Henry, General Purpose MPU Division General Manager, STMicroelectronics. “The new STM32MP2 devices we are announcing today extend the performance trajectory, introducing our most powerful processing engine, now adding edge AI, and supported by the STM32 ecosystem to accelerate product development.” 

“We are able to build an industrial-grade gateway with unmatched reliability and security,” said said Marco Temporiti, R&D Software Manager, ISEO. “The seamless integration with Yocto Linux has streamlined our development process, allowing us to innovate with ease. And, ST’s 10-year longevity programme also ensures a long product lifecycle at reduced cost, setting a new standard in the industry.” 

S-Track worked with ST on a 2-channel network audio adapter using the previous STM32MP1 series 64bit processor to handle tasks such as converting network digital audio signals for transmission and reception.

“Now, we’re enthusiastic about the possibilities of the STM32MP2 series, which deliver improved power efficiency, enabling us to minimise cooling requirements in our enclosed casings,” said Yue Xiong, CEO of S-Track. “The integrated Cortex-M co-processor eliminates the need for a separate microcontroller, and support for Gigabit Ethernet with precision time protocol (PTP) enables accurate data transfer and synchronisation among devices.” 

 The STM32Cube ecosystem provides tools and dedicated MPU software packs including OpenSTLinux and OpenSTDroid for Android support. There are also evaluation boards that provide further help to simplify development and accelerate project completion. 

The first STM32MP2 MPUs are scheduled to enter volume production in June 2024. Sample requests and pricing information are available from local ST sales offices.



If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News


Linked Articles