NXP's i.MX RT1170 Crossover MCU "Launches the Gigahertz Microcontroller Era"

With a 1GHz Cortex-M7, 400MHz Cortex-M4, and 2D GPU, NXP is positioning its latest part between microcontroller and application processor.

NXP Semiconductors has announced the i.MX RT1170 "crossover" 28nm fully-depleted silicon-on-insulator (FD-SOI) microcontroller unit (MCU), a power-efficient design which nevertheless manages to clock its primary Arm Cortex-M7 processing core at up to 1GHz while packing a secondary Cortex-M4 core running at 400MHz.

"NXP saw the potential early on to create high-performance crossover MCUs, utilising the latest applications processor architecture and design philosophies," says Geoff Lees, senior vice president and general manager for microcontrollers at NXP, of the company's latest release. "Now, with the i.MX RT1170 breaking the gigahertz barrier, we have opened up edge computing to all these technology possibilities."

In addition to its Cortex-M7 and Cortex-M4 cores, the i.MX RT1170 includes a 2D vector graphics core, NXP's in-house Pixel Processing Pipeline (PxP) 2D graphics accelerator, and its EdgeLock 400A embedded security platform. Depending on model chosen the part can include up to 2MB of on-chip static RAM (SRAM) with up to 512KB optionally configured for as Tightly Coupled Memory (TCM) for the Cortex-M7 and 256KB for the Cortex-M4, both with ECC error correction.

"As we move towards a world of a trillion connected devices, businesses are looking for real-time data insights, driving an increased requirement for on-device intelligence," adds Dipti Vachani, senior vice president and general manager for automotive and Internet of Things (IoT) at core IP provider Arm. "The i.MX RT1170 family efficiently combines enhanced on-device processing with low-latency performance, significantly lowering the bill of materials (BOM) cost, while pushing the boundaries of what’s possible for embedded and IoT applications."

The company is positioning the part as helping to push the "edge computing" model, pointing to the gigahertz-speed Cortex-M7 as assisting with machine learning and inference for voice, vision, and gesture recognition, natural language parsing, and the like. NXP's own benchmarks claim the on-chip memory and high-speed microcontroller boost facial recognition performance fivefold over its nearest competitors, while the OpenVG 1.1 compliant graphics core can accelerate user interfaces on 1080p displays at 30 frames per second or 720p at 60 frames per second - ideal, the company claims, for "smart home, industrial, and automotive cockpit applications."

NXP has confirmed it will be demonstrating the i.MX RT1170 at Arm TechCon 2019, showcasing a new record CoreMark benchmark run of 6,468 at Booth #731 on October 8th-10th 2019. More information on the part itself, meanwhile, can be found on the NXP website.

Gareth Halfacree
Freelance journalist, technical author, hacker, tinkerer, erstwhile sysadmin. For hire: freelance@halfacree.co.uk.
Latest articles
Sponsored articles
Related articles
Latest articles
Read more
Related articles