Power-Efficient Wireless MCU Incorporates Neural Processing

09 April 2024

Introduced at Embedded World today, the Balletto from Alif Semiconductor is a highly integrated wireless microcontroller unit (MCU) aimed at use in wearable, hearable, home automation and smart building applications.

It has the hardware optimisation capabilities needed to deal with edge-located artificial intelligence (AI) and machine learning (ML) workloads - including speech recognition, vocal targeting, beam forming, adaptive noise cancellation (ANC), audio encoding/decoding and suchlike. Among the functional elements encompassed by this device are an Arm Cortex-M55 processing core (tallying a 704 EEMBC CoreMark score when running at 160MHz), an Arm Helium M-profile vector extension (MVE) for enhanced digital signal processing performance, a 46GOPS Arm Ethos-U55 embedded neural processor, high-resolution data conversion, plus Bluetooth LE and Thread connectivity, a +10dBm output high-power amplifier, a +4dBm output low-power amplifier, etc. I3C, USB-HS, MIPI, 2x CAN-FD interfacing is also included, as well as 77 GPIOs. The proprietary aiPM technology employed means that just the logic and memory resources being used will be powered - thereby keeping the current consumption involved to a minimum. The RF aspect allows concurrent Bluetooth LE 5.3 and Thread operations via its on-chip antenna. Consequently, it is well suited to use in Matter-based implementations.

As Sree Durbha, Senior Director of Product Marketing at Alif Semiconductor, explained to EPDT from the show floor; “Endpoint based AI will be essential for a broad array of customer use cases. With our new Balletto wireless MCUs, we will be able to assist OEMs in placing intelligence at closer to where the data is coming from and where it needs to be actioned, while also satisfying the power efficiency and cost criteria that they must adhere to.”

Contact Details and Archive...

Print this page | E-mail this page

This website uses cookies primarily for visitor analytics. Certain pages will ask you to fill in contact details to receive additional information. On these pages you have the option of having the site log your details for future visits. Indicating you want the site to remember your details will place a cookie on your device. To view our full cookie policy, please click here. You can also view it at any time by going to our Contact Us page.