Computing-in-memory technology is poised to eliminate the massive data communications bottlenecks otherwise associated with performing artificial intelligence (AI) speech processing at the network’s edge, but requires an embedded memory solution that simultaneously performs neural network computation and stores weights.
Microchip Technology, via its Silicon Storage Technology (SST) subsidiary, announced that its SuperFlash memBrain neuromorphic memory solution has solved this problem with the WITINMEM neural processing SoC (system-on-chip), the first in volume production that enables sub-mA systems to reduce speech noise and recognise hundreds of command words, in real time and immediately after power-up.
Microchip has worked with WITINMEM to incorporate Microchip’s memBrain analog in-memory computing solution, based on SuperFlash technology, into WITINMEM’s ultra-low-power SoC. The SoC features computing-in-memory technology for neural networks processing including speech recognition, voiceprint recognition, deep speech noise reduction, scene detection and health status monitoring. WITINMEM, in turn, is working with multiple customers to bring products to market during 2022 based on this SoC.
Microchip’s memBrain neuromorphic memory product is optimised to perform vector matrix multiplication (VMM) for neural networks. It enables processors used in battery-powered and deeply embedded edge devices to deliver the highest possible AI inference performance per Watt. This is accomplished by both storing the neural model weights as values in the memory array and using the memory array as the neural compute element. The result is 10 to 20 times lower power consumption than alternative approaches, along with lower overall processor bill of materials (BOM) costs because external DRAM and NOR are not required.
Permanently storing neural models inside the memBrain solution’s processing element also supports instant-on functionality for real-time neural network processing. WITINMEM has leveraged SuperFlash technology’s floating gate cells’ non-volatility to power down its computing-in-memory macros during the idle state to further reduce leakage power in demanding IoT use cases.
Accelerate development of physical AI deployments Altron Arrow
DSP, Micros & Memory
With Avocado OS now available on the HummingBoard RZ-V2N-
AIoT and SolidSense AIoT V2N from SolidRun, teams can move from prototype to deployed fleet in weeks.
Read more...AI-ready edge MPU for HMIs Future Electronics
DSP, Micros & Memory
The Renesas RZ/G3E MPU is a high-performance microprocessor designed to enable advanced HMI systems with integrated artificial intelligence capabilities at the edge.
Read more...Industrial-grade ESP32-S3 controller
DSP, Micros & Memory
Erqos Technologies has introduced the EQSP32CE, a CE-certified, industrial-grade ESP32-S3 controller designed for developers who want the flexibility of the ESP32 ecosystem in hardware that can be deployed directly into real-world automation.
Read more...Universal NFC device Altron Arrow
DSP, Micros & Memory
Delivering high-end performance in a compact 4 x 4 mm package, the multipurpose NFC reader from ST Microelectronics, enables the convenience of contactless interaction and features for various end applications.
Read more...Compact low-power 32-bit platform EBV Electrolink
DSP, Micros & Memory
Microchip’s PIC32CM PL10 microcontroller family expands the company’s Arm Cortex-M0+ portfolio, delivering a compact, low-power 32-bit platform designed for cost-sensitive embedded applications.
Read more...Bridging the gap between prototype and production
DSP, Micros & Memory
Choosing between the FRDM i.MX 93, FRDM i.MX 91 and FRDM i.MX 91S development platforms can be intimidating, but once designers understand how each platform aligns with their application’s requirements, the decision becomes straightforward.
Read more...Low-power memory born for edge AI iCorp Technologies
DSP, Micros & Memory
As intelligence moves from the cloud to the device, memory become one of the most important design decisions in modern electronics. Edge-AI products – from smart speakers and surveillance cameras to ADAS modules and wearables – need to move data fast, but they also need to sip power. Winbond’s low-density LPDDR4/LPDDR4X SDRAM range is built to strike that balance.
Read more...Compact direct Time-of-Flight 3D LiDAR module Altron Arrow
AI & ML DSP, Micros & Memory
The VL53L9 from STMicroelectronics is the first direct Time-of-Flight (dToF) 3D LiDAR all-in-one module in ST’s portfolio, offering a resolution of 2,3K zones, wide field of view, on-chip processing, 100 frames per second, and sensing range from 5 centimeters to 9 meters.
Read more...SoC brings scalable edge AI to life Altron Arrow
AI & ML
The NXP i.MX 937 applications processor is optimised for performance without excessive power draw and bridges the gap between entry-level chips and high-end processors.
While every effort has been made to ensure the accuracy of the information contained herein, the publisher and its agents cannot be held responsible for any errors contained, or any loss incurred as a result. Articles published do not necessarily reflect the views of the publishers. The editor reserves the right to alter or cut copy. Articles submitted are deemed to have been cleared for publication. Advertisements and company contact details are published as provided by the advertiser. Technews Publishing (Pty) Ltd cannot be held responsible for the accuracy or veracity of supplied material.
printer friendly version