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.
The end of ‘entry-level’: STMicroelectronics’ STM32C5 sets a new baseline for embedded systems
DSP, Micros & Memory
[Sponsored] Instead of incrementally improving legacy Cortex-M0+ architectures, STM32C5 introduces a Cortex-M33-based platform into the entry-level category. This changes not only performance expectations, but also how engineers approach system architecture, consolidation, and long-term scalability.
Read more...GigaDevice expands GD25UF Series density NuVision Electronics
DSP, Micros & Memory
GigaDevice has announced the expanded density range of its GD25UF series 1,2 V ultra-low power SPI NOR Flash, now spanning from 8 Mb to 256 Mb.
Read more...ARINC 429 line driver evaluation board ASIC Design Services
DSP, Micros & Memory
Holt Integrated Circuits have announced the release of the ADK-85104 Evaluation Board, a compact, ready-to-use platform designed to help engineers rapidly evaluate and characterise Holt’s HI-85104.
Read more...Highly integrated 24-channel mixed signal IC EBV Electrolink
DSP, Micros & Memory
Microchip Technology has announced the LX4580, a 24-channel mixed-signal IC designed to replace multiple discrete components with a single device that supports synchronised data acquisition, fault monitoring, and motor control.
Read more...Lower-power Thread and BLE connectivity iCorp Technologies
DSP, Micros & Memory
Espressif has released the ESP32-H21, a low-power wireless SoC aimed at Thread, Matter, Zigbee, and Bluetooth LE device designs.
Read more...Touch-enabled 32-bit MCU 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...Compact 6 A automotive buck converter Altron Arrow
Power Electronics / Power Management
Delivering up to 6 A of continuous output current, the DCP0606Y from STMicroelectronics enables efficient regulation of low-voltage rails commonly used in modern vehicle electronics and industrial systems.
Read more...Build smarter with UNO Q Electrocomp Express
DSP, Micros & Memory
The Arduino UNO Q’s hybrid design combines a Linux Debian-capable microprocessor with a real-time STM32U585 microcontroller making it the perfect dual-brain platform for the next innovation.
Read more...Next-gen modules for rugged edge AI systems Altron Arrow
Computer/Embedded Technology
Designed for real-world edge deployments where systems do not sit still, SolidRun’s P100 COMx6 series targets mobile platforms as well as harsh, mission-critical environments.
Read more...Compact AI modules for imaging Otto Wireless Solutions
DSP, Micros & Memory
SIMCom has introduced two compact smart AI modules, the SIM8666 and SIM8668, designed to simplify the development of imaging-based IoT applications.
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