Neural Network

Renesas has introduced a high-end AI MCU family with triple processors and security. The highest spec devices in the ‘RA8P1’ microcontroller family combine a 1GHz Arm Cortex-M85 processor with a 256 MAC/cycle 400MHz Arm Ethos-U55 neural processing unit and a 250MHz Cortex-M33 CPU. “This combination delivers CPU performance of over 7,300 CoreMarks and AI performance of 256Gop/s,” according to the ...

DeepX is to start production of its DX-M1 neural processor unit IC in the second quarter of this year, according to the company, which claims for it “the highest power-efficiency and performance efficiency in the world”. The company has published ResNet-50 figures in support of these claims: >10Top/s/W and 60frame/s/Top/s. Total capability per IC is 25Top/s. It is due to ...

The IEEE’s International Solid-State Circuit Conference in San Francisco featured an overview of next-generation high-performance CPUs. AMD revealed aspects of Zen 5, its x86-64 microprocessor for desktops and laptops. Built on TSMC’s 4nm FinFET process, the 55mm2 eight cores have a total of 8.6bn transistors. Each core has a 1Mbyte private L2 cache and there is 32Mbyte of shared L3. ...

Alif Semiconductor has integrated Arm’s Ethos-U85 neural processing unit (NPU) into its second generation of its ‘Ensemble’ microcontrollers for AI and machine learning. It is “the world’s first implementation of the Ethos-U85 in an endpoint AI MCU”, according to Arm IoT general manager Paul Williamson. “With Alif’s high bandwidth memory and power management, [the new parts] support NPU operators required ...

TDK has created a spin-memristor for analogue neural networks, and built a network that can separate three types of sound in real-time. It has been collaborating on memristors with French research lab CEA since 2020, and has now announced a collection of memristors packaged in an IC (described as ‘three elements by two sets’, photo). Semiconductor process behind this IC ...

BrainChip has created <1mW neural processing core intellectual property for speech, audio and vital signs analysis. Called Akida Pico and described as event-based co-processor, it is intended for “voice wake detection, keyword spotting, speech noise reduction, audio enhancement, presence detection, personal voice assistant, automatic doorbell, wearable AI and appliance voice interfaces”, according to the company. As a co-processor, it would ...

Aaeon is aiming at in-vehicle surveillance systems for busses and law-enforcement with a PC built around Nvidia’s Jetson Orin NX artificial intelligence processor and equipped with eight power-over-Ethernet ports. Called Boxer-8658AI, there are two versions: one with a hex-core Cortex-A78AE v8.2 64bit CPU and 8Gbyte of LPDDR5 memory, and the other with 16Gbyte and an octa-core processor. “For in-vehicle or ...

Ceva has announced a neural network processing core aimed at SoCs needing to run TinyML models. There are two versions: NPN32 with 32 int8 MACs NPN64 with 64 int8 MACs “Both of which benefit from Ceva-NetSqueeze for direct processing of compressed model weights,” according to the company. “NPN32 is optimised for most TinyML workloads targeting voice, audio, object detection and ...

Alif Semiconductor has removed the Bluetooth transceiver from its Balletto B1 microcontroller to create an MCU with (or without) 46Gop/s of neural network processing that will be available in packages as small as a 3.9 x 3.9mm 90bump WLCSP. Dubbed E1C, the family all get a single 160MHz Arm Cortex-M55 CPU with Helium vector processing extensions, then some will also ...

Raspberry Pi 5 now has the option of an AI co-processor for neural networks, artificial intelligence and machine learning. The AI kit comprises the same M.2 HAT+ recently announced for holding NVMe memory drives, instead loaded with 13Top/s Hailo-8L AI processor. Connection, according to Raspberry Pi, is over its single-lane “PCIe 3.0 connection running at 8Gbit/s” – which is the ...