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 ...
Tag Archives: neural network
AI processor intellectual property aimed at TinyML
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 ...
46Gop/s of neural network processing in a 3.9 x 3.9mm package
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 turns to Halio for 13Top/s AI acceleration
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 ...
Arm’s most powerful neural processor for microcontrollers
Arm has announced its most powerful microcontroller-grade neural processor, which will reach 4Top/s in its maximum configuration and is 20% more power efficient that its previous neural processors. Named Ethos-U85 and configurable with between 128 and 2,048 MACs, it is intended to have enough performance to locally run heavy AI algorithms such as ‘transformers’, as well as convolutional neural networks. ...
Fraunhofer IESE partners for AI chip network-on-chip architecture
Faster on-die memory access for AI processing could spring from a collaboration between network-on-chip intellectual property company Arteris and the Fraunhofer Institute for Experimental Software Engineering (Fraunhofer IESE). Memory access is important with neural network algorithms as their execution requires large quantities of data to be transferred between processing elements and memory, increasing emphasis on the performance of the access ...
IBM’s analogue AI chip achieves 400Gop/s/mm2
IBM has revealed an analogue in-memory IC for implementing neural networks. The device stores weights locally as analogue levels as conductance in phase-change memory, and implements analogue multiply-accumulate calculation. For analogue AI processing “two key challenges need to be overcome: These memory arrays need to compute with precision on par with existing digital systems, and they need to be able ...
Ceva adds cores and generative AI to neural processing IP portfolio
Ceva has filled-out its NeuPro-M family of neural processing units, and boosted its architecture for generative AI algorithms. “NeuPro-M NPU architecture and tools have been redesigned to support transformer networks in addition to convolutional neural networks,” according to the company. “This enables applications leveraging the capabilities of generative and classic AI to be developed and run on the NeuPro-M NPU.” ...
Halio adds 208Top/s PCIe processor board, and entry-level AI IC
AI chip maker Hailo has introduced a 208Top/s PCIe processor card for implementing neural networks, and an entry-level version of its Halio-8 IC. The PCIe cards, called ‘Hailo-8 Century’, execute at 400frame/s/W on the ResNet50 benchmark model, said the company, and the highest-performance version can run the same benchmark at 10,000frame/s. Versions start at 52Top/s, and video processing applications are ...
Ionic transistor for meuromorphic computing
Researchers at the Tokyo University of Science have developed an ionic transistor for neuromorphic computing. The ions in question are lithium, its ‘gate oxide’ is a solid lithium-ion-conducting glass-ceramic electrolyte, and its channel is lithium tungsten oxide that changes conductivity as ions are inserted. Physically, it is built around the electrolyte in the form of a 150μm thick ion-conducting glass-ceramic ...