Intel launched the Core Series 2 processors with P-cores at Embedded World 2026, targeting industrial edge applications that require deterministic real-time performance alongside AI workloads. The lineup spans 11 SKUs with up to 12 P-cores, 5.9 GHz turbo, 192GB DDR5-5600 with ECC, up to 16 PCIe Gen 5 lanes, and a 10-year longevity program, claiming […]
Artificial intelligence/ML
120 MHz flash supports AI inference from data center to edge
GigaDevice has expanded its GD25UF series SPI NOR Flash to cover densities from 8Mb to 256Mb, operating at 1.14V–1.26V with a maximum clock frequency of 120MHz (STR mode) and data throughput up to 80MB/s. The series supports Single, Dual, Quad, and DTR Quad SPI modes, offers 100,000 program/erase cycles and 20-year data retention, and is […]
Hardware accelerator cuts inference energy by 120x in new MCUs
Texas Instruments has introduced two new MCU families at Embedded World 2026. The MSPM0G5187 and the AM13Ex both integrate TI’s TinyEngine NPU, a dedicated hardware accelerator that runs deep learning inference with up to 90x lower latency and more than 120x lower energy per inference compared to MCUs without an accelerator. The MSPM0G5187 is an […]
600 MHz Cortex-M7, RISC-V, and Cortex-M33 MCUs target robotics, automotive, and edge AI
GigaDevice is demonstrating four application areas at Embedded World 2026 (Hall 5, Stand 5-129) built around its GD32 MCU families, Flash memory, and analog products. For humanoid robotics and industrial automation, the company is showing EtherCAT servo drive devices using the GD32H75E, a 600 MHz Arm Cortex-M7 MCU with 3,840 KB flash, 1,024 KB SRAM, […]
1.8 eTOPs NPU targets physical AI agent deployments at the edge
NXP Semiconductors has introduced the i.MX 93W, an applications processor. Purpose-built to accelerate physical AI deployment, the device integrates a dual-core Arm Cortex-A55 with a dedicated Arm Ethos NPU (up to 1.8 eTOPs) and an IW610 tri-radio module supporting Wi-Fi 6, Bluetooth LE, and 802.15.4 (Matter/Thread) in a single package, replacing up to 60 discrete […]
HBM4E controller supports 16 Gbps signaling per pin
Rambus Inc. has released its HBM4E Controller IP designed for next-generation AI accelerators and high-performance computing. The controller supports data rates up to 16 Gbps per pin, providing 4.1 TB/s of throughput per memory device. In an eight-device configuration, this architecture delivers over 32 TB/s of total memory bandwidth. The IP features low-latency operation and […]
Radar, microphones, and MCUs address connected device security needs
Infineon takes the floor at Embedded World 2026 in Nuremberg, March 10 – 12 (Hall 4A, Booth 138) with live demonstrations spanning microcontrollers, sensors, automotive, and robotics. On the MCU side, engineers will see PSOC and AURIX devices running edge AI and robotics workloads with deterministic real-time control, alongside the TRAVEO SDV Zonal Demo, which […]
How to approach AI hardware design to address the memory wall?
The transition from general-purpose computing to AI-specific hardware is driven by the specific computational and energy requirements of deep learning models. As these models scale to trillions of parameters, traditional architectures face the memory wall, where the energy required for data movement between memory and processing units significantly exceeds the energy consumed by the computation […]
AI-enabled workflows support automated V&V in toolchains
TASKING will be demonstrating its enhanced toolchain at Embedded World in Nuremberg. The end-to-end “compile, debug, test” toolschain integrates AI-driven workflows into embedded software development and verification, supporting functionally safe and secure real-time applications in automotive, aerospace and defense, industrial and robotics systems. Built on the Model Context Protocol, the toolchain enables large language models to […]
Neuromorphic processor reduces power in radar sensing systems
The jointly developed human-presence detection solution from Socionext and Innatera combines 60 GHz FMCW radar sensing with a neuromorphic Spiking Neural Processor to enable always-on detection at sub-milliwatt power levels. The system processes radar data directly at the edge to distinguish human from non-human motion, including stationary individuals, with reported accuracy above 99%, allowing connected […]
