xMEMS Labs, Inc. announced the expansion of its µCooling fan-on-a-chip platform to solid-state drives (SSDs). The technology enables in-drive active cooling for enterprise E3.S form factor SSDs used in AI data centers and NVMe M.2 SSDs used in laptop PCs. SSD thermal management has traditionally relied on passive heat spreaders and ambient airflow from system […]
Artificial intelligence
PCIe cards add solid-state storage to high-performance computers
HighPoint Technologies is changing the game with its new Rocket 7604A and Rocket 1604A PCIe Gen5 NVMe AICs, which deliver true x16 storage performance in a half-length, compact form factor. These solutions are ideal for small form factor tower servers, rackmount chassis, and edge computing environments where space is limited, but performance must remain uncompromised. […]
RISC-V based neuromorphic processor operates at sub-milliwatt power
Innatera announced the launch of Pulsar, its first commercially available microcontroller to bring brain-like intelligence into edge devices. Born from more than a decade of pioneering research, Pulsar delivers up to 100X lower latency and 500X lower energy consumption than conventional AI processors. With this breakthrough, Innatera brings a new class of ultra-efficient, brain-inspired intelligence directly to […]
Dual GPU server and IP68 s-paper recognized at COMPUTEX
Advantech has received recognition at the 2025 COMPUTEX Best Choice Awards for two new products. The AIR-420 Edge AI Application Server and EPD-304 NFC E-Paper Solution were selected as winners in the Best Product Category, representing the company’s first dual recognition in this competition. The Best Choice Award serves as a reference point for international […]
What is the HPC memory wall and how can you climb over it?
The high-performance computing (HPC) memory wall generally refers to the growing disparity between processor speed and memory bandwidth. When processor performance outpaces memory access speeds, this creates a bottleneck in overall system performance, particularly in memory-intensive applications like artificial intelligence (AI). This article begins by exploring the conventional definition of the memory wall and then […]
Edge computing hardware integrates with existing development toolchain for AI applications
ACT Expo New Eagle introduced the Raptor High-Performance Compute Platform, a rugged, GPU-enabled embedded controller built on a vision processing unit (VPU) from John Deere. The new platform marks the first high-performance compute target in the Raptor hardware lineup, significantly expanding the capabilities of New Eagle’s embedded control ecosystem. New Eagle will demonstrate the Raptor […]
What determines the size of the dataset needed to train an AI?
Large data sets are needed to train artificial intelligence (AI) algorithms. Large data sets can be expensive. So, how much data is enough? The complexity of the problem, the model complexity, the quality of the data, and the required level of accuracy primarily determine that. Data augmentation techniques can be used to increase the size […]
SPI NOR Flash operates with 0.2 µA deep power-down current
GigaDevice has unveiled the GD25NE series of dual-power supply SPI NOR Flash, designed specifically for 1.2 V system-on-chip (SoC) applications. The GD25NE series strengthens GigaDevice’s strategic dual-power supply Flash roadmap, providing seamless compatibility with next-generation 1.2 V SoCs and eliminating the need for an external booster circuit. With its higher performance and lower power consumption, the […]
COM Express Compact Type 6 module supports 128 GB memory capacity
Tria Technologies introduced the Tria C6C-RYZ8 COM Express Compact Type 6 module, based on the AMD Ryzen Embedded 8000 Series processor, to its portfolio during Embedded World 2025. This new member of Tria’s COM Express board family is based on AMD’s Zen 4 CPU architecture and provides a substantial performance improvement over previous board generations […]
Edge computing modules deliver 15 TOPs processing for vision applications
IMDT has announced the release of two new computing products based on the Renesas RZ/V2N processor: the V2N System-on-Module (SOM) and the V2N Single-Board Computer (SBC). These platforms are designed to support AI-driven vision applications at the edge while maintaining cost-effectiveness and energy efficiency. The new modules follow IMDT’s previous V2H-based solutions and aim to […]
