This review asks whether graphene-based nanosensors could enhance energy efficiency in AI by integrating memory and computation for advanced information processing.

The hunt is on for anything that can surmount AI’s perennial memory wall–even quick models are bogged down by the time and energy needed to carry data between processor and memory. Resistive RAM (RRAM ...

Just like each person has unique fingerprints, every CMOS chip has a distinctive "fingerprint" caused by tiny, random ...

IC design house PixArt held its earnings call on February 6, reporting that its fourth-quarter 2025 performance largely met expectations, with modest revenue growth. Gross margin, however, declined ...

Data center AI is driving a dramatic ramp in the growth of silicon photonics foundries: 8X growth in just 6 years, from 2026 to 2032. Scale-out is the major driver now. Scale-up will become the ...

SAN FRANCISCO — Researchers from CEA-List and CEA-Leti today unveiled at ISSCC the first electro-optical router with dynamic, frame-level optical routing integrated with CMOS control logic, marking a ...

A team at the University of California, San Diego has redesigned how RRAM operates in an effort to accelerate the execution ...

Just like each person has unique fingerprints, every CMOS chip has a distinctive "fingerprint" caused by tiny, random manufacturing variations ...

A total of $45 million was received in Hawk orders from this IDM customer for AI applications to be delivered in 2026MIGDAL HAEMEK, Israel, Feb. 10, 2026 ...

JEDEC’s HBM4 and the emerging SPHBM4 standard boost bandwidth and expand packaging options, helping AI and HPC systems push past the memory and I/O walls.

The AI boost offered by the CPU and GPU combo gives creative applications a power boost further enhanced by the OCuLink eGPU option ...

GF’s industry-leading FDX platform is ideally suited for applications in Physical AI that are optimized for long battery life in small form factors, thanks to its ultra-low power and low leakage ...