Hardware & Semiconductors
56 articles RSS
Cisco Unveils 102.4 Tbps Silicon One G300 Chip to Challenge Nvidia and Broadcom in AI Data Center Networking
Cisco's 3nm G300 switching silicon promises 33% better network utilization and 70% energy savings with liquid cooling, targeting the $600 billion AI infrastructure buildout.
Samsung Ships First HBM4 Chips, Beating SK Hynix to Market in the Race to Feed AI's Memory Hunger
Samsung begins commercial HBM4 shipments with 3 TB/s bandwidth per stack, gaining a timing edge over SK Hynix as memory becomes the critical bottleneck in AI infrastructure.
D-Wave's $550M Quantum Circuits Acquisition Accelerates Error-Corrected Gate-Model Computing
D-Wave Quantum Inc. announces $550 million acquisition of Quantum Circuits Inc. to combine annealing and gate-model quantum technologies, with first dual-rail system planned for 2026 delivery.
Europe Opens Its Largest Chips Act Facility as Imec Inaugurates the 2.5 Billion Euro NanoIC Pilot Line
Belgium's imec launches NanoIC, a sub-2nm semiconductor pilot line backed by 2.5 billion euros in public and private funding, marking Europe's biggest bet yet on closing the gap with Asian and American chipmakers.
Positron AI Reaches Unicorn Status With $230M Series B, Betting That Inference — Not Training — Is Where Nvidia Can Be Beat
Reno-based Positron AI has raised $230 million at a $1B+ valuation, claiming its Atlas chip matches Nvidia's H100 inference performance at one-third the power while its next-gen Asimov silicon promises six times the memory of Nvidia's Rubin.
Intel Announces Data-Center GPU Push to Challenge Nvidia's AI Chip Dominance
Intel CEO Lip-Bu Tan reveals plans to build data-center GPUs and hires former Qualcomm architect Eric Demers to lead the effort.
Stanford's Optical Cavity Arrays Chart Path to Million-Qubit Quantum Computers
Stanford researchers demonstrate a scalable optical cavity system enabling parallel readout of quantum bits, with prototypes already exceeding 500 cavities.
NVIDIA Unveils Rubin: A Six-Chip Platform Promising 10x Cost Reduction for AI Inference
NVIDIA announces its most ambitious AI platform yet at CES 2026, integrating six new chips designed to dramatically reduce the cost of running AI models.