Qualcomm gives Mojo away to loosen Nvidia’s grip
Qualcomm has open-sourced Mojo as part of a cunning plan to loosen Nvidia’s grip on…
ai accelerators
SK Hynix tries to stop HBM cooking itself
SK Hynix is trying to keep HBM from cooking itself as demand for AI chips…
AMD’s AI wobble puts Su under pressure
AMD chief executive Lisa Su is facing fresh doubts as delayed AI chips and Nvidia’s…
Microsoft bets on both sides of the AI rack war
Software King of the World, Microsoft will deploy rack-scale AI systems from both AMD and…
SanDisk wants to stack NAND where AI can reach it
SanDisk is looking at a more aggressive way to deal with AI’s memory bottleneck by…
Google cooks up a TPU split for inference and training
Google is trying to cut Nvidia out of the AI chip gravy train. The Alphabet…
AMD gets more HBM4 from Samsung
AMD chief executive Lisa Su headed to South Korea to lock down supply, and Samsung…
Jensen Huang signs off on Samsung’s HBM4
Samsung showed up at Nvidia’s GTC 2026 developer conference booth with an HBM4 chip, which…
Lisa Su heads down memory lane
AMD chief executive Lisa Su is flying to South Korea to meet with executives and…
Rambus turns HBM4E up to 16Gbps per pin
Rambus wants your AI superchip to stop choking on memory bandwidth. The outfit has rolled…