Hot Chips 2026: Micron warns HBM wafer penalty is widening with every generation — AI memory uses 3x more silicon than DDR5, company says memory wall is ‘gettin

Micron’s presentation put compute performance scaling at roughly three times every two years and HBM bandwidth at under two times, a divergence Sreeramaneni summarized by saying “the memory wall is still present, and, in…

Decades-long Linux ownership dispute effectively dead after Xinuos appeal rejected — US Court of Appeals halts the legal wrangling over IBM’s and Red Hat’s use

Mark Tyson is a news editor at Tom’s Hardware. He enjoys covering the full breadth of PC tech; from business and semiconductor design to products approaching the edge of reason. “,”collapsible”:{“enabled”:true,”maxHeight…

Commodore unveils striking Cyberpunk 2077 version of its C64U made in partnership with CD Projekt Red — Commodore 77 special edition uses more powerful AMD Arti

Watch On Commodore says that the C77 is the first franchise hardware partnership in the firm’s 68-year history. “I have been a fan of the game since its release, and it was rewarding to learn in my discussions with their…

OpenAI’s 700W Jalapeño ASIC outpaces 1,400W Nvidia flagship GPU — claims up to 1.9x throughput per kilowatt and 3.6x lower latency, co-developed with Broadcom

OpenAI is procuring those inputs while deepening its financial dependence on the company it just benchmarked. On August 17, Nvidia agreed to provide up to $105 billion in financing for an OpenAI-leased data center campus…