For years, buying a laptop or desktop was simple. You checked the processor, looked at the amount of RAM, maybe considered ...

Named Jalapeño, the new processor was designed specifically for the unique needs of OpenAI's inference systems.

Part 1 of this min-series established why CXL Type 3 memory expanders matter for capacity-bound workloads and where expander ...

The short and medium-term outlook for NVIDIA in China depends heavily on U.S. export policy. In the long run, it will depend on its ability to compete with local alternatives.

Cutting corners: Faced with rising memory costs, Meta says it is reusing old DDR4 RAM in its servers rather than buying new hardware. The company revealed this week that it is repurposing DDR4 memory ...

Solving a tricky 3D integration problem could boost bandwidth and keep chips cooler ...

A Linux vulnerability that allows untrusted virtual machines to gain root access to host machines is one of two high-severity ...

Nvidia launched a revenue-sharing model with AI cloud partners Sharon AI and Firmus, combining GPU sales with recurring cloud ...

Qualcomm unveils Dragonfly data center AI portfolio and HBC tech, naming Meta and Microsoft as early customers.

Qualcomm is making a major push into the datacenter market. And though it is late to the game, the mobile-chip giant believes it can make an impact by delivering a lower total cost of ownership and ...

The company is replacing hard-to-find high bandwidth memory (HBM) with LPDDR5X in its latest Versal processor.

China's Zhipu AI is in early discussions with domestic chip design houses about building a bespoke AI processor for its GLM model family, The Information reported, as 27-times growth in daily token ...