| Mobile Web

Search results for SRAM

Industry

GPU standalone era may end as integrated design determines AI chip performance

The focus of competition in AI chips is shifting from standalone GPUs to integrated CPU-GPU designs that package processors and memory to optimise data flow. U.S.-listed CPU makers Intel and AMD have surged, reflecting rising demand for CPUs and DPUs as inference and agentic AI workloads expand. Nvidia is also pushing CPU offerings and tighter CPU-GPU integration, while memory is becoming a core component. The trend could benefit South Korean memory makers SK Hynix and Samsung Electronics.

Industry

SemiFive pushes to commercialise eMRAM-based edge AI chip

SemiFive and ICY Tech said on May 7 they succeeded in taping out an edge AI semiconductor based on Samsung Foundry\'s 8-nanometre eMRAM technology. They said it is the first case in Asia in which 8-nanometre eMRAM technology is introduced into a commercial product. The project combined ICY Tech\'s processing-near-memory technology with SemiFive\'s SoC design platform to enable AI computing in edge environments without a separate network connection.

AI & Enterprise

Anthropic in talks to buy inference chips from UK AI chip startup Fractile

Anthropic is considering adding UK AI chip startup Fractile as a new supplier of AI server chips, alongside Google, Amazon and Nvidia, The Information reported. Citing two people who spoke with Fractile executives, the report said Anthropic recently held talks to buy inference chips that could ship as soon as next year. The report said Anthropic aims to diversify suppliers and improve its negotiating leverage as annual server and chip spending is expected to reach tens of billions of dollars.