NVIDIA's newest memory architecture for custom AI accelerators does something that no commercially available high-bandwidth memory standard has done before: it moves the memory controller off the ...

Edge applications such as machine vision and industrial automation often require more memory than an FPGA’s on-chip RAM ...

A new neural-network architecture developed by researchers at Google might solve one of the great challenges for large language models (LLMs): extending their memory at inference time without ...

Marvell, the fabless chip firm labeled the “next trillion-dollar company” by Nvidia CEO Jensen Huang, continued its AI infrastructure march with a solid-state drive (SSD) controller line aimed at ...

Use left and right arrow keys to seek audio. Chinese chip maker Innosilicon has announced it has provided its domestic customers with its new LPDDR6/5X memory controller IP. Innosilicon's new ...

A new technical paper titled “A Case for Self-Managing DRAM Chips: Improving Performance, Efficiency, Reliability, and Security via Autonomous in-DRAM Maintenance Operations” was published by ...

AMD has added references to GDDR7 memory support within its open-source Linux graphics driver code, a change that points toward the memory standard being used on the company's next-generation RDNA 5 ...

Delivering unrivaled memory bandwidth in a compact, high-capacity footprint, has made HBM the memory of choice for AI training. HBM3 is the third major generation of the HBM standard, with HBM3E ...

GUANGDONG HENGQIN, China, September 01, 2025--(BUSINESS WIRE)--Montage Technology today announced the launch of its CXL® 3.1 Memory eXpander Controller (MXC, Part No. M88MX6852), now in sampling phase ...