Semiconductor Engineering

Mixed SRAM And eDRAM Cell For Area And Energy-Efficient On-Chip AI Memory (Yale Univ.)

“AI chips commonly employ SRAM memory as buffers for their reliability and speed, which contribute to high performance. However, SRAM is expensive and demands significant area and energy consumption.
Semiconductor Engineering

Computational SRAM (C-SRAM) Solution Combining In- and Near-Memory Computing Approaches

New academic paper titled “Towards a Truly Integrated Vector Processing Unit for Memory-bound Applications Based on a Cost-competitive Computational SRAM Design Solution”, from researchers at Univ.
Hosted on MSN

Faster than SRAM! New flash memory tech from China is millions of times faster than NAND rivals from US, Japan or Korea - but please change its name

Chinese researchers have developed super-fast non volatile flash memory Graphene channel enables 400 picosecond write speed and persistent storage "PoX" device targets AI bottlenecks with low power, ...
EDN

Why has Nordic Semi acquired an embedded memory supplier?

Memory has become an increasingly vital ingredient of the ultra-low-power Internet of Things (IoT) chip designs, and that’s apparent from Nordic Semiconductor’s acquisition of low-voltage embedded ...
WREG

Alliance Memory to Highlight Latest SRAM, DRAM, eMMC, and Flash Memory ICs at electronica 2022

KIRKLAND, Wash., Nov. 07, 2022 (GLOBE NEWSWIRE) -- Alliance Memory today announced its technology lineup for electronica 2022, taking place Nov. 15-18 at the Trade Fair Center in Munich, Germany.