Atom-thin, content-addressable memory enables edge AI applications

Recent advances in the field of artificial intelligence (AI) have opened new exciting possibilities for the rapid analysis of ...
Morningstar

Numem Addresses AI’s Dirty Secret: Memory Is the Real Bottleneck

SUNNYVALE, Calif., June 10, 2025 (GLOBE NEWSWIRE) -- AI has a memory problem. Traditional SRAM and DRAM were never designed to meet the scale and intensity of today’s AI workloads – and their ...
Morningstar

Credo Unveils Industry’s First Memory Fanout Gearbox for Scalable, High-Bandwidth AI Inference

Weaver—the First Product in Credo’s OmniConnect Family—Overcomes Memory Bottlenecks in AI Inference Workloads to Boost Memory Density and Throughput Credo Technology Group Holding Ltd (Credo) (NASDAQ: ...
Semiconductor Engineering

Accelerator Architecture For In-Memory Computation of CNN Inferences Using Racetrack Memory

A new technical paper titled “Hardware-software co-exploration with racetrack memory based in-memory computing for CNN inference in embedded systems” was published by researchers at National ...
EDN

RRAM: Non-volatile memory for high-performance embedded applications

Non-volatile memory is an important component in a wide range of high-performance embedded applications. Especially, many consumer, industrial, and medical applications need increased re-writability ...