A Nature paper describes an innovative analog in-memory computing (IMC) architecture tailored for the attention mechanism in large language models (LLMs). They want to drastically reduce latency and ...

We all know AI has a power problem. On the whole, global AI usage already drew as much energy as the entire nation of Cyprus did in 2021. But engineering researchers at the University of Minnesota ...

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 ...

Tested against a dataset of handwritten images from the Modified National Standards and Technology database, the interface-type memristors realized a high image recognition accuracy of 94.72%. (Los ...

With the explosion of AI-rich embedded applications, how do you build the performance needed into embedded microcontrollers? One approach is to offload matrix-vector model operations to an in-memory ...

Until now, researchers have been limited in developing photonic memory for AI processing -- gaining one important attribute like speed while sacrificing another like energy usage. An international ...

Artificial intelligence has been bottlenecked less by raw compute than by how quickly models can move data in and out of memory. A new generation of memory-centric designs is starting to change that, ...

Compute Express Link (CXL) devices can take advantage of available PCIe interfaces to open an additional conduit that complements the overtaxed memory bus. More lanes, more data movement, more ...

Neo Semiconductor X-HBM architecture will deliver 32K-bit wide data bus and potentially 512 Gbit per die density. It offering 16X more bandwidth or 10X higher density than traditional HBM. NEO ...

A new technical paper titled “Memory-Centric Computing: Solving Computing’s Memory Problem” was published by researchers at ETH Zurich. “Computing has a huge memory problem. The memory system, ...