The Next Platform

Chewing A Billion By Billion Matrix Crammed Into Gigabytes Of Memory

Sometimes, to appreciate a new technology or technique, we have to get into the weeds a bit. As such, this article is somewhat more technical than usual. But the key message that new libraries called ...
Hosted on MSN

New 3D-stacked memory tech seeks to dethrone HBM in AI inference — d-Matrix claims 3DIMC will be 10x faster and 10x more efficient

Memory startup d-Matrix is claiming its 3D stacked memory will be up to 10x faster and run at up to 10x greater speeds than HBM. d-Matrix's 3D digital in-memory compute (3DIMC) technology is the ...
SiliconANGLE

D-Matrix reveals plan to break through AI’s ‘memory wall’ with 3D DRAM-based chip architecture

Artificial intelligence computing startup D-Matrix Corp. said today it has developed a new implementation of 3D dynamic random-access memory technology that promises to accelerate inference workloads ...
Semiconductor Engineering

SparseP: Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory Systems

“Several manufacturers have already started to commercialize near-bank Processing-In-Memory (PIM) architectures. Near-bank PIM architectures place simple cores close to DRAM banks and can yield ...
Hackaday

Interactive Core Memory Shield Helps Explains The Past

[Andy Geppert] sends in his incredibly clever interactive core memory shield. In a great display of one hacker’s work being the base for another’s, [Andy] started out with [Jussi Kilpelainen]’s core ...
Business Wire

d-Matrix Unlocks New Potential with Reinforcement Learning Based Compiler for At Scale Digital In-Memory Compute Platforms

SANTA CLARA, Calif.--(BUSINESS WIRE)--Today, d-Matrix, a leader in high-efficiency AI-compute and inference, announced a collaboration with Microsoft using its low-code reinforcement learning (RL) ...