Interesting Engineering on MSN

500 billion ops per second: China achieves 4-fold computing speed with new AI architecture

Tao said the integrated system combines the strengths of two devices in frequency generation, modulation, and in-memory ...
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 ...
Xinhuanet

Chinese researchers create novel computing architecture for major power boost

BEIJING, Jan. 12 (Xinhua) -- Chinese researchers have developed an innovative computational architecture that enhances computing power nearly fourfold, thereby opening new possibilities in fields like ...
insideHPC

GridGain Systems Introduces Next-Generation In-Memory Computing Platform

GridGain Systems, provider of enterprise-grade in-memory computing platform solutions based on Apache® Ignite™, today announced GridGain 8.1. The solution expands the bounds of in-memory computing ...
Business Wire

d-Matrix Unveils Corsair, the World’s Most Efficient AI Computing Platform for Inference ...

ATLANTA--(BUSINESS WIRE)--d-Matrix today officially launched Corsair™, an entirely new computing paradigm designed from the ground-up for the next era of AI inference in modern datacenters. Corsair ...
SDxCentral

EnCharge AI closes oversubscribed $100m Series B funding round for development of analog in ...

AI chip startup EnCharge AI has closed a $100 million Series B funding round. The oversubscribed round was led by Tiger Global and saw participation from Samsung Ventures and HH-CTBC. It brings the ...