New graphene-based flash memory writes data in 400 picoseconds, shattering all speed records

New graphene-based flash memory writes data in 400 picoseconds, shattering all speed records

Breaking Speed Records: Introducing PoX

Recently, researchers at Fudan University in Shanghai unveiled a groundbreaking flash memory device known as “PoX.” This innovative device can program data in just 400 picoseconds, making it the fastest semiconductor charge storage device ever recorded. The implications of this achievement are profound, especially in the field of artificial intelligence.

One of the remarkable feats of PoX is its ability to perform 25 billion operations per second, surpassing previous world records by a significant margin. This speed is crucial as AI models continue to grow in complexity and scale, demanding faster and more efficient memory technologies.

Traditional volatile memories like static RAM and dynamic RAM offer impressive speeds but lose all stored information when power is cut. Non-volatile memories like flash storage, on the other hand, retain data without power and consume less energy. However, they have historically lagged in speed compared to their volatile counterparts.

The research team at Fudan University, led by Professor Zhou Peng, revolutionized flash memory technology by leveraging graphene’s unique properties and implementing a Dirac band structure. Through a mechanism called “super-injection,” they achieved an almost unrestricted flow of charge into the storage layer, eliminating the speed bottleneck that has plagued non-volatile memory for years.

According to Zhou Peng, the difference in performance is staggering, with PoX working a billion times faster than a typical USB flash drive. This unprecedented speed opens up a wide range of applications beyond consumer electronics, particularly in the realm of artificial intelligence.

With its unmatched speed and low power consumption, PoX has the potential to revolutionize real-time processing of massive datasets in AI applications while also mitigating energy inefficiencies associated with data movement.

Leave a Reply

Your email address will not be published. Required fields are marked *