Memory technology enabling future computing systems

Although the astounding progress through Moore’s law has made possible the demonstrations of truly remarkable tasks of artificial intelligence (AI), the AI revolution is challenging the semiconductor technology itself. In fact, the achieved results are at the expense of an energy consumption orders...

Full description

Saved in:
Bibliographic Details
Main Author: Paolo Fantini
Format: Article
Language:English
Published: AIP Publishing LLC 2025-06-01
Series:APL Machine Learning
Online Access:http://dx.doi.org/10.1063/5.0253063
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Although the astounding progress through Moore’s law has made possible the demonstrations of truly remarkable tasks of artificial intelligence (AI), the AI revolution is challenging the semiconductor technology itself. In fact, the achieved results are at the expense of an energy consumption orders of magnitude higher than the one of the human brain. Definitively, biology figures out a better way to process data. So, radically new approaches, in some way emulating the human mind, are essential for creating a more efficient next generation information technology. This work draws the directions that address the building of more efficient future computing systems, namely, (a) the memory and storage technology roadmap; (b) innovative interconnect systems between memory and logic devices; and (c) overcoming of the von Neumann computing paradigm.
ISSN:2770-9019