Analog Superposition Increases Effective PCM Storage Density (IBM Research Europe)
Analog Superposition Increases Effective PCM Storage Density (IBM Research Europe)
Researchers at IBM Research Europe have published an analog phase-change memory (PCM) architecture that stores multiple AI vectors in the same storage medium through superposition, increasing effective storage density while allowing a tunable trade-off between precision and density. Tests on prototype PCM hardware showed inference accuracy close to full-precision software. The study was released as an arXiv preprint under a CC BY-NC-SA 4.0 license.
Researchers at IBM Research Europe published “Superposed analog memory for vector storage in neural networks.”
Summary:
Researchers demonstrated an analog phase-change memory architecture that stores multiple AI vectors in superposition, increasing effective storage density with a tunable accuracy tradeoff. Tests on prototype PCM hardware showed inference accuracy close to full-precision software.
Find the technical paper here. October 2026
Vasilopoulos, Athanasios, Patrick Diener, Michael Hersche, Abbas Rahimi, and Abu Sebastian. “Superposed analog memory for vector storage in neural networks.” arXiv preprint arXiv:2610.26118 (2026). CC BY-NC-SA 4.0 License
Source: Semiconductor Engineering Chips and Packaging · semiengineering.com