Advances and Trends in Low-Power Logic-Compatible Phase Change Memory (PCM): A Comprehensive Survey

View at publisher Summarise with VIRAT
Authors: D Saranyanandhini, N. Shanmugasundaram, Mohan Kumar M, Nandhini M
Cited by: 0
References: 11

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Phase Change Memory (PCM) is a non-volatile technology which has received significant interest as a next-generation compute in-memory technology and artificial intelligence, as well as a high performance and energy efficient embedded system. This paper contains an in-depth experimental study of lowpower, logic compatible 40 nm PCM cells, principally regarding their reliability, reliability, and compatibility with neuromorphic and artificial intelligence devices. The wide characterization of the devices included endurance cycling, resistance drift experiments, high temperature data retention tests, and variability tests. At 120° C, retention studies indicate that with a heat of more than 120° C a memory life of more than ten years is observed and endurance tests indicates good performance up to 200,000 program/erase cycles with no memory window erosion. The measurements of drift in high resistance and low resistance stages reflect the resistance development that is well controlled and statistical measures confirm narrow distributions that are vital to stable operation and multi-level programming. The potential of PCM arrays is also validated by analysis in binary neural network models, wherein the robustness of the performance of the simulated inference distributions is obtained with simulated noise and unpredictability in the devices. On the whole, the results make low power PCM one of the leaders in embedded and artificial intelligence computing systems that offer scalable integration of the system, a high endurance level, precise programmability, and long term data retention.

Fields of Study & Subjects

Advanced Memory and Neural Computing Phase-change materials and chalcogenides Ferroelectric and Negative Capacitance Devices

Publication details

Journal / source
International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS)
Pages
1–7
Publication date
8 January 2026
Language
EN