High-Precision Close-to-Analog Programming of PCM Cells as Devices for AiMC Edge-AI
One of the most appealing characteristics of Phase-Change Memory (PCM) technology is the ability to store analog quantities as conductances. To fruitfully exploit this feature in Analog in-Memory Computing (AiMC) applications, highprecision programming algorithms are required. In this paper, a method to reach a fairly arbitrary number of analog levels in PCM cells is proposed. The algorithm has been validated on an AiMC prototype, designed and fabricated using a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$28-\text{nm}$</tex> FD-SOI process by STMicroelectronics to compute <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$512 \times 512$</tex> signed Matrix-Vector Multiplications (MVMs), achieving an Equivalent Number of Bits (ENOB) of 10.55, which improves state-of-theart weights programming accuracy for PCM-based hardware accelerators.
Authors
- Andrea Lico (ORCID: https://orcid.org/0000-0001-5267-2421)
- Laura Greco (ORCID: https://orcid.org/0000-0002-3914-8614)
- Alessio Antolini (ORCID: https://orcid.org/0000-0003-0952-3839)
- E. Calvetti
- Riccardo Vignali (ORCID: https://orcid.org/0000-0002-4026-8883)
- A. Cabrini (ORCID: https://orcid.org/0000-0003-1862-2409)
- Francesco Zavalloni (ORCID: https://orcid.org/0000-0003-0103-8126)
- R. Zurla (ORCID: https://orcid.org/0000-0002-4315-1269)
- Eleonora Franchi Scarselli (ORCID: https://orcid.org/0000-0001-6994-2088)
- M. Pasotti (ORCID: https://orcid.org/0000-0003-4988-9982)
- Luca Iannelli
- J.C. Bertolini
Institutions
- STMicroelectronics (Switzerland) (CH)
- University of Pavia (IT)
- STMicroelectronics (Italy) (IT)
- University of Bologna (IT)
Publication Details
- Published
- 2025-09-08
- DOI
- https://doi.org/10.1109/esserc66193.2025.11214085
- Primary Topic
- Advanced Memory and Neural Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00