SySCIM: SystemC-AMS Simulation of Memristive Computation In-Memory

• Published in: Proceedings - Design, Automation, and Test in Europe Conference and Exhibition pp. 1467 - 1472
• Main Authors: Shadmehri, Seyed Hossein Hashemi, BanaGozar, Ali, Kamal, Mehdi, Stuijk, Sander, Afzali-Kusha, Ali, Pedram, Massoud, Corporaal, Henk
• Format: Conference Proceeding
• Language: English
• Published: EDAA 14.03.2022
• Subjects: computation-in-memory; Computational modeling; Integrated circuit interconnections; memristor; Memristors; Nonvolatile memory; Performance evaluation; Phase change materials; Program processors; reliability; simulation
• ISSN: 1558-1101
• DOI: 10.23919/DATE54114.2022.9774749

Computation-in-memory (CIM) is one of the most appealing computing paradigms, especially for implementing artificial neural networks. Non-volatile memories like ReRAMs, PCMs, etc., have proven to be promising candidates for the realization of CIM processors. However, these devices and their driving circuits are subject to non-idealities. This paper presents a comprehensive platform, named SysCIM, for simulating memristor-based CIM systems. SySCIM considers the impact of the non-idealities of the CIM components, including memristor device, memristor crossbar (interconnects), analog-to-digital converter, and transimpedance amplifier, on the vector-matrix multiplication performed by the CIM unit. The CIM modules are described in SystemC and SystemC-AMS to reach a higher simulation speed while maintaining high simulation accuracy. Experiments under different crossbar sizes show SySCIM performs simulations up to 117 x faster than HSPICE with less than 4% accuracy loss. The modular design of SySCIM provides researchers with an easy design-space exploration tool to investigate the effects of various non-idealities.