Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Fully Automated Platform for Evaluating ReRAM Crossbars

Rebecca Pelke, Felix Staudigl, Niklas Thomas, Nils Bosbach, Mohammed Hossein, Jose Cubero-Cascante, Leticia Bolzani Poehls, Rainer Leupers, Jan Moritz Joseph

TL;DR

The paper tackles the challenge of variability in ReRAM crossbars used for CIM and neuromorphic applications by introducing a fully automated platform that extends the NeuroBreakoutBoard with a dedicated controller board and host-PC interface. It details three hardware modules—Configurable Signal Interconnection, Voltage Pulse Generator, and Current Sensing—and a microcontroller-driven workflow, plus a Python API for automated experiment control. A case study on TiN/Ti/HfO2/TiN cells demonstrates how read voltage influences Cycle-to-Cycle variation and read disturb, with findings that reading in the reset direction improves stability and reduces disturbance. The work delivers a practical, time-saving, and consistent measurement infrastructure and outlines future enhancements to enable matrix-vector multiplication measurements and multi-bit testing.

Abstract

Resistive Random Access Memory (ReRAM) is a promising candidate for implementing Computing-in-Memory (CIM) architectures and neuromorphic circuits. ReRAM cells exhibit significant variability across different memristive devices and cycles, necessitating further improvements in the areas of devices, algorithms, and applications. To achieve this, understanding the stochastic behavior of the different ReRAM technologies is essential. The NeuroBreakoutBoard (NBB) is a versatile instrumentation platform to characterize Non-Volatile Memories (NVMs). However, the NBB itself does not provide any functionality in the form of software or a controller. In this paper, we present a control board for the NBB able to perform reliability assessments of 1T1R ReRAM crossbars. In more detail, an interface that allows a host PC to communicate with the NBB via the new control board is implemented. In a case study, we analyze the Cycle-to-Cycle (C2C) variation and read disturb TiN/Ti/HfO2/TiN cells for different read voltages to gain an understanding of their operational behavior.

A Fully Automated Platform for Evaluating ReRAM Crossbars

TL;DR

The paper tackles the challenge of variability in ReRAM crossbars used for CIM and neuromorphic applications by introducing a fully automated platform that extends the NeuroBreakoutBoard with a dedicated controller board and host-PC interface. It details three hardware modules—Configurable Signal Interconnection, Voltage Pulse Generator, and Current Sensing—and a microcontroller-driven workflow, plus a Python API for automated experiment control. A case study on TiN/Ti/HfO2/TiN cells demonstrates how read voltage influences Cycle-to-Cycle variation and read disturb, with findings that reading in the reset direction improves stability and reduces disturbance. The work delivers a practical, time-saving, and consistent measurement infrastructure and outlines future enhancements to enable matrix-vector multiplication measurements and multi-bit testing.

Abstract

Resistive Random Access Memory (ReRAM) is a promising candidate for implementing Computing-in-Memory (CIM) architectures and neuromorphic circuits. ReRAM cells exhibit significant variability across different memristive devices and cycles, necessitating further improvements in the areas of devices, algorithms, and applications. To achieve this, understanding the stochastic behavior of the different ReRAM technologies is essential. The NeuroBreakoutBoard (NBB) is a versatile instrumentation platform to characterize Non-Volatile Memories (NVMs). However, the NBB itself does not provide any functionality in the form of software or a controller. In this paper, we present a control board for the NBB able to perform reliability assessments of 1T1R ReRAM crossbars. In more detail, an interface that allows a host PC to communicate with the NBB via the new control board is implemented. In a case study, we analyze the Cycle-to-Cycle (C2C) variation and read disturb TiN/Ti/HfO2/TiN cells for different read voltages to gain an understanding of their operational behavior.
Paper Structure (10 sections, 7 figures, 1 table)

This paper contains 10 sections, 7 figures, 1 table.

Table of Contents

  1. Introduction
  2. Structure
  3. Configurable Signal Interconnection Module
  4. Voltage Pulse Generator Module
  5. Current Sensing Module
  6. The Proposed Controler Board and Interface
  7. Validation of the Proposed Controller Board and Interface
  8. Cycle-To-Cycle Variation
  9. Read Disturb
  10. Conclusion

Figures (7)

  • Figure 1: ispva perez2019toward voltage sequence
  • Figure 2: 1T1R crossbar (pseudo crossbar)
  • Figure 3: Integration of nbb into automated measuring system
  • Figure 4: Setup and main loop of the control board
  • Figure 5: Extract of API functions
  • ...and 2 more figures