Nonlinear selectorless memory technologies for high-density storage and beyond-von-Neumann computing: a review
Abstract
With the rapid advancement of artificial intelligence (AI), there is an urgent demand for emerging technologies that can deliver low-power storage alongside high-performance computing. Traditional volatile memories-such as static random access memory and dynamic random access memory-which are closely integrated with the central processing unit, are approaching their physical scaling limits. This not only constrains performance but also increases manufacturing complexity. To address these limitations, emerging non-volatile memory (NVM) technologies have gained attention for their potential to support in-memory and near-memory computing, where memory functions as both a storage and computational unit. However, as memory array sizes increase, 'sneak-path' currents flowing through unintended parallel pathways become more prominent, leading to operational issues such as disturbance and read/write errors. To mitigate these effects, active devices such as transistors are integrated into memory architectures, forming 1-transistor-1-resistor (1T-1R) configurations. Despite these innovations, scalability remains a significant challenge, hindering the widespread adoption of advanced memory technologies. Selectorless memory, is proposed as the solution with its intrinsic nonlinear behaviors which rectified the leakage currents in the array without integrating with external access devices. In this review, we will discuss the current state-of-the-art of emerging memory technologies, which…
Read the paper
Related studies
- Diarylethenes for Memories and Switches
- Long-Term Potentiation and Memory
- Social Memory Studies: From “Collective Memory” to the Historical Sociology of Mnemonic Practices
- The Cognitive Neuroscience of Working Memory
- Memory aging and brain maintenance
- Effector and Memory CTL Differentiation
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.