Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2605.21912 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913151287558144 |
|---|---|
| author | Raman, Siddhartha Raman Sundara |
| author_facet | Raman, Siddhartha Raman Sundara |
| contents | As conventional technology scaling approaches physical and power limitations, modern computing systems increasingly face performance bottlenecks arising from memory latency, energy consumption, scalability constraints, and data movement overheads. Simultaneously, emerging workloads such as machine learning, graph analytics, and scientific computing demand memory technologies with higher bandwidth, lower latency, improved energy efficiency, and greater storage density. These challenges have motivated extensive research into both room-temperature memories and cryogenic memory systems targeted toward superconducting and quantum computing platforms.
This chapter presents an overview of volatile and non-volatile memory technologies operating across room-temperature and cryogenic environments. The discussion includes SRAM, DRAM, embedded DRAM (eDRAM), NAND/NOR Flash, Resistive Random Access Memory (RRAM), Magneto-resistive Random Access Memory (MRAM), and Ferroelectric Field-Effect Transistor (FeFET)-based memories. In addition, cryogenic technologies including UTBB-SOI-based pseudo-static storage circuits and Josephson Junction Field-Effect Transistor (JJFET)-based devices are discussed in the context of ultra-low-temperature computing systems. The chapter highlights the operational principles, read/write mechanisms, retention behavior, and tradeoffs among area, performance, scalability, and energy efficiency across these memory technologies, while examining challenges and opportunities for future room-temperature and cryogenic computing architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_21912 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Emerging memory technologies at room/cryogenic temperature Raman, Siddhartha Raman Sundara Hardware Architecture As conventional technology scaling approaches physical and power limitations, modern computing systems increasingly face performance bottlenecks arising from memory latency, energy consumption, scalability constraints, and data movement overheads. Simultaneously, emerging workloads such as machine learning, graph analytics, and scientific computing demand memory technologies with higher bandwidth, lower latency, improved energy efficiency, and greater storage density. These challenges have motivated extensive research into both room-temperature memories and cryogenic memory systems targeted toward superconducting and quantum computing platforms. This chapter presents an overview of volatile and non-volatile memory technologies operating across room-temperature and cryogenic environments. The discussion includes SRAM, DRAM, embedded DRAM (eDRAM), NAND/NOR Flash, Resistive Random Access Memory (RRAM), Magneto-resistive Random Access Memory (MRAM), and Ferroelectric Field-Effect Transistor (FeFET)-based memories. In addition, cryogenic technologies including UTBB-SOI-based pseudo-static storage circuits and Josephson Junction Field-Effect Transistor (JJFET)-based devices are discussed in the context of ultra-low-temperature computing systems. The chapter highlights the operational principles, read/write mechanisms, retention behavior, and tradeoffs among area, performance, scalability, and energy efficiency across these memory technologies, while examining challenges and opportunities for future room-temperature and cryogenic computing architectures. |
| title | Emerging memory technologies at room/cryogenic temperature |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2605.21912 |