Abstract

As technology scaling is approaching a stand-still with architectural advancements on modern day processors struggling to improve performance, coupled with the rise in machine learning topologies demanding better performing processors, there is a pressing need to address the reasons behind today’s performance bottleneck. These reasons include long access latency of memory technologies, scalability of memory designs, energy inefficiency incurred by increased performance, and additional area overhead. To explore these issues, a holistic understanding of existing memory technologies is essential. In this chapter, a review of different memory designs starting from volatile memory technologies such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), NAND/NOR flash to emerging non-volatile memory technologies such as Resistive Random Access Memory (RRAM), Magneto-resistive random access memory (MRAM), Ferroelectric Field effect transistor (FeFET) is presented, with specific consideration of tradeoffs involving area, performance, energy.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call