Resistive RAM for next-generation nonvolatile memory
Bogdan Govoreanu, imec Leuven
EETimes (3/12/2012 1:25 PM EDT)
Since its introduction in 1988 by Toshiba1, NAND flash nonvolatile memory has undergone an unprecedented growth, becoming one of today’s technology drivers. Although NAND flash memory has scaled to 1x-nm feature sizes, shrinking cell sizes reduce the number of electrons stored on the floating gate. Resistive RAM (RRAM) provides an alternative. In this article, we review the main performance figures of hafnium-oxide (HfO2)-based RRAM cells4 from a scalability perspective, outlining their strengths as well as the main challenges ahead.
A NAND flash nonvolatile memory cell, usually a floating gate transistor, implements the memory function by charge stored on the floating gate. With a charge transfer mechanism onto/from the storage medium that relies on tunneling and a serial (string) architecture, NAND memory features high operating voltages (with associated chip area consumption for the on-chip voltage generation), rather long cell program/erase (P/E) times, and slow read-access times. These drawbacks are, however, compensated for by the very compact array architecture and extremely low energy-consumption-per-bit operation, which eventually enabled fabrication of high-density memory arrays, at low cost and with a chip storage capacity increasing impressively.
To read the full article, click here
Related Semiconductor IP
- ONFI Nand Flash Software Driver
- SPI NAND Flash Memory Model
- NAND Flash Memory Model
- NAND Flash Synthesizable Transactor
- Nand Flash Controller
Related Articles
- FengHuang: Next-Generation Memory Orchestration for AI Inferencing
- Selecting the right Nonvolatile Memory IP: Applications and Alternatives
- Argument for anti-fuse non-volatile memory in 28nm high-K metal gate
- Using non-volatile memory IP in system on chip designs
Latest Articles
- A Low-Latency ASIC Architecture for Real-Time Line Segment Detection
- BitFair: A 12nm Bit-Serial CNN Accelerator with Learnable Early Termination and Adaptive Bit Ordering for Ultra-Low-Power XR Vision
- A Flexible Sparsity-Aware FPGA Accelerator with Column-Wise Compression for Efficient CNN Inference
- Reducing Instruction-Fetch Energy in RISC-V for Embedded AI Processing via Dynamic and Static Loop Caching
- SPARC: Automated Root-Cause Analysis of Pre-Silicon Power Side-Channel Leakage in the Processor Design Flow