A scalable, cost-effective phase change RAM technology
S. Lee, H. Park et al., Hynix Semiconductor Inc.
5/21/2012 3:28 PM EDT
Abstract
We successfully developed highly scalable and cost-effective PCRAM technology based on 0.007 µm2 (4F2, 84-nm pitch) sized novel cell scheme. The chip size and density are 33.207-mm2 and 1 Gb. The device functionality and reliability were clearly demonstrated through fully integrated chip, which showed a promising feasibility for productive NVM applications.
Introduction
So far, PCRAM (phase change RAM) research has been focused on mobile application such as NOR and/or LPDDR2 NVM [1-3]. PCRAM can also merge the attractive points of NAND and DRAM in one chip, which makes a prospective potential for the new application concept like storage-class memory (SCM) to reduce the performance gap between DRAM and SSD. Furthermore, PCRAM can be alternatively compatible for working memory and storage type application. Therefore, it can be started in the middle point of system architecture which moves to memory-like and/or storage-like. In recent, industry is also considering feasibility for various new applications. However, PCRAM production cost is still questionable. In this paper, we report a technological platform and attractive breakthrough which should be significantly addressed to implement cost-competitive and highly scalable PCRAM.
To read the full article, click here
Related Semiconductor IP
- NVM OTP XBC TSMC N7 1.8V
- NVM OTP XBC TSMC N6 1.8V
- NVM OTP XBC TSMC N5A 1.2V Automotive Grade 1 with Functional Safety
- NVM OTP XBC TSMC N5 1.2V
- NVM OTP XBC TSMC N4P 1.2V
Related Articles
- The Growing Importance of AI Inference and the Implications for Memory Technology
- Hybrid Change Makes WLAN QoS Come to Life
- Reverse Disaggregation - How Silicon IP Will Change the Semiconductor Supply Chain
- Fully Digital Implemented Phase Locked Loop
Latest Articles
- Crypto-RV: High-Efficiency FPGA-Based RISC-V Cryptographic Co-Processor for IoT Security
- In-Pipeline Integration of Digital In-Memory-Computing into RISC-V Vector Architecture to Accelerate Deep Learning
- QMC: Efficient SLM Edge Inference via Outlier-Aware Quantization and Emergent Memories Co-Design
- ChipBench: A Next-Step Benchmark for Evaluating LLM Performance in AI-Aided Chip Design
- COVERT: Trojan Detection in COTS Hardware via Statistical Activation of Microarchitectural Events