Enhancing Data Storage Reliability and Error Correction in Multilevel Flash Memories
Researchers at the University of Bremen have proposed an innovative solution to tackle the challenge of programming and data erasure issues in the latest flash memory generation. The proposed solution involves implementing a parallel architecture for the Bose-Chaudhuri-Hocquenghem (BCH) decoder's sub-blocks and a three-stage pipeline to increase throughput. Additionally, an algorithm based on XOR sharing is introduced to reduce the hardware requirements of the BCH decoder block.
Key Takeaways:
- The size reduction of transistors in the latest flash memory generation has resulted in programming and data erasure issues, posing a significant challenge for reliable data storage.
- BCH codes are employed in the controllers of these memories to ensure reliable data storage, but decoding these codes requires careful consideration of factors such as delay in error correction and hardware requirements.
- The proposed solution, which includes a parallel architecture for the BCH decoder's sub-blocks and a three-stage pipeline, can reduce area complexity by 50% for BCH (279, 256, 3) and significantly reduce error correction time to 4.1 ns.
- The proposed solution has been simulated using VHDL hardware description language and synthesized with Xilinx ISE software to validate its effectiveness.
- The research concluded that the proposed decoder can outperform existing BCH decoder blocks currently available, demonstrating its potential for enhancing data storage reliability and error correction in multilevel flash memories.
- Researchers have identified that the proposed solution can be applied to other types of memories, such as nor and nand flash memories, to improve their storage capabilities.
- The research has been peer-reviewed and published in the Journal of Circuits, Systems and Computers, with a citation of "Enhancing Data Storage Reliability and Error Correction In Multilevel nor and Nand Flash Memories Through Optimal Design of Bch Codes."
Statistics:
- 4.1 ns: error correction time achieved by the proposed decoder
- 50%: reduction in area complexity for BCH (279, 256, 3)
- 3: number of stages in the pipeline adopted in the proposed decoder
Sources:
- NewsRx. Data on Data Storage Detailed by Researchers at University of Bremen (Enhancing Data Storage Reliability and Error Correction In Multilevel nor and Nand Flash Memories Through Optimal Design of Bch Codes). Information Technology Newsweekly, 2025; p 99. (Journal of Circuits, Systems and Computers)
- University of Bremen. Institute for Computer Science. Bremen, Germany.