• 반도체디스플레이기술학회지
• /
• 제19권3호
• /
• pp.112-117
• /
• 2020

NAND flash memory is a non-volatile memory that retains stored data even without power supply. Internal memory used as a data storage device and solid-state drive (SSD) is used in portable devices such as smartphones and digital cameras. However, NAND flash memory carries the risk of electric shock, which can cause errors during read/write operations, so use error correction codes to ensure reliability. It efficiently recovers bad block information, which is a defect in NAND flash memory. BBT (Bad Block Table) is configured to manage data to increase stability, and as a result of experimenting with the error correction code algorithm, the bit error rate per page unit of 4Mbytes memory was on average 0ppm, and 100ppm without error correction code. Through the error correction code algorithm, data stability and reliability can be improved.

• International Journal of Knowledge Content Development & Technology
• /
• 제5권2호
• /
• pp.75-101
• /
• 2015

In this paper, we investigate the notion of error correction memory applied to technical texts. The main purpose is to introduce flexibility and context sensitivity in the detection and the correction of errors related to Constrained Natural Language (CNL) principles. This is realized by enhancing error detection paired with relatively generic correction patterns and contextual correction recommendations. Patterns are induced from previous corrections made by technical writers for a given type of text. The impact of such an error correction memory is also investigated from the point of view of the technical writer's cognitive activity. The notion of error correction memory is developed within the framework of the LELIE project an experiment is carried out on the case of fuzzy lexical items and negation, which are both major problems in technical writing. Language processing and knowledge representation aspects are developed together with evaluation directions.

• 한국정보통신학회논문지
• /
• 제26권10호
• /
• pp.1559-1562
• /
• 2022

As electronic devices technology scales down into the deep-submicron to achieve high-density, low power and high performance integrated circuits, multiple bit upsets by soft errors have become a major threat to on-chip memory systems. To address the soft error problem, single error correction, double error detection and double adjacent error correction (SEC-DED-DAEC) codes have been recently proposed. But these codes do not troubleshoot mis-correction problem. We propose the SEC-DED_DAEC code with without mis-correction. The decoder for proposed code is implemented as hardware and verified. The results show that there is no mis-correction in the proposed codes and the decoder can be employed on-chip memory system.

• Journal of information and communication convergence engineering
• /
• 제19권1호
• /
• pp.22-28
• /
• 2021

Convolutional neural networks (CNNs) are one of the most frequently used artificial intelligence techniques. Among CNN-based applications, small and timing-sensitive applications have emerged, which must be reliable to prevent severe accidents. However, as the small and timing-sensitive systems do not have sufficient system resources, they do not possess proper error protection schemes. In this paper, we propose MATE, which is a low-cost CNN weight error correction technique. Based on the observation that all mantissa bits are not closely related to the accuracy, MATE replaces some mantissa bits in the weight with error correction codes. Therefore, MATE can provide high data protection without requiring additional memory space or modifying the memory architecture. The experimental results demonstrate that MATE retains nearly the same accuracy as the ideal error-free case on erroneous DRAM and has approximately 60% accuracy, even with extremely high bit error rates.

• 한국정보통신학회논문지
• /
• 제26권11호
• /
• pp.1747-1750
• /
• 2022

As shrinking the semiconductor process into the deep sub-micron to achieve high-density, low power and high performance integrated circuits, MBU (multiple bit upset) by soft errors is one of the major challenge of on-chip memory systems. To address the MBU, single error correction, double error detection and double adjacent error correction (SEC-DED-DAEC) codes have been recently proposed. But these codes do not resolve mis-correction. We propose the SEC-DED-DAEC-TAED(triple adjacent error detection) code without mis-corrections. The generated H-matrix by the proposed heuristic algorithm to accomplish the proposed code is implemented as hardware and verified. The results show that there is no mis-correction in the proposed codes and the 2-stage pipelined decoder can be employed on-chip memory system.

• 전기학회논문지
• /
• 제59권2호
• /
• pp.417-422
• /
• 2010

When memory devices are exposed to space environments, they suffer various effects such as SEU(Single Event Upset). Memory systems for space applications are generally equipped with error detection and correction(EDAC) logics against SEUs. In this paper, several error detection and correction codes - RS(10,8) code, (7,4) Hamming code and (16,8) code - are analyzed and compared with each other. Each code is implemented using VHDL and its performances(encoding/decoding speed, required memory size) are compared. Also the failure probability equation of each EDAC code is derived, and the probability value is analyzed for various occurrence rates of SEUs which the STSAT-3 possibly suffers. Finally, the EDAC algorithm for STSAT-3 is determined based on the comparison results.

• 한국정보통신학회논문지
• /
• 제21권3호
• /
• pp.601-606
• /
• 2017

고성능 디지털 회로 개발과 구현에 사용되는 SRAM 기반 FPGA(Field Programmable Gate Array)는 configuration memory가 SRAM으로 구현되었기 때문에 configuration memory에 소프트 에러가 발생하는 경우 오동작하게 된다. Xilinx사의 FPGA는 configuration memory 영역에 추가된 ECC(Error Correction Code)와 CRC(Cyclic Redundancy Code) 그리고 이들을 활용하는 SEM(Soft Error Mitigation) Controller를 이용하여 이러한 소프트 에러의 영향을 줄일 수 있다. 본 연구에서는 SRAM 기반 FPGA에서 SEM Controller에 의해 configuration memory 영역이 소프트 에러로부터 보호될 때 FPGA의 신뢰도를 가용성 관점에서 해석하고 그 효과를 분석하였다. 이를 위해 FPGA 계열별 SEM Controller의 소프트 에러 정정 성능에 따른 가용성 함수를 유도하고 FPGA 계열별 사례를 적용하여 비교하였다. 연구 결과는 SRAM 기반 FPGA의 선정 및 가용성 예측에 활용될 수 있을 것으로 기대된다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(5)
• /
• pp.39-42
• /
• 2001

This paper proposes the design technique of memory sparing to overcome memory hard error Memory Sparing is used to increase the reliability and availability of commercial, military and space computer such as a Data Server, Communication Server, Flight Computer in airplane and On-Board Computer in spacecraft. But the documents about this technique are rare and hard to find. This paper has some useful information about memory error correction and memory error management.

• 한국군사과학기술학회지
• /
• 제8권3호
• /
• pp.42-50
• /
• 2005

In this paper, a novel method is proposed how the ECC(Error Correction Code) in server system can be investigated and the robustness of each system against noisy environment and element failure in memory module has been verified. Chipset manufacturers have hided the algorithm of their Hamming code and the user has difficulty in verification of the robustness of each system. The proposed method is very simple, but the outputs of the experiment explain the core ability of error correction in server system and helps the detection of the failure element. On the basis of these results, we could expect the robustness of digitalized weapon system and the efficient design of our own error correction code.

• 제어로봇시스템학회논문지
• /
• 제17권11호
• /
• pp.1101-1105
• /
• 2011

Radiation particles can introduce temporary errors in memory systems. To protect against these errors, so-called soft errors, error detection and correcting codes are used. In addition, scrubbing is applied which is a fundamental technique to avoid the accumulation of soft errors. This paper introduces an optimal scrubbing scheme, which is suitable for a system with auto error detection and correction logic. An auto error detection and correction logic can correct soft errors without CPU's writing operation. The proposed scrubbing scheme leads to maximum reliability by considering both allowable scrubbing load and the periodic accesses to memory by the tasks running in the system.