Nowadays, single event upsets (SEUs) altering digital circuits are becoming a bigger concern for memory applications. This paper presents an error-detection method for difference-set cyclic codes with majority logic decoding. Majority logic decodable codes are suitable for memory applications due to their capability to correct a large number of errors. However, they require a large decoding time that impacts memory performance. The proposed fault-detection method significantly reduces memory access time when there is no error in the data read. The technique uses the majority logic decoder itself to detect failures, which makes the area overhead minimal and keeps the extra power consumption low.
5 April 2012 in IEEE Transactions on Circuits and Systems I: Regular Papers
Error Correction Codes (ECCs) are commonly used to protect memories from soft errors. As technology scales, Multiple Cell Upsets (MCUs) become more common and affect a larger number of cells. An option to protect memories against MCUs is to use advanced ECCs that can correct more than one error per word. In this area, the use of one step majority logic decodable codes has recently been proposed for memory applications. Difference Set (DS) codes are one example of these codes. In this paper, a scheme is presented to protect a memory from MCUs using Difference Set codes. The proposed scheme exploits the localization of the errors in an MCU, as well as the properties of DS codes, to provide enhanced error correction capabilities. The properties of the DS codes are also used to reduce the decoding time. The scheme has been implemented in HDL, and circuit area and speed estimates are provided.
Reliability is a major concern for electronic circuits, especially for those that operate in harsh environments. One source of problems are Single Event Upsets (SEU), which change the value of flip flops and memory cells. SEUs are a major issue for SRAM-based Field Programmable Gate Arrays (FPGAs), as they may alter the circuit functionality, creating errors that will only be removed if the device is reprogrammed. The cost of traditional techniques to deal with SEUs, like triplication, can be excessive in some applications. One example are Space systems, in which power consumption and weight are limited. In those cases, the use of ad hoc protection techniques that can reduce the cost is interesting. In this paper, new protection techniques for adaptive equalizers implemented in SRAM-based FPGAs are presented. The proposed techniques use the knowledge of the equalizer to provide effective protection at a lower cost. The results show a reduction of up to 70% in the use of resources in comparison to the commercial XTMR solution.
7 May 2012 in IEEE Transactions on Nuclear Science
Nowadays the reliability issues of SRAM-based Field Programmable Gate Arrays (FPGAs) operating in harsh environments are well understood. One major effect is Single Event Upsets (SEUs), which are able to invert the stored logical value in flip-flops and memory cells. This issue is more serious when the affected memory cells are part of the configuration memory used for programming the circuit functionality. The consequences may be alterations of the circuit functionality causing errors which may only be corrected by reprogramming the device. For a better understanding of the robustness of programmed circuits, this paper compares two decoders for Error Correction Codes (ECCs). A Hamming Decoder and a One-Step Majority Logic Decoder (OS-MLD) for the Difference-Set Cyclic Codes (DSCC) are analyzed yielding surprisingly unexpected results for their SEU susceptibility, which are interesting for application designers.