Soft-error detection using control flow assertions (original) (raw)

HETA: Hybrid Error-Detection Technique Using Assertions

IEEE Transactions on Nuclear Science, 2013

This paper presents HETA, a hybrid technique based on assertions and a non-intrusive enhanced watchdog module to detect SEE faults in microprocessors. These types of faults have a major influence in the microprocessor's control flow, causing incorrect jumps in the program's execution flow. In order to protect the system, a non-intrusive hardware module is implemented in order to monitor the data exchanged between the microprocessor and its memory. Since the hardware itself is not capable of detecting all control flow errors, it is enhanced to support a new software-based technique. Also, previous techniques are used to reach higher detection rates. A fault injection campaign is performed using a MIPS microprocessor. Simulation results show high detection rates with a small amount of performance degradation and area overhead.

Quantitative Analysis of Control Flow Checking Mechanisms for Soft Errors

Proceedings of the The 51st Annual Design Automation Conference on Design Automation Conference - DAC '14, 2014

Control Flow Checking (CFC) based techniques have gained a reputation of providing effective, yet low-overhead protection from soft errors. The basic idea is that if the control flowor the sequence of instructions that are executed-is correct, then most probably the execution of the program is correct. Although researchers claim the effectiveness of the proposed CFC techniques, we argue that their evaluation has been inadequate and can even be wrong! Recently, the metric of vulnerability has been proposed to quantify the susceptibility of computation to soft errors. Laced with this comprehensive metric, we quantitatively evaluate the effectiveness of several existing CFC schemes, and obtain surprising results. Our results show that existing CFC techniques are not only ineffective in protecting computation from soft errors, but that they incur additional power and performance overheads. Software-only CFC protection schemes (CFCSS [14], CFCSS+NA [2], and CEDA [18]) increase system vulnerability by 18% to 21% with 17% to 38% performance overhead; Hybrid CFC protection technique, CFEDC [4] also increases the vulnerability by 5%; While the vulnerability remains almost the same for hardware only CFC protection technique, CFCET [15], they cause overheads of design cost, area, and power due to the hardware modifications required for their implementations.

S-SETA: Selective Software-Only Error-Detection Technique Using Assertions

IEEE Transactions on Nuclear Science, 2015

Software-based techniques offer several advantages to increase the reliability of processor-based systems at very low cost, but they cause performance degradation and an increase of the code size. To meet constraints in performance and memory, we propose SETA, a new control-flow software-only technique that uses assertions to detect errors affecting the program flow. SETA is an independent technique, but it was conceived to work together with previously proposed data-flow techniques that aim at reducing performance and memory overheads. Thus, SETA is combined with such data-flow techniques and submitted to a fault injection campaign. Simulation and neutron induced SEE tests show high fault coverage at performance and memory overheads inferior to the state-of-the-art.

Control Flow Checking or Not? (for Soft Errors)

ACM Transactions on Embedded Computing Systems, 2019

Huge leaps in performance and power improvements of computing systems are driven by rapid technology scaling, but technology scaling has also rendered computing systems susceptible to soft errors. Among the soft error protection techniques, Control Flow Checking (CFC) based techniques have gained a reputation of being lightweight yet effective. The main idea behind CFCs is to check if the program is executing the instructions in the right order. In order to validate the protection claims of existing CFCs, we develop a systematic and quantitative method to evaluate the protection achieved by CFCs using the metric of vulnerability. Our quantitative analysis indicates that existing CFC techniques are not only ineffective in providing protection from soft faults, but incur additional performance and power overheads. Our results show that software-only CFC protection schemes increase system vulnerability by 18%--21% with 17%--38% performance overhead and hybrid CFC protection increases v...

A New Approach to Selectively Implement Control Flow Error Detection Techniques

Advances on P2P, Parallel, Grid, Cloud and Internet Computing, 2019

Many software-implemented control flow error detection techniques have been proposed over the years. In an effort to reduce their overhead, recent research has focused on selective approaches. However, correctly applying these approaches can be difficult. This paper aims to address this concern and proposes a new approach. Our new approach is easier to implement and is applicable on any existing control flow error detection technique. To prove its validity, we apply our new approach to the Random Additive Control Flow Error Detection technique and perform fault injection experiments. The results show that the selective implementation has approximately the same error detection ratio with a decrease in execution time overhead.

Hybrid Technique for Soft Error Detection in Dependable Embedded Software: a First Experiment

2019 IEEE XXVIII International Scientific Conference Electronics (ET), 2019

Embedded systems’ hardware can be impacted by soft errors, which causes either a data flow error or a control flow error in the systems’ software. To counter such errors, numerous software-implemented techniques have been proposed to detect either one of them. However, there exist few techniques that are designed to detect both types of errors. This paper aims to fill that gap by proposing a software-implemented technique that has been designed to detect both data flow and control flow errors, called Data and Control Flow Error Detection (DCFED). We verified the technique using a fault injection campaign and compared the measured results to those of a similar technique, called Software Implemented Error Detection (SIED). The results show that DCFED achieves a higher error detection ratio.

Impact of selectively implementing control flow error detection techniques

Internet of Things, 2020

Many software-implemented control flow error detection techniques have been proposed over the years. In an effort to reduce their overhead, recent research has focused on selective approaches. However, correctly applying these approaches can be difficult because their respective literature gives little guidance on the practical implementation. This paper aims to address this concern and proposes a new approach. Our new approach is easier to implement and is applicable on any existing control flow error detection technique. To prove its validity, we apply our new approach to five different control flow error detection techniques and perform fault injection experiments. The results show that the selective implementation, while decreasing the imposed overhead, can have a negative impact on error detection ratio.

Software-based control flow checking against transient faults in industrial environments

2014

Mechatronic systems operating in industrial environments are subject to a variety of threats because of harsh conditions. Industrial systems usually use commercial off-the shelf (COTS) equipment which are not robust and safe against hostile conditions and therefore require fault-tolerance considerations. This paper presents a novel and efficient method for online detection of control flow errors, called software-based control flow checking (SCFC). It is implemented purely in software and does not manipulate the hardware architecture of the system. Redundant instructions and signatures are embedded into the program at compile time and are utilized for control flow checking at run time. The signatures of the basic blocks are derived from the program graph. It is shown in the paper that SCFC method can increase single detection capability to 14.7% and the fault coverage to 6.12% averagely in comparison with other methods without any increase in memory and performance overheads. In the paper, besides experimental evaluations, analytical evaluations are also carried out, based on probability principles. The detection ability of each method used is thus computed. These computations verify the experimental results and show that SCFC can detect more errors than other methods suggested in literature. Considering the memory limitations in some (such as space) applications and the trend towards the requirement for faster execution of programs, we suggest a novel metric called fitness parameter which incorporates these. It is a better measure than the previously proposed ones since it considers the fault coverage, the memory overhead and the execution time (performance overhead) of each method simultaneously, as well as the detection capability.

SEDSR: Soft Error Detection Using Software Redundancy

Journal of Software Engineering and Applications, 2012

This paper presents a new method for soft error detection using software redundancy (SEDSR) that is able to detect transient faults. Soft errors damage the control flow and data of programs and designers usually use hardware-based solutions to handle them. Software-based techniques for soft error detection force less cost and delay to systems and do not change their configuration. Therefore, these kinds of methods are appropriate alternatives for hardware-based techniques. SEDSR has two separate parts for data and control flow errors detection. Fault injection method is used to compare SEDSR with previous methods of this field based on the new parameter of "Evaluation Factor" that takes in account fault coverage, memory and performance overheads. These parameters are important in real time safety critical applications. Experimental results on SPEC2000 and some traditional benchmarks of this field show that SEDSR is much better than previous methods of this field. SEDSR's evaluation factor is about 50% better than other methods of this field. These results show its success in satisfaction of the existing tradeoff between fault coverage, performance and memory overheads.

Dynamic binary control-flow errors detection

2005

Shrinking microprocessor feature size will increase the soft-error rates to unacceptable levels in the near future. While reliable systems typically employ hardware techniques to address soft-errors, software techniques can provide a less expensive and more flexible alternative. This paper presents a control-flow error classification and proposes new software based control-flow error detection techniques. The new techniques are better than the previous ones in the sense that they detect errors in all the brancherror categories. We also compare the performance of our new techniques with that of the previous ones using our dynamic binary translator.