This paper proposes a mixed-grained reconfigurable architecture consisting of fine-grained and coarse-grained fabrics, each of which can be configured for different levels of reliability depending on the reliability requirement of target applications, e.g. mission-critical applications to consumer products. Thanks to the fine-grained fabrics, the architecture can accommodate a state machine, which is indispensable for exploiting C-based behavioral synthesis to trade latency with resource usage through multi-step processing using dynamic reconfiguration. In implementing the architecture, the strategy of dynamic reconfiguration, the assignment of configuration storage and the number of implementable states are key factors that determine the achievable trade-off between used silicon area and latency. We thus split the configuration bits into two classes; state-wise configuration bits and state-invariant configuration bits for minimizing area overhead of configuration bit storage. Through a case study, we experimentally explore the appropriate number of implementable states. A proof-of-concept VLSI chip was fabricated in 65nm process. Measurement results show that applications on the chip can be working in a harsh radiation environment. Irradiation tests also show the correlation between the number of sensitive bits and the mean time to failure. Furthermore, the temporal error rate of an example application due to soft errors in the datapath was measured and demonstrated for reliability-aware mapping.

This paper proposes a novel method to determine a priority for applying selective triple modular redundancy (selective TMR) against single event upset (SEU) to achieve cost-effective reliable implementation of application circuits onto coarse-grained reconfigurable architectures (CGRAs). The priority is determined by an estimation of the vulnerability of each node in the data flow graph (DFG) of the application circuit. The estimation is based on a weighted sum of the node parameters which characterize impact of the SEU in the node on the output data. This method does not require time-consuming placement-and-routing processes, as well as extensive fault simulations for various triplicating patterns, which allows us to identify the set of nodes to be triplicated for minimizing the vulnerability under given area constraint at the early stage of design flow. Therefore, the proposed method enables us efficient design space exploration of reliability-oriented CGRAs and their applications.

Fault tolerant methods using dynamically reconfigurable devices have been studied to overcome wear-out failures. However, quantitative comparisons have not been sufficiently assessed on device lifetime enhancement with these methods, whereas they have mainly been evaluated individually from various viewpoints such as additional hardware overheads, performance, and downtime for fault recovery. This paper presents quantitative lifetime evaluations performed by simulating the fault-avoidance procedures of five representative methods under the same conditions in wear-out scenarios, applications, and device architecture. The simulation results indicated that improvements of up to 70% mean-time-to-failure (MTTF) in comparison with ideal fault avoidance could be achieved by using methods of fault avoidance with ‘row direction shift’ and ‘dynamic partial reconfiguration’. ‘Column shift’, on the other hand, attained a high degree of stability with moderate improvements in MTTF. The experimental results also revealed that spare basic elements (BEs) should be prevented from aging so that improvements in MTTF would not be adversely affected. Moreover, we found that the selection of initial mappings guided by wire utilization could increase the lifetimes of partial reconfiguration based fault avoidance.

This paper proposes a reliability evaluation environment for coarse-grained reconfigurable architectures. This environment is designed so that it can be easily extended to different target architectures and applications by automating the generation of the simulation inputs such as HDL codes for fault injection and configuration information. This automation enables us to explore a huge design space in order to efficiently analyze area/reliability trade-offs and find the best solution. This paper also shows demonstrative examples of the design space exploration of coarse-grained reconfigurable architectures using the proposed environment. Through the demonstrations, we discuss relationship between coarse-grained architectures and reliability, which has not yet been addressed in existing literatures and show the feasibility of the proposed environment.

Time redundancy is sometimes an only option for enhancing circuit reliability when the circuit area is severely restricted. In this paper, a time-redundant error-correction scheme, which is particularly suitable for coarse-grained reconfigurable arrays (CGRAs), is proposed. It judges the correctness of the executions by comparing the results of two identical runs. Once a mismatch is found, the second run is terminated immediately to start the third run, under the assumption that the errors tend to persist in many applications, for selecting the correct result in the three runs. The circuit area and reliability of the proposed method is compared with a straightforward implementation of time-redundancy and a selective triple modular redundancy (TMR). A case study on a CGRA revealed that the area of the proposed method is 1% larger than that of the implementation for the selective TMR. The study also shows the proposed scheme is up to 2.6x more reliable than the full-TMR when the persistent error is predominant.