This work presents the evaluation of a new dual-core lockstep hybrid approach aimed to improve the fault tolerance in microprocessors. Our approach takes advantage of modern multicore processor resources to combine software-based lockstep with a custom hardware observer. The first is used to duplicate data and instruction flows; meanwhile, the second is in charge of the control-flow monitoring. The proposal has been implemented in a dual-core ARM microprocessor and validated with low-energy proton irradiation and emulated fault injection campaigns. The results show an improvement of one order of magnitude in the cross section of the benchmarks tested, even considering the worst case scenario.
This work explores the diagnosis capabilities of the enriched information provided by microprocessors trace subsystem combined with laser fault injection. Laser fault injection campaigns with delimited architectural regions have been accomplished on an ARM Cortex-A9 device. Experimental results demonstrate the capability of the presented technique to provide additional information of the various error mechanisms that can happen in a microprocessor. A comparison with radiation campaigns presented in previous work is also discussed, showing that laser fault injection results are in good agreement with neutron and proton radiation results.
11 March 2025 in IEEE Transactions on Nuclear Science
We present an IP called TRACER designed to detect errors and observe the behavior of ARM processor architectures during execution in a non-intrusive manner using the information provided by the trace interface. The TRACER IP has a modular design that can be parameterized to fit a wide variety of ARM processor implementations and software applications. It supports both program and data tracing through the ARM trace embedded modules (ITM, PTM and ETMv4). Experimental results with heavy ions have been conducted on two different processors with Cortex-A9 and Cortex-M7 architectures, respectively. The results demonstrate that the proposed IP can provide very high error detection capabilities.
4 May 2020 in IEEE Transactions on Nuclear Science