Compiler-based fault tolerance is a cost-effective and flexible family of solutions that transparently improves software reliability. This paper evaluates a compiler tool for fault detection via laser injection and α-particle exposure. A novel memory allocation strategy is proposed to mitigate the effects of multi-bit upsets. We integrated the detection mechanism with a recovery solution based on mixed-criticality scheduling. The results demonstrate the error detection and recovery capabilities in realistic scenarios: reducing undetected errors, enhancing system reliability, and advancing software-implemented fault tolerance.

Modern HPC systems must be designed considering different parameters, which include cost, performance, and throughput, as well as non-functional properties, such as power/energy consumption and reliability. This paper describes the work performed and the results achieved by the partners of the Italian National Research Center for HPC, Big Data and Quantum Computing in the frame of the sub-project dealing with Future HPC architectures and solutions. The work in this subproject focused on advanced design and monitoring techniques for devising energy- and power-efficient, reliable parallel architectures based on open standards (e.g., RISC-V) and design space exploration techniques and tools. This paper provides a summary of the achieved results and developed products stemming from the activities of the different partners.

Software-Implemented Hardware Fault Tolerance (SIHFT) is advantageous in critical systems where hardware solutions cannot be used due to competing non-functional constraints. Recent works have focused on developing compiler-based protection mechanisms, relying on debuggers and other software mechanisms to introduce single event upsets. In this work, we test a compiler-based technique using physical radiation testing methods, including laser fault injection and alpha-particle exposure. During this evaluation, we identified previously unknown issues that required further development, including a novel memory allocation strategy for improved reliability. Furthermore, we integrated this fault detection solution with a hard real-time recovery mechanism that exploits mixed-criticality scheduling to demonstrate the overall system recovery capabilities. The results show the effectiveness of the proposed approach in detecting faults even under real-world radiation conditions, representing an important step toward the maturity of SIHFT techniques.