At extreme scale, the frequency of silent errors – a class of errors that remain undetected by low-level error detection mechanisms – increases significantly with the computational complexity of the application and the scale of the computing infrastructure. As hardware and software advances are made to usher in the next scientific era of computing, developing new approaches to mitigate the impact of silent errors remains a challenging problem. In this work, we propose an energy-aware fault-tolerance model, referred to diffReplication to overcome silent errors. In the proposed model, the main process is associated with one replica that executes at the same rate as the main process, and one diffReplica that is executed at a fraction of the main process' execution rate. If the main and its replica reach consensus at the end of a computation phase, the state of the diffReplica is updated and computation is resumed. If the synchronization attempt results in a disagreement, however, the diffReplica increases its execution speed to complete the computation and quickly reach the synchronization barrier. Assuming a single error over any given synchronization interval, a majority voting is used to reach consensus and tolerate silent errors. To further enhance its performance, diffReplication is augmented with speculative execution, whereby the main or its fast replica is selected to continue execution without waiting for the diffReplica. The selection process is based on the previous behaviour of the main and its replica. A performance analysis study is carried out to assess the performance of diffReplication, in terms of the energy saving and time-to-completion reduction achieved by the diffReplication scheme. The experiment shows that speculative execution reduces the time to completion with additional energy, and dynamic decision-making balances the energy consumption and time to completion. 

silent error, fault tolerance, extreme-scale, heterogeneous environment