DRIFT: Decoupled CompileR-Based Instruction-Level Fault-Tolerance.

Compiler-based error detection methodologies replicate the instructions of the program and insert checks wherever it is needed. The checks evaluate code correctness and decide whether or not an error has occurred. The replicated instructions and the checks cause a large slow-down. In this work, we focus on reducing the error detection overhead and improving the system's performance without degrading fault-coverage. DRIFT achieves this by decoupling the execution of the code (original and replicated) from the checks. The checks are compare and jump instructions. The latter ones sequentialize the code and prohibit the compiler from performing aggressive instruction scheduling optimizations. We call this phenomenon basic-block fragmentation. DRIFT reduces the impact of basic-block fragmentation by breaking the synchronized execute-check-confirm-execute cycle. In this way, DRIFT generates a scheduler-friendly code with more ILP. As a result, it reduces the performance overhead down to 1.29x (on average) and outperforms the state-of-the-art by up to 29.7% retaining the same fault-coverage. The evaluation was done on an Itanium2 by running MediabenchII and SPEC2000 benchmark suites.