Evaluating Performance and Reliability of Selective Redundant Multithreading for GPGPU Applications

Abstract

With the widespread use of GPU architectures in general-purpose computations, evaluating the soft error vulnerability of GPGPU programs and employing efficient fault tolerance techniques for more reliable execution becomes more prominent. Performing full redundancy, based on the redundant execution of the complete program, results in resource consumption and performance loss as well as energy inefficiency. Therefore, determining the most error-prone regions of the target program code and replicating only those parts maintains both high performance and acceptable error rates. In this study, we propose a partial redundant multithreading mechanism based on the soft error vulnerability of GPGPU applications and perform a trade-off analysis between performance and reliability. Firstly, we perform fault injection experiments to evaluate the SDC rates for each kernel function. Then, based on the outcome of the fault injection experiments, we determine the kernel function to-be-replicated. According to the pragmas denoting the redundancy points in the source code, our custom LLVM pass generates the code that enables the redundant execution for the specified code region. We evaluate both the reliability and performance of the redundant execution scenarios measuring the execution time of the redundant program generated by our compiler-managed redundancy technique. Our results demonstrate that protecting only the most vulnerable kernel functions enables high reliability without hurting the performance significantly. © 2021 The Authors.