Space Expansion of Feature Selection for Designing more Accurate Error Predictors
This work addresses the need for more reliable error predictors to ensure user experience in energy-efficient approximate computing systems, representing an incremental advancement in feature selection techniques.
The paper tackled the problem of improving error prediction accuracy in approximate computing by proposing a scheduling-aware feature selection method that uses intermediate hardware accelerator results, achieving significant accuracy improvements over prior methods that only used accelerator inputs.
Approximate computing is being considered as a promising design paradigm to overcome the energy and performance challenges in computationally demanding applications. If the case where the accuracy can be configured, the quality level versus energy efficiency or delay also may be traded-off. For this technique to be used, one needs to make sure a satisfactory user experience. This requires employing error predictors to detect unacceptable approximation errors. In this work, we propose a scheduling-aware feature selection method which leverages the intermediate results of the hardware accelerator to improve the prediction accuracy. Additionally, it configures the error predictors according to the energy consumption and latency of the system. The approach enjoys the flexibility of the prediction time for a higher accuracy. The results on various benchmarks demonstrate significant improvements in the prediction accuracy compared to the prior works which used only the accelerator inputs for the prediction.