Gem5Pred: Predictive Approaches For Gem5 Simulation Time
This addresses a bottleneck for researchers and practitioners using Gem5 by providing predictive tools, though it is incremental as it builds on existing models.
The paper tackles the problem of predicting simulation time in the Gem5 hardware simulator, which is time-consuming, by introducing a new dataset and using CodeBERT-based models, achieving a Mean Absolute Error of 0.546 for regression and an Accuracy of 0.696 for classification.
Gem5, an open-source, flexible, and cost-effective simulator, is widely recognized and utilized in both academic and industry fields for hardware simulation. However, the typically time-consuming nature of simulating programs on Gem5 underscores the need for a predictive model that can estimate simulation time. As of now, no such dataset or model exists. In response to this gap, this paper makes a novel contribution by introducing a unique dataset specifically created for this purpose. We also conducted analysis of the effects of different instruction types on the simulation time in Gem5. After this, we employ three distinct models leveraging CodeBERT to execute the prediction task based on the developed dataset. Our superior regression model achieves a Mean Absolute Error (MAE) of 0.546, while our top-performing classification model records an Accuracy of 0.696. Our models establish a foundation for future investigations on this topic, serving as benchmarks against which subsequent models can be compared. We hope that our contribution can simulate further research in this field. The dataset we used is available at https://github.com/XueyangLiOSU/Gem5Pred.