Gem5Pred: Predictive Approaches For Gem5 Simulation Time

TL;DR

This paper introduces a novel dataset and predictive models for estimating Gem5 simulation time, addressing the challenge of long simulation durations with models leveraging CodeBERT, and provides benchmarks for future research.

Contribution

The paper creates the first dataset for Gem5 simulation time prediction and develops models using CodeBERT, establishing benchmarks for future work.

Findings

Regression MAE of 0.546 achieved

Classification accuracy of 0.696 achieved

Models serve as benchmarks for future research

Abstract

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.