Comparative Analysis of Machine Learning Models for Performance Prediction of the SPEC Benchmarks

Abstract

Simulation-based performance prediction is complicated and time-consuming. In this study, we apply supervised learning to predict the performance scores of Standard Performance Evaluation Corporation (SPEC) benchmarks. The SPEC CPU2017 is a public dataset of results obtained by executing 43 standardised performance benchmarks organised into 4 suites on various system configurations. This paper analyses the dataset and aims to answer the following questions: I) can we accurately predict the SPEC results based on the configurations provided in the dataset, without having to actually run the benchmarks? II) what are the most important hardware and software features? III) what are the best predictive models and hyperparameters, in terms of prediction error and time? and IV) can we predict the performance of future systems using the past data? We present how to prepare data, select features, tune hyperparameters and evaluate regression models based on Multi-Task Elastic-Net, Decision Tree, Random Forest, and Multi-Layer Perceptron neural networks estimators. Feature selection is performed in three steps: removing zero variance features, removing highly correlated features, and Recursive Feature Elimination based on different feature importance metrics: elastic-net coefficients, tree-based importance measures and Permutation Importance. We select the best models using grid search on the hyperparameter space, and finally, compare and evaluate the performance of the models. We show that tree-based models with the original 29 features provide accurate predictions with an average error of less than 4%. The average error of faster Decision Tree and Random Forest models with 10 features is still below 6% and 5% respectively.

Spatiotemporal Patterns of Methane and Nitrous Oxide Emissions in China’s Inland Waters Identified by Machine Learning Technique

“…To improve the modeling efficiency, feature selection was performed to exclude the features with relatively low importance scores. − In our study, we initially evaluated the prediction performance of the model using 8 input features and recorded the importance score for each feature. The feature importance score reflects the contribution of each feature to the model’s predictions.…”

Predicting the Performance of a Computing System with Deep Networks

“…Although their work demonstrates the validity of using Deep Learning on SPEC datasets, their underlying problem is quite different to ours. The closest work to ours is that of Tousi and Lujan [30], which uses MLPs for the prediction of computer performance. We go further by demonstrating how the use of Convolutional Neural Networks can be used to provide better results.…”

Komparasi Evaluasi Kinerja Siswa Belajar dengan Mengggunakan Algoritma Machine Learning

“…dalam pengelolahan pada Data mining baru selain diperkenalkan di sektor bisnis, tetapi juga terbukti diterapkan untuk sector pada pendidikan [2]. Begitupun memprediksi kinerja akademik siswa sangat penting untuk mengembangkan strategi bagi pelajar yang lemah untuk meningkatkan kinerja mereka secara keseluruhan karena kinerja siswa tergantung pada perbedaan faktor sosial, demografi, psikologis, dan keluarga [3]. untuk meningkatkan prestasi siswa di lembaga pendidikan, beberapa mengupayakan yang dapat dilakukan untuk meningkatkan perbaikkan dalam pendidikan perlu juga untuk dilakukan [4].…”