Selection from several computer systems with different hardware features resulting in different software performance is a critical problem to solve. The problem becomes even more challenging when access to computer systems with different features is difficult. We had proposed a novel solution, �cross performance prediction with scaling,� in our previous work. In the scaling model, we predicted the physical system's runtime using a machine learning model trained only on a performance dataset of simulation-based systems applying a scaling factor to the predicted runtime. In this article, we propose another novel idea, �cross performance prediction with transfer learning,� that uses transfer learning to solve the same problem. This model predicts the target physical system's performance using a machine learning model trained on a combined performance dataset from simulation-based systems and an accessible source physical system. We evaluate both the models using several benchmark algorithms from SD-VBS and MiBench suites. Our scaling model results have achieved a prediction error of 10%�25% for general-purpose systems, whereas the transfer learning model has higher errors in the range of 50%. We have also developed a method to extract the rules built during the decision tree model's training to predict the runtime.
This paper summarizes the background and motivation behind the�Let�s HPC�project, the design philosophy of the platform, the present capabilities of the platform, as well as the plans for future developments.
