TY - GEN
T1 - HPC Application Performance Prediction with Machine Learning on New Architectures
AU - Yokelson, Dewi
AU - Charest, Marc Robert Joseph
AU - Li, Ying Wai
PY - 2023/7/28
Y1 - 2023/7/28
N2 - We explore a modeling approach for scientific application performance on high-performance computer architectures using machine learning techniques. Multiple linear regression models and neural networks were evaluated for effectiveness in constructing performance models to predict the execution time of an application. Performance metrics collected during run time, together with hardware specifications, were used as input features for the performance models. Our two-step machine learning approach improved the R2 score for performance prediction: we first performed feature selection to select a subset of metrics that are the most relevant for execution time prediction; machine learning models were then trained to predict this subset of performance metrics, which then served as the inputs for the final performance model construction in the second step. This two-step approach resulted in promising results during our case study. Regression models achieved an R2 score up to 93% and a neural network model achieved an R2 score of over 94% when applied to predict the execution time on an unseen computer architecture. These results are comparable to existing methods that require more upfront hardware and systems knowledge, implying that our method is more approachable for application developers without extensive performance knowledge.
AB - We explore a modeling approach for scientific application performance on high-performance computer architectures using machine learning techniques. Multiple linear regression models and neural networks were evaluated for effectiveness in constructing performance models to predict the execution time of an application. Performance metrics collected during run time, together with hardware specifications, were used as input features for the performance models. Our two-step machine learning approach improved the R2 score for performance prediction: we first performed feature selection to select a subset of metrics that are the most relevant for execution time prediction; machine learning models were then trained to predict this subset of performance metrics, which then served as the inputs for the final performance model construction in the second step. This two-step approach resulted in promising results during our case study. Regression models achieved an R2 score up to 93% and a neural network model achieved an R2 score of over 94% when applied to predict the execution time on an unseen computer architecture. These results are comparable to existing methods that require more upfront hardware and systems knowledge, implying that our method is more approachable for application developers without extensive performance knowledge.
UR - http://www.scopus.com/inward/record.url?scp=85169416223&partnerID=8YFLogxK
U2 - 10.1145/3588993.3597262
DO - 10.1145/3588993.3597262
M3 - Conference contribution
T3 - PERMAVOST 2023 - Proceedings of the 2023 on Performance Engineering, Modelling, Analysis, and Visualization Strategy
SP - 1
EP - 8
BT - PERMAVOST 2023 - Proceedings of the 2023 on Performance Engineering, Modelling, Analysis, and Visualization Strategy
PB - Unknown Publisher
T2 - 3rd Workshop on Performance Engineering, Modelling, Analysis, and Visualization Strategy, PERMAVOST 2023
Y2 - 28 July 2023
ER -