Guiding Application Users via Estimation of Computational Resources for Massively Parallel Chemistry Computations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tabassum, Tanzila, Subasi, Omer, Panyala, Ajay, Ebiapia, Epiya, Baumgartner, Gerald, Mutlu, Erdal, P., Sadayappan, Kowalski, Karol
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916969404432384
author Tabassum, Tanzila
Subasi, Omer
Panyala, Ajay
Ebiapia, Epiya
Baumgartner, Gerald
Mutlu, Erdal
P.
Sadayappan
Kowalski, Karol
author_facet Tabassum, Tanzila
Subasi, Omer
Panyala, Ajay
Ebiapia, Epiya
Baumgartner, Gerald
Mutlu, Erdal
P.
Sadayappan
Kowalski, Karol
contents In this work, we develop machine learning (ML) based strategies to predict resources (costs) required for massively parallel chemistry computations, such as coupled-cluster methods, to guide application users before they commit to running expensive experiments on a supercomputer. By predicting application execution time, we determine the optimal runtime parameter values such as number of nodes and tile sizes. Two key questions of interest to users are addressed. The first is the shortest-time question, where the user is interested in knowing the parameter configurations (number of nodes and tile sizes) to achieve the shortest execution time for a given problem size and a target supercomputer. The second is the cheapest-run question in which the user is interested in minimizing resource usage, i.e., finding the number of nodes and tile size that minimizes the number of node-hours for a given problem size. We evaluate a rich family of ML models and strategies, developed based on the collections of runtime parameter values for the CCSD (Coupled Cluster with Singles and Doubles) application executed on the Department of Energy (DOE) Frontier and Aurora supercomputers. Our experiments show that when predicting the total execution time of a CCSD iteration, a Gradient Boosting (GB) ML model achieves a Mean Absolute Percentage Error (MAPE) of 0.023 and 0.073 for Aurora and Frontier, respectively. In the case where it is expensive to run experiments just to collect data points, we show that active learning can achieve a MAPE of about 0.2 with just around 450 experiments collected from Aurora and Frontier.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20667
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Guiding Application Users via Estimation of Computational Resources for Massively Parallel Chemistry Computations
Tabassum, Tanzila
Subasi, Omer
Panyala, Ajay
Ebiapia, Epiya
Baumgartner, Gerald
Mutlu, Erdal
P.
Sadayappan
Kowalski, Karol
Machine Learning
Computational Engineering, Finance, and Science
Distributed, Parallel, and Cluster Computing
In this work, we develop machine learning (ML) based strategies to predict resources (costs) required for massively parallel chemistry computations, such as coupled-cluster methods, to guide application users before they commit to running expensive experiments on a supercomputer. By predicting application execution time, we determine the optimal runtime parameter values such as number of nodes and tile sizes. Two key questions of interest to users are addressed. The first is the shortest-time question, where the user is interested in knowing the parameter configurations (number of nodes and tile sizes) to achieve the shortest execution time for a given problem size and a target supercomputer. The second is the cheapest-run question in which the user is interested in minimizing resource usage, i.e., finding the number of nodes and tile size that minimizes the number of node-hours for a given problem size. We evaluate a rich family of ML models and strategies, developed based on the collections of runtime parameter values for the CCSD (Coupled Cluster with Singles and Doubles) application executed on the Department of Energy (DOE) Frontier and Aurora supercomputers. Our experiments show that when predicting the total execution time of a CCSD iteration, a Gradient Boosting (GB) ML model achieves a Mean Absolute Percentage Error (MAPE) of 0.023 and 0.073 for Aurora and Frontier, respectively. In the case where it is expensive to run experiments just to collect data points, we show that active learning can achieve a MAPE of about 0.2 with just around 450 experiments collected from Aurora and Frontier.
title Guiding Application Users via Estimation of Computational Resources for Massively Parallel Chemistry Computations
topic Machine Learning
Computational Engineering, Finance, and Science
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2509.20667