Towards Run Time Estimation of the Gaussian Chemistry Code for SEAGrid Science Gateway

TL;DR

This paper investigates methods to predict the run time of the Gaussian chemistry code within the SEAGrid science gateway, aiming to enhance resource management and workflow efficiency in scientific computing.

Contribution

It characterizes a dataset of Gaussian code runs and explores various regression methods for run time prediction, providing insights into application-specific modeling.

Findings

Identified key features influencing run time.

Compared different regression techniques for accuracy.

Outlined future research directions.

Abstract

Accurate estimation of the run time of computational codes has a number of significant advantages for scientific computing. It is required information for optimal resource allocation, improving turnaround times and utilization of science gateways. Furthermore, it allows users to better plan and schedule their research, streamlining workflows and improving the overall productivity of cyberinfrastructure. Predicting run time is challenging, however. The inputs to scientific codes can be complex and high dimensional. Their relationship to the run time may be highly non-linear, and, in the most general case is completely arbitrary and thus unpredictable (i.e., simply a random mapping from inputs to run time). Most codes are not so arbitrary, however, and there has been significant prior research on predicting the run time of applications and workloads. Such predictions are generally application-specific, however. In this paper, we focus on the Gaussian computational chemistry code. We characterize a data set of runs from the SEAGrid science gateway with a number of different studies. We also explore a number of different potential regression methods and present promising future directions.