DDDmitry Duplyakin

Dmitry Duplyakin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dmitry Duplyakin has a total of 47 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    HPC Digital Twins for Evaluating Scheduling Policies, Incentive Structures and their Impact on Power and Cooling

    by Matthias Maiterth, Wesley H. Brewer, Jaya S. Kuruvella, Arunavo Dey, Tanzima Z. Islam, Rashadul Kabir, Kevin Menear, Dmitry Duplyakin, Tapasya Patki, Terry Jones, et al.


  • Open Access

    Energy-Aware HPC Scheduling with LLM-Based Power Prediction

    by Kevin Menear, Alex Wilkinson, Tim Dykes, Utz-Uwe Haus, Dmitry Duplyakin


  • Open Access

    Same Data, Different Audiences: Using Personas to Scope a Supercomputing Job Queue Visualization

    by Connor Scully-Allison, Kevin Menear, Kristin Potter, Andrew McNutt, Katherine E. Isaacs, Dmitry Duplyakin

    Domain-specific visualizations sometimes focus on narrow, albeit important, tasks for one group of users. This focus limits the utility of a visualization to other groups working with the same data. While tasks elicited from other groups can present a design pitfall if not disambiguated, they also present a design opportunity -- development of visualizations that support multiple groups. This development choice presents a trade off of broadening the scope but limiting support for the more narrow tasks of any one group, which in some cases can enhance the overall utility of the visualization. We investigate this scenario through a design study where we develop \textit{Guidepost}, a notebook-embedded visualization of supercomputer queue data that helps scientists assess supercomputer queue wait times, machine learning researchers understand prediction accuracy, and system maintainers analyze usage trends. We adapt the use of personas for visualization design from existing literature in the HCI and software engineering domains and apply them in categorizing tasks based on their uniqueness across the stakeholder personas. Under this model, tasks shared between all groups should be supported by interactive visualizations and tasks unique to each group can be deferred to scripting with notebook-embedded visualization design. We evaluate our visualization with nine expert analysts organized into two groups: a "research analyst" group that uses supercomputer queue data in their research (representing the Machine Learning researchers and Jobs Data Analyst personas) and a "supercomputer user" group that uses this data conditionally (representing the HPC User persona). We find that our visualization serves our three stakeholder groups by enabling users to successfully execute shared tasks with point-and-click interaction while facilitating case-specific programmatic analysis workflows.

  • Open Access

    Tandem Predictions for HPC jobs

    by Kevin Menear, Kadidia Konate, Kristi Potter, Dmitry Duplyakin

    At the core of the predictive analytics applied to High Performance Computing (HPC), the most prominent tasks are the prediction of job runtimes and the prediction of job queue times, both of which have the potential for informing HPC users during their every-day decision making. Accurate runtime predictions can help users better choose so-called wallclock times at job submission, decreasing the odds of their jobs waiting in queues longer than necessary. The accurate and timely queue time predictions offered for the available partitions can inform the favorable selection of partitions for running jobs. This potential is well understood as we see in the abundance of research studies that propose solutions for these tasks, including the work published in the last several years. These tasks are seemingly receptive to the Machine Learning (ML) solutions, considering that there is no shortage of training data where HPC centers over time run millions and millions of jobs. However, we study the existing research literature, as well as look for examples in the toolchains supported on the exemplar HPC facilities, and, surprisingly, do not find any practical solutions that are ready to be adopted. We interpret this as a manifestation of the shortage of UX/UI efforts that support HPC analytics and also as a sign that the research has not come to the consensus on solving these tasks. In this study, we aim to shed new light on the long-running task of job queue time prediction by exploring the utility of runtime predictions in improving prediction accuracy and, actually, predicting these two metrics together, in tandem. In other words, we show how runtime predictions become valuable input in the queue time modeling. We challenge the existing approaches to feature engineering for the queue time prediction and describe promising results we obtained for a large dataset of HPC jobs from a supercomputer at the National Renewable Energy Laboratory.


  • Open Access

    Quantifying Uncertainty in HPC Job Queue Time Predictions

    by Kevin Menear, Connor Scully-Allison, Dmitry Duplyakin

    High Performance Computing (HPC) has developed at an unprecedented pace in recent decades. This growth has demanded corresponding development in the area of HPC Operational Data Analytics (ODA), which encompasses a wide range of data analysis techniques, ML/AI efforts, tools, and visualizations. Published studies in ODA offer a variety of practical ways to inform HPC users, administrators, procurement managers, and other stakeholders. Uncertainty analysis, however, is rare in the related published literature. For instance, we identify only 1 out of 14 existing studies focused on job queue time prediction that investigates the uncertainty aspect of their proposed predictions. We recognize the utmost importance uncertainty quantification can have in such predictive analytics solutions, with consequences in how users interpret information they receive, and attempt to bridge this gap. With the goal of improving access to such insights, we develop a process for determining upper and lower bounds of the predicted queue times of a regression model at a specified confidence level. Our current research is focused on the uncertainty in predicting job queue times, yet our approach may be employed in predicting other metrics.


  • Open Access

    Is Knowledge about Running Applications Helping Improve Runtime Prediction of HPC Jobs?

    by Kevin Menear, Dmitry Duplyakin

    High-performance computing systems rely upon scheduling algorithms to achieve high utilization. These schedulers rely upon user estimates of job resource requirements, such as runtime, to determine optimal scheduling of incoming jobs. These user estimates, however, are prone to error. To mitigate this error, significant research has been directed at providing better estimates of job runtime, usually employing machine learning techniques. These techniques are dependent upon the input features selected. Among the possible features is the primary application used by the job. In a survey of more than 20 papers directed at improving runtime prediction, only four included primary application as an input feature. We focus this investigation specifically on the value of adding primary application as an input feature, and find that it does improve model performance, especially for jobs with longer runtimes, though this improvement varies based on the application used. We recommend further research to determine the cause of this variability as well as an optimal strategy for employing a mixture of models both including and not including primary application as a feature.


  • Open Access

    Mastering HPC Runtime Prediction: From Observing Patterns to a Methodological Approach

    by Kevin Menear, Ambarish Nag, Jordan Perr-Sauer, Monte Lunacek, Kristi Potter, Dmitry Duplyakin

    The continual expansion of high-performance computing (HPC) brings with it an increasing need for efficiency. Heavy investment in energy, hardware, and software infrastructure to support peta- and exascale computing requires the optimization of existing systems and, wherever possible, the discernment and adoption of best-practices towards these goals. Such is the case for runtime prediction. When a job is submitted to an HPC system, an estimate of its runtime is provided by the user in the form of “requested wallclock”. Error in this user-provided estimate can lead to jobs being prematurely killed by the scheduler, increased wait time on the queue, and decreased system utilization. More than fifteen years of research has been directed at mitigating these effects by using data-driven runtime predictions. Codified here is a set of commonalities and insights emerging from this body of work, which we present as recommendations and best practices. These practices are combined into a methodological approach described and evaluated on an 11-million-job dataset from the National Renewable Energy Laboratory’s petascale HPC system, Eagle. This dataset and the accompanying codebase have been released to the public domain for the benefit of the wider HPC research community.


  • Open Access

    graphenv: a Python library for reinforcement learning on graph search spaces

    by David Biagioni, Charles Edison Tripp, Struan Clark, Dmitry Duplyakin, Jeffrey Law, Peter C. St. John


  • Open Access

    Modeling Subsurface Performance of a Geothermal Reservoir Using Machine Learning

    by Dmitry Duplyakin, Koenraad F. Beckers, Drew L. Siler, Michael J. Martin, Henry E. Johnston

    Geothermal power plants typically show decreasing heat and power production rates over time. Mitigation strategies include optimizing the management of existing wells—increasing or decreasing the fluid flow rates across the wells—and drilling new wells at appropriate locations. The latter is expensive, time-consuming, and subject to many engineering constraints, but the former is a viable mechanism for periodic adjustment of the available fluid allocations. In this study, we describe a new approach combining reservoir modeling and machine learning to produce models that enable such a strategy. Our computational approach allows us, first, to translate sets of potential flow rates for the active wells into reservoir-wide estimates of produced energy, and second, to find optimal flow allocations among the studied sets. In our computational experiments, we utilize collections of simulations for a specific reservoir (which capture subsurface characterization and realize history matching) along with machine learning models that predict temperature and pressure timeseries for production wells. We evaluate this approach using an “open-source” reservoir we have constructed that captures many of the characteristics of Brady Hot Springs, a commercially operational geothermal field in Nevada, USA. Selected results from a reservoir model of Brady Hot Springs itself are presented to show successful application to an existing system. In both cases, energy predictions prove to be highly accurate: all observed prediction errors do not exceed 3.68% for temperatures and 4.75% for pressures. In a cumulative energy estimation, we observe prediction errors that are less than 4.04%. A typical reservoir simulation for Brady Hot Springs completes in approximately 4 h, whereas our machine learning models yield accurate 20-year predictions for temperatures, pressures, and produced energy in 0.9 s. This paper aims to demonstrate how the models and techniques from our study can be applied to achieve rapid exploration of controlled parameters and optimization of other geothermal reservoirs.