Search NASA⌕ Search

SEARCH · Search NASA

Results for “workload”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Integrating the PanDA Workload Management System with the Vera C. Rubin Observatory

The Vera C. Rubin Observatory will produce an unprecedented astronomical data set for studies of the deep and dynamic universe. Its Legacy Survey of Space and Time (LSST) will image the entire southern sky every three to four days and produce tens of petabytes of raw image data and associated calibration data over the course of the experiment’s run. More than 20 terabytes of data must be stored every night, and annual campaigns to reprocess the entire dataset since the beginning of the survey will be conducted over ten years. The Production and Distributed Analysis (PanDA) system was evaluated by the Rubin Observatory Data Management team and selected to serve the Observatory’s needs due to its demonstrated scalability and flexibility over the years, for its Directed Acyclic Graph (DAG) support, its support for multi-site processing, and its highly scalable complex workflows via the intelligent Data Delivery Service (iDDS). PanDA is also being evaluated for prompt processing where data must be processed within 60 seconds after image capture. This paper will briefly describe the Rubin Data Management system and its Data Facilities (DFs). Finally, it will describe in depth the work performed in order to integrate the PanDA system with the Rubin Observatory to be able to run the Rubin Science Pipelines using PanDA.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

TrioSim: A Lightweight Simulator for Large-Scale DNN Workloads on Multi-GPU Systems

Deep Neural Networks (DNNs) have become increasingly capable of performing tasks ranging from image recognition to content generation. The training and inference of DNNs heavily rely on GPUs, as GPUs' massively parallel architecture delivers extremely high computing capability. With the growing complexity of DNNs and the size of training datasets, training DNNs with a large number of GPUs is becoming a prevalent strategy. Researchers have been exploring how to design software and hardware systems for GPU farms to achieve the best utilization, efficiency, and DNN accuracy during training or inference. However, when designing and deploying such systems, designers usually rely on testing on physical hardware platforms equipped with many GPUs, incurring high costs that are almost prohibitive for system designers to test different configurations and designs, even for highly resourceful companies. While an alternative solution is to test on GPU simulators, they are often too slow for these l

Li, Ying [William & Mary, Williamsburg, VA, USA] (↗
DOE OSTI2025

User-based I/O Profiling for Leadership Scale HPC Workloads

I/O constitutes a significant portion of most of the application run-time. Spawning many such applications concurrently on an HPC system leads to severe I/O contention. Thus, understanding and subsequently reducing I/O contention induced by such multi-tenancy is critical for the efficient and reliable performance of the HPC system. In this study, we demonstrate that an application’s performance is influenced by the command line arguments passed to the job submission. We model an application’s I/O behavior based on two factors: past I/O behavior within a time window and user-configured I/O settings via command-line arguments. We conclude that I/O patterns for well-known HPC applications like E3SM and LAMMP are predictable, with an average uncertainty below 0.25 (A probability of 80%) and near zero (A probability of 100%) within a day. However, I/O pattern variance increases as the study time window lengthens. Additionally, we show that for 38 users and at least 50 applications constituting approximately 93000 job submissions, there is a high correlation between a submitted command line and the past command lines made within 1 to 10 days submitted by the user. We claim the length of this time window is unique per user.

Yazdani, Ahmad Hossein [Virginia Tech, Blacksburg]↗
DOE OSTI2024

Decode the Workload: Training Deep Learning Models for Efficient Compute Cluster Representation

Monitoring the status of a high throughput computing cluster running computationally intensive production jobs is a crucial yet challenging system administration task due to the complexity of such systems. To this end, we train autoencoders using the Linux kernel CPU metrics of the cluster. Additionally, we explore assisting these models with graph neural networks to share information across threads within a compute node. The models are compared in terms of their ability to: 1) Produce a compressed latent representation that captures the salient features of the input, 2) Detect anomalous activity, and 3) Make distinction between different kinds of jobs run at Jefferson Lab. The goal is to have a robust encoder whose compressed embeddings are used for several downstream tasks. We extend this study further by deploying these models in a human-in-the-loop production-based setting for the anomaly detection task and discuss the associated implementation aspects such as continual learning and the criterion to generate alarms. This study represents a first step in the endeavor towards building self-supervised large-scale foundation models for computing centers.

Mohammed, Ahmed↗
NASA NTRS1978

Time estimation as a secondary task to measure workload: Summary of research

Actively produced intervals of time were found to increase in length and variability, whereas retrospectively produced intervals decreased in length although they also increased in variability with the addition of a variety of flight-related tasks. If pilots counted aloud while making a production, however, the impact of concurrent activity was minimized, at least for the moderately demanding primary tasks that were selected. The effects of feedback on estimation accuracy and consistency were greatly enhanced if a counting or tapping production technique was used. This compares with the minimal effect that feedback had when no overt timekeeping technique was used. Actively made verbal estimates of sessions filled with different activities performed during the interval were increased. Retrospectively made verbal estimates, however, increased in length as the amount and complexity of activities performed during the interval were increased.

Hart, S. G.↗
NASA NTRS1980

Multi-modal information processing for visual workload relief

The simultaneous performance of two single-dimensional compensatory tracking tasks, one with the left hand and one with the right hand, is discussed. The tracking performed with the left hand was considered the primary task and was performed with a visual display or a quickened kinesthetic-tactual (KT) display. The right-handed tracking was considered the secondary task and was carried out only with a visual display. Although the two primary task displays had afforded equivalent performance in a critical tracking task performed alone, in the dual-task situation the quickened KT primary display resulted in superior secondary visual task performance. Comparisons of various combinations of primary and secondary visual displays in integrated or separated formats indicate that the superiority of the quickened KT display is not simply due to the elimination of visual scanning. Additional testing indicated that quickening per se also is not the immediate cause of the observed KT superiority.

Burke, M. W.↗
NASA NTRS1980

Instrument scan - Is it an indicator of the pilot's workload

Results of an investigation of the relationship between an aircraft pilot's visual scanning of instruments and the level of mental activity during a simulated approach and landing are presented. Noting that periods of activity which demand either close to 100% of human capacity or low levels of capacity are the times when most errors are committed, trials were conducted with three NASA test pilots in a terminal configured vehicle simulator. The pilots flew a normal approach while verbally responding to three digit stimuli to be judged plus or minus according to an order of magnitude scheme, and also while using a control stick to extinguish a light that came on and off to the right and left of the instrument panel. Eyescans of the instrumentation were monitored, and determinations were made of the most common instruments used during approach and flare. Fixation on instruments was found to increase with the arithmetic tasks.

Ephrath, A. R.↗
NASA NTRS1983

Behavioral indicators of pilot workload

Using a technique that requires a subject to consult an imagined or remembered spatial array while performing a visual task, a reliable reduction in the number of directed eye movements that are available for the acquisition of visual information is shown.

Galanter, E.↗
NASA NTRS1984

Objective measure of pilot workload

Timesharing behavior in a data-entry task, similar to a pilot entering navigation data into an on-board computer is investigated. Auditory reaction time as a function of stimulus information and dimensionality is examined. This study has direct implications for stimulus selection for secondary tasks used in the GAT flight simulator at Ames Research Center. Attenuation effects of heat and cold stress in a psychological refractory period task were studied. The focus of interest is the general effects of stress on attention rather than upon specific temperature related phenomena.

Kantowitz, B. H.↗