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 217 records · Page 12

Predictive Features of a Cockpit Traffic Display: A Workload Assessment

Eighteen pilots flew a series of traffic avoidance maneuvers in an experiment designed to assess the support offered and workload imposed by different levels of traffic display information in a free flight simulation. Three display prototypes were compared which differed in traffic information provided. A BASELINE (BL) display provided current and (2nd order) predicted information regarding ownship and current information of an intruder aircraft, represented on lateral and vertical displays in a coplanar suite. An INTRUDER PREDICTOR (IP) display, augmented the baseline display by providing lateral and vertical prediction of the intruder aircraft. A THREAT VECTOR (TV) display added to the IP display a vector that indicates the direction from ownship to the intruder at the predicted point of closest contact (POCC). The length of the vector corresponds to the radius of the protected zone, and the distance of the intersection of the vector with ownship predictor, corresponds to the time available till POCC or loss of separation. Pilots time shared the traffic avoidance task with a secondary task requiring them to monitor the top of the display for faint targets. This task simulated the visual demands of out-of-cockpit scanning, and hence was used to estimate the head-down time required by the different display formats. The results revealed that both display augmentations improved performance (safety) as assessed by predicted and actual loss of separation (i.e., penetration of the protected zone). Both enhancements also reduced workload, as assessed by the NASA TLX scale. The intruder predictor display produced these benefits with no substantial impact on the qualitative nature of the avoidance maneuvers that were selected. The threat vector produced the safety benefits by inducing a greater degree of (effective) lateral maneuvering, thus partially offsetting the benefits of reduced workload. The three displays did not differ in terms of their effect on performance of the monitoring task, used to infer head-down time, nor in the extent of vertical or airspeed maneuvering. The results are discussed in terms of their implications for 19 cognitive engineering design features.

Wickens, Christopher D.↗

Autotasked Performance in the NAS Workload: A Statistical Analysis

A statistical analysis of the workload performance of a production quality FORTRAN code for five different Cray Y-MP hardware and system software configurations is performed. The analysis was based on an experimental procedure that was designed to minimize correlations between the number of requested CPUs and the time of day the runs were initiated. Observed autotasking over heads were significantly larger for the set of jobs that requested the maximum number of CPUs. Speedups for UNICOS 6 releases show consistent wall clock speedups in the workload of around 2. which is quite good. The observed speed ups were very similar for the set of jobs that requested 8 CPUs and the set that requested 4 CPUs. The original NAS algorithm for determining charges to the user discourages autotasking in the workload. A new charging algorithm to be applied to jobs run in the NQS multitasking queues also discourages NAS users from using auto tasking. The new algorithm favors jobs requesting 8 CPUs over those that request less, although the jobs requesting 8 CPUs experienced significantly higher over head and presumably degraded system throughput. A charging algorithm is presented that has the following desirable characteristics when applied to the data: higher overhead jobs requesting 8 CPUs are penalized when compared to moderate overhead jobs requesting 4 CPUs, thereby providing a charging incentive to NAS users to use autotasking in a manner that provides them with significantly improved turnaround while also maintaining system throughput.

Carter, R. L.↗

The Primary Flight Display and Its Pathway Guidance: Workload, Performance, and Situation Awareness

In two experiments carried out in a high fidelity general aviation flight simulator, 42 instrument rated pilots flew a pathway-in-the-sky (tunnel) display through a series of multi-leg curved stepdown approaches through mountainous terrain. Both experiments examined how properties of the tunnel influenced flight path tracking performance, traffic awareness, terrain awareness and workload (assessed both by subjective and secondary task performance measures). Experiment 1, flown in simulated VMC, compared high and low intensity tunnels, with a less cluttered follow-me-airplane (FMA). The results revealed that both tunnels supported better flight path tracking than the FMA, because of the availability of more preview information. Increasing tunnel intensity, while reducing subjective workload, had no benefit on tracking, and degraded traffic detection performance. In Experiment 2, flown mostly in IMC, the low intensity tunnel was flown with a large (10 inch x 8 inch) and small (8 inch x 6.5 inch) display, representing a geometric field of view (GFOV) of either 30 degrees or 60 degrees. Most measures of flight path tracking performance favored the smaller display, and particularly the 60 degree GFOV, which presented a smaller appearing tunnel, and a wider range of terrain depiction. The larger GFOV also supported better terrain awareness, and yielded a lower secondary task assessment of workload. In both experiments, the final landing approach was terminated by a runway obstruction, and the tunnel guided pilots on a missed approach. In nearly all cases, pilots failed to notice an air hazard that lay in the missed approach path, but was only depicted in the outside view.

Wickens, Christopher D.↗

An Investigation of the Combined Effect of Stress, Fatigue and Workload on Human Performance: Position Paper

Stress, fatigue, and workload affect worker performance. NSF reported that 61% of respondents state losing concentration at work while 79% occasionally or frequently made errors as a result of being fatigued. Shift work, altered work schedules, long hours of continuous wakefulness, and sleep loss can create sleep and circadian disruptions that degrade waking fundions causing stress and fatigue. Review of the literature has proven void of information that links the combined effects of fatigue, stress, and workload to human performance. This paper will address which occupational factors within stress, fatigue, and workload were identified as occupational contributors to performance changes. The results of this research will be apglied to underlying models and algorithms that will help predict performance changes in control room operators.

Mock, Jessica↗

The Impact of Data Communications Messages in the Terminal Area on Flight Crew Workload and Eye Scanning

This paper, to accompany a discussion panel, describes a collaborative FAA and NASA research study to determine the effect Data Communications (Data Comm) messages have on flight crew workload and eye scanning behavior in busy terminal area operations. In the Next Generation Air Transportation System Concept of Operations, for the period 2017-2022, the FAA envisions Data Comm between controllers and the flight crew to become the primary means of communicating non-time critical information. Four research conditions were defined that span current day to future equipage levels (Voice with Paper map, Data Comm with Paper map, Data Comm with Moving Map Display with ownship position displayed, Data Comm with Moving Map, ownship and taxi route displayed), and were used to create arrival and departure scenarios at Boston Logan Airport. Preliminary results for workload, situation awareness, and pilot head-up time are presented here. Questionnaire data indicated that pilot acceptability, workload, and situation awareness ratings were favorable for all of the conditions tested. Pilots did indicate that there were times during final approach and landing when they would prefer not to hear the message chime, and would not be able to make a quick response due to high priority tasks in the cockpit.

Comstock, James R., Jr.↗

Effects of Autonomous sUAS Separation Methods on Subjective Workload, Situation Awareness, and Trust

The Unmanned Aircraft System (UAS) Traffic Management (UTM) concept was designed to support autonomous small UAS operations at a large-scale and without direct human intervention. However, human-autonomy interactions will be impacted by situation awareness, workload, and trust in the autonomy. Method: Nine participants monitored live small UAS operations in a representative UTM system during a series of traffic conflict scenarios and then provided subjective responses regarding situation awareness, workload, and trust in the autonomous separation method. The study employed a 3 (Separation Method: Autonomous Sense and Avoid, Geofence, Manual) × 2 (Incursion: High, Medium) within subjects design. Results: Situation awareness ratings for both autonomous separation methods were significantly lower than the manual condition. An interaction indicated differential workload ratings for the Autonomous Sense and Avoid separation ratings. Trust ratings significantly dropped when the Geofencing separation method failed. Conclusion: Subjective responses of remote operators in the UTM system are affected by the vehicle separation methods. Operators’ understanding of decisions made by the autonomous systems onboard the vehicle likely influence this effect

UAS↗

Parallel Particle Advection Bake-Off for Scientific Visualization Workloads

There are multiple algorithms for parallelizing particle advection for scientific visualization workloads. While many previous studies have contributed to the understanding of individual algorithms, our study aims to provide a holistic understanding of how algorithms perform relative to each other on various workloads. To accomplish this, we consider four popular parallelization algorithms and run a “bake-off” study (i.e., an empirical study) to identify the best matches for each. The study includes 216 tests, going to a concurrency of up to 8192 cores and considering data sets as large as 34 billion cells with 300 million particles. Overall, our study informs three important research questions: (1) which parallelization algorithms perform best for a given workload?, (2) why?, and (3) what are the unsolved problems in parallel particle advection? In terms of findings, we find that the seeding box is the most important factor in choosing the best algorithm, and also that there is a significant opportunity for improvement in execution time, scalability, and efficiency.

Pugmire, Dave↗

Heart Rate Variability as a Measure of Airport Ramp-Traffic Controllers Workload

Heart Rate Variability (HRV) has been reported to reflect the person's cognitive and emotional stress levels, and may offer an objective measure of human-operator's workload levels, which are recorded continuously and unobtrusively to the task performance. The present paper compares the HRV data collected during a human-in-the-loop simulation of airport ramp-traffic control operations with the controller participants' own verbal self-reporting ratings of their workload.

workload↗

Evaluation of Performance, Fatigue and Workload during Real-time, Reactive Telerobotic Mission Control Operations

Telerobotic operations involve a user operating a robot from a different location from where the activity is taking place. It can be difficult for humans to maintain performance when faced with physiological stressors, such as fatigue or illness. Operations require vigilance for extended periods, raising safety concerns surrounding operator’s fatigue and workload. Every hour of wakefulness increases the drive to sleep, causing decreased reaction time (RT), increased lapses in attention (RT > 500 ms), and decreased memory capability. The NASA Task Load Index (NASA-TLX) was created to evaluate the multiple attributes surrounding workload (e.g., mental and physical demands). The upcoming Volatiles Investigating Polar Exploration Rover (VIPER) mission involves remotely controlling a lunar vehicle from an Earth-based mission control station. The goal of VIPER is to excavate the moon for volatiles (water) deep in the surface near the South Pole for a 100-day, continuous operation.

Fatigue↗

Predictive Model for Workload in Remote Operators During sUAS Contingency Scenarios

The increase in automated capabilities of small Uncrewed Aerial Systems (sUAS) has enabled the human operators to manage larger numbers of vehicles simultaneously. As this happens, the operational paradigm shifts to an m:N configuration where multiple operators (m) are managing multiple vehicles (N) together. However, many questions about how operators will interact with each other and share interaction across the vehicle pool are yet unanswered. Therefore, stakeholders from government and industry have partnered to develop ground control station concepts for such operations. The work presented in this paper aims to identify factors that contribute to operator workload. A supervised machine learning-based method built using Support Vector Machines and K-fold cross-validation was used to create workload prediction models for various NASA TLX subscales by leveraging features related to interactions and their relative timings during m:N operations. Results show that the models yielded fairly high predictive accuracies ranging from ~60-75%.

workload prediction↗

The WorkQueue project: A task queue for the CMS workload management system

We present the development and first experience of a new component (termed WorkQueue) in the CMS workload management system. This component provides a link between a global request system (Request Manager) and agents (WMAgents) which process requests at compute and storage resources (known as sites). These requests typically consist of creation or processing of a data sample (possibly terabytes in size). Unlike the standard concept of a task queue, the WorkQueue does not contain fully resolved work units (known typically as jobs in HEP). This would require the WorkQueue to run computationally heavy algorithms that are better suited to run in the WMAgents. Instead the request specifies an algorithm that the WorkQueue uses to split the request into reasonable size chunks (known as elements). An advantage of performing lazy evaluation of an element is that expanding datasets can be accommodated by having job details resolved as late as possible. The WorkQueue architecture consists of a global WorkQueue which obtains requests from the request system, expands them and forms an element ordering based on the request priority. Each WMAgent contains a local WorkQueue which buffers work close to the agent, this overcomes temporary unavailability of the global WorkQueue and reduces latency for an agent to begin processing. Elements are pulled from the global WorkQueue to the local WorkQueue and into the WMAgent based on the estimate of the amount of work within the element and the resources available to the agent. WorkQueue is based on CouchDB, a document oriented NoSQL database. The WorkQueue uses the features of CouchDB (map/reduce views and bi-directional replication between distributed instances) to provide a scalable distributed system for managing large queues of work. The project described here represents an improvement over the old approach to workload management in CMS which involved individual operators feeding requests into agents. This new approach allows for a system where individual WMAgents are transient and can be added or removed from the system as needed.

Ryu, S.↗

Early Evaluation of Fugaku A64FX Architecture Using Climate Workloads

The Energy Exascale Earth System Model (E3SM) Project is an ongoing, state-of-the-science Earth system modeling, simulation, and prediction project that targets efficient utilization of U.S. Department of Energy’s (DOE) supercomputers to meet the science needs of the nation and the mission needs of DOE. This work focuses on our early evaluation of the A64FX architecture on Fugaku supercomputer using E3SM benchmarks. We will present results that track hardware trends, facilitate architecture comparison and the specific impact on our workload using an atmospheric model benchmark. We have two variants of the code written in Fortran and C++/Kokkos respectively which were used to collect data on a variety of CPU and GPU platforms. Furthermore, we have conducted a comparative evaluation of the compilers on the A64FX architecture and found GNU to be the best performer for our workload. Our experience so far indicates that Fugaku/A64FX shows promising energy efficiency (performance/Watt) with further performance gains possible through architecture-aware optimization efforts.

Sreepathi, Sarat↗

Power Profile Monitoring and Tracking Evolution of System-Wide HPC Workloads

The power & energy demands of HPC machines have grown significantly. Modern exascale HPC systems require tens of megawatts of combined power for computing resources and cooling facilities at full capacity. The current energy trend is not sustainable for future HPC systems, and there is a need to work toward the energy efficiency aspect of HPC performance. Energy awareness of the HPC applications at the job level is essential for running an efficient HPC system. This work aims to develop a pipeline to provide a production-level system-wide overview of the HPC workloads' power profile while handling evolving workloads exhibiting new power trends. We developed an open-set classification model for HPC jobs based on the properties of power profiles to continuously provide a system-wide holistic view of recently completed jobs. The pipeline helps continuously monitor the job-level power usage pattern of HPC and enables us to capture the new trends in applications' power behavior. We employed a comprehensive set of techniques to generate job-level data, custom-designed feature extraction methods to extract critical features from jobs' power profiles, clustering techniques powered by generative modeling, and open-set classification for identifying job profiles into known classes or an unknown set. With extensive evaluations, we demonstrate the effectiveness of each component in our pipeline. We provide an analysis of the resulting clusters that characterize the power profile landscape of the Summit supercomputer from more than 60K jobs executed in a year. The open-set classification classifies the known data sets into known classes with high accuracy and identifies unknown data noints with over 85% accuracy.

Karimi, Ahmad Maroof↗

SU-F-T-101: Insight into Dosimetry Workload and Planning Timelines: A 6 Year Review at One Institution

Purpose: To elucidate realistic clinical treatment planning workload and timelines to improve understanding for patients, payers, and other institutions involved in radiotherapy processes. Methods: A web based tool was developed using Oracle Express (Oracle Corp, Redwood City, CA) which allowed communication between the physicians and staff about the current state of the patient plan. For 6 years, all patient courses were logged and time-stamped in 22 discreet steps which detailed start and stop times for simulation, contouring, and treatment planning tasks. This data was combined with the treatment planning database (TPDB) using the Eclipse Scripting API (Varian Medical Systems, Palo Alto, CA) to cross-identify plans between the two systems. This time data was analyzed across our dosimetry staff and treatment modality. Results: In 6 years, 110,477 patient statuses were time-logged for 9683 courses of treatment using our internal software. The courses contained 8305 unique patients who were binned into one of 11 diagnosis site categories. 8253 courses could be reconciled against the TPDB using timestamp data from patient statuses. The average planning volume per dosimetrist was 375.8 ± 142.4 plans per year with the average number of planning revisions per dosimetrist of 71.0 ± 27.1 plans per year. The median treatment planning times by modality ranged from to 48.3 hours for IMRT plans 5 fields or less to 119.6 hours for IMRT with 8 or more fields. Two arc VMAT, three arc VMAT, and 3D plans median times were 89.1 hours, 113.8 hours, and 50.9 hours respectively. Conclusion: Using our web based tool, we have demonstrated the ability to quantify treatment planning timelines and workloads which could help in setting appropriate expectations for patients, payers, and hospital administration. COI: Author received monies from Varian Medical Systems for research and teaching honorarium.

60 APPLIED LIFE SCIENCES↗

Comparative I/O workload characterization of two leadership class storage clusters. In: PDSW '15 Proceedings of the 10th Parallel Data Storage Workshop

The Oak Ridge Leadership Computing Facility (OLCF) is a leader in large-scale parallel file system development, design, deployment and continuous operation. For the last decade, the OLCF has designed and deployed two large center-wide parallel file systems. The first instantiation, Spider 1, served the Jaguar supercomputer and its predecessor, Spider 2, now serves the Titan supercomputer, among many other OLCF computational resources. The OLCF has been rigorously collecting file and storage system statistics from these Spider systems since their transition to production state. In this paper we present the collected I/O workload statistics from the Spider 2 system and compare it to the Spider 1 data. Our analysis show that the Spider 2 workload is more more write-heavy I/O compared to Spider 1 (75% vs. 60%, respectively). The data also show the OLCF storage policies such as periodic purges are effectively managing the capacity resource of Spider 2. Furthermore, due to improvements in tdm_multipath and ib_srp software, we are utilizing the Spider 2 system bandwidth and latency resources more effectively. The Spider 2 bandwidth usage statistics shows that our system is working within the design specifications. However, it is also evident that our scientific applications can be more effectively served by a burst buffer storage layer. All the data has been collected by monitoring tools developed for the Spider ecosystem. We believe the observed data set and insights will help us better design the next-generation Spider file and storage system. It will also be helpful to the larger community for building more effective large-scale file and storage systems.

Gunasekaran, Raghul↗

Tuyere: Enabling Scalable Memory Workloads for System Exploration

Memory technologies are under active development. Meanwhile, workloads on contemporary computing systems are increasing rapidly in size and diversity. Such dynamics in hardware and software further widen the gap between memory system design and performance evaluation. In this work, we propose a data-centric abstraction of high-performance computing applications for fast exploration of new memory technologies. We also provide a framework that uses a formal modeling language to describe the abstraction, automatically translates abstractions into memory traffic, and directly interfaces with cycle-accurate simulators. We evaluated the framework using 20 workloads and validated the memory traffic profile, the simulation results, and the relative memory changes of four memory technologies. Our results show that the data-centric abstraction can accurately capture application behavior adaptable to different input problems and can expedite system exploration.

Peng, Ivy Bo↗

Evaluating HPC Scheduling Strategies for Urgent Workloads

Scientific computing centers increasingly face workloads with diverse urgency requirements, driven by applications that demand rapid or even immediate execution. Appropriately configured scheduling policies can significantly improve both user satisfaction and overall cluster utilization. In this work, we present a systematic analysis of scheduler configurations under scenarios where a fraction of jobs have urgent computing needs. We evaluate multiple job scheduling simulators, develop a lightweight job-submission emulation framework, and create tools to analyze and visualize the resulting scheduling data. Our study identifies key trade-offs between responsiveness, fairness, and efficiency, and offers a set of practical scheduling configurations (particularly for Slurm) that can be tailored to HPC environments supporting mixed-urgency workloads.

Maheshwari, Ketan [ORNL] (ORCID:000000033800662X)↗