Search NASA⌕ Search

SEARCH · Search NASA

Results for “runtime performance”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

DARMA-Kokkos Data and Execution Interoperability WBS 2.3.1.04 Milestone 16 (ECP Milestone Report)

DARMA (Distributed Asynchronous Resilient Models for Applications) is a runtime library supporting the Sandia ATDM (Advanced Technology Development and Mitigation) program. The main application drivers fall within the ECP milestone 2.2.5.03 ADNN03-ASC ATDM SNL Application, which includes applications that require load balancing and asynchronous communication for high performance. The DARMA runtime infrastructure has been modified to be compatible with Kokkos/OpenMP parallelization within tasks, which is a critical requirement for high performance for the Sandia ATDM apps. DARMA development has occurred in parallel with a verification milestone for ATDM in FY18. For FY19, DARMA should impact ATDM by enabling dynamic load balancing and communication through only incremental changes to the existing verified MPI codes. DARMA can now support the intra-kernel thread parallelization in the parent MPI apps, allowing DARMA to be easily added without rewriting individual math kernels. The results presented here demonstrate the DARMA results for an MPI mini-app.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Graph Algorithms in PGAS: Chapel and UPC++

The Partitioned Global Address Space (PGAS) programming model can be implemented «««< HEAD either with programming language features or with runtime library APIs, each implementation favoring different aspects (e.g., productivity, abstraction, flexibility, or performance). Certain language and runtime features, such as collectives, explicit and asynchronous communication primitives, and constructs facilitating overlap of communication and computation (such as futures and conjoined futures) can enable better performance and scaling for irregular applications, in particular for distributed graph analytics. We compare graph algorithms in one of each of these environments: the Chapel PGAS programming language and the UPC++ PGAS runtime library. We implement algorithms for breadth-first search and triangle counting graph kernels in both environments. We discuss the code in each of the environments, and compile performance data on a Cray Aries and an Infiniband platform. Our results show that the library-based approach of UPC++ currently provides strong performance while Chapel provides a high-level abstraction that, harder to optimize, still provides comparable performance. We argue that various language primitives and runtime library features should be considered in conjunction with each other to design future graph analytics libraries so as to incorporate the best of both worlds.

Distributed Algorithms, Graph algorithms, HPC↗
DOE OSTI2022

CALORIE: A Constraint Language and Optimizing Runtime for Exascale Power Management (Final Report)

This final technical report summarizes the key accomplishments on the CALORIE project, a DOE Early Career award received by PI Henry Hoffmann at the University of Chicago. CALORIE’s main goal was to create principled methodologies, tools, and practices to help scientists and high-performance computing (HPC) operators maximize the performance and insights obtained from scientific computing applications in the face of exascale power constraints. The project accomplished these goals by completing the following objectives: • Designing a language for describing application goals (including constraints and objectives) and system capabilities. The application goals will include things like which simulations or simulations plus in situ analysis will be run together, what the power constraints are, and what requirements there are for in situ analysis (for example, a desired frame rate for visualization). The system capabilities include all components that can be adjusted to tradeoff power and performance. • Designing a runtime system that takes specified goals and capabilities and dynamically determines what capabilities to use to meet the goals. This runtime adapts to changes in goals, application behavior, or available capabilities to automatically maintain the goals despite unexpected disturbances. • Developing a foundational understanding of how power constraints affect the problem of scheduling applications in large-scale systems. This report provides an overview of the accomplishments related to each of these key objectives.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Performance analysis and optimization for scalable deployment of deep learning models for country-scale settlement mapping on Titan supercomputer

Here, we present a scalable object detection workflow for detecting objects, such as settlements, from remotely sensed (RS) imagery. We have successfully deployed this workflow on Titan supercomputer and utilized it for the task of mapping human settlement at a country scale. The performance of various stages in the workflow was analyzed before making it operational. The workflow implemented various strategies to address issues such as suboptimal resource utilization and long-tail effects due to unbalanced image workload, data loss due to runtime failures, and maximum wall-time constraints imposed by Titan's job scheduling policy. A mean shift clustering–based static load balancing strategy was implemented, which partitions the image load such that each partition contained similar-sized images. Furthermore, a checkpoint-restart strategy was added in the workflow as a fault-tolerance mechanism to prevent the data losses due to unforeseen runtime failures. The performance of the above-mentioned strategies was observed in various scenarios, such as node failure, exceeding wall time, and successful completion. Using this workflow, we have examined an RS data set that has a spatial resolution of 0.31 m and is comprised of 685 675 km 2 of area of the Republic of Zambia in under six hours using 5426 nodes of the Titan supercomputer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

TBAA20: Task-Based Algorithms and Applications

The new challenges posed by Exascale system architectures have resulted in difficulty achieving a desired scalability using traditional distributed ­memory runtimes. Task­-based programming models show promise in addressing these challenges, providing application developers with a productive and performant approach to programming on next generation systems. Empirical studies show that task-based models can overcome load ­balancing issues that are inherent to traditional distributed ­memory runtimes, and that task-­based runtimes perform comparably to those systems when balanced. This panel is designed to explore the advantages of task-­based programming models on modern and future HPC systems from an industry, university, and national lab perspective. It aims at gathering application experts and proponents of these models to present concrete and practical examples of using task­-based runtimes to overcome the challenges posed by Exascale system architectures. This report describes the objectives, activities, and outcomes of the panel TBAA: Task­-Based Algorithms and Applications which was held at the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 20) on November 18, 2020.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Performance Analysis and Optimization for Scientific Data Workloads

Scientific data generated at experimental and observational facilities are increasingly being processed on large-scale compute systems. Most of the experimental data analysis workflows are not designed or implemented to run on large scale environments and take full advantage of HPC compute and storage resources. These applications are unlike the traditional tightly-coupled scientific applications and hence face significant performance and scalability challenges as the volume of data increases exponentially. In this paper, we conduct a performance and scalability analysis for experimental analysis applications and workflows operating on data from light sources. Our analysis detects and quantifies I/O performance, scalability and runtime bottlenecks for three data analysis applications that run on NERSC resources. Based on our analysis we propose and implement a set of optimizations that lead to reducing the amount of time spent on I/O operations by almost 90%.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2024

Launch Complex 39B, SWMU 009, 2023 Performance Monitoring and Air Sparge Expansion Construction Completion Report, Kennedy Space Center, Florida

The 2023 Performance Monitoring and Construction Completion Report (PM-CCR) presents the findings, observations, and results for Air Sparging (AS) operations and expansion activities, as well as sitewide groundwater monitoring for Launch Complex 39B (LC39B), Solid Waste Management Unit (SWMU) 009, at Kennedy Space Center (KSC), Florida. The reporting period for activities covered under this PM-CCR is from January 1, 2023, to December 31, 2023. At LC39B, AS operations began in 2017 in the area west of the launch pad, in the liquid oxygen (LOX) tank area located northwest of the launch pad, and in an area outside of the perimeter fence to protect nearby Outstanding Florida Waters (OFW). The LC39B AS system was installed with 279 AS wells to depths ranging from 23 to 60 feet below land surface (bls), including the sump, correlating to top of screen depths ranging from 20 to 57 feet bls. In December 2022, a total of 22 AS wells were abandoned to support launch pad crane operations, and in November 2023, the system was expanded with five additional AS wells installed to 13 or 17 feet bls near the LOX tank. The remedial objective of the LC39B AS Interim Measure (IM) is to actively decrease concentrations of contaminants of concern (COCs) in groundwater, specifically trichloroethene (TCE), cis-1,2-Dichloroethene (cDCE), and vinyl chloride (VC), to less than their respective Natural Attenuation Default Concentrations (NADCs), so LC39B can transition into a Long-Term Monitoring (LTM) program. This PM-CCR presents the following information for LC39B: • AS system operations and maintenance (O&M) (Year 7 of operation) from January 2023 to December 2023, to include AS trailer relocation in March 2023 and subsequent replacement and re-start in June 2023. • Construction completion details for AS system expansion, which included installation of five new AS wells and one new monitoring well in November 2023. As part of expansion activities, soil samples were also collected for petroleum analysis; no exceedances were identified, and no further investigation for petroleum is warranted. • Performance monitoring results for groundwater sampling events conducted in May/June 2023 (30 wells) and November 2023 (31 wells) in the AS IM area and in the Low Concentration Plume (LCP) areas located north and east of the launch pad for volatile organic compound (VOC) analysis. • Sampling results for one monitoring well, LOX-IW0012S, which is sampled for aluminum on an annual basis (May/June 2023). This well was resampled in November 2023 for both total and dissolved aluminum. Due to a communication error with the laboratory, the May/June 2023 sample was analyzed for total aluminum only. • Groundwater sampling results for per- and polyfluoroalkyl substances (PFAS) collected from seven monitoring wells during the May/June 2023 event to further investigate the Former Sewage Treatment Plant #6 and Percolation Pond area, west of the launch pad. O&M and performance monitoring results show that the AS system at LC39B is operating as designed and meeting performance criteria. Overall runtime was 45 percent (%) during the reporting period (January to December), but the operational runtime was 78% during the timeframe when the system could run (June to December). The most significant downtime contributor was post-launch crane operations following the Artemis launch on November 16, 2022, which lasted until June 2023. During that timeframe, the AS trailer at LC39B was relocated to another KSC remediation site (Wilson Corners) and was subsequently replaced with the AS trailer from the Paint & Oil Locker (POL) remediation site at KSC to resume AS system operations. Performance monitoring results in the AS IM and LCP areas continue to show reduction in COC concentrations over time when compared to baseline levels. In 2023, only one monitoring well (MW0048) detected a COC exceeding its NADC (VC at 740 micrograms per liter [µg/L]), which marks the baseline result for this new well installed during system expansion. Across the rest of the site, VC concentrations have declined or remained stable during the 2023 sampling events. Excluding MW0048, the highest VC result in 2023 was during the May/June sampling event with a concentration of 63 µg/L at MW0032, which is located near MW0048 and the AS expansion area by the LOX tank. TCE was detected in select monitoring wells in the IM area in 2023, but only two locations exceeded the State of Florida Groundwater Cleanup Target Level (GCTL): MW0032 (21 µg/L in May/June 2023 and 9.1 µg/L in November 2023) and MW0036 (5.0 µg/L in November 2023). MW0036 is also located near the LOX tank, on the north side, where the AS system is still operational (Zone Z4). cDCE and trans-1,2-dichloroethene concentrations were less than laboratory method detection limits or their respective GCTLs in all wells sampled in 2023. Near the OFW located northwest of the launch complex, all COC concentrations were less than laboratory method detection limits from monitoring wells (MW0039, MW0040, and LOXTA0002S) sampled in 2023. Aluminum results from LOX-IW0012S, which has been sampled routinely since 2006, detected a total aluminum concentration of 3,900 µg/L during the May/June 2023 sampling event. Results from the November 2023 event detected 5,700 µg/L for total aluminum and 5,500 µg/L for dissolved aluminum. These concentrations slightly decreased from the previous year but remain relatively consistent with historical detections. Aluminum will continue to be sampled on an annual basis at this well as results still exceed the GCTL of 200 µg/L and the Upper Limit of the KSC Background Concentration of 280 µg/L. PFAS results detected nine different PFAS compounds (out of 32 analyzed) from seven wells sampled. Two PFAS compounds, perfluorooctanesulfonic acid (PFOS) and perfluorooctanoic acid (PFOA), currently have FDEP Provisional GCTLs of 70 nanograms per liter (ng/L). All seven samples collected resulted in concentrations less than the FDEP Provisional GCTLs for both PFAS compounds; no exceedances were observed. PFOS and PFOA also have assigned United States Environmental Protection Agency (USEPA) Maximum Contaminant Levels (MCLs) of 4 nanograms per liter (ng/L). None of the PFOS results exceeded the USEPA MCLs. PFOA was detected in two samples above the USEPA MCL at concentrations of 5.8 ng/L (ECS-IW0009I) and 5.5 ng/L (ECS-IW0009S). Three other PFAS compounds, perfluorohexanesulfonic acid (PFHxS), perfluoro-n-nonanoic acid (PFNA), and hexafluoropropylene oxide dimer acid (GenX), currently have USEPA MCLs of 10 ng/L. PFHxS, PFNA, and GenX were not detected at concentrations greater than their respective USEPA MCLs in any of the seven wells. PFAS compounds without FDEP Provisional GCTLs or USEPA MCLs were screened against USEPA RSLs. No other detections exceeded their respective USEPA RSLs. Additional PFAS sampling will be conducted as part of a future PFAS Site Assessment. Based on O&M activities and performance monitoring, the following is recommended for LC39B: • Continue with Year 8 AS system operation within Zone Z4, which includes the AS expansion area. Zone Z3, which has been off since 2018, should remain off as no rebound has been observed. Zones Z1 and Z2, which were turned off at the end of 2022, will remain shut down as monitoring well results have consistently been below GCTLs or have low-level detections with stable or decreasing trends (Meeting Minute 2402-M10, Decision 2402-D30). • Continue with performance monitoring in 2024 with the same monitoring well network as 2023, except with the addition of MW0048 in both semi-annual events. Baseline concentrations for this well were collected during the November 2023 performance monitoring event. Semi-annual sampling should be planned for the May 2024 and November 2024 timeframes (Meeting Minute 2402-M10, Decision 2402-D31). • Continue sampling monitoring well, LOX-IW0012S, for aluminum (total and dissolved) on an annual basis in May 2024. It is also recommended to re-develop this well prior to the next sampling event (Meeting Minute 2402-M10, Decision 2402-D32). The above recommendations for LC39B were presented at the February 2024 KSCRT Meeting, with Team consensus reached on the path forward. The contents of this PM-CCR were also presented at this meeting.

Deborah M Wilson↗
DOE OSTI2018

Online Diagnosis of Performance Variation in HPC Systems Using Machine Learning

As the size and complexity of HPC systems grow in line with advancements in hardware and software technology, HPC systems increasingly suffer from performance variation due to shared resource contention as well as software- and hardware-related problems. Such performance variations can lead to failures and inefficiencies, and are among the main challenges in system resiliency. To minimize the impact of performance variation, one must quickly and accurately detect and diagnose the anomalies that cause the variation and take mitigating actions. However, it is difficult to identify anomalies based on the voluminous, high-dimensional, and noisy data collected by system monitoring infrastructures. This paper presents a novel machine learning based framework to automatically diagnose performance anomalies at runtime. Our framework leverages historical resource usage data to extract signatures of previously-observed anomalies. We first convert the collected time series data into easy-to-compute statistical features. We then identify the features that are required to detect anomalies, and extract the signatures of these anomalies. At runtime, we use these signatures to diagnose anomalies with negligible overhead. Here, we evaluate our framework using experiments on a real-world HPC supercomputer and demonstrate that our approach successfully identifies 98% of injected anomalies and consistently outperforms existing anomaly diagnosis techniques.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Exploring Architectural-Aware Affinity Policies in Modern HPC Runtimes

Modern commodity and High-Performance Computing (HPC) systems are evolving with complex CPU architectures. These architectures now feature higher core and NUMA domain counts and implement features such as hyperthreading. When considering significant differences in hardware configurations, library availability, and hardware-tailored system/software stacks, which could substantially vary from one system to another, performance portability is hard to achieve. Throughout the years, this trend resulted in an increasingly high burden on application developers to fine-tune their workloads for each architecture. This work explores how hardware-dependent aspects such as locality/process/thread affinity affect performance in modern CPU architectures. We focus our study on the Global Memory and Threading (GMT) distributed runtime system as a representative of Partitioned Global Address Space (PGAS) software stacks commonly adopted for productivity. In particular, to appreciate performance implications, we evaluate GMT’s thread affinity policies, and, introduce two new ones which exploit architectural awareness. Finally, we explore alternative NUMA configurations via different process bindings and perform a scalability study on three HPC clusters with varying CPU architectures and NUMA layouts. Our analysis indicates that more complex architectures are more affected by affinity and binding policies and highlights the importance of setting proper runtime configurations to achieve superior performance.

Di Dio Lavore, Ian↗
DOE OSTI2026

Temporal Convolutional Network Using Empirical Mode Decomposition to Detect Faults in Grid Connected Systems

Grid-connected power electronic systems require timely and reliable fault detection to prevent equipment damage and reduce downtime. This paper presents a forecasting-based anomaly detection pipeline that decomposes voltage and current measurements into intrinsic mode functions (IMFs) using empirical mode decomposition (EMD), then trains a causal temporal convolutional network (TCN) on normal-operation IMF data to predict short-horizon future dynamics. Deviations between forecasts and observations are summarized as reliability-weighted residual scores and thresholded per sensor using robust statistics with temporal persistence constraints to suppress false positives. To reduce runtime, EMD is performed on downsampled signals for detection, while raw-rate EMD is applied only within a short region of interest for high-frequency interpretability near detected events. Results on a simulated grid-connected converter system demonstrate that IMF-domain forecasting improves anomaly separability relative to raw-signal forecasting and provides interpretable evidence of faults across decomposition channels.

Sutton, Elizabeth [ORNL] (ORCID:0009000078885935)↗
DOE OSTI2024

AGILE GETRS

AGILE GETRS provides an optimized implementation of DETRS that is faster than vendor optimized libraries for small (< 4000) problem sizes. These small problems sizes are of interest to researchers in the Grid Research Integration and Deployment Center (GRID-C) researching real-time power electronics simulations. In addition to our implementation of DETRS, this code provides a test using Google Benchmark which generates matrices of various sizes, fills them with random numbers, runs GETRS, verifies the solution is correct and reports average runtime and other performance metrics.

Hahn, Steven [Oak Ridge National Laboratory (ORNL)↗
DOE OSTI2021

Exascale models of stellar explosions: Quintessential multi-physics simulation

The ExaStar project aims to deliver an efficient, versatile, and portable software ecosystem for multi-physics astrophysics simulations run on exascale machines. The code suite is a component-based multi-physics toolkit, built on the capabilities of current simulation codes (in particular Flash-X and Castro), and based on the massively parallel adaptive mesh refinement framework AMReX. It includes modules for hydrodynamics, advanced radiation transport, thermonuclear kinetics, and nuclear microphysics. The code will reach exascale efficiency by building upon current multi- and many-core packages integrated into an orchestration system that uses a combination of configuration tools, code translators, and a domain-specific asynchronous runtime to manage performance across a range of platform architectures. The target science includes multi-physics simulations of astrophysical explosions (such as supernovae and neutron star mergers) to understand the cosmic origin of the elements and the fundamental physics of matter and neutrinos under extreme conditions.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2018

Realizing High-Performance Parallel Computing Final Report CRADA No. TC-0319-92

The objectives of this project were to improve the programming environment for scientific applications on shared-memory (SMP) and massively-parallel (MMP) computer systems and to develop high-performance, parallel rational drug design applications. The collaborators, IBM Corp., BioNumerik Pharmaceuticals (BNP), and Lawrence Livermore National Laboratory (LLNL), each brought unique expertise to the project. IBM contributed state-of-the-art SMP and MMP computer systems; BNP provided proprietary quantum mechanical and statistical mechanical molecular dynamics codes and experimental data; and LLNL contributed its high-performance Sisal compilers, runtime systems, and programming tools.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

Real-Time Discovery Services over Large, Heterogeneous and Complex Healthcare Datasets Using Schema-Less, Column-Oriented Methods

We present a service platform for schema-leess exploration of data and discovery of patient-related statistics from healthcare data sets. The architecture of this platform is motivated by the need for fast, schema-less, and flexible approaches to SQL-based exploration and discovery of information embedded in the common, heterogeneously structured healthcare data sets and supporting components (electronic health records, practice management systems, etc.) The motivating use cases described in the paper are clinical trials candidate discovery, and a treatment effectiveness analysis. Following the use cases, we discuss the key features and software architecture of the platform, the underlying core components (Apache Parquet, Drill, the web services server), and the runtime profiles and performance characteristics of the platform. We conclude by showing dramatic speedup with some approaches, and the performance tradeoffs and limitations of others.

Apache Drill Apache Parquet Column Oriented Stores↗
DOE OSTI2024

An exploration of online-simulation-driven portfolio scheduling in Workflow Management Systems

Workflow Management Systems used to automate the execution of scientific workflow applications on parallel and distributed computing platforms must make scheduling decisions at runtime. A large number of workflow scheduling algorithms have been proposed in the literature, but often these algorithms are evaluated based on simplifying assumptions that may not hold in practice. Furthermore, published algorithm evaluation and/or comparison results are necessarily only for a subset of all possible scenarios, and thus may not include scenarios relevant to particular use-cases. Consequently, it is difficult for Workflow Management Systems (WMSs) developers to decide which scheduling algorithm should be implemented. To obviate this difficulty, one possible approach is to implement a portfolio of scheduling algorithms and select the most effective algorithm at runtime. One method for performing this selection is to run an online simulation for each algorithm in the portfolio. The algorithm that leads to the best performance, in simulation, is selected for future use. The above simulation-driven portfolio scheduling (SDPS) approach has been proposed in a few parallel and distributed computing contexts. The main objective of this work is to evaluate the feasibility and potential merit of SDPS if implemented in WMSs. Here we perform this evaluation using simulated WMS executions, where the simulations are instantiated from real-world platform and workflow configurations. Our main finding is that SDPS is on par with or outperforms an approach in which a single algorithm is used, where this algorithm is the one that performs best on average across all our experimental scenarios. Furthermore, we find that SDPS remains an attractive proposition even in the presence of high levels of simulation error and for simulators with relatively low levels of sophistication. In many of our experimental scenarios we find that mitigating simulation error at runtime can further improve performance. Finally, we show that simulation overhead can be made sufficiently low for SDPS to be feasible in practice.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Adaptive Runtime Features For Distributed Graph Algorithms

Performance of distributed graph algorithms can benefit greatly by forming rapport between algorithmic abstraction and the underlying runtime system that is responsible for scheduling work and exchanging messages. However, due to their dynamic and irregular nature of computation, distributed graph algorithms written in different programming models impose varying degree of workload pressure on the runtime. To cope with such vastly different workload characteristics, a runtime has to make several trade-offs. One such trade-off arises, for example, when the runtime scheduler has to choose among alternatives such as whether to execute algorithmic work, or progress the network by probing network buffers, or throttle sending messages (termed flow control). This tradeoff decides between optimizing the throughput of a runtime scheduler by increasing the rate of execution of algorithmic work, and reducing the latency of the network messages. Another trade-off exists when a decision has to be made about when to send aggregated messages in buffers (message coalescing). This decision chooses between trading off latency for network bandwidth and vice versa. At any instant, such trade-offs emphasize either on improving the quantity of work being executed (by maximizing the scheduler throughput) or on improving the quality of work (by prioritizing better work). However, encoding static policies for different runtime features (such as flow control, coalescing) can prevent graph algorithms from achieving their full potential, thus can undermine the actual performance of a distributed graph algorithm . In this paper, we investigate runtime support for distributed graph algorithms in the context of two paradigms: variants of wellknown Bulk-Synchronous Parallel model and asynchronous programming model. We explore generic runtime features such as message coalescing (aggregation) and flow control and show that execution policies of these features need to be adjusted over time to make a positive impact on the execution time of a distributed graph algorithm. Since synchronous and asynchronous graph algorithms have different workload characteristics, not all of such runtime features may be good candidates for adaptation. Each of these algorithmic paradigms may require different set of features to be adapted over time. We demonstrate which set of feature(s) can be useful in each case to achieve the right balance of work in the runtime layer. Existing implementation of different graph algorithms can benefit from adapting dynamic policies in the underlying runtime.

Firoz, Jesun S.↗