Performance and Energy Management in High Performance Computing Systems Using Application-Level Behavioral Attribute Driven Techniques
Explore the source record for details and available documents.
97 MATHEMATICS AND COMPUTING↗
SEARCH · Search NASA
Results for “application behavioral metrics”
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.
Frosted Tracks
SAND2025-01893O Frosted Tracks is a software tool to group trajectories according to sequences of their behavior. The goal is to start with a very large number of trajectories and identify groups that exhibit similar behavior patterns. The application combines TICC and Metric DBSCAN clustering algorithms for behavioral segmentation and labeling of air/sea trajectory data. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.
Dalbey, Keith↗
Quantum error mitigation by hidden inverses protocol in superconducting quantum devices
We present a method to improve the convergence of variational algorithms based on hidden inverses (HIs) to mitigate coherent errors. In the context of error mitigation, this means replacing the hardware implementation of certain Hermitian gates with their inverses. Doing so results in noise cancellation and a more resilient quantum circuit. This approach improves performance in a variety of two-qubit error models where the noise operator also inverts with the gate inversion. We apply the mitigation scheme on superconducting quantum processors running the variational quantum eigensolver (VQE) algorithm to find the H 2 ground-state energy. When implemented on superconducting hardware we find that the mitigation scheme effectively reduces the energy fluctuations in the parameter learning path in VQE, reducing the number of iterations for a converged value. We also provide a detailed numerical simulation of VQE performance under different noise models and explore how HIs and randomized compiling affect the underlying loss landscape of the learning problem. These simulations help explain our experimental hardware outcomes, helping to connect lower-level gate performance to application-specific behavior in contrast to metrics like fidelity which often do not provide an intuitive insight into observed high level performance.
75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
A performance study of the time-varying cache behavior: a study on APEX, Mantevo, NAS, and PARSEC
Cache has long been used to minimize the latency of main memory accesses by storing frequently used data near the processor. Processor performance depends on the underlying cache performance. Therefore, significant research has been done to identify the most crucial metrics of cache performance. Although the majority of research focuses on measuring cache hit rates and data movement as the primary cache performance metrics, cache utilization is significantly important. We investigate the application’s locality using cache utilization metrics. In addition, we present cache utilization and traditional cache performance metrics as the program progresses providing detailed insights into the dynamic application behavior on parallel applications from four benchmark suites running on multiple cores. We explore cache utilization for APEX, Mantevo, NAS, and PARSEC, mostly scientific benchmark suites. Our results indicate that 40% of the data bytes in a cache line are accessed at least once before line eviction. Also, on average a byte is accessed two times before the cache line is evicted for these applications. Moreover, we present runtime cache utilization, as well as, conventional performance metrics that illustrate a holistic understanding of cache behavior. To facilitate this research, we build a memory simulator incorporated into the Structural Simulation Toolkit (Rodrigues et al. in SIGMETRICS Perform Eval Rev 38(4):37–42, 2011). Finally, our results suggest that variable cache line size can result in better performance and can also conserve power.
97 MATHEMATICS AND COMPUTING↗
Drilling Down I/O Bottlenecks with Cross-layer I/O Profile Exploration
I/O performance monitoring tools such as Darshan and Recorder collect I/O-related metrics on production systems and help understand the applications' behavior. However, some gaps prevent end-users from seeing the whole picture when it comes to detecting and drilling down to the root causes of I/O performance slowdowns and where those problems originate. These gaps arise from limitations in the available metrics, their collection strategy, and the lack of translation to actionable items that could advise on optimizations. This paper highlights such gaps and proposes solutions to drill down to the source code level to pinpoint the root causes of I/O bottlenecks scientific applications face by relying on cross-layer analysis combining multiple performance metrics related to I/O software layers. We demonstrate with two real applications how metrics collected in high-level libraries (which are closer to the data models used by an application), enhanced by source-code insights and natural language translations, can help streamline the understanding of I/O behavior and provide guidance to end-users, developers, and supercomputing facilities on how to improve I/O performance. Using this cross-layer analysis and the heuristic recommendations, we attained up to 6.9× speedup from run-as-is executions.
Ather, Hammad↗
Development and Application of Schema Based Occupant-Centric Building Performance Metrics
Occupant behavior can significantly influence the operation and performance of buildings. Many occupant-centric key performance indicators (KPIs) rely on having accurate counts of the number of occupants in a building, which is very different to how occupancy information is currently collected in the majority of buildings today. To address this gap, the authors develop a standardized methodology for the calculation of percent space utilization for buildings, which is formulated with respect to two prevalent operational data schemas: the Brick Schema and Project Haystack. The methodology is scalable across different levels of spatial granularity and irrespective of sensor placement. Moreover, the methods are intended to make use of typical occupancy sensors that capture presence level occupancy and not counts of people. Since occupant-hours is a preferable metric to use in KPI calculations, a method to convert between percent space utilization and occupant-hours using the design occupancy for a space is also developed. The methodology is demonstrated on a small commercial office space in Boulder, Colorado using data collected between June 2018 and February 2019. A multiple linear regression is performed that shows strong evidence for a relationship between building energy consumption and percent space utilization.
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
Compressive properties of silicone Bouligand structures
Abstract This article presents an examination of silicone, Bouligand lattices in compression. Appearing frequently in biological organisms and manufacturing design, Bouligand structures comprise layers of parallel strands or fibers oriented in a helical fashion. They can exhibit exceptional fracture resistance when composed of rigid or composite materials. The behavior of elastomeric Bouligand structures, however, is less well understood. Additively manufactured (AM) elastomeric lattices have applications in stress mitigation, medical devices, and soft robotics. This article demonstrates that Bouligand structures are a useful addition to the design space of AM elastomers. By adjusting the layer-rotation parameters, lattice stress can increase by more than 300% without altering the porosity. Additionally, we introduce path length metrics that help explain the observed relationship between layer rotation and compression response. Impact statement Additive manufacturing (AM) continues to push the boundary of manufacturable structures and enhance the ability to robustly design for specific properties and behaviors. The more we understand the design space of a novel AM microstructure, the greater its application range. In this article, we describe the mechanical behavior of helicoidal, elastomeric lattices and introduce path length metrics to help explain their stress response. We show that these structures can exhibit a large range of mechanical behaviors in compression, making them well suited for applications such as stress mitigation and impact absorption. Additionally, the path length metrics could become useful design tools and may be applicable to a larger set of cellular structures. These findings expand our ability to rapidly design materials with highly specific and customizable properties to meet the needs of modern engineering challenges. Graphical abstract
Van Meerbeek, I. M. (ORCID:000000021258132X)↗
A comparison of metrics to evaluate the effects of hydro-facility passage stressors on fish
Hydropower is the most common form of renewable energy, and countries worldwide are considering expanding hydropower to new areas. One of the challenges of hydropower deployment is mitigation of the environmental impacts including water quality, habitat alterations, and ecosystem connectivity. For fish species that inhabit river systems with hydropower facilities, passage through the facility to access spawning and rearing habitats can be particularly challenging. Fish moving downstream through a hydro-facility can be exposed to a number of stressors (e.g., rapid decompression, shear forces, blade strike and collision, and turbulence), which can all affect fish survival in direct and indirect ways. Many studies have investigated the effects of hydro-turbine passage on fish; however, the comparability among studies is limited by variation in the metrics and biological endpoints used. Future studies investigating the effects of hydro-turbine passage should focus on using metrics and endpoints that are easily comparable. This review summarizes four categories of metrics that are used in fisheries research and have application to hydro-turbine passage (i.e., mortality, injury, molecular metrics, behavior) and evaluates them based on several criteria (i.e., resources needed, invasiveness, comparability among stressors and species, and diagnostic properties). Additionally, these comparisons are put into context of study setting (i.e., laboratory vs. field). Overall, injury and molecular metrics are ideal for studies in which there is a need to understand the mechanisms of effect, whereas behavior and mortality metrics provide information on the whole body response of the fish. The study setting strongly influences the comparability among studies. In laboratory-based studies, stressors can be controlled by both type and magnitude, allowing for easy comparisons among studies. In contrast, field studies expose fish to realistic passage environments but the comparability is limited. Based on these results, future studies, whether lab or field-based, should focus on metrics that relate to mortality for ease of comparison.
fish↗
Fine-Grained Application Energy and Power Measurements on the Frontier Exascale System
The increasing complexity and power/energy demands of heterogeneous exascale systems, such as the Frontier supercomputer, present significant challenges for measuring and optimizing power consumption in applications. Current tools either lack the resolution to capture fine-grained power and energy measurements, fail to validate in-band measurements against out-of-band power sensors, or cannot integrate this information with application performance events in a scalable manner. This paper introduces a novel open-source performance toolkit that integrates extended PAPI components with Score-P plugins to enable in-band, fine-grained power and energy measurements, while also supporting validation using power meter measurements for both CPUs and GPUs. One key contribution is the ability to perform millisecond-level power and energy measurements for AMD MI250X GPUs, mapping them to application performance events within a single trace and measurement system that scales. Our toolkit combines coarse-grained measurements from cray_pm counters with high-resolution metrics from rocm_smi and RAPL, converting GPU instantaneous accumulated energy into power to capture both transient and steady-state power behavior, a capability often missed by out-of-band and monitoring tools. By mapping these metrics to specific application regions, developers can identify energy hotspots, address inefficiencies in GPU kernel execution, and validate in-band measurements against external measurements. We demonstrate the effectiveness of this approach through case studies using benchmarks such as GPU rocblas_sgemm, BLIS c_blas_dgemm, and rocHPL, highlighting the variability of the measurements and the impact of transient power spikes on kernel-level efficiency.
Hernandez Mendoza, Oscar [ORNL] (ORCID:00000002538↗
UMAMI: A Recipe for Generating Meaningful Metrics through Holistic I/O Performance Analysis
I/O efficiency is essential to productivity in scientific computing, especially as many scientific domains become more data-intensive. Many characterization tools have been used to elucidate specific aspects of parallel I/O performance, but analyzing components of complex I/O subsystems in isolation fails to provide insight into critical questions: how do the I/O components interact, what are reasonable expectations for application performance, and what are the underlying causes of I/O performance problems? To address these questions while capitalizing on existing component-level characterization tools, we propose an approach that combines on-demand, modular synthesis of I/O characterization data into a unified monitoring and metrics interface (UMAMI) to provide a normalized, holistic view of I/O behavior. We evaluate the feasibility of this approach by applying it to a month-long benchmarking study on two distinct largescale computing platforms. We present three case studies that highlight the importance of analyzing application I/O performance in context with both contemporaneous and historical component metrics, and we provide new insights into the factors affecting I/O performance. By demonstrating the generality of our approach, we lay the groundwork for a production-grade framework for holistic I/O analysis.
97 MATHEMATICS AND COMPUTING↗
MemFriend: Understanding Memory Performance with Spatial-Temporal Affinity
In HPC applications, memory access behavior is one of the main factors affecting performance. Improving an application’s memory access behavior involves optimizing data layout and/or restructuring code, and requires studying spatial-temporal data locality. Existing data locality analyses focus on single-location metrics and are restricted to evaluating temporal locality. We introduce spatial-temporal affinity metrics that quantify temporal access proximity, forward access correlation, and nearby access correlation between pairs of memory locations. We describe methods for distinguishing between potential vs. realized affinity and for reasoning about affinity at multiple resolutions (3D, 2D, 1D). Finally, we construct spatial-temporal affinity signatures that classify memory behavior and that be used to reason about changes in software (data relayout, code refactoring) or hardware (caching, prefetching). We describe methods for signature visualization, interpretation, and quantitative comparison of signatures. We evaluate our methodology using applications with variants that contrast data structures, data layouts and algorithms. We show that spatial-temporal affinity analysis provides novel insights and enables predictive reasoning about application performance when contrasted with reuse distance analysis.
Suriyakumar, Yasodhadevi↗
Exact solutions of (n+1)-dimensional Yang-Mills equations in curved space-time
In the context of a semiclassical approach where vectorial gauge fields can be considered as classical fields, we obtain exact static solutions of the SU(N) Yang-Mills equations in an (n+1)-dimensional curved space-time, for the cases n=1,2,3. As an application of the results obtained for the case n=3, we consider the solutions for the anti-de Sitter and Schwarzschild metrics. We show that these solutions have a confining behavior and can be considered as a first step in the study of the corrections of the spectra of quarkonia in a curved background. Since the solutions that we find in this work are valid also for the group U(1), the case n=2 is a description of the (2+1) electrodynamics in the presence of a point charge. For this case, the solution has a confining behavior and can be considered as an application of the planar electrodynamics in a curved space-time. Finally we find that the solution for the case n=1 is invariant under a parity transformation and has the form of a linear confining solution. - Highlights: Black-Right-Pointing-Pointer We study exact static confining solutions of the SU(N) Yang-Mills equations in an (n+1)-dimensional curved space-time. Black-Right-Pointing-Pointer The solutions found are a first step in the study of the corrections on the spectra of quarkonia in a curved background. Black-Right-Pointing-Pointer A expression for the confinement potential in low dimensionality is found.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Simulation-aided occupant-centric building design: A critical review of tools, methods, and applications
Occupants are active participants in their built environment, affecting its performance while simultaneously being affected by its design and indoor environmental conditions. With recent advances in computer modeling, simulation tools, and analysis techniques, topics such as human-building interactions and occupant behavior have gained significant interest in the literature given their premise of improving building design processes and operating strategies. In practice, the focus of occupant-centric literature has been mostly geared towards the latter (i.e., operation), leaving the implications on building design practices underexplored. This paper fills the gap by providing a critical review of existing studies applying computer-based modeling and simulation to guide occupant-centric building design. The reviewed papers are organized along four main themes, namely occupant-centric: (i) metrics of building performance, (ii) modeling and simulation approaches, (iii) design methods and applications, and (iv) supporting practices and mechanisms. Important barriers are identified for a more effective application of occupant-centric building design practices, including the limited consideration of metrics beyond energy efficiency (e.g., occupant well-being and space planning), the limited implementation and validation of the proposed methods, and the lack of integration of occupant behavior modeling in existing building performance simulation tools. Finally, future research directions are discussed, covering large-scale international data collection efforts to move from generic assumptions about occupant behavior to specific/localized knowledge, improved metrics of measuring building performance, and improved industry practices, such as building codes, to promote an occupant-in-the-loop approach to the building design process.
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
Data-driven analysis to understand GPU hardware resource usage of optimizations
With heterogeneous systems, the number of GPUs per chip increases to provide computational capabilities for solving science at a nanoscopic scale. However, low utilization for single GPUs defies the need to invest more money in expensive accelerators. Although related work develops optimizations to improve application performance, none studies how these optimizations impact hardware resource usage or average GPU utilization. Here, this paper takes a data-driven analysis approach in addressing this gap by (1) characterizing how hardware resource usage affects device utilization, execution time, or both, (2) presenting a multiobjective metric to identify important application-device interactions that can be optimized to improve device utilization and application performance jointly, (3) studying hardware resource usage behaviors of several optimizations for a benchmark application, and finally (4) identifying optimization opportunities for several scientific proxy applications based on their hardware resource usage behaviors. Furthermore, we demonstrate the applicability of our methodology by applying the identified optimizations to a proxy application, which improves the execution time, device utilization, and power consumption by up to 29.6%, 5.3% and 26.5% respectively.
Computer science↗
Online thermal profile prediction for large format additive manufacturing: A hybrid CNN-LSTM based approach
Large format additive manufacturing (LFAM) is an advanced 3D printing technique that efficiently fabricates large-scale components through a layer-by-layer extrusion and deposition process. Accurate surface layer temperature monitoring is essential to prevent manufacturing failures and ensure final product quality. Traditional physics-based offline approaches for simulating thermal behavior are often inefficient and complex, posing challenges on real-time, in-situ monitoring. Here, to address this, we propose a data-driven hybrid CNN-LSTM model to predict sequential thermal images of arbitrary length using real-time infrared thermal imaging. In this approach, a Convolutional Neural Networks (CNN) is trained offline to capture spatial features, reduce dimensional complexity, and enhance time efficiency, while a stacked Long Short-Term Memory (LSTM) is applied online to capture temporal information for improved prediction of future thermal behavior in subsequent printing layers. Model performance is evaluated using MSE, SSIM, and PSNR metrics and is benchmarked against stacked LSTM and convolutional LSTM models, demonstrating superior accuracy and applicability. Additionally, to mitigate noise from moving extruders and gantry backgrounds in thermal images, a fine-tuned semantic segmentation model is implemented offline to extract printing geometry, enabling precise temperature tracking along the tool path for further thermal analysis. The frameworks developed in this study significantly advance temperature monitoring, thermal analysis, and in-situ manufacturing control for LFAM, bridging the gap between theoretical modeling and practical application.
Geometry extraction↗
PAPI software-defined events for in-depth performance analysis
The methodology and standardization layer provided by the Performance Application Programming Interface (PAPI) has played a vital role in application profiling for almost two decades. It has enabled sophisticated performance analysis tool designers and performance-conscious scientists to gain insights into their applications by simply instrumenting their code using a handful of PAPI functions that “just work” across different hardware components. In the past, PAPI development had focused primarily on hardware-specific performance metrics. However, the rapidly increasing complexity of software infrastructure poses new measurement and analysis challenges for the developers of large-scale applications. In particular, acquiring information regarding the behavior of libraries and runtimes—used by scientific applications—requires low-level binary instrumentation, or APIs specific to each library and runtime. No uniform API for monitoring events that originate from inside the software stack has emerged. In this article, we present our efforts to extend PAPI’s role so that it becomes the de facto standard for exposing performance-critical events, which we refer to as software-defined events (SDEs), from different software layers. Upgrading PAPI with SDEs enables monitoring of both types of performance events—hardware- and software-related events—in a uniform way, through the same consistent PAPI. The goal of this article is threefold. First, we motivate the need for SDEs and describe our design decisions regarding the functionality we offer through PAPI’s new SDE interface. Second, we illustrate how SDEs can be utilized by different software packages, specifically, by showcasing their use in the numerical linear algebra library MAGMA-Sparse, the tensor algebra library TAMM that is part of the NWChem suite, and the compiler-based performance analysis tool Byfl. Third, we provide a performance analysis of the overhead that results from monitoring SDEs and discuss the trade-offs between overhead and functionality.
Jagode, Heike↗
Square Root Statistics of Density Matrices and Their Applications
To estimate the degree of quantum entanglement of random pure states, it is crucial to understand the statistical behavior of entanglement indicators such as the von Neumann entropy, quantum purity, and entanglement capacity. These entanglement metrics are functions of the spectrum of density matrices, and their statistical behavior over different generic state ensembles have been intensively studied in the literature. As an alternative metric, in this work, we study the sum of the square root spectrum of density matrices, which is relevant to negativity and fidelity in quantum information processing. In particular, we derive the finite-size mean and variance formulas of the sum of the square root spectrum over the Bures–Hall ensemble, extending known results obtained recently over the Hilbert–Schmidt ensemble.
97 MATHEMATICS AND COMPUTING↗
Demonstration of the Coating Analysis Capabilities in BISON
In order to improve the accident tolerance of light water reactor (LWR) fuel, coated cladding materials have been proposed which exhibit much slower oxidation kinetics in high-temperature steam than Zr-alloys. This behavior should decrease the energy release due to oxidation and allow the cladding to remain integral longer in the presence of high-temperature steam, making accident mitigation more likely. In order to determine how these coating materials will adjust the behavior of the Zr-alloy cladding during normal reactor operation, simulations have been performed using the Bison fuel performance code. This analysis focused on modeling and comparing the integral thermo-mechanical performance of coated and uncoated zircaloy cladding with uranium dioxide fuel under normal operating conditions. This analysis demonstrates the ability to model a discrete meshed coating bonded to the cladding exterior and provides a comparison with an uncoated fuel rod. A generic range of coating material properties are implemented given the differences and unknowns regarding the proprietary coating properties used by the vendors. A main-effects analysis was performed to identify trends and sensitivities in how coating material properties affect key fuel performance metrics. Lastly, because residual stresses are expected to form in the coating, arising from the high temperature coating application process and application techniques, an additional analysis was performed to identify the impact of these stresses on the cladding behavior. Future analysis efforts will target more comprehensive documentation of this main effects analysis by sampling the results at the beginning and middle-of-life in order to capture important behavior before and during the onset of gap closure.
11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗