Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel application frameworks”

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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Data Analytics for Electrical Distribution Systems with Micro PMUs (GMLC 1.4.9 Technical Report)

This report describes how electrical utilities with residential, industrial, commercial and government customers make decisions using Data Analytics (DA) applications and discusses how OpenFMB was leveraged to share that data among disparate types of devices for DA. OpenFMB is a data standard developed by utilities for distributed communication and control of power system assets. Here we explored how OpenFMB can be used for sharing analytics and what those analytics could be for a set of representative grid devices. A review of DA applications performed by electrical utilities and customers is presented. An overview of how the testbed we used was built and configured is summarized. Several experiments which were carried out to explore the capabilities of OpenFMB alongside other data sharing mechanisms for gathering sensor measurements and sharing analytics is also discussed. And finally a comparison of OpenFMB and LBNL’s SPARK framework is summarized. Today’s electrical utilities focus on monitoring the real-time customer consumptions, offering new real-time tariff models based on customer usage habits (rewards and punishments), providing energy peak during peak load times (plan energy generation and distribution), improving the load management for transformers and power lines, and controlling the energy and grid resources efficiently. On the other hand, the DA applications for residential customers are based on modifying the customer electricity usage habit to save money, making accurate and timely decisions for electrical billing. However, the DA applications for industrial, commercial and government customers focus on creating efficient programs to improve the environmental condition (reducing CO₂ emission), developing better load forecasting for industrial and/or commercial activities. In this project, a testbed was built to explore how the OpenFMB framework can be used to distribute data among various types of representative grid edge devices. Micro PMUs (Phasor Measurement Unit) were used to collect and transmit data to an OpenPDC server alongside relays with a framework configured with a system using OpenFMB to collect and transmit data. The testbed was composed of a physical asset based on a 60 Hz AC radial power system constructed using SI-GRID components. The power system consisted of a 3-phase 14 volts line-to-ground (24 volts line-to-line) power source, three 3-phase line emulators, a programmable resistive load bank, two smart relays, two micro PMUs, and a (SCADA) and Phasor Data Concentrator (PDC) computer. This testbed configuration allowed us to perform breaker operation tests collecting data from the micro PMUs and from the relays’ sensors. During the micro PMU breaker operation tests we collected the measured and estimated fundamental voltages, currents, frequency as well as the total true, reactive and apparent power. The displacement power factor from two micro PMUs located in parallel power lines was also used. The software steps for the implementation of the Synchrophasor system are explained in detail in this report. The setting (1-2-3) and data collection (4-5) phases were performed with a free download open source software. In the setting phase, the micro PMUs were set (1), the data stream for each micro PMU was validated, and the connection and configuration files were created (2). The PDC computer was set using the connection and configuration files of the micro PMUs (3). In the data collection phase, the binary data from the micro PMUs was collected (4), and the binary data files of the micro PMUs was converted to analyze the test results (5). OpenFMB was configured to use protocol translators to read Modbus and transform the reading into the OpenFMB data model to be read for DA applications.Our experiments showed that by leveraging the OpenFMB data model and the micro PMUs together we could obtain better situational awareness of network faults, which in some cases could lead to failures in the system and would be less perceivable otherwise. For example, in one experiment the fundamental RMS current angle, and the fundamental displacement power factor (estimated by the ratio between the measured real and apparent total power) had a disturbance at the micro PMU connected to the beginning of the parallel power line because the breaker was opened without the operators or SCADA system’s knowledge, and no current was available. Based on the breaker state scenarios and micro PMU locations, the DA applications using the current angle and displacement power factor from the micro PMUs should be studied in detail to avoid a non-desired measurement that could affect the decision from the DA. Also, the sample rates for PMU, Relay and micro PMU devices were compared. The DA application improved the control and operation between the electrical utilities and their customers (residential, industrial, transportation, commercial and government). The higher the sample rate, the better the quality of the measurement for DA estimations.

42 ENGINEERING↗
DOE OSTI2017

Building Halo Merger Trees from the Q Continuum Simulation

Cosmological N-body simulations rank among the most computationally intensive efforts today. A key challenge is the analysis of structure, substructure, and the merger history for many billions of compact particle clusters, called halos. Effectively representing the merging history of halos is essential for many galaxy formation models used to generate synthetic sky catalogs, an important application of modern cosmological simulations. Generating realistic mock catalogs requires computing the halo formation history from simulations with large volumes and billions of halos over many time steps, taking hundreds of terabytes of analysis data. We present fast parallel algorithms for producing halo merger trees and tracking halo substructure from a single-level, density-based clustering algorithm. Merger trees are created from analyzing the halo-particle membership function in adjacent snapshots, and substructure is identified by tracking the "cores" of merging halos - sets of particles near the halo center. Core tracking is performed after creating merger trees and uses the relationships found during tree construction to associate substructures with hosts. The algorithms are implemented with MPI and evaluated on a Cray XK7 supercomputer using up to 16,384 processes on data from HACC, a modern cosmological simulation framework. We present results for creating merger trees from 101 analysis snapshots taken from the Q Continuum, a large volume, high mass resolution, cosmological simulation evolving half a trillion particles.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2016

Advances in Geologic Disposal System Modeling and Application to Crystalline Rock

The Used Fuel Disposition Campaign (UFDC) of the U.S. Department of Energy (DOE) Office of Nuclear Energy (NE), Office of Fuel Cycle Technology (OFCT) is conducting research and development (R&D) on geologic disposal of used nuclear fuel (UNF) and high-level nuclear waste (HLW). Two of the high priorities for UFDC disposal R&D are design concept development and disposal system modeling (DOE 2011). These priorities are directly addressed in the UFDC Generic Disposal Systems Analysis (GDSA) work package, which is charged with developing a disposal system modeling and analysis capability for evaluating disposal system performance for nuclear waste in geologic media (e.g., salt, granite, clay, and deep borehole disposal). This report describes specific GDSA activities in fiscal year 2016 (FY 2016) toward the development of the enhanced disposal system modeling and analysis capability for geologic disposal of nuclear waste. The GDSA framework employs the PFLOTRAN thermal-hydrologic-chemical multi-physics code and the Dakota uncertainty sampling and propagation code. Each code is designed for massively-parallel processing in a high-performance computing (HPC) environment. Multi-physics representations in PFLOTRAN are used to simulate various coupled processes including heat flow, fluid flow, waste dissolution, radionuclide release, radionuclide decay and ingrowth, precipitation and dissolution of secondary phases, and radionuclide transport through engineered barriers and natural geologic barriers to the biosphere. Dakota is used to generate sets of representative realizations and to analyze parameter sensitivity.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2019

MAESTROeX: A Massively Parallel Low Mach Number Astrophysical Solver

@e present MAESTROeX, a massively parallel solver for low Mach number astrophysical flows. The underlying low Mach number equation set allows for efficient, long-time integration for highly subsonic flows compared to compressible approaches. MAESTROeX is suitable for modeling full spherical stars as well as well as planar simulations of dynamics within localized regions of a star, and can robustly handle several orders of magnitude of density and pressure stratification. Previously, we have described the development of the predecessor of MAESTROeX, called MAESTRO, in a series of papers. Here, we present a new, greatly simplified temporal integration scheme that retains the same order of accuracy as our previous approaches. We also explore the use of alternative spatial mapping of the one-dimensional base state onto the full Cartesian grid. The code leverages the new AMReX software framework for block-structured adaptive mesh refinement (AMR) applications, allowing for scalability to large fractions of leadership-class machines. Finally, using our previous studies on the convective phase of single-degenerate progenitor models of SNe Ia as a guide, we characterize the performance of the code and validate the new algorithmic features. Like MAESTRO, MAESTROeX is fully open source.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Multi-Source Machine Learning and Thermoplastics Enhanced Aerostructure Manufacturing (mTEAM)

RTX Technology Research Center (RTRC), together with Collins Aerospace (Collins) and Oak Ridge National Laboratory (ORNL) has developed an Artificial Intelligence (AI) / Machine Learning (ML) guided solution to advance the manufacturing and assembly of high performance and lightweight thermoplastic composite (TPC) aerospace products. The solution aims to lower risk, cost and lead time for induction heating based welding and consolidation processes for TPC structure. The cost and lead time of part and material specific process development for induction welding (IW) and induction consolidation will be reduced by replacing traditional empirical methods with optimization methods that merge AI/ML and physics-based process simulations and process experiments with sensing and controls. TPC-IW process development is empirical in nature, and uncertainties in material & process behavior exist near & far from the induction coil. Physics-based simulations can be leveraged directly for process optimization but can be too computationally expensive to run in high fidelity and real time to do robust process optimization. The key impact of successful TPC induction consolidation and welding is cost & lead time reduction for part & material specific consolidation and welding recipes. This is an enabler for more rapid deployment of TPC structures via joining assembly, which can reduce energy & cost intensive usage of autoclaves & ovens. The solution aimed to advance the U.S. Department of Energy’s interests in using thermoplastics and automation in composite manufacturing for improvement of products for existing markets via increased production speeds, reduced costs, and lowered use of energy. Welded TPC structures can offer significant weight & energy savings for high-value commercial aerospace & industrial applications compared to metal & thermoset composite structures assembled by mechanical fastening and/or adhesive bonding. The project was organized into two Budget Periods. Budget Period 1 (BP1) was 15 months and its goal was to perform ML process optimization framework development & deployment on lab-coupon aerostructure components. A Go/No-Go Review was performed at the end of BP1 to verify fulfilment of key tasks & milestones to justify a Go Decision to move into the next Budget Period. Budget Period 2 (BP2) was 12 months and its goal was the deployment of the ML framework for ML process optimization of pilot industrial scale aerostructure components. The overall project aim was to develop & demonstrate ML-enhanced modeling framework that learns process-property mapping from multiple data sources at different fidelities. During BP1, the team accomplished key tasks & milestones to demonstrate the concept of multi-source ML for TPC aerostructure consolidation and assembly. First, the team completed documentation of induction based TPC heating requirements including baseline metrics to compare measured results against. Next the team completed demonstration of data generation from physics-based simulations for ML surrogate model generation and demonstrated the integration of physics-based simulation data into multi-source AI/ML algorithms. In parallel, the team established the lab-coupon scale induction welding system and completed a process to label and reduce generated data from physics-based simulation and experiments for ML surrogate models to enable multi-source ML model training & testing. To complete BP1, the team integrated physics-based simulation data and experimental data into multi-source ML algorithms. This was based on the team completing ML deployment of the induction welding on a lab system at RTRC and AI/ML deployment on existing induction welding line at Collins. ORNL visited both Collins and RTRC sites to witness the TPC induction welding process. Then, ORNL designed and constructed a new version of their vision-based sensing system better adapted to acquire process signals of the TPC induction welding process for process anomaly and defect detection. In BP2, the team accomplished key tasks & milestones to scale up multi-source ML for TPC aerostructure consolidation and assembly from the lab-coupon scale to the pilot-industrial scale. In BP2, the team demonstrated real time anomaly & defect detection via experiments performed by ORNL & RTRC. The team completed ML-optimization heating trials for TPC induction consolidation at Collins, and the team confirmed pilot industrial scale experimental data from Collins was compatible with the developed ML pipeline from RTRC. The team completed sub-element scale ML process optimization demonstration at RTRC, where the team leveraged RTRC’s robotic TPC welding setup to de-risk the ML process optimization by performing ML analysis of recorded temperatures to account for complex part features. Then, the team applied its ML-derived control strategies and ML process optimization framework at Collins to the pilot-industrial scale on a demo skin-stiffener part representative of a nacelle aerostructure fan cowl section. The key innovation is the AI/ML framework enabling effective process development of high performance, lightweight, energy efficient TPCs for composite aircraft structures.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Dynamic Modeling, Trajectory Optimization, and Linear Control of Cable-Driven Parallel Robots for Automated Panelized Building Retrofits

The construction industry faces a growing need for automation to reduce costs, improve accuracy and productivity, and address labor shortages. One area that stands to benefit significantly from automation is panelized prefabricated building envelope retrofits, which can improve a building’s energy efficiency in heating and cooling interior spaces. In this paper, we propose using cable-driven parallel robots (CDPRs), which can effectively lift and handle large objects, to install these panels. However, implementing CDPRs presents significant challenges because of their nonlinear dynamics, complex trajectory planning, and precise control requirements. To tackle these challenges, this work focuses on a new application of established control and trajectory optimization theories in a CDPR simulation of a building envelope retrofit under real-world conditions. We first model the dynamics of CDPRs, highlighting the critical role of damping in system behavior. Building on this dynamic model, we formulate a trajectory optimization problem to generate feasible and efficient motion plans for the robot under operational and environmental constraints. Given the high precision required in the construction industry, accurately tracking the optimized trajectory is essential. However, challenges such as partial observability and external vibrations complicate this task. To address these issues, a Linear Quadratic Gaussian control framework is applied, enabling the robot to track the optimized trajectories with precision. Simulation results show that the proposed controller enables precise end effector positioning with errors under 4 mm, even in the presence of external wind disturbances. Through comprehensive simulations, our approach allows for an in-depth exploration of the system’s nonlinear dynamics, trajectory optimization, and control strategies under controlled yet highly realistic conditions. The results demonstrate the feasibility of CDPRs for automating panel installation and provide insights into their practical deployment.

CDPR↗
DOE OSTI2020

A non-cooperative meta-modeling game for automated third-party calibrating, validating and falsifying constitutive laws with parallelized adversarial attacks

The evaluation of constitutive models, especially for high-risk and high-regret engineering applications, requires efficient and rigorous third-party calibration, validation and falsification. While there are numerous efforts to develop paradigms and standard procedures to validate models, difficulties may arise due to the sequential, manual, and often biased nature of the commonly adopted calibration and validation processes, thus slowing down data collections, hampering the progress towards discovering new physics, increasing expenses and possibly leading to misinterpretations of the credibility and application ranges of proposed models. This work attempts to introduce concepts from game theory and machine learning techniques to overcome many of these existing difficulties. Here, we introduce an automated meta-modeling game where two competing AI agents systematically generate experimental data to calibrate a given constitutive model and to explore its weakness such that the experiment design and model robustness can be improved through competitions. The two agents automatically search for the Nash equilibrium of the meta-modeling game in an adversarial reinforcement learning framework without human intervention. In particular, a protagonist agent seeks to find the more effective ways to generate data for model calibrations, while an adversary agent tries to find the most devastating test scenarios that expose the weaknesses of the constitutive model calibrated by the protagonist. By capturing all possible design options of the laboratory experiments into a single decision tree, we recast the design of experiments as a game of combinatorial moves that can be resolved through deep reinforcement learning by the two competing players. Our adversarial framework emulates idealized scientific collaborations and competitions among researchers to achieve a better understanding of the application range of the learned material laws and prevent misinterpretations caused by conventional AI-based third-party validation. Numerical examples are given to demonstrate the wide applicability of the proposed meta-modeling game with adversarial attacks on both human-crafted constitutive models and machine learning models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Regional-scale fault-to-structure earthquake simulations with the EQSIM framework: Workflow maturation and computational performance on GPU-accelerated exascale platforms

Continuous advancements in scientific and engineering understanding of earthquake phenomena, combined with the associated development of representative physics-based models, is providing a foundation for high-performance, fault-to-structure earthquake simulations. However, regional-scale applications of high-performance models have been challenged by the computational requirements at the resolutions required for engineering risk assessments. The EarthQuake SIMulation (EQSIM) framework, a software application development under the US Department of Energy (DOE) Exascale Computing Project, is focused on overcoming the existing computational barriers and enabling routine regional-scale simulations at resolutions relevant to a breadth of engineered systems. This multidisciplinary software development—drawing upon expertise in geophysics, engineering, applied math and computer science—is preparing the advanced computational workflow necessary to fully exploit the DOE’s exaflop computer platforms coming online in the 2023 to 2024 timeframe. Achievement of the computational performance required for high-resolution regional models containing upward of hundreds of billions to trillions of model grid points requires numerical efficiency in every phase of a regional simulation. This includes run time start-up and regional model generation, effective distribution of the computational workload across thousands of computer nodes, efficient coupling of regional geophysics and local engineering models, and application-tailored highly efficient transfer, storage, and interrogation of very large volumes of simulation data. This article summarizes the most recent advancements and refinements incorporated in the workflow design for the EQSIM integrated fault-to-structure framework, which are based on extensive numerical testing across multiple graphics processing unit (GPU)-accelerated platforms, and demonstrates the computational performance achieved on the world’s first exaflop computer platform through representative regional-scale earthquake simulations for the San Francisco Bay Area in California, USA.

58 GEOSCIENCES↗
NASA NTRS1993

Mapping and monitoring changes in vegetation communities of Jasper Ridge, CA, using spectral fractions derived from AVIRIS images

An important application of remote sensing is to map and monitor changes over large areas of the land surface. This is particularly significant with the current interest in monitoring vegetation communities. Most of traditional methods for mapping different types of plant communities are based upon statistical classification techniques (i.e., parallel piped, nearest-neighbor, etc.) applied to uncalibrated multispectral data. Classes from these techniques are typically difficult to interpret (particularly to a field ecologist/botanist). Also, classes derived for one image can be very different from those derived from another image of the same area, making interpretation of observed temporal changes nearly impossible. More recently, neural networks have been applied to classification. Neural network classification, based upon spectral matching, is weak in dealing with spectral mixtures (a condition prevalent in images of natural surfaces). Another approach to mapping vegetation communities is based on spectral mixture analysis, which can provide a consistent framework for image interpretation. Roberts et al. (1990) mapped vegetation using the band residuals from a simple mixing model (the same spectral endmembers applied to all image pixels). Sabol et al. (1992b) and Roberts et al. (1992) used different methods to apply the most appropriate spectral endmembers to each image pixel, thereby allowing mapping of vegetation based upon the the different endmember spectra. In this paper, we describe a new approach to classification of vegetation communities based upon the spectra fractions derived from spectral mixture analysis. This approach was applied to three 1992 AVIRIS images of Jasper Ridge, California to observe seasonal changes in surface composition.

Sabol, Donald E., Jr.↗
DOE OSTI2019

Fit Fly: A Case Study of Interconnect Innovation through Parallel Simulation

To meet the demand for exascale-level performance from high-performance computing (HPC) interconnects, many system architects are turning to simulation results for accurate and reliable predictions of the performance of prospective technologies. Testing full-scale networks with a variety of benchmarking tools, including synthetic workloads and application traces, can give crucial insight into what ideas are most promising without needing to physically construct a test network. While flexible, however, this approach is extremely compute time intensive. We address this time complexity challenge through the use of large-scale, optimistic parallel simulation that ultimately leads to faster HPC network architecture innovations. In this paper we demonstrate this innovation capability through a real-world network design case study. Specifically, we have simulated and compared four extreme-scale interconnects: Dragonfly, Megafly, Slim Fly, and a new dual-rail-dual-plane variation of the Slim Fly network topology. We present this new variant of Slim Fly, dubbed Fit Fly, to show how interconnect innovation and evaluation-beyond what is possible through analytic methods-can be achieved through parallel simulation. We validate and compare the model with various network designs using the CODES interconnect simulation framework. By running large-scale simulations in a parallel environment, we are able to quickly generate reliable performance results that can help network designers break ground on the next generation of high-performance network designs.

High Performance Computing↗
DOE OSTI2017

High-order asynchrony-tolerant finite difference schemes for partial differential equations

Synchronizations of processing elements (PEs) in massively parallel simulations, which arise due to communication or load imbalances between PEs, significantly affect the scalability of scientific applications. We have recently proposed a method based on finite-difference schemes to solve partial differential equations in an asynchronous fashion – synchronization between PEs is relaxed at a mathematical level. While standard schemes can maintain their stability in the presence of asynchrony, their accuracy is drastically affected. In this work, we present a general methodology to derive asynchrony-tolerant (AT) finite difference schemes of arbitrary order of accuracy, which can maintain their accuracy when synchronizations are relaxed. We show that there are several choices available in selecting a stencil to derive these schemes and discuss their effect on numerical and computational performance. We provide a simple classification of schemes based on the stencil and derive schemes that are representative of different classes. Their numerical error is rigorously analyzed within a statistical framework to obtain the overall accuracy of the solution. Results from numerical experiments are used to validate the performance of the schemes.

42 ENGINEERING↗
DOE OSTI2025

QCD–Gravity Double Copy in Regge Asymptotics: From \(2\rightarrow n\) Amplitudes to Radiation in Shockwave Collisions

This paper discusses multi-particle production in QCD and in gravity at ultrarelativistic energies, their double-copy relations, and strong parallels in emergent shockwave dynamics. Dispersive techniques are applied to derive the BFKL equation for multi-gluon production in Regge asymptotics. Identical methods apply in gravity and are captured by a gravitational Lipatov equation. The building blocks in both cases are Lipatov vertices and reggeized propagators satisfying double-copy relations; in gravity, Weinberg’s soft theorem is recovered as a limit of the Lipatov framework. BFKL evolution in QCD generates wee parton states of maximal occupancy characterized by an emergent semi-hard saturation scale. Renormalization group equations in the Color Glass Condensate (CGC) EFT describe wee parton correlations and their rapidity evolution. A shockwave picture of deeply inelastic scattering and hadron–hadron collisions follows, with multi-particle production described by Cutkosky’s rules in strong time-dependent fields. Gluon radiation in the CGC EFT has a double copy in gravitational shockwave collisions, with a similar correspondence applicable between gluon and graviton shockwave propagators. Possible extensions of this semi-classical double copy are outlined for computing multi-particle production in gravitational shockwave collisions, self-force and tidal contributions, and classical and quantum noise in the focusing of geodesics.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
NASA NTRS2000

High Order Discontinuous Gelerkin Methods for Convection Dominated Problems with Application to Aeroacoustics

This project is about the investigation of the development of the discontinuous Galerkin finite element methods, for general geometry and triangulations, for solving convection dominated problems, with applications to aeroacoustics. On the analysis side, we have studied the efficient and stable discontinuous Galerkin framework for small second derivative terms, for example in Navier-Stokes equations, and also for related equations such as the Hamilton-Jacobi equations. This is a truly local discontinuous formulation where derivatives are considered as new variables. On the applied side, we have implemented and tested the efficiency of different approaches numerically. Related issues in high order ENO and WENO finite difference methods and spectral methods have also been investigated. Jointly with Hu, we have presented a discontinuous Galerkin finite element method for solving the nonlinear Hamilton-Jacobi equations. This method is based on the RungeKutta discontinuous Galerkin finite element method for solving conservation laws. The method has the flexibility of treating complicated geometry by using arbitrary triangulation, can achieve high order accuracy with a local, compact stencil, and are suited for efficient parallel implementation. One and two dimensional numerical examples are given to illustrate the capability of the method. Jointly with Hu, we have constructed third and fourth order WENO schemes on two dimensional unstructured meshes (triangles) in the finite volume formulation. The third order schemes are based on a combination of linear polynomials with nonlinear weights, and the fourth order schemes are based on combination of quadratic polynomials with nonlinear weights. We have addressed several difficult issues associated with high order WENO schemes on unstructured mesh, including the choice of linear and nonlinear weights, what to do with negative weights, etc. Numerical examples are shown to demonstrate the accuracies and robustness of the methods for shock calculations. Jointly with P. Montarnal, we have used a recently developed energy relaxation theory by Coquel and Perthame and high order weighted essentially non-oscillatory (WENO) schemes to simulate the Euler equations of real gas. The main idea is an energy decomposition under the form epsilon = epsilon(sub 1) + epsilon(sub 2), where epsilon(sub 1) is associated with a simpler pressure law (gamma)-law in this paper) and the nonlinear deviation epsilon(sub 2) is convected with the flow. A relaxation process is performed for each time step to ensure that the original pressure law is satisfied. The necessary characteristic decomposition for the high order WENO schemes is performed on the characteristic fields based on the epsilon(sub l) gamma-law. The algorithm only calls for the original pressure law once per grid point per time step, without the need to compute its derivatives or any Riemann solvers. Both one and two dimensional numerical examples are shown to illustrate the effectiveness of this approach.

Shu, Chi-Wang↗
DOE OSTI2022

m-CUBES An efficient and portable implementation of multi-dimensional integration for gpus

The task of multi-dimensional numerical integration is frequently encountered in physics and other scientific fields, e.g., in modeling the effects of systematic uncertainties in physical systems and in Bayesian parameter estimation. Multi-dimensional integration is often time-prohibitive on CPUs. Efficient implementation on many-core architectures is challenging as the workload across the integration space cannot be predicted a priori. We propose m-Cubes, a novel implementation of the well-known Vegas algorithm for execution on GPUs. Vegas transforms integration variables followed by calculation of a Monte Carlo integral estimate using adaptive partitioning of the resulting space. m-Cubes improves performance on GPUs by maintaining relatively uniform workload across the processors. As a result, our optimized Cuda implementation for Nvidia GPUs outperforms parallelization approaches proposed in past literature. We further demonstrate the efficiency of m-Cubes by evaluating a six-dimensional integral from a cosmology application, achieving significant speedup and greater precision than the CUBA library's CPU implementation of VEGAS. We also evaluate m-Cubes on a standard integrand test suite. m-Cubes outperforms the serial implementations of the Cuba and GSL libraries by orders of magnitude speedup while maintaining comparable accuracy. Our approach yields a speedup of at least 10 when compared against publicly available Monte Carlo based GPU implementations. In summary, m-Cubes can solve integrals that are prohibitively expensive using standard libraries and custom implementations. A modern C++ interface header-only implementation makes m-Cubes portable, allowing its utilization in complicated pipelines with easy to define stateful integrals. Compatibility with non-Nvidia GPUs is achieved with our initial implementation of m-Cubes using the Kokkos framework.

Sakiotis, Ioannis↗
DOE OSTI2017

Data Structures for Extreme Scale Computing

As computing problems of national importance grow, the government meets the increased demand by funding the development of ever larger systems. The overarching goal of the work supported in part by this grant is to increase efficiency of programming and performing computations on these large computing systems. In past work, we have demonstrated that some of these computations once thought to require expensive hardware designs and/or complex, special-purpose programming may be executed efficiently on low-cost commodity cluster computing systems using a general-purpose “latency-tolerant” programming framework. One important developed application of the ideas underlying this framework is graph database technology supporting social network pattern matching used by US intelligence agencies to more quickly identify potential terrorist threats. This database application has been spun out by the Pacific Northwest National Laboratory, a Department of Energy Laboratory, into a commercial start-up, Trovares Inc. We explore an alternative application of the same underlying ideas to a well-studied challenge arising in engineering: solving unstructured sparse linear equations. Solving these equations is key to predicting the behavior of large electronic circuits before they are fabricated. Predicting that behavior ahead of fabrication means that designs can optimized and errors corrected ahead of the expense of manufacture.

42 ENGINEERING↗
DOE OSTI2023

Extending OpenSHMEM with Aggregation Support for Improved Message Rate Performance

OpenSHMEM is a highly efficient one-sided communication API that implements the PGAS parallel programming model, and is known for its low latency communication operations that can be mapped efficiently to RDMA capabilities of network interconnects. However, applications that use OpenSHMEM can be sensitive to point-to-point message rates, as many-to-many communication patterns can generate large amounts of small messages which tend to overwhelm network hardware that has predominantly been optimised for bandwidth over message rate. Additionally, many important emerging classes of problems such as data analytics are similarly troublesome for the irregular access patterns they employ. Message aggregation strategies have been proven to significantly enhance network performance, but their implementation often involves complex restructuring of user code, making them unwieldy. This paper shows how to combine the best qualities of message aggregation within the communication model of OpenSHMEM such that applications with small and irregular access patterns can improve network performance while maintaining their algorithmic simplicity. We do this by providing a path to a message aggregation framework called conveyors through a minimally intrusive OpenSHMEM extension introducing aggregation contexts that fit more naturally to the OpenSHMEM atomics, gets, and puts model. We test these extensions using four of the bale 3.0 applications which contain essential many-to-many access patterns to show how they can produce performance improvements of up to 65×.

Welch, Aaron↗
DOE OSTI2017

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↗
DOE OSTI2025

Scale-up Unlearnable Examples Learning with High-performance Computing

Recent advancements in AI models, like ChatGPT, are structured to retain user interactions, which could inadvertently include sensitive healthcare data. In the healthcare field, particularly when radiologists use AI-driven diagnostic tools hosted on online platforms, there is a risk that medical imaging data may be repurposed for future AI training without explicit consent, spotlighting critical privacy and intellectual property concerns around healthcare data usage. Addressing these privacy challenges, a novel approach known as Unlearnable Examples (UEs) has been introduced, aiming to make data unlearnable to deep learning models. A prominent method within this area, called Unlearnable Clustering (UC), has shown improved UE performance with larger batch sizes but was previously limited by computational resources (e.g., a single workstation). To push the boundaries of UE performance with theoretically unlimited resources, we scaled up UC learning across various datasets using Distributed Data Parallel (DDP) training on the Summit supercomputer. Our goal was to examine UE efficacy at high-performance computing (HPC) levels to prevent unauthorized learning and enhance data security, particularly exploring the impact of batch size on UE’s unlearnability. Utilizing the robust computational capabilities of the Summit, extensive experiments were conducted on diverse datasets such as Pets, MedMNist, Flowers, and Flowers102. Our findings reveal that both overly large and overly small batch sizes can lead to performance instability and affect accuracy. However, the relationship between batch size and unlearnability varied across datasets, highlighting the necessity for tailored batch size strategies to achieve optimal data protection. The use of Summit’s high-performance GPUs, along with the efficiency of the DDP framework, facilitated rapid updates of model parameters and consistent training across nodes. Our results underscore the critical role of selecting appropriate batch sizes based on the specific characteristics of each dataset to prevent learning and ensure data security in deep learning applications. The source code is publicly available at https: // github. com/ hrlblab/ UE_ HPC .

Zhu, Yanfan [Vanderbilt University, Nashville, TN,↗