Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “computer system 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 1,603 records · Page 89

Impact of Data Placement on Resilience in Large-Scale Object Storage Systems

Distributed object storage architectures have become the de facto standard for high-performance storage in big data, cloud, and HPC computing. Object storage deployments using commodity hardware to reduce costs often employ object replication as a method to achieve data resilience. Repairing object replicas after failure is a daunting task for systems with thousands of servers and billions of objects, however, and it is increasingly difficult to evaluate such scenarios at scale on realworld systems. Resilience and availability are both compromised if objects are not repaired in a timely manner. In this work we leverage a high-fidelity discrete-event simulation model to investigate replica reconstruction on large-scale object storage systems with thousands of servers, billions of objects, and petabytes of data. We evaluate the behavior of CRUSH, a well-known object placement algorithm, and identify configuration scenarios in which aggregate rebuild performance is constrained by object placement policies. After determining the root cause of this bottleneck, we then propose enhancements to CRUSH and the usage policies atop it to enable scalable replica reconstruction. We use these methods to demonstrate a simulated aggregate rebuild rate of 410 GiB/s (within 5% of projected ideal linear scaling) on a 1,024-node commodity storage system. We also uncover an unexpected phenomenon in rebuild performance based on the characteristics of the data stored on the system.

Carns, Philip↗

Balancing Particle and Mesh Computation in a Particle-In-Cell Code

The XGC1 plasma microturbulence particle-in-cell simulation code has both particle-based and mesh-based computational kernels that dominate performance. Both of these are subject to load imbalances that can degrade performance and that evolve during a simulation. Each separately can be addressed adequately, but optimizing just for one can introduce significant load imbalances in the other, degrading overall performance. A technique has been developed based on Golden Section Search that minimizes wallclock time given prior information on wallclock time, and on current particle distribution and mesh cost per cell, and also adapts to evolution in load imbalance in both particle and mesh work. In problems of interest this doubled the performance on full system runs on the XK7 at the Oak Ridge Leadership Computing Facility compared to load balancing only one of the kernels.

Worley, Patrick H↗

The role of quantum computing in advancing scientific high-performance computing: A perspective from the ADAC institute

Quantum computing (QC) has gained significant attention over the past two decades due to its potential for speeding up classically demanding tasks. This transition from an academic focus to a thriving commercial sector is reflected in substantial global investments. While advancements in qubit counts and functionalities continue at a rapid pace, current quantum systems still lack the scalability for practical applications, facing challenges such as too high error rates and limited coherence times. Here, this perspective paper examines the relationship between QC and high-performance computing (HPC), highlighting their complementary roles in enhancing computational efficiency. It is widely acknowledged that even fully error-corrected QC will not be suited for all computational tasks. Rather, future compute infrastructures are anticipated to employ quantum acceleration within hybrid systems that integrate HPC and QC. While QC can enhance classical computing, traditional HPC remains essential for maximizing quantum acceleration. This integration is a priority for supercomputing centers and companies, sparking innovation to address the challenges of merging these technologies. The novelty of this work lies in its unique perspective, reflecting the collective insights of the Accelerated Data Analytics and Computing (ADAC) Institute, a global consortium of over 20 leading HPC centers. Recognizing the growing importance of QC, ADAC established a Quantum Computing Working Group in 2023 to foster collaboration and knowledge-sharing among its members. This paper synthesizes insights from the group’s collaborative efforts and incorporates findings from a member survey that captures shared experiences, ongoing projects, and strategic directions. By outlining the current landscape and challenges of QC integration into HPC ecosystems, this work offers HPC specialists practical and forward-looking guidance on the opportunities and implications of QC in computationally intensive endeavors.

Accelerated Data Analytics and↗

Generalized gas-solid adsorption modeling: Single-component equilibria

Over the last several decades, modeling of gas–solid adsorption at equilibrium has generally been accomplished through the use of isotherms such as the Freundlich, Langmuir, Tóth, and other similar models. While these models are relatively easy to adapt for describing experimental data, their simplicity limits their generality to be used with many different sets of data. This limitation forces engineers and scientists to test each different model in order to evaluate which one can best describe their data. Additionally, the parameters of these models all have a different physical interpretation, which may have an effect on how they can be further extended into kinetic, thermodynamic, and/or mass transfer models for engineering applications. Therefore, it is paramount to adopt not only a more general isotherm model, but also a concise methodology to reliably optimize for and obtain the parameters of that model. A model of particular interest is the Generalized Statistical Thermodynamic Adsorption (GSTA) isotherm. The GSTA isotherm has enormous flexibility, which could potentially be used to describe a variety of different adsorption systems, but utilizing this model can be fairly difficult due to that flexibility. To circumvent this complication, a comprehensive methodology and computer code has been developed that can perform a full equilibrium analysis of adsorption data for any gas-solid system using the GSTA model. The code has been developed in C/C++ and utilizes a Levenberg–Marquardt’s algorithm to handle the non-linear optimization of the model parameters. Since the GSTA model has an adjustable number of parameters, the code iteratively goes through all number of plausible parameters for each data set and then returns the best solution based on a set of scrutiny criteria. Data sets at different temperatures are analyzed serially and then linear correlations with temperature are made for the parameters of the model. The end result is a full set of optimal GSTA parameters, both dimensional and non-dimensional, as well as the corresponding thermodynamic parameters necessary to predict the behavior of the system at temperatures for which data were not available. It will be shown that this code, utilizing the GSTA model, was able to describe a wide variety of gas-solid adsorption systems at equilibrium.In addition, a physical interpretation of these results will be provided, as well as an alternate derivation of the GSTA model, which intends to reaffirm the physical meaning.

97 MATHEMATICS AND COMPUTING↗

Distributing Power Grid State Estimation on HPC Clusters A System Architecture Prototype

The future power grid is expected to further expand with highly distributed energy sources and smart loads. The increased size and complexity lead to increased burden on existing computational resources in energy control centers. Thus the need to perform real-time assessment on such systems entails efficient means to distribute centralized functions such as state estimation in the power system. In this paper, we present our early prototype of a system architecture that connects distributed state estimators individually running parallel programs to solve non-linear estimation procedure. The prototype consists of a middleware and data processing toolkits that allows data exchange in the distributed state estimation. We build a test case based on the IEEE 118 bus system and partition the state estimation of the whole system model to available HPC clusters. The measurement from the testbed demonstrates the low overhead of our solution.

Distributed architecture↗

UNITY: Unified Memory and Storage Space

UNITY is a 36-month project focused on providing design and evaluate a new distributed storage paradigm that unifies the traditionally distinct application views of memory- and file-based data storage into a single scalable and resilient environment. The project is a collaboration among Oak Ridge National Laboratory (ORNL, Lead institution), Los Alamos National Labs (LANL), and Georgia Tech (GT). The main contributions of the GT team have been around development of low level systems software for best leveraging the capabilities of new types of persistent memory technologies, and for development of methods for intelligent data management across memory/storage substrates with heterogeneous components. GT contributed the Phoenix library for optimized checkpoint/restart for HPC I/O for systems with non-volatile memory (NVM), the NVStream library for NVM-specialized streaming I/O for HPC workflows, the CoMerge, Mnemo and Kleio solutions for intelligent data management on NVM-based systems. These contributions result in significant improvements in both application performance and system efficiency.

97 MATHEMATICS AND COMPUTING↗

Computational Modeling and Assessment Of Nanocoatings for Ultra Supercritical Boilers

Forced outages and boiler unavailability in conventional coal-fired fossil power plants is most often caused by fireside corrosion of boiler waterwalls. Industry-wide, the rate of wall thickness corrosion wastage of fireside waterwalls in fossil-fired boilers has been of concern for many years. It is significant that the introduction of nitrogen oxide (NOx) emission controls with staged burners systems has increased reported waterwall wastage rates to as much as 120 mils (3 mm) per year. Moreover, the reducing environment produced by the low-NOx combustion process is the primary cause of accelerated corrosion rates of waterwall tubes made of carbon and low alloy steels. Improved coatings, such as the MCrAl nanocoatings evaluated here (where M is Fe, Ni, and Co), are needed to reduce/eliminate waterwall damage in subcritical, supercritical, and ultra-supercritical (USC) boilers. The first two tasks of this six-task project-jointly sponsored by EPRI and the U.S. Department of Energy (DE-FC26-07NT43096)-have focused on computational modeling of an advanced MCrAl nanocoating system and evaluation of two nanocrystalline (iron and nickel base) coatings, which will significantly improve the corrosion and erosion performance of tubing used in USC boilers. The computational model results showed that about 40 wt.% is required in Fe based nanocrystalline coatings for long-term durability, leading to a coating composition of Fe-25Cr-40Ni-10 wt.% Al. In addition, the long term thermal exposure test results further showed accelerated inward diffusion of Al from the nanocrystalline coatings into the substrate. In order to enhance the durability of these coatings, it is necessary to develop a diffusion barrier interlayer coating such TiN and/or AlN. The third task 'Process Advanced MCrAl Nanocoating Systems' of the six-task project jointly sponsored by the Electric Power Research Institute, EPRI and the U.S. Department of Energy (DE-FC26-07NT43096)- has focused on processing of advanced nanocrystalline coating systems and development of diffusion barrier interlayer coatings. Among the diffusion interlayer coatings evaluated, the TiN interlayer coating was found to be the optimum one. This report describes the research conducted under the Task 3 workscope.

36 MATERIALS SCIENCE↗

Continuation and bifurcation analysis of large-scale dynamical systems with LOCA.

Dynamical systems theory provides a powerful framework for understanding the behavior of complex evolving systems. However applying these ideas to large-scale dynamical systems such as discretizations of multi-dimensional PDEs is challenging. Such systems can easily give rise to problems with billions of dynamical variables, requiring specialized numerical algorithms implemented on high performance computing architectures with thousands of processors. This talk will describe LOCA, the Library of Continuation Algorithms, a suite of scalable continuation and bifurcation tools optimized for these types of systems that is part of the Trilinos software collection. In particular, we will describe continuation and bifurcation analysis techniques designed for large-scale dynamical systems that are based on specialized parallel linear algebra methods for solving augmented linear systems. We will also discuss several other Trilinos tools providing nonlinear solvers (NOX), eigensolvers (Anasazi), iterative linear solvers (AztecOO and Belos), preconditioners (Ifpack, ML, Amesos) and parallel linear algebra data structures (Epetra and Tpetra) that LOCA can leverage for efficient and scalable analysis of large-scale dynamical systems.

99 GENERAL AND MISCELLANEOUS↗

Performance analysis of novel thermal storage integrated heat pump system in a residential building at the hot climate for demand flexibility

A novel thermal energy storage integrated heat pump system was proposed to reshape the electricity load profile of residential buildings while maintaining thermal comfort. High-fidelity computer simulations are needed for evaluating the feasibility of the proposed system. This study investigates the annual performance of the proposed system through Modelica-based system simulations. A rule-based control strategy was developed to shift the electric demand of a typical single-family house in Atlanta, GA from peak to off-peak hours to utilize the Time-of-Use electricity rate to lower the energy costs for conditioning the building. For comparison, a conventional air-source heat pump system serving the same building was also developed. Simulation results indicate that the proposed system is capable of shifting around 90% of the building's electricity consumption for meeting the thermal demand from peak to off-peak hours on a daily basis. In addition, the annual power consumption and operating cost for running the HVAC system can be reduced by 6% and 34%, respectively, compared with the conventional air-source heat pump.

Shi, Liang↗

VAN-DAMME: GPU-accelerated and symmetry-assisted quantum optimal control of multi-qubit systems

We present an open-source software package, VAN-DAMME (Versatile Approaches to Numerically Design, Accelerate, and Manipulate Magnetic Excitations), for massively-parallelized quantum optimal control (QOC) calculations of multi-qubit systems. To enable large QOC calculations, the VAN-DAMME software package utilizes symmetry-based techniques with custom GPU-enhanced algorithms. This combined approach allows for the simultaneous computation of hundreds of matrix exponential propagators that efficiently leverage the intra-GPU parallelism found in high-performance GPUs. In addition, to maximize the computational efficiency of the VAN-DAMME code, we carried out several extensive tests on data layout, computational complexity, memory requirements, and performance. These extensive analyses allowed us to develop computationally efficient approaches for evaluating complex-valued matrix exponential propagators based on Padé approximants. To assess the computational performance of our GPU-accelerated VAN-DAMME code, we carried out QOC calculations of systems containing 10 - 15 qubits, which showed that our GPU implementation is 18.4× faster than the corresponding CPU implementation. Our GPU-accelerated enhancements allow efficient calculations of multi-qubit systems, which can be used for the efficient implementation of QOC applications across multiple domains.

97 MATHEMATICS AND COMPUTING↗

A multi-platform evaluation of the randomized CX low-rank matrix factorization in Spark

We investigate the performance and scalability of the randomized CX low-rank matrix factorization and demonstrate its applicability through the analysis of a 1TB mass spectrometry imaging (MSI) dataset, using Apache Spark on an Amazon EC2 cluster, a Cray XC40 system, and an experimental Cray cluster. We implemented this factorization both as a parallelized C implementation with hand-tuned optimizations and in Scala using the Apache Spark high-level cluster computing framework. We obtained consistent performance across the three platforms: using Spark we were able to process the 1TB size dataset in under 30 minutes with 960 cores on all systems, with the fastest times obtained on the experimental Cray cluster. In comparison, the C implementation was 21X faster on the Amazon EC2 system, due to careful cache optimizations, bandwidth-friendly access of matrices and vector computation using SIMD units. We report these results and their implications on the hardware and software issues arising in supporting data-centric workloads in parallel and distributed environments.

Gittens, Alex↗

HP-MDR: High-performance and Portable Data Refactoring and Progressive Retrieval with Advanced GPUs

Scientific applications produce vast amounts of data, posing grand challenges in the underlying data management and analytic tasks. Progressive compression is a promising way to address this problem, as it allows for on-demand data retrieval with significantly reduced data movement cost. However, most existing progressive methods are designed for CPUs, leaving a gap for them to unleash the power of today’s heterogeneous computing systems with GPUs.In this work, we propose HP-MDR, a high-performance and portable data refactoring and progressive retrieval framework for GPUs. Our contributions are four-fold: (1) We carefully optimize the bitplane encoding and lossless encoding, two key stages in progressive methods, to achieve high performance on GPUs; (2) We propose pipeline optimization and incorporate it with data refactoring and progressive retrieval workflows to further enhance the performance for large data process; (3) We leverage our framework to enable high-performance data retrieval with guaranteed error control for common Quantities of Interest; (4) We evaluate HP-MDR and compare it with state of the arts using five real-world datasets. Experimental results demonstrate that HP-MDR delivers an average 13.68 × and 6.31 × throughput in data refactoring and progressive retrieval tasks, respectively. It also leads to 11.22 × throughput for recomposing required data representations under Quantity-of-Interest error control and 6.04 × performance for the corresponding end-to-end data retrieval, when compared with state-of-the-art solutions.

Li, Yanliang [University of Oregon]↗

Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems

Abstract Predicting complex dynamics in physical applications governed by partial differential equations in real-time is nearly impossible with traditional numerical simulations due to high computational cost. Neural operators offer a solution by approximating mappings between infinite-dimensional Banach spaces, yet their performance degrades with system size and complexity. We propose an approach for learning neural operators in latent spaces, facilitating real-time predictions for highly nonlinear and multiscale systems on high-dimensional domains. Our method utilizes the deep operator network architecture on a low-dimensional latent space to efficiently approximate underlying operators. Demonstrations on material fracture, fluid flow prediction, and climate modeling highlight superior prediction accuracy and computational efficiency compared to existing methods. Notably, our approach enables approximating large-scale atmospheric flows with millions of degrees, enhancing weather and climate forecasts. Here we show that the proposed approach enables real-time predictions that can facilitate decision-making for a wide range of applications in science and engineering.

97 MATHEMATICS AND COMPUTING↗

Distributed and communication-efficient solutions to linear equations with special sparse structure

In this paper we report two distributed and communication-efficient algorithms based on the multi-agent system are proposed to solve a system of linear equations with the Laplacian sparse system matrix. One algorithm is based on the gradient descent method in optimization. In this algorithm, the agents only share partial information instead of all of their collective state vectors to save significant communication. The other algorithm is obtained by approximating Newton’s method for a faster convergence rate. Although it requires twice as much communication as the first one, it is still communication-efficient given the low dimension of the information shared among agents. The convergence at a linear rate is proved for both algorithms, and a comprehensive comparison of their convergence rate, communication burden, and computation costs is also performed. The proposed algorithms can be applied to various systems to solve those problems that can be modeled as a system of linear equations with a Laplacian sparse system matrix. Simulation results with the electric power system illustrate their effectiveness.

42 ENGINEERING↗

Comparison of a Full-Scale and a 1:10 Scale Low-Speed Two-Stroke Marine Engine Using Computational Fluid Dynamics

International marine shipping is a growing component of international trade; a vast majority of all the world’s goods are being transported on large ocean-going vessels. The International Maritime Organization (IMO) introduced the Energy Efficiency Design Index in 2013, a regulatory framework of associated metrics for reducing emissions of CO 2 per tonne-mile from shipping by approximately 10% each decade. Therefore, decarbonizing the maritime sector requires the development of new fuel sources. Because of the extremely large physical size of the internal combustion engines present in shipping vessels, experimental iterative development of the engine and fuel system is cost-prohibitive. Thus, the ability to perform combustion system development in a scaled platform that can be more easily operated and modeled computationally is of interest. To that end, scaling relationships are needed to translate the results from a smaller engine to a larger counterpart. Scaling studies to date have been restricted to low scaling ratios, four-stroke light-duty engines, and under-resolved computational fluid dynamic simulations that likely do not accurately capture the physics of scaling. In this work, computational models of a 1:10 scale and a full-scale two-stroke crosshead low-speed marine engine were created and validated against experiments obtained in a real 1:10 scale engine installed at Oak Ridge National Laboratory. Further, due to the large size of the full-scale engine, the model required large high-performance computing resources to be evaluated. The availability of high-performance computing resources at the Department of Energy’s Leadership Computing Facilities is an enabler of the current work. The results of the small- and large-scale engine simulations were compared to analyze the effectiveness of the appropriate scaling laws under these extreme scaling ratio conditions.

33 ADVANCED PROPULSION SYSTEMS↗

A Step Towards the Final Frontier: Lessons Learned from Acceptance Testing of the First HPE/Cray EX 3000 System at ORNL

In this paper, we summarize the deployment of the Air Force Weather (AFW) HPC11 system at Oak Ridge National Laboratory (ORNL) including the process followed to successfully complete acceptance testing of the system. HPC11 is the first HPE/Cray EX 3000 system that has been successfully released to its user community in a federal facility. HPC11 consists of two identical 800-node supercomputers, Fawbush and Miller, with access to two independent and identical Lustre parallel file systems. HPC11 is equipped with Slingshot 10 interconnect technology and relies on the HPE Performance Cluster Manager (HPCM) software for system configuration. ORNL has a clearly defined acceptance testing process used to ensure that every new system deployed can provide the necessary capabilities to support user workloads. We worked closely with HPE and AFW to develop a set of tests that used the United Kingdom’s Meteorological Office’s Unified Model (UM) and 4DVAR. We also included benchmarks and applications from the Oak Ridge Leadership Computing Facility (OLCF) portfolio to fully exercise the HPE/Cray programming environment and evaluate the functionality and performance of the system. Acceptance testing of HPC11 required parallel execution of each element on Fawbush and Miller. In addition, careful coordination was needed to ensure successful acceptance of the newly deployed Lustre file systems alongside the compute resources. In this work, we present test results from specific system components and provide an overview of the issues identified, challenges encountered, and the lessons learned along the way.

Melesse Vergara, Veronica↗

SU-E-T-164: Characterization of Breast Deformation During Accuboost TM Treatment

Purpose: During treatment using AccuboostTM (Advanced Radiation Therapy, Tyngsboro, MA) applicators the breast is compressed between two paddles in order to immobilize it. This causes the breast tissue to expand. The purpose of this study was to analyze the nature of this deformation. Methods: CT scans of a breast phantom (Computerized Imaging Reference Systems, Norfolk, VA) were acquired at different compressions in the cranial-caudal (CC) direction. These were performed by placing the phantom between two plates whose position is controlled by a manual crank. The phantom masses were contoured in order to simulate the clips placed after surgery. For all scans the mean distance between the masses was computed. Additionally, deformable registration was performed between two scans using the Velocity software (Varian Medical Systems, Palo Alto, CA) to assess the shifts of each of these masses. Results: As the compression increases so does the average distance between the masses. The relationship between deformation and compression is not linear. Additionally, the largest displacements are in the direction of compression. The mean shift is 1.8mm. The shifts in the RT-LT direction and ANT-POST direction are 1.1 mm and 0.7 mm respectively Conclusion: When treating patients the clips shift their position as a Result of the plate compression. For CC compressions this is not a problem if they shift their position primarily in the superior-inferior direction. The problem of not being able to cover all clips (target area) can arise when they shift position on a plane perpendicular to the patient. For clips which are already near the chest wall, care should be exercised not to compress the breast in such a way as to move those clips out of the treatable area.These preliminary results show a larger shift in the RT-LT direction than the ANT-POST one. Further research will seek to either confirm or infirm this.

60 APPLIED LIFE SCIENCES↗