TOSS-2020: A Commodity Software Stack for High-Performance Computing
Explore the source record for details and available documents.
Computer science↗
SEARCH · Search NASA
Results for “software 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.
Sensor Anomaly Detection for Nuclear Reactor Systems Utilizing Linear Regression and K-Means Unsupervised Machine Learning
Nuclear reactors and related systems are becoming increasingly complex due to advancing technologies in next-generation power reactors. This increased complexity necessitates enhanced automation and data management capabilities. To successfully realize autonomous systems, methods must be developed to handle vast volumes of data and effectively distinguish anomalous data from noise and expected data. While impressive models utilizing digital twins and similar approaches are under development, here we propose a simplified model for analyzing fundamental methods and techniques. Initially, we created a general dataset by using initial data from PCTRAN in order to represent ideal steady-state conditions. We then inserted anomalies based on prevalent sensor anomaly types (e.g., point anomalies, linear drift, and downward deviations), along with unusual anomalies such as exponential drift and upward deviations. To detect anomalies, we developed a program that employs data partitioning and linear regression to preprocess and filter the anomalous data. A K-Means machine learning (ML) method was then applied to separate and count the data within the anomalous partition. The results from all datasets—apart from exponential growth—demonstrated positive outcomes, with each returning multiple instances of greaterthan-95% accuracy. We conducted further investigations using Idaho National Laboratory’s RAVEN software to perform a sensitivity analysis on the input variables (R 2 Tolerance, Slope Tolerance, and Window Size) and found that the output variables (Accuracy and Time) were most sensitive to the Window Size. Despite the promising results published, further development is required to effectively apply these methods to nuclear systems. Nevertheless, the strengths of this approach are evident and hold promise for future applications in the field.
21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
Comparing Solargraf Shading Predictions to On-Site Shading Measurements
NREL evaluated the statistical equivalence between SAVs calculated by Enphase Energy using using their Solargraf software to perform remote shading analysis, and SAVs measured by NREL on-site using a Solmetric SunEye 210 shade measurement tool.
PV modeling↗
MOOSE ProbML: Parallelizable Probabilistic Machine Learning and Uncertainty Quantification Capabilities
The Multiphysics Object Oriented Simulation Environment (MOOSE) is a widely used open- source finite element software for performing multiphysics multiscale simulations in a massively parallel fashion. Recently, the computational team at Idaho National Laboratory (INL) has implemented Probabilistic Machine Learning (ProbML) capabilities in MOOSE—in a parallelized fashion—and enable active learning with large-scale computational models for tasks such as surrogate model development, scale bridging, forward/inverse uncertainty quantification (UQ), Bayesian optimization, etc. This presentation summarizes these developments in MOOSE along with demonstrations on several real applications relevant to nuclear energy. At the fundamental level, samplers like Monte Carlo/Latin Hypercube, variance reduction, parallelized Markov Chain Monte Carlo (MCMC) support uncertainty propagation in both forward and inverse settings. These samplers can be integrated with the Gaussian processes (GP) suite in MOOSE, which offer several variants like scalar GPs, multi-output GPs, and deep GPs, to enable active learning. These GPs can be tuned using gradient-based optimization methods like Adam and its variants or gradient-free methods like the elliptical slice sampler (a variant of MCMC adept under Gaussian settings) for more complex covariance kernels or likelihoods whose gradient computations can be cumbersome. A variety of batch acquisition functions permit parallelized evaluation of the computational model and support different learning objectives with high efficiency like Bayesian inference, global surrogate development, optimization, etc. Furthermore, libtorch integration supports training, evaluation, and re-training of neural networks and other complex machine learning models in active learning settings. The impacts of these developments are shown on several real applications: (1) nuclear fuel inverse UQ and model inadequacy assessment using the Kennedy O’Hagan framework; (2) uncertainty aware surrogate modeling for additive manufacturing to predict field quantities; (3) nuclear reactor rare events analysis; and (4) complex fluid flow prediction using a global surrogate with quantified prediction uncertainty. Finally, the outlook of MOOSE ProbML is discussed for both outer-loop and inner-loop computations in the broad view to accelerate fuels and materials qualification, address gaps in knowledge and data, and assess new reactor/fuel systems.
11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
TriPoll
TriPoll is software to perform surveys of triangles within large graphs containing metadata. In TriPoll, users define their own callback functions that get executed on the metadata of each triangle within a graph as triangles are identified. This functionality makes it possible for users to perform advanced analyses and gather statistics about specific classes of triangles of interest.
Steil, TrevorW↗
Software engineering to sustain a high-performance computing scientific application: QMCPACK
We provide an overview of the software engineering efforts and their impact in QMCPACK, a production-level ab-initio Quantum MonteCarlo open-source code targeting high-performance computing (HPC) systems. Aspects included are: (i) strategic expansion ofcontinuous integration (CI) targeting CPU, using GitHub Actions runners, and graphics processing units (GPU) in pre-exascalesystems, using self-hosted hardware; (ii) incremental reduction of memory leaks using sanitizers, (iii) incorporation of Dockercontainers for CI and reproducibility, and (iv) refactoring efforts to improve maintainability, testing coverage, and memory lifetime management. We quantify the value of these improvements by providing metrics to illustrate the shift towards a predictive, rather than reactive, sustainable maintenance approach. Our goal, in documenting the impact of these efforts on QMCPACK, is to contribute to the body of knowledge on the importance of research software engineering (RSE) for the sustainability of community HPC codes and scientific discovery at scale.
Godoy, William↗
Single-Bar SMT Testing on Alloy 617 using Software Controls
INL has performed simplified model testing using a variable in the software control program to compare with the testing performed at ORNL, which uses hardware to modify the control signal. The INL tests compared well with the ORNL tests, showing similar stress and strain values, as well as similarly shaped hysteresis loops. This demonstrates that possibility of performing simplified model testing without any hardware modifications.
36 MATERIALS SCIENCE↗
Viskores: Integrating Parallel Scientific Visualization Research into Applications
Viskores is a scientific visualization library that is the primary deployment of such algorithms to the parallel accelerated processors of modern DOE supercomputers. In this paper, we review the capabilities provided by Viskores and how these capabilities are leveraged by other software in the high-performance computing ecosystem. We discuss the Viskores data representation and pay particular attention to array management. Through this array management we describe how data is adapted between Viskores and other software along with strategies for converting dynamic, polymorphic objects to static representations better suited to GPU processing. We conclude with several examples of Viskores integrating with high-performance software that is used in production today.
Moreland, Ken [ORNL] (ORCID:0000000270513288)↗
NCCS High Performance GMRES Mixed Precision
HPG-MxP is a software package that performs a fixed number of multigrid preconditioned (using a Gauss-Seidel smoother) Generalized minimal residual (PGMRES) iterations in order to solve a possibly nonsymmetric large sparse linear system of equations. It is designed to be a benchmark to measure a computer's performance for sparse linear algebra workloads typical in scientific computing while allowing the use of mixed precision methods. The solution is required to have convergence characteristics and accuracy similar to double precision GMRES. It is based on the High Performance Conjugate Gradient Benchmark (HPCG) which restricts all implementations to use only the IEEE double precision format (FP64). The original implementation (https://github.com/hpg-mxp/hpg-mxp) was written by Ichitaro Yamazaki, Jennifer Loe, Christian Glusa, Sivasankaran Rajamanickam, Piotr Luszczek, and Jack Dongarra. Please refer to that repository for documentation on the original implementation. This version is maintained by the National Center for Computational Sciences at Oak Ridge National Laboratory. It is highly scalable and optimized for Oak Ridge Leadership Computing Facility (OLCF) systems, particularly Frontier.
Kashi, Aditya [Oak Ridge National Laboratory (ORNL↗
Status of Multiple Channel Fuel Performance Capabilities Within the SAS4A/SASSYS-1 Safety Analysis Software
SAS4A/SASSYS-1 (SAS) is a fast-running simulation tool used to perform deterministic analysis of anticipated events as well as design basis and beyond design basis accidents for advanced liquid-metal-cooled nuclear reactors. It is a critical element of safety analysis capabilities for the U.S. Department of Energy and is utilized within industry to perform the transient safety analyses required to support the licensing of Liquid Metal-cooled Fast Reactors (LMFRs). Although SAS is exceptionally fast for most transient scenarios, fuel performance calculations, along with the associated pre-transient characterization of the fuel pin, may be required for transient scenarios where fuel pin failure is hypothesized. Both the pre-transient characterization and the transient fuel performance calculation are necessary to properly quantify margins to potential fuel failure and assess the time spent potentially exceeding such margins during events. While safety analysis calculations with fuel performance models provide a more detailed characterization of the reactor during a transient, the pre-transient characterization can be time-consuming and computationally expensive. Often, large numbers of fuel pins have been exposed to similar pre-transient irradiation conditions. Similarly, the same pre-transient fuel characterization may be applicable to numerous transient conditions. This provides an opportunity to optimize the SAS computational framework such that pre-transient fuel characterization can be shared across multiple channels (fuel pins) and across multiple simulations, thus dramatically reducing overall computational costs. This report summarizes progress toward enhancing the SAS computational framework to support shared, multiple channel fuel performance characterizations intended to significantly reduce computational costs. Preliminary testing has shown that the computational time saved by using the pre-transient sharing capability is approximately equal to the time it takes to perform the pre-transient characterization.
22 GENERAL STUDIES OF NUCLEAR REACTORS↗
GDSA PFLOTRAN Development (FY2021)
The Spent Fuel & Waste Science and Technology (SFWST) Campaign of the U.S. Department of Energy (DOE) Office of Nuclear Energy (NE), Office of Spent Fuel & Waste Disposition (SFWD) is conducting research and development (R&D) on geologic disposal of spent nuclear fuel (SNF) and high-level nuclear waste (HLW). A high priority for SFWST disposal R&D is to develop a disposal system modeling and analysis capability for evaluating disposal system performance for nuclear waste in geologic media. This report describes fiscal year (FY) 2021 advances of the PFLOTRAN Development group of the SFWST Campaign. The mission of this group is to develop a geologic disposal system modeling capability for nuclear waste that can be used to probabilistically assess the performance of generic disposal concepts. In FY 2021, development proceeded along three main thrusts: software infrastructure, code performance, and process model advancement. Software infrastructure improvements included implementing an Agile software development framework and making improvements to the QA Test Suite. Code performance improvements included development of advanced linear and nonlinear solvers as well as design of flexible smoothing algorithms for capillary pressure functions. Process modeling advancements included the addition of flexible thermal conductivity function definitions and refinement of multi-continuum reactive transport to support Sandia’s participation in DECOVALEX
11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
PFLOTRAN Development FY2021
The Spent Fuel & Waste Science and Technology (SFWST) Campaign of the U.S. Department of Energy (DOE) Office of Nuclear Energy (NE), Office of Spent Fuel & Waste Disposition (SFWD) is conducting research and development (R&D) on geologic disposal of spent nuclear fuel (SNF) and high-level nuclear waste (HLW). A high priority for SFWST disposal R&D is to develop a disposal system modeling and analysis capability for valuating disposal system performance for nuclear waste in geologic media. This report describes fiscal year (FY) 2021 advances of the PFLOTRAN Development group of the SFWST Campaign. The mission of this group is to develop a geologic disposal system modeling capability for nuclear waste that can be used to probabilistically assess the performance of generic disposal concepts. In FY 2021, development proceeded along three main thrusts: software infrastructure, code performance, and process model advancement. Software infrastructure improvements included implementing an Agile software development framework and making improvements to the QA Test Suite. Code performance improvements included development of advanced linear and nonlinear solvers as well as design of flexible smoothing algorithms for capillary pressure functions. Process modeling advancements included the addition of flexible thermal conductivity function definitions and refinement of multi-continuum reactive transport to support Sandia’s participation in DECOVALEX. This report fulfills the GDSA PFLOTRAN Development Work Package Level 3 Milestone – PFLOTRAN Development, FY2021, M3SF-21SN010304072.
12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
Evolution of the SLATE linear algebra library
SLATE (Software for Linear Algebra Targeting Exascale) is a distributed, dense linear algebra library targeting both CPU-only and GPU-accelerated systems, developed over the course of the Exascale Computing Project (ECP). While it began with several documents setting out its initial design, significant design changes occurred throughout its development. In some cases, these were anticipated: an early version used a simple consistency flag that was later replaced with a full-featured consistency protocol. In other cases, performance limitations and software and hardware changes prompted a redesign. Sequential communication tasks were parallelized; host-to-host MPI calls were replaced with GPU device-to-device MPI calls; more advanced algorithms such as Communication Avoiding LU and the Random Butterfly Transform (RBT) were introduced. Early choices that turned out to be cumbersome, error prone, or inflexible have been replaced with simpler, more intuitive, or more flexible designs. Applications have been a driving force, prompting a lighter weight queue class, nonuniform tile sizes, and more flexible MPI process grids. Of paramount importance has been building a portable library that works across several different GPU architectures – AMD, Intel, and NVIDIA – while keeping a clean and maintainable codebase. Here we explore the evolving design choices and their effects, both in terms of performance and software sustainability.
Gates, Mark↗
FORCE Regression Testing
Via programs including the Light Water Reactor Sustainability and Integrated Energy Systems, the U.S. Department of Energy has invested in the Framework for Optimization of ResourCes and Economics (FORCE) software framework (Idaho National Laboratory 2024a) for the technical and economic analysis of nuclear-integrated energy systems (IES). Nuclear IES expand the use of nuclear from traditional baseload electricity generation to a flexible and adaptive source of combined heat and power. Nuclear heat can be used in the production of a variety of energy currencies such as hydrogen and ammonia as well as other heat applications including water desalination and district heating. FORCE is designed with the intent to provide interconnected analysis tools that enable the accurate technical and economic assessment of specific nuclear IES configurations for individual energy markets. FORCE consists of three main analysis pathways: HYBRID (Idaho National Laboratory 2024b), which contains high-resolution physical models for IES; Holistic Energy Resource Optimization Network (HERON) (Idaho National Laboratory 2024c), which analyzes IES long-term economic viability; and Optimization of Real-time Capacity Allocation (ORCA) (Idaho National Laboratory 2024d), designed for real-time control of IES via digital twins and optimal decision making, including autonomous and remote operation research. Development of the FORCE ecosystem is guided by three pillars: capability, which assures that the computational requirements of IES analysis are met by the software tools; reliability, which provides for consistent code performance and expected behaviors; and accessibility, which lowers the barrier to entry for using the software and accelerates analysis by users beyond the FORCE primary developers. Reliability of the FORCE ecosystem is established according to the American Nuclear Society?s Nuclear Quality Assurance (NQA-1) program [American Society of Mechanical Engineers 1982], with specific levels of software quality assurance (SQA) within NQA-1 applied to each software tool in FORCE. As the tools within FORCE have matured, some integration algorithms to accurately connect the software tools for holistic analysis have been developed and deployed within the FORCE software repository. In accordance with NQA-1 standards, regression tests are required to guarantee the software performs consistently even when new capabilities are added to the software. In this report, we document the deployment of both unit tests, which test the consistent behavior of small pieces of the FORCE code base, as well as integration tests, which test the consistent performance of full use cases for the FORCE integration algorithms. We further document the encapsulation of these tests within a test harness, which collectively checks for each successful test completion on demand. Finally, we document the automation of the test harness using GitHub Actions [GitHub 2024], which require all tests succeed before any new capability or other changes can be added to the FORCE integration software
97 MATHEMATICS AND COMPUTING↗
Creating Continuous Integration Infrastructure for Software Development on U.S. Department of Energy High-Performance Computing Systems
The Exascale Computing Project (ECP) software deployment effort developed and advanced DevOps capabilities. One goal was to enable robust continuous integration (CI) workflows that span the protected high performance computing (HPC) environments found within many of the Department of Energy’s (DOE) national laboratories. This article highlights several challenges encountered with enabling automation, such as charging models for CI jobs, and meeting individualized security requirements that revolve around strongly associating running code with a human identity. Here, it also describes how the Jacamar CI tool evolved to meet latter requirements and became a key aspect of the solutions currently offered. Derived from this experience, we offer a conceptual framework for understanding current and future CI challenges at DOE facilities and offer suggestions for long-term solutions.
97 MATHEMATICS AND COMPUTING↗
Enhancing Performance Contracts with Monitoring-Based Commissioning (MBCx)
Integrating monitoring-based commissioning (MBCx) software tools into performance contracts is a timely topic given recent developments in MBCx software offerings and the growing number of MBCx deployments nationwide. Many commercial building owners have started to install MBCx software tools that tie in advanced metering infrastructure, building automation systems, and local weather data to enable ongoing commissioning and identify energy conservation measures. To support federal and commercial building owners in understanding, procuring, and implementing MBCx software tools, this report provides an overview of their capabilities, the MBCx process, and how MBCx can be integrated into - and benefit - each phase of a performance contract. This report is intended to spur increased use of MBCx in performance contracts, whether an agency has previously installed or is considering adding MBCx at the time of their project. Additionally, case studies illustrate successful experiences using MBCx within performance contracts at a university campus and across a large number of buildings managed by the General Services Administration.
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
Software stewardship and advancement of a high-performance computing scientific application: QMCPACK
Here, we provide an overview of the software engineering efforts and their impact in QMCPACK, a production-level ab-initio Quantum Monte Carlo open-source code targeting high-performance computing (HPC) systems. Aspects included are: (i) strategic expansion of continuous integration (CI) targeting CPUs, using GitHub Actions own runners, and NVIDIA and AMD GPUs used in pre-exascale systems, (ii) incremental reduction of memory leaks using sanitizers, (iii) incorporation of Docker containers for CI and reproducibility, and (iv) refactoring efforts to improve maintainability, testing coverage, and memory lifetime management. We quantify the value of these improvements by providing metrics to illustrate the shift towards a predictive, rather than reactive, maintenance approach. Our goal, in documenting the impact of these efforts on QMCPACK, is to contribute to the body of knowledge on the importance of research software engineering (RSE) for the stewardship and advancement of community HPC codes to enable scientific discovery at scale.
97 MATHEMATICS AND COMPUTING↗
Providing a Flexible and Comprehensive Software Stack Via Spack, an Extreme-Scale Scientific Software Stack, and Software Development Kits
To manage the complex demands of modern high-performance computing (HPC), software applications increasingly depend on software developed by other teams, often at other institutions. An HPC software ecosystem approach is required to support dependencies on third-party scientific software. An ecosystem approach provides layers of activity above the individual software product level that promote interoperability, quality improvement, porting, testing, and deployment. The U.S. Exascale Computing Project (ECP) developed its HPC software ecosystem using a three-pronged approach. First, the ECP adopted and invested in Spack, a package manager designed to handle complex HPC package dependencies. Second, the ECP created the Extreme Scale Scientific Software Stack, an effort that supports developing, deploying, and running scientific applications on HPC platforms. Third, the ECP supported software product communities, or software development kits, to develop and promote best practices, improve software interoperability, and other collaborative efforts. This article describes ECP contributions to HPC software ecosystem challenges.
97 MATHEMATICS AND COMPUTING↗