Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Parallel Supercomputers”

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 271 records · Page 15

A Block-Structured Adaptive Mesh Framework to Solve Radiation Transfer Equation in Irregular Embedded Geometries

Radiation transport arises in various scientific, industrial, and medical fields, and understanding its effect in applications is needed to make accurate predictions, safety assessments and performance optimizations. Solving the Radiation Transport Equation (RTE) is challenging due to its integro-differential nature, which involves both differential and integral terms. The differential term describes the change in radiation intensity due to absorption and emission, while the integral term accounts for scattering. The accurate modeling of radiation is further complicated in many applications due to the complex, irregular geometries. Various methods exist for solving the RTE, including the zonal, Monte Carlo, spherical harmonics, discrete ordinates, and finite volume methods. Traditional mesh-based approaches, which rely on structured or unstructured meshes, struggle with irregular geometries due to: a) the difficulty of conforming structured grids to irregular domains, b) challenges in enforcing boundary conditions correctly, and c) the additional computational cost of unstructured mesh methods. This work presents a second-order accurate method for solving the RTE in irregular geometries. The radiation intensity is discretized using the finite-volume method in both spatial and angular directions on regular Cartesian grid blocks. Leveraging the block-structured adaptive mesh refinement (AMR) framework provided by AMReX, our method refines the grid locally to reduce spatial discretization error, ensuring a converged numerical solution while minimizing computational costs elsewhere. A two-stage deferred correction approach is employed: First, a first-order discretization on grid blocks is solved using an algebraic multigrid method in HYPRE. Second, a correction term is applied explicitly to achieve second-order accuracy. The correction term is calculated by approximating the radiation flux on cell faces using a Total Variation Diminishing (TVD) scheme. This approach ensures quick convergence of the multigrid method while preserving higher-order accuracy of the numerical solution. Irregular geometries are resolved as embedded boundaries (EB), resulting in both cut cells and regular cells. In cut cells, we modify the fluxes using face fractions and incorporate additional contributions from EB boundary conditions. To ensure higher-order convergence near the EB interface, the correction term is modified by interpolating the radiation intensity to fictitious ghost points. The implementation takes advantage of modern supercomputers by leveraging AMReX’sMPI/X parallelization strategy where X can be MPI or a GPU accelerator including CUDA, HIP and DPC++. We validate our solver using classical test cases, both with and without EB, demonstrating accuracy and efficiency. Additionally, we analyze the impact of adaptive mesh refinement on solution accuracy and computational cost, highlighting the advantages of our approach for high-resolution radiation transport simulations.

computational fluid dynamics (CFD)↗

Spectral Analysis of Integrated Pressures on Patches with Unsteady Pressure-Sensitive Paint Measurements

The technique of Pressure-Sensitive Paint (PSP) is commonly used in the aerospace industry to measure surface pressures on the model of launch vehicles and airplanes in the wind tunnel test. Recent research has demonstrated that Unsteady Pressure-Sensitive Paint (uPSP) can be an essential tool for the assessment of the unsteady, aerodynamic phenomena. The work described in this paper is a part of NASA’s development of a new state-of-the-art uPSP capability in production wind tunnels. This paper describes the spectral analysis of integrated pressures on patches of the scale model of the Space Launch System (SLS) Block 1 cargo vehicle with the uPSP measurements, which were collected in the Ascent Transient Aerodynamics Test (ATAT) with the Unitary Plan Wind Tunnel 11-by-11-foot Transonic Wind Tunnel in September 2019 at NASA Ames Research Center. The patches are defined with x station values, indicating the position along length of the SLS vehicle, and azimuth angles of the scale model. For each patch, the polygons are determined from the surface cells of the grid of the model, clipped with the edges of the patch, and each of the polygons is divided into triangles. The integrated pressure of the patch is determined as the ratio of the sum of the forces on the triangles over the sum of the areas of the triangles. For each run of the test, the Cross Power Spectral Density (CPSD) and magnitude squared coherence are computed from the time series of the integrated pressures on the patches. The pressure integration is coded in C++ and the spectral analysis is coded in MATLAB. The results were generated with the execution of the compiled C++ and MATLAB codes in parallel on the NASA Pleiades supercomputer. The results of pressure integration and spectral analysis are presented in this paper, and the data consistency of the test is also demonstrated. Funding for this research was provided by the NASA Aerosciences Evaluation and Test Capabilities Project.

Pressure-Sensitive Paint↗

The Profiled Feldman-Cousins Method for Confidence Interval Construction for the Nova 3-Flavor Oscillation Analysis

The small interaction cross-section of neutrinos makes experimental neutrino physics particularly responsive to technological advancements. A significant development leveraged by the NOvA experiment is large-scale parallel processing, enabling novel computational approaches to longstanding experimental challenges. Central to managing the resulting high-throughput data is NOvA’s implementation of the Freight Train model, designed for efficient data production and handling.This dissertation details the methodology and execution of the NOvA 2024 3-Flavor Oscillation Analysis, supported by a comprehensive dataset spanning ten years. It emphasizes frequentist results refined through the Feldman-Cousins (FC) technique, specifically addressing confidence interval corrections in parameter estimation. The computational intensity associated with Feldman-Cousins arises from extensive Monte Carlo simulations, which were substantially mitigated through parallel computing on the Perlmutter supercomputer at the National Energy Research Scientific Computing Center (NERSC), employing the MPI framework.To further enhance computational efficiency, an Importance Sampling method is introduced and evaluated, demonstrating significant potential to reduce complexity, particularly in exploring extreme parameter space regions. This thesis presents both the successful application of advanced computational resources and the development of sophisticated statistical techniques, aiming to enhance the precision and scope of neutrino oscillation analyses.

Dye ajdye11190@gmail.com, Andrew Joseph [Mississip↗

Towards Scalable Deep Learning via I/O Analysis and Optimization

Deep learning systems have been growing in prominence as a way to automatically characterize objects, trends, and anomalies. Given the importance of deep learning systems, researchers have been investigating techniques to optimize such systems. An area of particular interest has been using large supercomputing systems to quickly generate effective deep learning networks: a phase often referred to as “training” of the deep learning neural network. As we scale existing deep learning frameworks—such as Caffe—on these large supercomputing systems, we notice that the parallelism can help improve the computation tremendously, leaving data I/O as the major bottleneck limiting the overall system scalability. In this paper, we first present a detailed analysis of the performance bottlenecks of Caffe on large supercomputing systems. Our analysis shows that the I/O subsystem of Caffe—LMDB—relies on memory-mapped I/O to access its database, which can be highly inefficient on large-scale systems because of its interaction with the process scheduling system and the network-based parallel filesystem. Based on this analysis, we then present LMDBIO, our optimized I/O plugin for Caffe that takes into account the data access pattern of Caffe in order to vastly improve I/O performance. Our experimental results show that LMDBIO can improve the overall execution time of Caffe by nearly 20-fold in some cases.

Pumma, Sarunya↗

Massive hybrid parallelism for fully implicit multiphysics

As hardware advances continue to modify the supercomputing landscape, traditional scientific software development practices will become more outdated, ineffective, and inefficient. The process of rewriting/retooling existing software for new architectures is a Sisyphean task, and results in substantial hours of development time, effort, and money. Software libraries which provide an abstraction of the resources provided by such architectures are therefore essential if the computational engineering and science communities are to continue to flourish in this modern computing environment. The Multiphysics Object Oriented Simulation Environment (MOOSE) framework enables complex multiphysics analysis tools to be built rapidly by scientists, engineers, and domain specialists, while also allowing them to both take advantage of current HPC architectures, and efficiently prepare for future supercomputer designs. MOOSE employs a hybrid shared-memory and distributed-memory parallel model and provides a complete and consistent interface for creating multiphysics analysis tools. In this paper, a brief discussion of the mathematical algorithms underlying the framework and the internal object-oriented hybrid parallel design are given. Representative massively parallel results from several applications areas are presented, and a brief discussion of future areas of research for the framework are provided. (authors)

97 MATHEMATICS AND COMPUTING↗

Massive parallelism in the future of science

Massive parallelism appears in three domains of action of concern to scientists, where it produces collective action that is not possible from any individual agent's behavior. In the domain of data parallelism, computers comprising very large numbers of processing agents, one for each data item in the result will be designed. These agents collectively can solve problems thousands of times faster than current supercomputers. In the domain of distributed parallelism, computations comprising large numbers of resource attached to the world network will be designed. The network will support computations far beyond the power of any one machine. In the domain of people parallelism collaborations among large groups of scientists around the world who participate in projects that endure well past the sojourns of individuals within them will be designed. Computing and telecommunications technology will support the large, long projects that will characterize big science by the turn of the century. Scientists must become masters in these three domains during the coming decade.

Denning, Peter J.↗

MASSIVE HYBRID PARALLELISM FOR FULLY IMPLICIT MULTIPHYSICS

As hardware advances continue to modify the supercomputing landscape, traditional scientific software development practices will become more outdated, ineffective, and inefficient. The process of rewriting/retooling existing software for new architectures is a Sisyphean task, and results in substantial hours of development time, effort, and money. Software libraries which provide an abstraction of the resources provided by such architectures are therefore essential if the computational engineering and science communities are to continue to flourish in this modern computing environment. The Multiphysics Object Oriented Simulation Environment (MOOSE) framework enables complex multiphysics analysis tools to be built rapidly by scientists, engineers, and domain specialists, while also allowing them to both take advantage of current HPC architectures, and efficiently prepare for future supercomputer designs. MOOSE employs a hybrid shared-memory and distributed-memory parallel model and provides a complete and consistent interface for creating multiphysics analysis tools. In this paper, a brief discussion of the mathematical algorithms underlying the framework and the internal object-oriented hybrid parallel design are given. Representative massively parallel results from several applications areas are presented, and a brief discussion of future areas of research for the framework are provided.

97 MATHEMATICS AND COMPUTING↗

Understanding Lustre Internals

Lustre was initiated and funded, almost a decade ago, by the U.S. Department of Energy (DoE) Office of Science and National Nuclear Security Administration laboratories to address the need for an open source, highly-scalable, high-performance parallel filesystem on by then present and future supercomputing platforms. Throughout the last decade, it was deployed over numerous medium-to-large-scale supercomputing platforms and clusters, and it performed and met the expectations of the Lustre user community. As it stands at the time of writing this document, according to the Top500 list, 15 of the top 30 supercomputers in the world use Lustre filesystem. This report aims to present a streamlined overview on how Lustre works internally at reasonable details including relevant data structures, APIs, protocols and algorithms involved for Lustre version 1.6 source code base. More importantly, it tries to explain how various components interconnect with each other and function as a system. Portions of this report are based on discussions with Oak Ridge National Laboratory Lustre Center of Excellence team members and portions of it are based on our own understanding of how the code works. We, as the authors team bare all responsibilities for all errors and omissions in this document. We can only hope it helps current and future Lustre users and Lustre code developers as much as it helped us understanding the Lustre source code and its internal workings.

97 MATHEMATICS AND COMPUTING↗

Genetic algorithm based task reordering to improve the performance of batch scheduled massively parallel scientific applications

The growth in size of networked high performance computers along with novel accelerator-based node architectures has further emphasized the importance of communication efficiency in high performance computing. The world's largest high performance computers are usually operated as shared user facilities due to the costs of acquisition and operation. Applications are scheduled for execution in a shared environment and are placed on nodes that are not necessarily contiguous on the interconnect. Furthermore, the placement of tasks on the nodes allocated by the scheduler is sub-optimal, leading to performance loss and variability. Here, we investigate the impact of task placement on the performance of two massively parallel application codes on the Titan supercomputer, a turbulent combustion flow solver (S3D) and a molecular dynamics code (LAMMPS). Benchmark studies show a significant deviation from ideal weak scaling and variability in performance. The inter-task communication distance was determined to be one of the significant contributors to the performance degradation and variability. A genetic algorithm-based parallel optimization technique was used to optimize the task ordering. This technique provides an improved placement of the tasks on the nodes, taking into account the application's communication topology and the system interconnect topology. As a result, application benchmarks after task reordering through genetic algorithm show a significant improvement in performance and reduction in variability, therefore enabling the applications to achieve better time to solution and scalability on Titan during production.

97 MATHEMATICS AND COMPUTING↗

P2P Technology for High-Performance Computing: An Overview

The transition from cluster computing to peer-to-peer (P2P) high-performance computing has recently attracted the attention of the computer science community. It has been recognized that existing local networks and dedicated clusters of headless workstations can serve as inexpensive yet powerful virtual supercomputers. It has also been recognized that the vast number of lower-end computers connected to the Internet stay idle for as long as 90% of the time. The growing speed of Internet connections and the high availability of free CPU time encourage exploration of the possibility to use the whole Internet rather than local clusters as massively parallel yet almost freely available P2P supercomputer. As a part of a larger project on P2P high-performance computing, it has been my goal to compile an overview of the 2P2 paradigm. I have studied various P2P platforms and I have compiled systematic brief descriptions of their most important characteristics. I have also experimented and obtained hands-on experience with selected P2P platforms focusing on those that seem promising with respect to P2P high-performance computing. I have also compiled relevant literature and web references. I have prepared a draft technical report and I have summarized my findings in a poster paper.

Follen, Gregory J.↗

Balar: A SST GPU Component for Performance Modeling and Profiling

Programmable accelerators have become commonplace in modern computing systems. Advances in programming models and the availability of massive amounts of data have created a space for massively parallel accelerators capable of maintaining context for thousands of concurrent threads resident on-chip. These threads are grouped and interleaved on a cycle-by-cycle basis among several massively parallel computing cores. One path for the design of future supercomputers relies on an ability to model the performance of these massively parallel cores at scale. The SST framework has been proven to scale up to run simulations containing tens of thousands of nodes. A previous report described the initial integration of the open-source, execution-driven GPU simulator, GPGPU-Sim, into the SST framework. This report discusses the results of the integration and how to use the new GPU component in SST. It also provides examples of what it can be used to analyze and a correlation study showing how closely the execution matches that of a Nvidia V100 GPU when running kernels and mini-apps.

97 MATHEMATICS AND COMPUTING↗

SST-GPU: A Scalable SST GPU Component for Performance Modeling and Profiling

Programmable accelerators have become commonplace in modern computing systems. Advances in programming models and the availability of unprecedented amounts of data have created a space for massively parallel accelerators capable of maintaining context for thousands of concurrent threads resident on-chip. These threads are grouped and interleaved on a cycle-by-cycle basis among several massively parallel computing cores. One path for the design of future supercomputers relies on an ability to model the performance of these massively parallel cores at scale. The SST framework has been proven to scale up to run simulations containing tens of thousands of nodes. A previous report described the initial integration of the open-source, execution-driven GPU simulator, GPGPU-Sim, into the SST framework. This report discusses the results of the integration and how to use the new GPU component in SST. It also provides examples of what it can be used to analyze and a correlation study showing how closely the execution matches that of a Nvidia V100 GPU when running kernels and mini-apps.

97 MATHEMATICS AND COMPUTING↗

Invited Paper: Benchmarking and Optimizing Data Movement on Emerging Heterogeneous Architectures

As supercomputers evolve, nodes are continually increasing in complexity. As a result, each generation of parallel systems brings new performance challenges. For instance, on recent systems inter-node communication has outperformed inter-socket, resulting in poor performance of many node-aware communication optimizations. Communication optimizations are critical for the performance and scalability of parallel applications, but are dependent on the parallel architecture, which varies significantly among recent generations of supercomputers. Furthermore, this paper investigates the performance of various paths of data movement on recent generations of systems, and analyzes the increased complexity of communication, particularly on recent heterogeneous systems. The paper also introduces MPI Advance, a communication library that enables optimizations to be created based on benchmark analysis of each emerging system.

benchmarking↗

Beyond the supercomputer

A NASA-directed development of massively parallel processor (MPP) computers is outlined, noting intended applications for data processing for near term earth resource and environment mapping, radar, and television transmissions. The MPP is designed to perform 100 billion operations/sec to obtain satisfactory image processing, while separate processing units correct distortions, register images, calculate correlation functions, and classify multispectral characteristics. Arrays of 1s and 0s will be manipulated in analog-to-digital conversions generating separate planes corresponding to powers of binaries. Data wires are replaced by fiber-optic tubes or thousands of wires, and single logic gates are replaced by thousands of logic gates and every memory element by thousands of memory elements. Features of the interconnections and the images control processor units are detailed, along with implementation of sliders for program flexibility.

Schaefer, D. H.↗

Massively Parallel, Three-Dimensional Transport Solutions for the k-Eigenvalue Problem

We have implemented a new multilevel parallel decomposition in the Denovo dis- crete ordinates radiation transport code. In concert with Krylov subspace iterative solvers, the multilevel decomposition allows concurrency over energy in addition to space-angle, enabling scalability beyond the limits imposed by the traditional KBA space-angle partitioning. Furthermore, a new Arnoldi-based k-eigenvalue solver has been implemented. The added phase-space concurrency combined with the high- performance Krylov and Arnoldi solvers has enabled weak scaling to O(100K) cores on the Jaguar XK6 supercomputer. The multilevel decomposition provides sucient parallelism to scale to exascale computing and beyond.

Arnoldi↗

Optics Program Modified for Multithreaded Parallel Computing

A powerful high-performance computer program for simulating and analyzing adaptive and controlled optical systems has been developed by modifying the serial version of the Modeling and Analysis for Controlled Optical Systems (MACOS) program to impart capabilities for multithreaded parallel processing on computing systems ranging from supercomputers down to Symmetric Multiprocessing (SMP) personal computers. The modifications included the incorporation of OpenMP, a portable and widely supported application interface software, that can be used to explicitly add multithreaded parallelism to an application program under a shared-memory programming model. OpenMP was applied to parallelize ray-tracing calculations, one of the major computing components in MACOS. Multithreading is also used in the diffraction propagation of light in MACOS based on pthreads [POSIX Thread, (where "POSIX" signifies a portable operating system for UNIX)]. In tests of the parallelized version of MACOS, the speedup in ray-tracing calculations was found to be linear, or proportional to the number of processors, while the speedup in diffraction calculations ranged from 50 to 60 percent, depending on the type and number of processors. The parallelized version of MACOS is portable, and, to the user, its interface is basically the same as that of the original serial version of MACOS.

Lou, John↗

Disk Failure Dataset from the Campaign Storage System

This dataset consists of 1,389 disk (HDD) failure events collected from the Campaign storage system at LANL. The Campaign system supported various compute platforms throughout its lifespan, including Cielo, Fire, Ice, and notably, the Trinity supercomputer. Each recorded event includes its detection timestamp (in ISO 8601 format) and details such as its location within the storage system—rack, enclosure, and drive slot number. The data, spanning from May 4, 2021, to July 25, 2023 (2 years, 2 months, and 22 days), represents failure events from the terminal years of Campaign's operational period, accounting for 26% of its total operational time.

97 MATHEMATICS AND COMPUTING↗