Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel programming”

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 865 records · Page 48
All sourcesNASA NTRSDOE OSTI
NASA NTRS1989

Computer-Aided Engineering Of Cabling

Program generates data sheets, drawings, and other information on electrical connections. DFACS program, centered around single data base, has built-in menus providing easy input of, and access to, data for all personnel involved in system, subsystem, and cabling. Enables parallel design of circuit-data sheets and drawings of harnesses. Also recombines raw information to generate automatically various project documents and drawings, including index of circuit-data sheets, list of electrical-interface circuits, lists of assemblies and equipment, cabling trees, and drawings of cabling electrical interfaces and harnesses. Purpose of program to provide engineering community with centralized data base for putting in, and gaining access to, functional definition of system as specified in terms of details of pin connections of end circuits of subsystems and instruments and data on harnessing. Primary objective to provide instantaneous single point of interchange of information, thus avoiding

Billitti, Joseph W.↗
DOE OSTI2024

Large language model evaluation for high–performance computing software development

We apply AI-assisted large language model (LLM) capabilities of GPT-3 targeting high-performance computing (HPC) kernels for (i) code generation, and (ii) auto-parallelization of serial code in C ++, Fortran, Python and Julia. Our scope includes the following fundamental numerical kernels: AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG, and language/programming models: (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). Kernel implementations are generated using GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code given simple + + prompt variants. To quantify and compare the generated results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. For auto-parallelization, we use ChatGPT interactively giving simple prompts as in a dialogue with another human including simple “prompt engineering” follow ups. Results suggest that correct outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general-purpose Python can benefit from adding language keywords, while Julia prompts perform acceptably well for its Threads and CUDA.jl programming models. Finally, we expect to provide an initial quantifiable point of reference for code generation in each programming model using a state-of-the-art LLM. Overall, understanding the convergence of LLMs, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1990

Execution time support for scientific programs on distributed memory machines

Optimizations are considered that are required for efficient execution of code segments that consists of loops over distributed data structures. The PARTI (Parallel Automated Runtime Toolkit at ICASE) execution time primitives are designed to carry out these optimizations and can be used to implement a wide range of scientific algorithms on distributed memory machines. These primitives allow the user to control array mappings in a way that gives an appearance of shared memory. Computations can be based on a global index set. Primitives are used to carry out gather and scatter operations on distributed arrays. Communications patterns are derived at runtime, and the appropriate send and receive messages are automatically generated.

Berryman, Harry↗
NASA NTRS2000

Numerical Propulsion System Simulation: An Overview

The cost of implementing new technology in aerospace propulsion systems is becoming prohibitively expensive and time consuming. One of the main contributors to the high cost and lengthy time is the need to perform many large-scale hardware tests and the inability to integrate all appropriate subsystems early in the design process. The NASA Glenn Research Center is developing the technologies required to enable simulations of full aerospace propulsion systems in sufficient detail to resolve critical design issues early in the design process before hardware is built. This concept, called the Numerical Propulsion System Simulation (NPSS), is focused on the integration of multiple disciplines such as aerodynamics, structures and heat transfer with computing and communication technologies to capture complex physical processes in a timely and cost-effective manner. The vision for NPSS, as illustrated, is to be a "numerical test cell" that enables full engine simulation overnight on cost-effective computing platforms. There are several key elements within NPSS that are required to achieve this capability: 1) clear data interfaces through the development and/or use of data exchange standards, 2) modular and flexible program construction through the use of object-oriented programming, 3) integrated multiple fidelity analysis (zooming) techniques that capture the appropriate physics at the appropriate fidelity for the engine systems, 4) multidisciplinary coupling techniques and finally 5) high performance parallel and distributed computing. The current state of development in these five area focuses on air breathing gas turbine engines and is reported in this paper. However, many of the technologies are generic and can be readily applied to rocket based systems and combined cycles currently being considered for low-cost access-to-space applications. Recent accomplishments include: (1) the development of an industry-standard engine cycle analysis program and plug 'n play architecture, called NPSS Version 1, (2) A full engine simulation that combines a 3D low-pressure subsystem with a 0D high pressure core simulation. This demonstrates the ability to integrate analyses at different levels of detail and to aerodynamically couple components, the fan/booster and low-pressure turbine, through a 3D computational fluid dynamics simulation. (3) Simulation of all of the turbomachinery in a modern turbofan engine on parallel computing platform for rapid and cost-effective execution. This capability can also be used to generate full compressor map, requiring both design and off-design simulation. (4) Three levels of coupling characterize the multidisciplinary analysis under NPSS: loosely coupled, process coupled and tightly coupled. The loosely coupled and process coupled approaches require a common geometry definition to link CAD to analysis tools. The tightly coupled approach is currently validating the use of arbitrary Lagrangian/Eulerian formulation for rotating turbomachinery. The validation includes both centrifugal and axial compression systems. The results of the validation will be reported in the paper. (5) The demonstration of significant computing cost/performance reduction for turbine engine applications using PC clusters. The NPSS Project is supported under the NASA High Performance Computing and Communications Program.

Lytle, John K.↗
DOE OSTI2024

Custom Accessors: Enabling Scalable Data Ingestion, (Re-)Organization, and Analysis on Distributed Systems

The emerging class of high velocity and high volume data analytic workflows comprise interwoven data ingestion, organization, and processing stages, with ingestion and organization steps often contributing comparable or even higher computational costs than actual processing steps. Since complex workflows consist of a variety of phases that view and use data differently, being able to construct efficient, scalable, distributed data structures (arrays, vectors, sets, maps, and multi-maps) is essential and requires custom methods to extend and shrink containers, analyze and position data, and, maintain globallyconsistent meta-data. In this paper, we propose a novel datastructure access paradigm based on the concept of Accessors. At a high level, accessors are customizable callable objects that can modify the behavior of insert, read, update, and delete operations for distributed containers while preserving atomicity guarantees. Accessors provide a very clean and natural way to implement a variety of programming patterns, e.g., conditional insertion/deletion and cascading computations, which would be otherwise hard (or even impossible) to express in parallel and distributed settings without using locks. We demonstrate the practicality and usefulness of our approach with two representative use cases and study the performance of these applications on a distributed High-Performance Computing system. Our analysis highlights that our proposed abstraction allows for an effective overlapping and concurrent execution of different workflow steps (e.g., data ingestion and analysis), which in a conventional analytics pipeline would execute sequentially, contributing cumulatively to the overall latency.

Castellana, Vito G. [BATTELLE (PACIFIC NW LAB)] (O↗
DOE OSTI2024

Parallel Variable Population Multi-Objective Optimizer (pvpmoo) v1.0

This is a parallel variable population multi-objective optimizer with an adaptive unified differential evolution algorithm or a genetic algorithm. It can also be used for single objective optimization. Some features of this code include: 1) The population size varies from generation to generation to save the total # of objective function evaluations. 2) The population is uniformly distributed to a number of parallel processors for simultaneous objective function evaluation. 3) The objective function evaluation can be attained from an external simulation program with control variables in its input file and objectives calculated from its output files. 4) The optimizer includes an adaptive unified differential evolution algorithm and a real value genetic algorithm. The parameters in the unified differential evolution algorithm can be chosen to attain any mutation schemes in the published literature.

Qiang, Ji↗
NASA NTRS1974

SEASAT study documentation

The proposed spacecraft consists of a bus module, containing all subsystems required for support of the sensors, and a payload module containing all of the sensor equipment. The two modules are bolted together to form the spacecraft, and electrical interfaces are accomplished via mated connectors at the interface plane. This approach permits independent parallel assembly and test operations on each module up until mating for final spacecraft integration and test operations. Proposed program schedules recognize the need to refine sensor/spacecraft interfaces prior to proceeding with procurement, reflect the lead times estimated by suppliers for delivery of equipment, reflect a comprehensive test program, and provide flexibility for unanticipated problems. The spacecraft systems are described in detail along with aerospace ground equipment, ground handling equipment, the launch vehicle, imaging radar incorporation, and systems tests.

Source record↗
NASA NTRS1981

Memory-based frame synchronizer

A frame synchronizer for use in digital communications systems wherein data formats can be easily and dynamically changed is described. The use of memory array elements provide increased flexibility in format selection and sync word selection in addition to real time reconfiguration ability. The frame synchronizer comprises a serial-to-parallel converter which converts a serial input data stream to a constantly changing parallel data output. This parallel data output is supplied to programmable sync word recognizers each consisting of a multiplexer and a random access memory (RAM). The multiplexer is connected to both the parallel data output and an address bus which may be connected to a microprocessor or computer for purposes of programming the sync word recognizer. The RAM is used as an associative memory or decorder and is programmed to identify a specific sync word. Additional programmable RAMs are used as counter decoders to define word bit length, frame word length, and paragraph frame length.

Stattel, R. J.↗
NASA NTRS1980

Solid-propellant rocket motor internal ballistics performance variation analysis, phase 5

The results of research aimed at improving the predictability of internal ballistics performance of solid-propellant rocket motors (SRM's) including thrust imbalance between two SRM's firing in parallel are presented. Static test data from the first six Space Shuttle SRM's is analyzed using a computer program previously developed for this purpose. The program permits intentional minor design biases affecting the imbalance between any two SMR's to be removed. Results for the last four of the six SRM's, with only the propellant bulk temperature as a non-random variable, are generally within limits predicted by theory. Extended studies of internal ballistic performance of single SRM's are presented based on an earlier developed mathematical model which includes an assessment of grain deformation. The erosive burning rate law used in the model is upgraded and made more general. Excellent results are obtained in predictions of the performances of five different SRM's of quite different sizes and configurations. These SRM's all employ PBAN type propellants with ammonium perchlorate oxidizer and 16 to 20% aluminum except one which uses carboxyl terminated butadiene binder. The only non-calculated parameters in the burning rate equations that are changed for the different SRM's are the zero crossflow velocity burning rate coefficients and exponents. The results, in general, confirm the importance of grain deformation. The improved internal ballistic model makes practical development of an effective computer program for application of an optimization technique to SRM design which is also demonstrated. The program uses a pattern search technique to minimize the difference between a desired thrust-time trace and one calculated based on the internal ballistic model.

Sforzini, R. H.↗
NASA NTRS1990

Beam rider for an Articulated Robot Manipulator (ARM) accurate positioning of long flexible manipulators

Laser beam positioning and beam rider modules were incorporated into the long hollow flexible segment of an articulated robot manipulator (ARM). Using a single laser beam, the system determined the position of the distal ARM endtip, with millimetric precision, in six degrees of freedom, at distances of up to 10 meters. Preliminary designs, using space rated technology for the critical systems, of a two segmented physical ARM, with a single and a dual degree of freedom articulation, were developed, prototyped, and tested. To control the positioning of the physical ARM, an indirect adaptive controller, which used the mismatch between the position of the laser beam under static and dynamic conditions, was devised. To predict the behavior of the system and test the concept, a computer simulation model was constructed. A hierarchical artificially intelligent real time ADA operating system program structure was created. The software was designed for implementation on a dedicated VME bus based Intel 80386 administered parallel processing multi-tasking computer system.

Malachowski, M. J.↗
NASA NTRS1991

Parallel computing using a Lagrangian formulation

A new Lagrangian formulation of the Euler equation is adopted for the calculation of 2-D supersonic steady flow. The Lagrangian formulation represents the inherent parallelism of the flow field better than the common Eulerian formulation and offers a competitive alternative on parallel computers. The implementation of the Lagrangian formulation on the Thinking Machines Corporation CM-2 Computer is described. The program uses a finite volume, first-order Godunov scheme and exhibits high accuracy in dealing with multidimensional discontinuities (slip-line and shock). By using this formulation, a better than six times speed-up was achieved on a 8192-processor CM-2 over a single processor of a CRAY-2.

Liou, May-Fun↗
NASA NTRS1992

Network issues for large mass storage requirements

File Servers and Supercomputing environments need high performance networks to balance the I/O requirements seen in today's demanding computing scenarios. UltraNet is one solution which permits both high aggregate transfer rates and high task-to-task transfer rates as demonstrated in actual tests. UltraNet provides this capability as both a Server-to-Server and Server-to-Client access network giving the supercomputing center the following advantages highest performance Transport Level connections (to 40 MBytes/sec effective rates); matches the throughput of the emerging high performance disk technologies, such as RAID, parallel head transfer devices and software striping; supports standard network and file system applications using SOCKET's based application program interface such as FTP, rcp, rdump, etc.; supports access to the Network File System (NFS) and LARGE aggregate bandwidth for large NFS usage; provides access to a distributed, hierarchical data server capability using DISCOS UniTree product; supports file server solutions available from multiple vendors, including Cray, Convex, Alliant, FPS, IBM, and others.

Perdue, James↗
NASA NTRS1992

Parallel computing using a Lagrangian formulation

This paper adopts a new Lagrangian formulation of the Euler equation for the calculation of two dimensional supersonic steady flow. The Lagrangian formulation represents the inherent parallelism of the flow field better than the common Eulerian formulation and offers a competitive alternative on parallel computers. The implementation of the Lagrangian formulation on the Thinking Machines Corporation CM-2 Computer is described. The program uses a finite volume, first-order Godunov scheme and exhibits high accuracy in dealing with multidimensional discontinuities (slip-line and shock). By using this formulation, we have achieved better than six times speed-up on a 8192-processor CM-2 over a single processor of a CRAY-2.

Liou, May-Fun↗
NASA NTRS1996

Research on computer systems benchmarking

This grant addresses the topic of research on computer systems benchmarking and is more generally concerned with performance issues in computer systems. This report reviews work in those areas during the period of NASA support under this grant. The bulk of the work performed concerned benchmarking and analysis of CPUs, compilers, caches, and benchmark programs. The first part of this work concerned the issue of benchmark performance prediction. A new approach to benchmarking and machine characterization was reported, using a machine characterizer that measures the performance of a given system in terms of a Fortran abstract machine. Another report focused on analyzing compiler performance. The performance impact of optimization in the context of our methodology for CPU performance characterization was based on the abstract machine model. Benchmark programs are analyzed in another paper. A machine-independent model of program execution was developed to characterize both machine performance and program execution. By merging these machine and program characterizations, execution time can be estimated for arbitrary machine/program combinations. The work was continued into the domain of parallel and vector machines, including the issue of caches in vector processors and multiprocessors. All of the afore-mentioned accomplishments are more specifically summarized in this report, as well as those smaller in magnitude supported by this grant.

Smith, Alan Jay↗
NASA NTRS1997

An Efficient Multiblock Method for Aerodynamic Analysis and Design on Distributed Memory Systems

The work presented in this paper describes the application of a multiblock gridding strategy to the solution of aerodynamic design optimization problems involving complex configurations. The design process is parallelized using the MPI (Message Passing Interface) Standard such that it can be efficiently run on a variety of distributed memory systems ranging from traditional parallel computers to networks of workstations. Substantial improvements to the parallel performance of the baseline method are presented, with particular attention to their impact on the scalability of the program as a function of the mesh size. Drag minimization calculations at a fixed coefficient of lift are presented for a business jet configuration that includes the wing, body, pylon, aft-mounted nacelle, and vertical and horizontal tails. An aerodynamic design optimization is performed with both the Euler and Reynolds Averaged Navier-Stokes (RANS) equations governing the flow solution and the results are compared. These sample calculations establish the feasibility of efficient aerodynamic optimization of complete aircraft configurations using the RANS equations as the flow model. There still exists, however, the need for detailed studies of the importance of a true viscous adjoint method which holds the promise of tackling the minimization of not only the wave and induced components of drag, but also the viscous drag.

Reuther, James↗
NASA NTRS2014

Catalyst for Expanding Human Spaceflight

History supplies us with many models of how and how not to commercialize an industry. This presentation draws parallels between industries with government roots, like the railroad, air transport, communications and the internet, and NASAs Commercial Crew Program. In these examples, government served as a catalyst for what became a booming industry. The building block approach the Commercial Crew Program is taking is very simple -- establish a need, laying the groundwork, enabling industry and legal framework.

Industry catalyst↗
NASA NTRS2016

Improving Fidelity of Launch Vehicle Liftoff Acoustic Simulations

Launch vehicles experience high acoustic loads during ignition and liftoff affected by the interaction of rocket plume generated acoustic waves with launch pad structures. Application of highly parallelized Computational Fluid Dynamics (CFD) analysis tools optimized for application on the NAS computer systems such as the Loci/CHEM program now enable simulation of time-accurate, turbulent, multi-species plume formation and interaction with launch pad geometry and capture the generation of acoustic noise at the source regions in the plume shear layers and impingement regions. These CFD solvers are robust in capturing the acoustic fluctuations, but they are too dissipative to accurately resolve the propagation of the acoustic waves throughout the launch environment domain along the vehicle. A hybrid Computational Fluid Dynamics and Computational Aero-Acoustics (CFD/CAA) modeling framework has been developed to improve such liftoff acoustic environment predictions. The framework combines the existing highly-scalable NASA production CFD code, Loci/CHEM, with a high-order accurate discontinuous Galerkin (DG) solver, Loci/THRUST, developed in the same computational framework. Loci/THRUST employs a low dissipation, high-order, unstructured DG method to accurately propagate acoustic waves away from the source regions across large distances. The DG solver is currently capable of solving up to 4th order solutions for non-linear, conservative acoustic field propagation. Higher order boundary conditions are implemented to accurately model the reflection and refraction of acoustic waves on launch pad components. The DG solver accepts generalized unstructured meshes, enabling efficient application of common mesh generation tools for CHEM and THRUST simulations. The DG solution is coupled with the CFD solution at interface boundaries placed near the CFD acoustic source regions. Both simulations are executed simultaneously with coordinated boundary condition data exchange.

Liever, Peter↗
DOE OSTI2024

Control And Optimization Modular Modeling Application For Nuclear Deployment

The purpose of the COMMAND code is to provide a flexible, scalable tool for use in developing, integrating, and testing the technologies necessary for achieving autonomous operations of advanced nuclear reactors. The code enables users to efficiently implement custom simulations and experiments by combining key methods from different software modules. These modules are focused on: modeling and simulation tools, such as nuclear simulation tools used for high-fidelity modeling (e.g., Reactor Excursion and Leak Analysis Program [RELAP5-3D] and Monte Carlo N-Particle [MCNP]); machine learning and optimization tools (e.g., anomaly detection and data-driven modeling techniques); advanced control in its digital, high-performance, and supervisory control forms (e.g., proportional integral derivative (PID) control and model predictive control (MPC); and integration with hardware through industrial communication protocols. To ensure flexibility and scalability, COMMAND was designed to be both modular—the software “pieces” all inherit from generic building blocks and can be combined and connected to create complicated simulations—and high performing—designed for parallel processing, enabling simulations and experiments to take advantage of multi-core computers, servers, and nodes. The code is written in the Python programming language due to the language's popularity, active community, and open-source and cross-platform nature. Maintaining consistency with other simulation tools used within the nuclear energy community, users implement simulations and experiments through text input files, which define components, parameters, connections, etc., through lines of text. Given that COMMAND is written in Python, these input files are native Python scripts, and so use the standard Python structure and formatting. This also enables users to take advantage of Python's extensive package library to develop custom capabilities for their specific use cases.

Faber, Jacob [Idaho National Laboratory (INL), Ida↗