Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “computer graphics”

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 1,441 records · Page 80
All sourcesNASA NTRSDOE OSTI
NASA NTRS2007

Design Application Translates 2-D Graphics to 3-D Surfaces

Fabric Images Inc., specializing in the printing and manufacturing of fabric tension architecture for the retail, museum, and exhibit/tradeshow communities, designed software to translate 2-D graphics for 3-D surfaces prior to print production. Fabric Images' fabric-flattening design process models a 3-D surface based on computer-aided design (CAD) specifications. The surface geometry of the model is used to form a 2-D template, similar to a flattening process developed by NASA's Glenn Research Center. This template or pattern is then applied in the development of a 2-D graphic layout. Benefits of this process include 11.5 percent time savings per project, less material wasted, and the ability to improve upon graphic techniques and offer new design services. Partners include Exhibitgroup/Giltspur (end-user client: TAC Air, a division of Truman Arnold Companies Inc.), Jack Morton Worldwide (end-user client: Nickelodeon), as well as 3D Exhibits Inc., and MG Design Associates Corp.

Source record↗
NASA NTRS1989

Integrated modeling tool for performance engineering of complex computer systems

This report summarizes Advanced System Technologies' accomplishments on the Phase 2 SBIR contract NAS7-995. The technical objectives of the report are: (1) to develop an evaluation version of a graphical, integrated modeling language according to the specification resulting from the Phase 2 research; and (2) to determine the degree to which the language meets its objectives by evaluating ease of use, utility of two sets of performance predictions, and the power of the language constructs. The technical approach followed to meet these objectives was to design, develop, and test an evaluation prototype of a graphical, performance prediction tool. The utility of the prototype was then evaluated by applying it to a variety of test cases found in the literature and in AST case histories. Numerous models were constructed and successfully tested. The major conclusion of this Phase 2 SBIR research and development effort is that complex, real-time computer systems can be specified in a non-procedural manner using combinations of icons, windows, menus, and dialogs. Such a specification technique provides an interface that system designers and architects find natural and easy to use. In addition, PEDESTAL's multiview approach provides system engineers with the capability to perform the trade-offs necessary to produce a design that meets timing performance requirements. Sample system designs analyzed during the development effort showed that models could be constructed in a fraction of the time required by non-visual system design capture tools.

Wright, Gary↗
DOE OSTI2021

An efficient numerical model for predicting residual stress and strain in parts manufactured by laser powder bed fusion

Abstract Computational modeling of additively manufactured structures plays an increasingly important role in product design and optimization. For laser powder bed fusion processes, the accurate modeling of stress and distortion requires large amount of computational cost due to very localized heat input and evolving complex geometries. The current study takes advantage of a graphics processing unit accelerated explicit finite element analysis code and approximated heat conduction analysis to predict the macroscopic thermo-mechanical behavior in laser selective melting. Adjacent layers and tracks were lumped to reduce the number of time steps and elements in the finite element model. The effects of track and layer grouping on prediction accuracy and solution efficiency are investigated to provide a guidance for a cost-effective simulation. Thin-wall builds from Inconel alloy 625 (IN625) powders were simulated by applying the developed modeling approach to get the detailed residual stress and distortion at a computational speed 50 times higher than conventional approach. Under repeated heating and cooling cycles, a high tensile stress was produced near surfaces of a build due to a larger shrinkage on surface than that in central area. It is also shown that horizontal stresses concentrate near the root and top layers of the IN625 build. The predicted residual elastic strain distribution was validated by the experimental measurement using x-ray synchrotron diffraction.

36 MATERIALS SCIENCE↗
NASA NTRS1979

Detailed description of the HP-9825A HFRMP trajectory processor (TRAJ)

The computer code for the trajectory processor of the HP-9825A High Fidelity Relative Motion Program is described in detail. The processor is a 12-degrees-of-freedom trajectory integrator which can be used to generate digital and graphical data describing the relative motion of the Space Shuttle Orbiter and a free-flying cylindrical payload. Coding standards and flow charts are given and the computational logic is discussed.

Kindall, S. M.↗
DOE OSTI2025

Empirically-calibrated H100 node power models for accurate AI training energy estimation

Accurately quantifying the energy use of artificial intelligence (AI) training is critical for infrastructure planning, carbon accounting, and sustainable data center operation, but few studies have directly measured the power consumption of production workloads on contemporary hardware. By combining empirical measurements from Brookhaven National Laboratory during AI training on 8-graphics-processing-unit H100 systems with open-source benchmarking data, we develop statistical models relating computational intensity to node-level power consumption. We measure the gap between manufacturer-rated thermal design power (TDP) and actual power demand during AI training. Our analysis reveals that even computationally intensive workloads operate at only 76% of the 10.2 kW TDP rating. Our architecture-specific model, calibrated to floating-point operations, predicts energy consumption with 11.4% mean absolute percentage error, significantly outperforming TDP-based approaches (27%–37% error). We identified distinct power signatures between transformer and convolutional neural network architectures, with transformers showing characteristic fluctuations that may impact grid stability. These results provide a measurement-grounded basis for improving AI training energy estimates, enabling more reliable infrastructure sizing, cost projections, and environmental impact assessments.

Newkirk, Alex C↗
DOE OSTI2020

MARBLE: A Multi-GPU Aware Job Scheduler for Deep Learning on HPC Systems

Deep learning (DL) has become a key tool for solving complex scientific problems. However, managing the multi-dimensional large-scale data associated with DL, especially atop extant multiple graphics processing units (GPUs) in modern supercomputers poses significant challenges. Moreover, the latest high-performance computing (HPC) architectures bring different performance trends in training throughput compared to the existing studies. Existing DL optimizations such as larger batch size and GPU locality-aware scheduling have little effect on improving DL training throughput performance due to fast CPU-to-GPU connections. Additionally, DL training on multiple GPUs scales sublinearly. Thus, simply adding more GPUs to a system is ineffective. To this end, we design MARBLE, a first-of-its-kind job scheduler, which considers the non-linear scalability of GPUs at the intra-node level to schedule an appropriate number of GPUs per node for a job. By sharing the GPU resources on a node with multiple DL jobs, MARBLE avoids low GPU utilization in current multi-GPU DL training on HPC systems. Our comprehensive evaluation in the Summit supercomputer shows that MARBLE is able to improve DL training performance by up to 48.3% compared to the popular Platform Load Sharing Facility (LSF) scheduler. Compared to the state-of-the-art of DL scheduler, Optimus, MARBLE reduces the job completion time by up to 47%.

Han, Jingoo↗
DOE OSTI2022

Kronecker-structured covariance models for multiway data

Many applications produce multiway data of exceedingly high dimension. Modeling such multi-way data is important in multichannel signal and video processing where sensors produce multi-indexed data, e.g. over spatial, frequency, and temporal dimensions. We will address the challenges of covariance representation of multiway data and review some of the progress in statistical modeling of multiway covariance over the past two decades, focusing on tensor-valued covariance models and their inference. We will illustrate through a space weather application: predicting the evolution of solar active regions over time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Matrix Product (GEMM) Performance Data from GPUs

Timing data for mixed precision GEMM matrix product operations on several GPU models, including NVIDIA V100 and A100, AMD MI100 and Intel P580. Also data from machine learning model training on this data using Scikit-learn.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1980

Linking of the BENSON graph-plotter with the Elektronika-1001 computer

A device, developed by the Institute of Space Research of the Academy of Sciences of the USSR, for linking the Elektronika-100I computer with the BENSON graph-plotter is described. Programs are compiled which provide display of graphic and alphanumeric information. Instructions for their utilization are given.

Valtts, I. Y.↗
NASA NTRS1981

Flow visualization using a computerized data acquisition system

A computer-driven traversing mechanism combined with mass data storage, data reduction programs, and general-purpose graphics programs permits a visualization of complex flows. A unique seven-hole probe is used which permits reasonably accurate measurements of all average flow properties if the local flow angle does not exceed 80 degrees. A description is given of the wake of a lifting canard surface as this wake passes over a wing. The flow includes concentrated and dissipating vortices, large regions of reduced total pressure, and local flow angles up to 60 deg. All these features can be clearly seen and accurately located in the graphical output.

Gallington, R.↗
NASA NTRS1988

Chemical constraints on the water and total oxygen abundances in the deep atmosphere of Jupiter

The mechanisms responsible for the observed H2O/H2 mixing ratio (HMR) in the Jovian troposphere are analyzed, with a focus on the relationship between HMR and O2 abundance and the abundance of the nonequilibrium trace gases CO and SiH4. The results of computations using a Jupiter atmosphere model consistent with recent observations (Bjoraker et al., 1986) are presented graphically and discussed in detail. It is found that the observed mixing ratios of CO (about 10 to the -9th) and SiH4 (upper limit 2-4 x 10 to the -9th) preclude O2 depletion and the presence of significant global H2O. The low observed HMRs (0.00003 at 6 bar) are tentatively attributed to local condensation in cloud-forming regions.

Fegley, Bruce, Jr.↗
NASA NTRS1989

Space shuttle propulsion estimation development verification, volume 1

The results of the Propulsion Estimation Development Verification are summarized. A computer program developed under a previous contract (NAS8-35324) was modified to include improved models for the Solid Rocket Booster (SRB) internal ballistics, the Space Shuttle Main Engine (SSME) power coefficient model, the vehicle dynamics using quaternions, and an improved Kalman filter algorithm based on the U-D factorized algorithm. As additional output, the estimated propulsion performances, for each device are computed with the associated 1-sigma bounds. The outputs of the estimation program are provided in graphical plots. An additional effort was expended to examine the use of the estimation approach to evaluate single engine test data. In addition to the propulsion estimation program PFILTER, a program was developed to produce a best estimate of trajectory (BET). The program LFILTER, also uses the U-D factorized algorithm form of the Kalman filter as in the propulsion estimation program PFILTER. The necessary definitions and equations explaining the Kalman filtering approach for the PFILTER program, the models used for this application for dynamics and measurements, program description, and program operation are presented.

Rogers, Robert M.↗
NASA NTRS1991

User manual for two simple postscript output FORTRAN plotting routines

Graphics is one of the important tools in engineering analysis and design. However, plotting routines that generate output on high quality laser printers normally come in graphics packages, which tend to be expensive and system dependent. These factors become important for small computer systems or desktop computers, especially when only some form of a simple plotting routine is sufficient. With the Postscript language becoming popular, there are more and more Postscript laser printers now available. Simple, versatile, low cost plotting routines that can generate output on high quality laser printers are needed and standard FORTRAN language plotting routines using output in Postscript language seems logical. The purpose here is to explain two simple FORTRAN plotting routines that generate output in Postscript language.

Nguyen, T. X.↗
NASA NTRS1992

HiRel - Reliability/availability integrated workstation tool

The HiRel software tool is described and demonstrated by application to the mission avionics subsystem of the Advanced System Integration Demonstrations (ASID) system that utilizes the PAVE PILLAR approach. HiRel marks another accomplishment toward the goal of producing a totally integrated computer-aided design (CAD) workstation design capability. Since a reliability engineer generally represents a reliability model graphically before it can be solved, the use of a graphical input description language increases productivity and decreases the incidence of error. The graphical postprocessor module HARPO makes it possible for reliability engineers to quickly analyze huge amounts of reliability/availability data to observe trends due to exploratory design changes. The addition of several powerful HARP modeling engines provides the user with a reliability/availability modeling capability for a wide range of system applications all integrated under a common interactive graphical input-output capability.

Bavuso, Salvatore J.↗
NASA NTRS1995

Windows Program For Driving The TDU-850 Printer

Program provides WYSIWYG compatibility between video display and printout. PDW is Microsoft Windows printer-driver computer program for use with Raytheon TDU-850 printer. Provides previously unavailable linkage between printer and IBM PC-compatible computers running Microsoft Windows. Enhances capabilities of Raytheon TDU-850 hardcopier by emulating all textual and graphical features normally supported by laser/ink-jet printers and makes printer compatible with any Microsoft Windows application. Also provides capabilities not found in laser/ink-jet printer drivers by providing certain Windows applications with ability to render high quality, true gray-scale photographic hardcopy on TDU-850. Written in C language.

Parrish, Brett T.↗
NASA NTRS1990

Building an intelligent tutoring system for procedural domains

Jobs that require complex skills that are too expensive or dangerous to develop often use simulators in training. The strength of a simulator is its ability to mimic the 'real world', allowing students to explore and experiment. A good simulation helps the student develop a 'mental model' of the real world. The closer the simulation is to 'real life', the less difficulties there are transferring skills and mental models developed on the simulator to the real job. As graphics workstations increase in power and become more affordable they become attractive candidates for developing computer-based simulations for use in training. Computer based simulations can make training more interesting and accessible to the student.

Warinner, Andrew↗
NASA NTRS1997

Sensitivity Analysis and Optimization of Aerodynamic Configurations with Blend Surfaces

A novel (geometrical) parametrization procedure using solutions to a suitably chosen fourth order partial differential equation is used to define a class of airplane configurations. Inclusive in this definition are surface grids, volume grids, and grid sensitivity. The general airplane configuration has wing, fuselage, vertical tail and horizontal tail. The design variables are incorporated into the boundary conditions, and the solution is expressed as a Fourier series. The fuselage has circular cross section, and the radius is an algebraic function of four design parameters and an independent computational variable. Volume grids are obtained through an application of the Control Point Form method. A graphic interface software is developed which dynamically changes the surface of the airplane configuration with the change in input design variable. The software is made user friendly and is targeted towards the initial conceptual development of any aerodynamic configurations. Grid sensitivity with respect to surface design parameters and aerodynamic sensitivity coefficients based on potential flow is obtained using an Automatic Differentiation precompiler software tool ADIFOR. Aerodynamic shape optimization of the complete aircraft with twenty four design variables is performed. Unstructured and structured volume grids and Euler solutions are obtained with standard software to demonstrate the feasibility of the new surface definition.

Thomas, A. M.↗