Search NASA⌕ Search

SEARCH · Search NASA

Results for “CUDA”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

A High-Performance Computing GNSS-aware Path Planning Algorithm for Safe Urban Flight Operations

The emergence and development of advanced technologies and vehicle types have created a growing demand for new forms of flight operations. These new and increasingly complex operational paradigms, such as Advanced and Urban Air Mobility (AAM/UAM), present regulatory authorities and the aviation community with several design-and-implementation challenges – particularly for highly autonomous vehicles. An overarching and daunting task is to develop protocols that can integrate these operations without compromising safety or disrupting traditional airspace operations. A shift toward a more predictive, autonomous, risk mitigation capability becomes critical to meet this challenge. This paper proposes and evaluates a computationally-efficient path planning approach to perform pre-flight planning and autonomous in-flight re-routing to minimize exposures to selected hazards. In our evaluation, hazards associated with degraded and missing critical GPS navigation data are considered. In this paper, we first present a high-performance computing path planning approach based on an adapted Bellman-Ford algorithm, developed in the CUDA programming language. Using the adapted path planning algorithm, we test this algorithm when encountering issues with GPS quality, and deliver an implementation that can produce flight paths that minimize exposure to risks, while maintaining a low computational burden. In our evaluation, the computation of periodic and aperiodic path updates are evaluated, prioritizing specific events as triggers for updates, based on changes to satellite availability. These critical events can lead to significant exposure to navigational hazards if not dealt with correctly.

GNSS↗
NASA NTRSDate not supplied

A High-Performance Computing GNSS-aware Path Planning Algorithm for Safe Urban Flight Operations

The emergence and development of advanced technologies and vehicle types have created a growing demand for new forms of flight operations. These new and increasingly complex operational paradigms, such as Advanced and Urban Air Mobility (AAM/UAM), present regulatory authorities and the aviation community with several design-and-implementation challenges – particularly for highly autonomous vehicles. An overarching and daunting task is to develop protocols that can integrate these operations without compromising safety or disrupting traditional airspace operations. A shift toward a more predictive, autonomous, risk mitigation capability becomes critical to meet this challenge. This paper proposes and evaluates a computationally-efficient path planning approach to perform pre-flight planning and autonomous in-flight re-routing to minimize exposures to selected hazards. In our evaluation, hazards associated with degraded and missing critical GPS navigation data are considered. In this paper, we first present a high-performance computing path planning approach based on an adapted Bellman-Ford algorithm, developed in the CUDA programming language. Using the adapted path planning algorithm, we test this algorithm when encountering issues with GPS quality, and deliver an implementation that can produce flight paths that minimize exposure to risks, while maintaining a low computational burden. In our evaluation, the computation of periodic and aperiodic path updates are evaluated, prioritizing specific events as triggers for updates, based on changes to satellite availability. These critical events can lead to significant exposure to navigational hazards if not dealt with correctly.

GNSS↗
NASA NTRSDate not supplied

Porting OVERFLOW CFD Code to GPUs: To Hackathons and Beyond!

OVERFLOW is an overset, structured computational fluid dynamics (CFD) code written in Fortran which is widely used in the government, industry, and academia. Over the last several years the OVERFLOW developers have been working to port miniapps based on computationally expensive parts of OVERFLOW to run on GPUs, primarily using OpenACC. This effort started at our first hackathon in 2019 and since then the OVERFLOW team has attended two additional hackathons (virtually). These hackathon environments have provided a great place to collaborate with others and learn from experts. These learning experiences enabled porting two miniapps to run effectively on NVIDIA GPUs using OpenACC. The first miniapp focused on motifs found in the solver itself and the final ported version runs three times fast ona single V100 compared to a 40 core, dual-socket Intel Skylake node. The speed up in this solverminiapp required multiple design changes including increasing the amount of parallelism available and the amount of work performed in each kernel. The second miniapp focused on overset MPI communication, also saw significant speedups over the CPU implementation using a CUDA-aware MPI implementation through OpenACC. This presentation will discuss our experience at the hackathons, our process of porting the miniapps to run on the GPUs, and several lessons learned throughout.

OpenACC↗
NASA NTRSDate not supplied

A Multi-Architecture Approach for Implicit Computational Fluid Dynamics on Unstructured Grids

High-performance computing (HPC) architectures are trending toward manycore paradigms such as graphics processing units (GPUs). Approximately half of the top 100 publicly disclosed supercomputers in the world utilize GPU accelerators for performance. This is in contrast to a decade ago, where there were only a few such machines in the top 100. It is not currently possible to compile and run legacy central processing unit (CPU) software efficiently on GPUs without significant refactoring. Though a number of frameworks offering performance portability exist, none offer a standardized specification that is supported by all major hardware vendors. Additionally, experiences show that obtaining a high percentage of peak performance often requires architecture-specific code. This work details a pragmatic multi-architecture computational fluid dynamics library focused on aerospace problems across the speed range from low subsonic to hypersonic flows involving thermochemical nonequilibrium. A thin abstraction layer above NVIDIA CUDA C++ is utilized, which enables primarily single-source software currently capable of running efficiently on multicore CPUs, NVIDIA GPUs, AMD GPUs, and Intel GPUs. Results on various problems of interest across the speed range are presented and performance is compared between various architectures.

GPU↗
NASA NTRSDate not supplied

A Multi-Architecture Approach for Implicit Computational Fluid Dynamics on Unstructured Grids

High-performance computing (HPC) architectures are trending toward manycore paradigms such as graphics processing units (GPUs). Approximately half of the top 100 publicly disclosed supercomputers in the world utilize GPU accelerators for performance. This is in contrast to a decade ago, where there were only a few such machines in the top 100. It is not currently possible to compile and run legacy central processing unit (CPU) software efficiently on GPUs without significant refactoring. Though a number of frameworks offering performance portability exist, none offer a standardized specification that is supported by all major hardware vendors. Additionally, experiences show that obtaining a high percentage of peak performance often requires architecture-specific code. This work details a pragmatic multi-architecture computational fluid dynamics library focused on aerospace problems across the speed range from low subsonic to hypersonic flows involving thermochemical nonequilibrium. A thin abstraction layer above NVIDIA CUDA C++ is utilized, which enables primarily single-source software currently capable of running efficiently on multicore CPUs, NVIDIA GPUs, AMD GPUs, and Intel GPUs. Results on various problems of interest across the speed range are presented and performance is compared between various architectures.

GPU↗
NASA NTRS2023

Framework for Extensible, Asynchronous Task Scheduling (FEATS) in Fortran

Most parallel scientific programs contain compiler directives (pragmas) such as those from OpenMP, explicit calls to runtime library procedures such as those implementing the Message Passing Interface (MPI), or compiler-specific language extensions such as those provided by CUDA. By contrast, the recent Fortran standards empower developers to express parallel algorithms without directly referencing lower-level parallel programming models. Fortran’s parallel features place the language within the Partitioned Global Address Space (PGAS) class of programming models. When writing programs that exploit data-parallelism, application developers often find it straightforward to develop custom parallel algorithms. Problems involving complex, heterogeneous, staged calculations, however, pose much greater challenges. Such applications require careful coordination of tasks in a manner that respects dependencies prescribed by a directed acyclic graph. When rolling one’s own solution proves difficult, extending a customizable framework becomes attractive. The paper presents the design, implementation, and use of the Framework for Extensible Asynchronous Task Scheduling (FEATS), which we believe to be the first task-scheduling tool written in modern Fortran. We describe the benefits and compromises associated with choosing Fortran as the implementation language, and we propose ways in which future Fortran standards can best support the use case in this paper.

Modern Fortran↗
NASA NTRS1976

Pulse height response of an optical particle counter to monodisperse aerosols

The pulse height response of a right angle scattering optical particle counter has been investigated using monodisperse aerosols of polystyrene latex spheres, di-octyl phthalate and methylene blue. The results confirm previous measurements for the variation of mean pulse height as a function of particle diameter and show good agreement with the relative response predicted by Mie scattering theory. Measured cumulative pulse height distributions were found to fit reasonably well to a log normal distribution with a minimum geometric standard deviation of about 1.4 for particle diameters greater than about 2 micrometers. The geometric standard deviation was found to increase significantly with decreasing particle diameter.

Wilmoth, R. G.↗
NASA NTRS1980

Outer planet satellite return missions using in situ propellant production

In situ production of oxygen and oxygen with hydrogen for utilization as return propellant from the Galilean satellites has been investigated. Europa has emerged as the preferred landing sight because of the availability of water ice and its surface temperature. When oxygen is used with methane transported from earth, a Europa sample return mission requires 4000 kg less estimated earth launch mass than a vehicle using space storable propellant. Neither methane nor oxygen require active refrigeration at Europa. When oxygen and hydrogen are both utilized to form the primary sample return propellant, the required processor mass increases, but the estimated earth launch mass requirement is reduced by an additional 550 kg.

Ash, R. L.↗
NASA NTRS1986

Direct simulation of hypersonic flows over blunt slender bodies

Results of a numerical study of low-density hypersonic flow about cylindrically blunted wedges and spherically blunted cones with body half angles of 0, 5, and 10 deg are presented. Most of the transitional flow regime encountered during entry between the free molecule and continuum regimes is simulated for a reentry velocity of 7.5 km/s by including freestream conditions of 70 to 100 km. The bodies are at zero angle of incidence and have diffuse and finite catalytic surfaces. Translational, thermodynamic, and chemical nonequilibrium effects are considered in the numerical simulation by utilizing the direct simulation Monte Carlo (DSMC) method. The numerical simulations show that noncontinuum effects such as surface temperature jump, and velocity slip are evident for all cases considered. The onset of chemical dissociation occurs at a simulated altitude of 96 km for the two-dimensional configurations. Comparisons between the DSMC and continuum viscous shock-layer calculations highlight the significant difference in flowfield structure predicted by the two methods.

Moss, J. N.↗
NASA NTRS1987

Nonequilibrium effects for hypersonic transitional flows

Presented are the results of numerical simulations of hypersonic flow about blunt cones and hemispherical nose configurations for reentry velocities of 7.5 and 10 km/s. Cone half angles 0, 5, and 10 deg are considered at zero angle of incidence; however, the focus is for the 5 deg cone. The body size and altitude ranges considered (70 to 110 km) are such that the flow is in the transitional regime. Translational, thermodynamic, and chemical nonequilibrium effects are considered in the numerical simulation by utilizing the direct simulation Monte Carlo (DSMC) method of Bird. The DSMC results are compared with those obtained with viscous shock-layer and Navier-Stokes methods. Comparisons between the DSMC and continuum calculations show the altitude range where differences in flowfield structure and surface quantities become significant. The current calculations show that the binary scaling similitude provides a means of correlating the blunt body surface quantities in the hypersonic, transitional regime. Furthermore, for the higher velocity entry conditions, the results highlight some of the concerns in the application of multitemperature continuum formulations, particularly the use of some proposed functional relations for the chemical rate constants under thermodynamic nonequilibrium conditions.

Moss, James N.↗
NASA NTRS1994

Characterization of spacecraft and environmental disturbances on a SmallSat

The objective of this study is to model the on-orbit vibration environment encountered by a SmallSat. Vibration control issues are common to the Earth observing, imaging, and microgravity communities. A spacecraft may contain dozens of support systems and instruments each a potential source of vibration. The quality of payload data depends on constraining vibration so that parasitic disturbances do not affect the payload's pointing or microgravity requirement. In practice, payloads are designed incorporating existing flight hardware in many cases with nonspecific vibration performance. Thus, for the development of a payload, designers require a thorough knowledge of existing mechanical devices and their associated disturbance levels. This study evaluates a SmallSat mission and seeks to answer basic questions concerning on-orbit vibration. Payloads were considered from the Earth observing, microgravity, and imaging communities. Candidate payload requirements were matched to spacecraft bus resources of present day SmallSats. From the set of candidate payloads, the representative payload GLAS (Geoscience Laser Altimeter System) was selected. The requirements of GLAS were considered very stringent for the 150 - 500 kg class of payloads. Once the payload was selected, a generic SmallSat was designed in order to accommodate the payload requirements (weight, size, power, etc.). This study seeks to characterize the on-orbit vibration environment of a SmallSat designed for this type of mission and to determine whether a SmallSat can provide the precision pointing and jitter control required for earth observing payloads.

Johnson, Thomas A.↗
NASA NTRS1996

Using Fast-Steering Mirror Control to Reduce Instrument Pointing Errors Caused by Spacecraft Jitter

The scope of this study was to investigate the benefit of using feedback control of a Fast Steering Mirror (FSM) to reduce instrument pointing errors. Initially, the study identified FSM control technologies and categorized them according to their use, range of applicability, and physical requirements. Candidate payloads were then evaluated according to their relevance in use of fast steering minor control technologies. This leads to the mission and instrument selection which served as the candidate mission for numerical modeling. A standard SmallSat was designed in order to accommodate the payload requirements (weight, size, power, etc.). This included sizing the SmallSat bus, sizing the solar array, choosing appropriate antennas, and identifying an attitude control system (ACS). A feedback control system for the FSM compensation was then designed, and the instrument pointing error and SmallSat jitter environment for open-loop and closed-loop FSM control were evaluated for typical SmallSat disturbances. The results were then compared to determine the effectiveness of the FSM feedback control system.

Antol, Jeffery↗
NASA NTRS2008

Analysis of the Effects of Vitiates on Surface Heat Flux in Ground Tests of Hypersonic Vehicles

To achieve the high enthalpy conditions associated with hypersonic flight, many ground test facilities burn fuel in the air upstream of the test chamber. Unfortunately, the products of combustion contaminate the test gas and alter gas properties and the heat fluxes associated with aerodynamic heating. The difference in the heating rates between clean air and a vitiated test medium needs to be understood so that the thermal management system for hypersonic vehicles can be properly designed. This is particularly important for advanced hypersonic vehicle concepts powered by air-breathing propulsion systems that couple cooling requirements, fuel flow rates, and combustor performance by flowing fuel through sub-surface cooling passages to cool engine components and preheat the fuel prior to combustion. An analytical investigation was performed comparing clean air to a gas vitiated with methane/oxygen combustion products to determine if variations in gas properties contributed to changes in predicted heat flux. This investigation started with simple relationships, evolved into writing an engineering-level code, and ended with running a series of CFD cases. It was noted that it is not possible to simultaneously match all of the gas properties between clean and vitiated test gases. A study was then conducted selecting various combinations of freestream properties for a vitiated test gas that matched clean air values to determine which combination of parameters affected the computed heat transfer the least. The best combination of properties to match was the free-stream total sensible enthalpy, dynamic pressure, and either the velocity or Mach number. This combination yielded only a 2% difference in heating. Other combinations showed departures of up to 10% in the heat flux estimate.

Cuda, Vincent↗
NASA NTRS2010

Heat Flux and Wall Temperature Estimates for the NASA Langley HIFiRE Direct Connect Rig

An objective of the Hypersonic International Flight Research Experimentation (HIFiRE) Program Flight 2 is to provide validation data for high enthalpy scramjet prediction tools through a single flight test and accompanying ground tests of the HIFiRE Direct Connect Rig (HDCR) tested in the NASA LaRC Arc Heated Scramjet Test Facility (AHSTF). The HDCR is a full-scale, copper heat sink structure designed to simulate the isolator entrance conditions and isolator, pilot, and combustor section of the HIFiRE flight test experiment flowpath and is fully instrumented to assess combustion performance over a range of operating conditions simulating flight from Mach 5.5 to 8.5 and for various fueling schemes. As part of the instrumentation package, temperature and heat flux sensors were provided along the flowpath surface and also imbedded in the structure. The purpose of this paper is to demonstrate that the surface heat flux and wall temperature of the Zirconia coated copper wall can be obtained with a water-cooled heat flux gage and a sub-surface temperature measurement. An algorithm was developed which used these two measurements to reconstruct the surface conditions along the flowpath. Determinations of the surface conditions of the Zirconia coating were conducted for a variety of conditions.

Cuda, Vincent, Jr.↗
NASA NTRS2008

Real-Time Wavefront Control for the PALM-3000 High Order Adaptive Optics System

We present a cost-effective scalable real-time wavefront control architecture based on off-the-shelf graphics processing units hosted in an ultra-low latency, high-bandwidth interconnect PC cluster environment composed of modules written in the component-oriented language of nesC. The architecture enables full-matrix reconstruction of the wavefront at up to 2 KHz with latency under 250 us for the PALM-3000 adaptive optics systems, a state-of-the-art upgrade on the 5.1 meter Hale Telescope that consists of a 64 x 64 subaperture Shack-Hartmann wavefront sensor and a 3368 active actuator high order deformable mirror in series with a 241 active actuator tweeter DM. The architecture can easily scale up to support much larger AO systems at higher rates and lower latency.

GPU↗
NASA NTRS2022

Instrumentation and Testing of Ground and Flight Hardware

The goal of this white paper is to highlight some of the key issues associated with the instrumentation and testing of ground and flight hardware. The information is arranged topically and follows a line of organization that begins with the development of test objectives, the development of requirements, the purchase and installation of instrumentation, and covers many considerations to ensure that measurements will provide the required data during the conduct of the test. Ideally, all of these considerations would be factored into a test program; however, due to programmatic, budgetary, and calendar restraints, only a subset of these factors will typically be considered. Although the primary emphasis of this text is on thermal measurements, all disciplines can benefit from these recommendations.

Thermocouple↗