Search NASA⌕ Search

SEARCH · Search NASA

Results for “hardware performance”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,171 records · Page 65
All sourcesNASA NTRSDOE OSTI
NASA NTRS1992

Scalable parallel communications

Coarse-grain parallelism in networking (that is, the use of multiple protocol processors running replicated software sending over several physical channels) can be used to provide gigabit communications for a single application. Since parallel network performance is highly dependent on real issues such as hardware properties (e.g., memory speeds and cache hit rates), operating system overhead (e.g., interrupt handling), and protocol performance (e.g., effect of timeouts), we have performed detailed simulations studies of both a bus-based multiprocessor workstation node (based on the Sun Galaxy MP multiprocessor) and a distributed-memory parallel computer node (based on the Touchstone DELTA) to evaluate the behavior of coarse-grain parallelism. Our results indicate: (1) coarse-grain parallelism can deliver multiple 100 Mbps with currently available hardware platforms and existing networking protocols (such as Transmission Control Protocol/Internet Protocol (TCP/IP) and parallel Fiber Distributed Data Interface (FDDI) rings); (2) scale-up is near linear in n, the number of protocol processors, and channels (for small n and up to a few hundred Mbps); and (3) since these results are based on existing hardware without specialized devices (except perhaps for some simple modifications of the FDDI boards), this is a low cost solution to providing multiple 100 Mbps on current machines. In addition, from both the performance analysis and the properties of these architectures, we conclude: (1) multiple processors providing identical services and the use of space division multiplexing for the physical channels can provide better reliability than monolithic approaches (it also provides graceful degradation and low-cost load balancing); (2) coarse-grain parallelism supports running several transport protocols in parallel to provide different types of service (for example, one TCP handles small messages for many users, other TCP's running in parallel provide high bandwidth service to a single application); and (3) coarse grain parallelism will be able to incorporate many future improvements from related work (e.g., reduced data movement, fast TCP, fine-grain parallelism) also with near linear speed-ups.

Maly, K.↗
NASA NTRS1980

Engine diagnostics program: CF6-50 engine performance deterioration

Cockpit cruise recordings and test cell data in conjunction with hardware inspection results from airline overhaul shops were analyzed to define the extent and magnitude of performance deterioration of the General Electric CF6-50 high bypass turbofan engine. The magnitude of short term deterioration was isolated from the long term, and the individual damage mechanisms that were the cause for the majority of the performance deterioration was identified. It was determined that the long term engine performance deterioration characteristics were different for the 3 aircraft types currently powered by the CF6-50 engine, but these differences were due to operational considerations (flight length and takeoff derate) and not to differences associated with the aircraft type. Unrestored losses, that is, performance deterioration which remains after engine refurbishment, represents over 70 percent of the total performance deterioration at engine shop visit. Superficial damage, such as, increased surface roughness, leading edge shape changes on airfoils, and increases in the average clearances between rotating and stationary components is the major contributor to these losses. Seventy one percent of the unrestored losses are cost effective to restore, and if implemented could reduce fuel consumed by CF6-50 engines by 26 million gallons in 1980.

Wulf, R. H.↗
NASA NTRS1999

Aqueous Cleaning and Validation for Space Shuttle Propulsion Hardware at the White Sands Test Facility

The NASA White Sands Test Facility (WSTF) has developed an entirely aqueous final cleaning and verification process to replace the current chlorofluorocarbon (CFC) 113 based process. This process has been accepted for final cleaning and cleanliness verification of WSTF ground support equipment. The aqueous process relies on ultrapure water at 50 C (323 K) and ultrasonic agitation for removal of organic compounds and particulate. The cleanliness is verified bv determining the total organic carbon (TOC) content and filtration with particulate counting. The effectiveness of the aqueous methods for detecting hydrocarbon contamination and particulate was compared to the accepted CFC 113 sampling procedures. Testing with known contaminants, such as hydraulic fluid and cutting and lubricating oils, to establish a correlation between aqueous TOC and CFC 113 nonvolatile residue (NVR) was performed. Particulate sampling on cleaned batches of hardware that were randomly separated and sampled by the two methods was performed. This paper presents the approach and results, and discusses the issues in establishing the equivalence of aqueous sampling to CFC 113 sampling, while describing the approach for implementing aqueous techniques on Space Shuttle Propulsion hardware.

Hornung, Steven D.↗
DOE OSTI2025

Preparing MPICH for exascale

The advent of exascale supercomputers heralds a new era of scientific discovery, yet it introduces significant architectural challenges that must be overcome for MPI applications to fully exploit its potential. Among these challenges is the adoption of heterogeneous architectures, particularly the integration of GPUs to accelerate computation. Additionally, the complexity of multithreaded programming models has also become a critical factor in achieving performance at scale. The efficient utilization of hardware acceleration for communication, provided by modern NICs, is also essential for achieving low latency and high throughput communication in such complex systems. In response to these challenges, the MPICH library, a high-performance and widely used Message Passing Interface (MPI) implementation, has undergone significant enhancements. Here, this paper presents four major contributions that prepare MPICH for the exascale transition. First, we describe a lightweight communication stack that leverages the advanced features of modern NICs to maximize hardware acceleration. Second, our work showcases a highly scalable multithreaded communication model that addresses the complexities of concurrent environments. Third, we introduce GPU-aware communication capabilities that optimize data movement in GPU-integrated systems. Finally, we present a new datatype engine aimed at accelerating the use of MPI derived datatypes on GPUs. These improvements in the MPICH library not only address the immediate needs of exascale computing architectures but also set a foundation for exploiting future innovations in high-performance computing. By embracing these new designs and approaches, MPICH-derived libraries from HPE Cray and Intel were able to achieve real exascale performance on OLCF Frontier and ALCF Aurora respectively.

Guo, Yanfei [Argonne National Laboratory (ANL), Ar↗
DOE OSTI2024

Neural network methods for radiation detectors and imaging

Recent advances in image data proccesing through deep learning allow for new optimization and performance-enhancement schemes for radiation detectors and imaging hardware. This enables radiation experiments, which includes photon sciences in synchrotron and X-ray free electron lasers as a subclass, through data-endowed artificial intelligence. We give an overview of data generation at photon sources, deep learning-based methods for image processing tasks, and hardware solutions for deep learning acceleration. Most existing deep learning approaches are trained offline, typically using large amounts of computational resources. However, once trained, DNNs can achieve fast inference speeds and can be deployed to edge devices. A new trend is edge computing with less energy consumption (hundreds of watts or less) and real-time analysis potential. While popularly used for edge computing, electronic-based hardware accelerators ranging from general purpose processors such as central processing units (CPUs) to application-specific integrated circuits (ASICs) are constantly reaching performance limits in latency, energy consumption, and other physical constraints. These limits give rise to next-generation analog neuromorhpic hardware platforms, such as optical neural networks (ONNs), for high parallel, low latency, and low energy computing to boost deep learning acceleration (LA-UR-23-32395).

edge computing↗
NASA NTRS2017

Surveys of Returned ISS Hardware for MMMOD Impacts

Since February 2001, the Hypervelocity Impact Technology (HVIT) group at the Johnson Space Center (JSC) in Houston has performed 35 post-flight inspections on space exposed hardware returned from the International Space Station (ISS). Data on 1,188 observations of micrometeoroid and orbital debris (MMOD) damage have been collected from these inspections. Survey documentation typically includes impact feature location and size measurements as well as microscopic photography (25-200x). Sampling of impacts sites for projectile residue was performed for the largest features. Results of energy dispersive X-ray spectroscopic analysis to discern impactor source are included in the database when available. This paper will focus on two inspections, the Pressurized Mating Adapter 2 (PMA-2) cover returned in 2015 after 1.6 years exposure with 26 observed impact features, and two Airlock shield panels returned in 2010 after 8.75 years exposure with 58 MMOD impacts. Feature sizes from the observed data are compared to predictions using the Bumper 3 risk assessment code.

Hyde, J. L.↗
DOE OSTI2024

Neural units with time-dependent functionality

We show that the time-resolved dynamics of an underdamped harmonic oscillator can be used to do multifunctional computation, performing distinct computations at distinct times within a single dynamical trajectory. We consider the amplitude of an oscillator whose inputs influence its frequency. The activity of the oscillator at fixed times is a nonmonotonic function of its inputs, so it can solve problems such as XOR that are not linearly separable. The activity of the oscillator at fixed input is a nonmonotonic function of time, so it is multifunctional in a temporal sense, and able to carry out distinct nonlinear computations at distinct times within the same dynamical trajectory. We show that a single oscillator, observed at different times, can act as all of the elementary logic gates and perform binary addition, the latter usually implemented in hardware using five logic gates. We show that a set of n oscillators, observed at different times, can perform an arbitrary number of analog-to-n-bit digital conversions. We also show that oscillators can be trained by gradient descent to perform distinct classification tasks at distinct times. Computing with time-dependent functionality can be done in or out of equilibrium, and suggests a way of reducing the number of parameters or devices required to do nonlinear computations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

GANpiler

Focal Area(s): Rather than augment or replace physical models with machine learning, we instead preserve the existing models and augment the underlying code with faster surrogate models created by generative adversarial networks (GAN). To leverage the performance optimization, we also propose a runtime system and user interfaces that allow prediction and tracking of accumulated error as well as dynamic, per-process decision making as to which model (if any) to use for each iteration. Science Challenge: This proposal sits at the nexus of two hard problems. First, climate models based on machine learning will be, by their nature, difficult to trust once their predictions begin diverging from the consensus. Second, compilers and hardware have been making only incremental performance gains for decades. GPGPUs have provided a welcome performance boost for codes that can take advantage of them, but there is no similar technology on the horizon to provide the next performance leap.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2011

Planetary Suit Hip Bearing Model for Predicting Design vs. Performance

Designing a planetary suit is very complex and often requires difficult trade-offs between performance, cost, mass, and system complexity. In order to verifying that new suit designs meet requirements, full prototypes must eventually be built and tested with human subjects. Using computer models early in the design phase of new hardware development can be advantageous, allowing virtual prototyping to take place. Having easily modifiable models of the suit hard sections may reduce the time it takes to make changes to the hardware designs and then to understand their impact on suit and human performance. A virtual design environment gives designers the ability to think outside the box and exhaust design possibilities before building and testing physical prototypes with human subjects. Reductions in prototyping and testing may eventually reduce development costs. This study is an attempt to develop computer models of the hard components of the suit with known physical characteristics, supplemented with human subject performance data. Objectives: The primary objective was to develop an articulating solid model of the Mark III hip bearings to be used for evaluating suit design performance of the hip joint. Methods: Solid models of a planetary prototype (Mark III) suit s hip bearings and brief section were reverse-engineered from the prototype. The performance of the models was then compared by evaluating the mobility performance differences between the nominal hardware configuration and hardware modifications. This was accomplished by gathering data from specific suited tasks. Subjects performed maximum flexion and abduction tasks while in a nominal suit bearing configuration and in three off-nominal configurations. Performance data for the hip were recorded using state-of-the-art motion capture technology. Results: The results demonstrate that solid models of planetary suit hard segments for use as a performance design tool is feasible. From a general trend perspective, the suited performance trends were comparable between the model and the suited subjects. With the three off-nominal bearing configurations compared to the nominal bearing configurations, human subjects showed decreases in hip flexion of 64%, 6%, and 13% and in hip abduction of 59%, 2%, and 20%. Likewise the solid model showed decreases in hip flexion of 58%, 1%, and 25% and in hip abduction of 56%, 0%, and 30%, under the same condition changes from the nominal configuration. Differences seen between the model predictions and the human subject performance data could be attributed to the model lacking dynamic elements and performing kinematic analysis only, the level of fit of the subjects with the suit, the levels of the subject s suit experience.

Cowley, Matthew S.↗
NASA NTRS2016

CASIS Fact Sheet: Hardware and Facilities

Vencore is a proven information solutions, engineering, and analytics company that helps our customers solve their most complex challenges. For more than 40 years, we have designed, developed and delivered mission-critical solutions as our customers' trusted partner. The Engineering Services Contract, or ESC, provides engineering and design services to the NASA organizations engaged in development of new technologies at the Kennedy Space Center. Vencore is the ESC prime contractor, with teammates that include Stinger Ghaffarian Technologies, Sierra Lobo, Nelson Engineering, EASi, and Craig Technologies. The Vencore team designs and develops systems and equipment to be used for the processing of space launch vehicles, spacecraft, and payloads. We perform flight systems engineering for spaceflight hardware and software; develop technologies that serve NASA's mission requirements and operations needs for the future. Our Flight Payload Support (FPS) team at Kennedy Space Center (KSC) provides engineering, development, and certification services as well as payload integration and management services to NASA and commercial customers. Our main objective is to assist principal investigators (PIs) integrate their science experiments into payload hardware for research aboard the International Space Station (ISS), commercial spacecraft, suborbital vehicles, parabolic flight aircrafts, and ground-based studies. Vencore's FPS team is AS9100 certified and a recognized implementation partner for the Center for Advancement of Science in Space (CASIS

Solomon, Michael R.↗
NASA NTRS1990

EMI testing adequacy and flight anomaly history

The effects of electromagnetic interference (EMI) and the space environment on the performance of long-duration spacecraft hardware are surveyed, and the implications for prelaunch test procedures are indicated. Topics addressed include the need for onboard environmental monitoring devices to aid in the identification of environmentally induced anomalies, environmental modeling methods, the existing spacecraft-anomaly data bases, electrostatic discharges, radiation effects, magnetic-field effects, and terrestrial sources of EMI. Statistical data on EMI-induced anomalies are presented in graphs and discussed in detail. It is recommended that testing beyond the current MIL-STD levels be performed on equipment for long-term missions such as the Space Station.

Kuberry, Richard W.↗
DOE OSTI2020

High performance context switching for virtualized FPGA accelerators

A hardware context manager in a field-programmable gate array (FPGA) device includes configuration logic configured to program one or more programming regions in the FPGA device based on configuration data for implementing a target configuration of the one or more programming regions. Context management logic in the hardware context manager is coupled with the configuration logic and saves a first context corresponding to the target configuration by retrieving first state information from the set of one or more programming regions, where the first state information is generated based on the target configuration, and storing the retrieved first state information in a context memory. The context management logic restores the first context by transferring the first state information from the context memory to the one or more programming regions, and causing the configuration logic to program the one or more programming regions based on the configuration data.

42 ENGINEERING↗
DOE OSTI2020

Optimizing software-directed instruction replication for GPU error detection

Software-only and software-hardware optimizations to reduce the overhead of intra-thread instruction duplication on a GPU or other instruction processor are disclosed. The optimizations trade off error containment for performance and include ISA extensions with limited hardware changes and area costs.

Hari, Siva↗
DOE OSTI2023

Evaluation of Distributed Power Apportioning with Net Load Management Engine in Microgrids Using Power Hardware-in-the-Loop Simulation

This article presents the performance evaluation of ratio consensus-based distributed power apportioning engine along with centralized net load management (NLM) engine that ensures viable and stable operation of an islanded microgrid. Managing net load variability in a microgrid with high penetrations of uncertain renewable generation and ever-changing load demands is a crucial need in order to ensure viable and stable operation of the microgrid. Centralized “dispatch-rule”-based and/or multi-agent-based distributed control of distributed energy resources (DERs) in microgrid are well accepted for microgrid by adapting ANSI/ISA-95-based hierarchical control architecture. In the application where microgrid network has large geographical span with multiple DERs dispersed in the network, high penetration of uncertain renewable energy resources, and ever-changing load demands, a judicious selection of techniques/solutions for managing net-load resources for maintaining viability and stability is required. With this motivation, this article proposes a novel solution to mitigate the challenges by incorporating a mixed centralized NLM engine and distributed power apportioning control of DERs and loads. A power-hardware-in-the-loop (PHIL) -based experiment is conducted with the centralized NLM engine and the distributed power apportioning engine along with two commercial inverters. The experimental results validates the efficacy of the proposed method in ensuring viability and stability of a microgrid.

hardware-in-the-loop simulation↗
DOE OSTI2017

A historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications

In this study, biological neural networks continue to inspire new developments in algorithms and microelectronic hardware to solve challenging data processing and classification problems. Here in this research, we survey the history of neural-inspired and neuromorphic computing in order to examine the complex and intertwined trajectories of the mathematical theory and hardware developed in this field. Early research focused on adapting existing hardware to emulate the pattern recognition capabilities of living organisms. Contributions from psychologists, mathematicians, engineers, neuroscientists, and other professions were crucial to maturing the field from narrowly-tailored demonstrations to more generalizable systems capable of addressing difficult problem classes such as object detection and speech recognition. Algorithms that leverage fundamental principles found in neuroscience such as hierarchical structure, temporal integration, and robustness to error have been developed, and some of these approaches are achieving world-leading performance on particular data classification tasks. Additionally, novel microelectronic hardware is being developed to perform logic and to serve as memory in neuromorphic computing systems with optimized system integration and improved energy efficiency. Key to such advancements was the incorporation of new discoveries in neuroscience research, the transition away from strict structural replication and towards the functional replication of neural systems, and the use of mathematical theory frameworks to guide algorithm and hardware developments.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1991

Demonstration of automated proximity and docking technologies

An autodock was demonstrated using straightforward techniques and real sensor hardware. A simulation testbed was established and validated. The sensor design was refined with improved optical performance and image processing noise mitigation techniques, and the sensor is ready for production from off-the-shelf components. The autonomous spacecraft architecture is defined. The areas of sensors, docking hardware, propulsion, and avionics are included in the design. The Guidance Navigation and Control architecture and requirements are developed. Modular structures suitable for automated control are used. The spacecraft system manager functions including configuration, resource, and redundancy management are defined. The requirements for autonomous spacecraft executive are defined. High level decisionmaking, mission planning, and mission contingency recovery are a part of this. The next step is to do flight demonstrations. After the presentation the following question was asked. How do you define validation? There are two components to validation definition: software simulation with formal and vigorous validation, and hardware and facility performance validated with respect to software already validated against analytical profile.

Anderson, Robert L.↗