Search NASA⌕ Search

SEARCH · Search NASA

Results for “hardware accelerators”

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 451 records · Page 25

Pyroshock Environments Characterized for Spacecraft Missions

Pyrotechnic shock, or pyroshock, is the transient response of a structure to loading induced by the ignition of pyrotechnic (explosive or propellant activated) devices. These devices are typically used to separate structural systems (e.g., separate a spacecraft from a launch vehicle) and deploy appendages (e.g., solar panels). Pyroshocks are characterized by high peak acceleration, high-frequency content, and short duration. Because of their high acceleration and high-frequency, pyroshocks can cause spaceflight hardware to fail. Verifying by test that spaceflight hardware can withstand the anticipated shock environment is considered essential to mission success. The Earth Observing System (EOS) AM-1 spacecraft for NASA's Mission to Planet Earth is scheduled to be launched on an Atlas IIAS vehicle in 1999, and the NASA Lewis Research Center is the launch vehicle integrator for this NASA Goddard Space Flight Center spacecraft. The EOS spacecraft was subjected to numerous ground shock tests to verify that its scientific instruments and avionics components will withstand the shock-induced vibration produced when the spacecraft separates from the launch vehicle. Shock test data from these tests represent the third largest available pyroshock database in the United States. Future spacecraft missions will directly benefit from the knowledge gained from these tests. The payload separation system used for EOS is a new system that operates by firing six separation nuts. This system was tested to verify its functional operation and to characterize the resulting shock levels. The launch vehicle contractor (Lockheed Martin Astronautics) and spacecraft contractor (Lockheed Martin Missiles & Space) completed 16 separation test firings. This resulted in an unusually large amount of pyroshock data. Typically, only one or two pyroshock test firings are performed for a spacecraft mission. Because of the size of this separation system shock database, engineers were able to perform unique statistical analyses to characterize the distribution of the test data. For example, it was proven that the shock data follow a lognormal distribution, a concept often assumed but rarely proven. The test-to-test repeatability of the shock source level was analyzed, and the effects of various test configurations and separation nut production lots were examined and quantified. Engineers investigated the change in shock level as the shock traveled from the spacecraft separation interface to the avionics components of the upper stage and analyzed the effects of the structural fidelity (simulator versus real) of the components and their weight on vibrational response. In addition, the shock attenuation with distance and across joints was quantified and compared with concepts originally generated in 1970, and the effects of separation nut preload and firing sequences effects were examined. Because of this EOS shock testing and the analyses performed at NASA Lewis, a significant amount of new information on pyroshock and its characteristics is now available to the aerospace industry. We hope that this information will help future spacecraft test planners to perform better and cheaper spacecraft separation shock tests and to better understand their test data.

Hughes, William O.↗

Benefits of Spacecraft Level Vibration Testing

NASA-HDBK-7008 Spacecraft Level Dynamic Environments Testing discusses the approaches, benefits, dangers, and recommended practices for spacecraft level dynamic environments testing, including vibration testing. This paper discusses in additional detail the benefits and actual experiences of vibration testing spacecraft for NASA Goddard Space Flight Center (GSFC) and Jet Propulsion Laboratory (JPL) flight projects. JPL and GSFC have both similarities and differences in their spacecraft level vibration test approach: JPL uses a random vibration input and a frequency range usually starting at 5 Hz and extending to as high as 250 Hz. GSFC uses a sine sweep vibration input and a frequency range usually starting at 5 Hz and extending only to the limits of the coupled loads analysis (typically 50 to 60 Hz). However, both JPL and GSFC use force limiting to realistically notch spacecraft resonances and response (acceleration) limiting as necessary to protect spacecraft structure and hardware from exceeding design strength capabilities. Despite GSFC and JPL differences in spacecraft level vibration test approaches, both have uncovered a significant number of spacecraft design and workmanship anomalies in vibration tests. This paper will give an overview of JPL and GSFC spacecraft vibration testing approaches and provide a detailed description of spacecraft anomalies revealed.

Spacecraft Vibration Test↗

Modular autopilot design and development featuring bayesian non-parametric adaptive control

According to an embodiment, there is provided an onboard integrated computational system for an unmanned aircraft system (“Stabilis” autopilot). This is an integrated suite of hardware, software, and data-to-decisions services that are designed to meet the needs of business and research developers of UAS. Stabilis is designed to accelerate the development of any UAS platform and avionics system; it does so with hardware modularity and software adaptation. The Stabilis offers multiple technological advantages technological advantages including: Plug-and-adapt functionality; Data-to-decisions capability; and, On board parallelization capability.

97 MATHEMATICS AND COMPUTING↗

Compact accelerator for medical therapy

A compact accelerator system having an integrated particle generator-linear accelerator with a compact, small-scale construction capable of producing an energetic (.about.70-250 MeV) proton beam or other nuclei and transporting the beam direction to a medical therapy patient without the need for bending magnets or other hardware often required for remote beam transport. The integrated particle generator-accelerator is actuable as a unitary body on a support structure to enable scanning of a particle beam by direction actuation of the particle generator-accelerator.

43 PARTICLE ACCELERATORS↗

Broadband single-shot electron spectrometer for GeV-class laser-plasma-based accelerators

Laser-plasma-based accelerators can provide electrons over a broad energy range and/or with large momentum spread. The electron beam energy distribution can be controlled via accurate control of laser and plasma properties, and beams with energies ranging from {approx_equal}0.5 to 1000 MeV have been observed. Measuring these energy distributions in a single shot requires the use of a diagnostic with large momentum acceptance and, ideally, sufficient resolution to accurately measure narrow energy spread beams. Such a broadband single-shot electron magnetic spectrometer for GeV-class laser-plasma-based accelerators has been developed at Lawrence Berkeley National Laboratory. Detailed descriptions of the design concept and hardware are presented, as well as a performance evaluation of the spectrometer. The spectrometer covered electron beam energies raging from 0.01 to 1.1 GeV in a single shot, and enabled the simultaneous measurement of the laser properties at the exit of the accelerator through the use of a sufficiently large pole gap. Based on measured field maps and third-order transport analysis, a few percent-level resolution and determination of the absolute energy were achieved over the entire energy range. Laser-plasma-based accelerator experiments demonstrated the capability of the spectrometer as a diagnostic and its suitability for measuring broadband electron sources.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

COMMISSIONING AND OPERATION OF THE CEBAF 100 MV CRYOMODULES

The Continuous Electron Beam Accelerator Facility (CEBAF) energy upgrade from 6 GeV to 12 GeV includes the installation of ten new 100 MV cryomodules and RF systems. The superconducting RF cavities are designed to operate CW at a maximum accelerating gradient of 19.3 MV/m. To support the higher gradients and higher Q{sub L} ({approx} 3 x 10{sup 7}), a new RF system has been developed and is being installed to power and control the cavities. The RF system employs digital control and 13 kW klystrons. Recently, two of these cryomodules and associated RF hardware and software have been installed and commissioned in the CEBAF accelerator. Electrons at linac currents up to 540 {micro}A have been successfully accelerated and used for nuclear physics experiments. This paper reports on the commissioning and operation of the RF system and cryomodules.

43 PARTICLE ACCELERATORS↗

Understanding Mixed Precision GEMM with MPGemmFI: Insights into Fault Resilience

Emerging deep learning workloads urgently need fast general matrix multiplication (GEMM). Thus, one of the critical features of machine-learning-specific accelerators such as NVIDIA Tensor Cores, AMD Matrix Cores, and Google TPUs is the support of mixed-precision enabled GEMM. For DNN models, lower-precision FP data formats and computation offer acceptable correctness but significant performance, area, and memory footprint improvement. While promising, the mixed-precision computation on error resilience remains unexplored. To this end, we develop a fault injection framework that systematically injects fault into the mixed-precision computation results. We investigate how the faults affect the accuracy of machine learning applications. Based on the characteristics of error resilience, we offer lightweight error detection and correction solutions that significantly improve the overall model accuracy by 75% if the models experience hardware faults. The solutions can be efficiently integrated into the accelerator's pipelines.

Fang, Bo↗

Spaceflight Environmental-Telemetry Data for Biological Science

There is a critical need for better access and visualization of spaceflight environmental telemetry and mission hardware data from sensors including relative humidity, carbon dioxide, oxygen, radiation, airflow, temperature, acceleration, and acoustics. Under the stewardship of the Ames Life Sciences Data Archive (ALSDA) and GeneLab, an effort is underway to consolidate, normalize and provide accessibility of archived mission environmental data and hardware information, with the purpose of providing important context to biological data. This effort is necessary to provide scientific context of its impact upon biological and biomedical data from spaceflight missions and experiments (genomic, metagenomic, gene expression, proteomic, metabolomic, physiological, phenomics, behavioral; tabular, imaging, video). Environmental spaceflight data is derived from dozens of sources, with various formats, and in the past year a pipeline is in development to collect, curate and present this data efficiently. In the upcoming year, a new Data Visualization Portal will utilize the standardized pipeline data to provide easy user access to compare parameters and environmental conditions between missions, locations, subjects, and durations. Environmental and hardware data enables broad accessibility and analytics, without the need for advanced data informatic expertise. Familiarity with the capabilities and limitations of a variety of existing hardware/tools is a strength that could be applied to creation of improved hardware for future ecosystems on the Moon and Mars. The intention is to make biological and environmental telemetry data maximally open-access and FAIR (findable, accessible, interoperable, reusable) for data mining-informatic approaches to support knowledge discovery necessary for low Earth orbit, cis-Lunar, Mars transit, and Mars surface missions.

Danielle K. Lopez↗

Microgravity Research Results and Experiences from the NASA Mir Space Station Program

The Microgravity Research Program Office (MRPO) participated aggressively in Phase I of the International Space Station Program using the Russian Mir Space Station. The Mir Station offered an otherwise unavailable opportunity to explore the advantages and challenges to long duration microgravity space research. Payloads with both NASA and commercial backing were included as well as cooperative research with the Canadian Space Agency (CSA). From this experience, much was learned about dealing with long duration on orbit science utilization and developing new working relationships with our Russian partner to promote efficient planning, operations, and integration to solve complexities associated with a multiple partner program. Microgravity participation in the NASA Mir Program began with the first joint NASA Mir flight to the Mir Space Station. The earliest participation setup acceleration measurement capabilities that were used throughout the Program. Research, conducted by all Microgravity science disciplines, continued on each subsequent increment for the entire three-year duration of the Program. The Phase I Program included the Microgravity participation of over 30 Fluids, Combustion, Materials, and Biotechnology Sciences and numerous commercially sponsored research payloads. In addition to the research gained from Microgravity investigations, long duration operation of facility hardware was tested. Microgravity facilities operated on Mir included the Space Acceleration Measurement System (SAMS), the Microgravity Glovebox (MGBX), the Biotechnology System (BTS) and the Canadian Space Agency sponsored Microgravity Isolation Mount (MIM). The Russian OPTIZONE Furnace was also incorporated into our material science research. All of these efforts yielded significant and useful scientific research data. This paper focuses on the microgravity research conducted onboard the Mir space station. It includes the Program preparation and planning necessary to support this type of cross increment research experience; the payloads which were flown; and summaries of significant microgravity science findings. Most importantly this paper highlights the various disciplines of microgravity research conducted during the International Space Station, Phase 1 Program onboard the Mir Station. A capsulation of significant research and the applicability of our findings are provided. In addition, a brief discussion of how future microgravity science gathering capabilities, hardware development and payload operations techniques have enhanced our ability to conduct long duration microgravity research.

Schagheck, R. A.↗

Automated Generation of Integrated Digital and Spiking Neuromorphic Machine Learning Accelerators

The growing numbers of application areas for artificial intelligence (AI) methods have led to an explosion of domain-specific accelerators that could support every new machine learning (ML) algorithm advancement, clearly highlighting the need for a capability to quickly and automatically transition from algorithm definition to hardware implementation and explore design space along a variety of SWaP (size, weight and Power). The software defined architectures (SODA) synthesizer implements a compiler-based modular infrastructure for the end-to-end generation of machine learning accelerators from high-level frameworks to hardware description language. At the same time, neuromorphic computing, by mimicking how the brain operates, promises to perform artificial intelligence tasks at efficiencies orders of magnitude higher than the current conventional tensor-processing based accelerators, as demonstrated by a variety of specialized designs leveraging Spiking Neural Networks (SNNs). Nevertheless, the mapping of an artificial neural network (ANN) to solutions supporting SNNs is still a non-trivial and very device-specific task, and completely lack the possibility to design hybrid systems that integrate conventional and spiking neural models. In this paper we discuss the support for such an integrated generation leveraging the SODA Synthesizer framework and its modular structure. In particular, we present a new MLIR dialect (part of the SODA frontend) that allows expressing spiking neural network features (e.g., available resources, spiking sequences, analog signal reading, etc.) and illustrate how it enables mapping to Spiking Neurons and deployment to the related specialized hardware (which, in the digital domain, could be generated through the other existing layers of the SODA Synthesizer). We then discuss the opportunities for even deeper integration afforded by the hardware compilation infrastructure, providing a path towards the generation of complex heterogeneous artificial intelligence systems.

Curzel, Serena↗

Production Level CFD Code Acceleration for Hybrid Many-Core Architectures

In this work, a novel graphics processing unit (GPU) distributed sharing model for hybrid many-core architectures is introduced and employed in the acceleration of a production-level computational fluid dynamics (CFD) code. The latest generation graphics hardware allows multiple processor cores to simultaneously share a single GPU through concurrent kernel execution. This feature has allowed the NASA FUN3D code to be accelerated in parallel with up to four processor cores sharing a single GPU. For codes to scale and fully use resources on these and the next generation machines, codes will need to employ some type of GPU sharing model, as presented in this work. Findings include the effects of GPU sharing on overall performance. A discussion of the inherent challenges that parallel unstructured CFD codes face in accelerator-based computing environments is included, with considerations for future generation architectures. This work was completed by the author in August 2010, and reflects the analysis and results of the time.

Duffy, Austen C.↗

The CEBAF Element Database and Related Operational Software

The newly commissioned 12GeV CEBAF accelerator relies on a flexible, scalable and comprehensive database to define the accelerator. This database delivers the configuration for CEBAF operational tools, including hardware checkout, the downloadable optics model, control screens, and much more. The presentation will describe the flexible design of the CEBAF Element Database (CED), its features and assorted use case examples.

43 PARTICLE ACCELERATORS↗

Performance Evaluation of Distributed Energy Resource Management Algorithm in Large Distribution Networks

This paper presents performance evaluation of hierarchical optimization and control for distributed energy resource management system (DERMS) in large distribution networks via an advanced hardware-in-the-loop (HIL) platform. The HIL platform provides realistic testing in a laboratory envi-ronment, including the accurate modeling of a full-scale dis-tribution system of 11,000 nodes, the DERMS software con-troller, and 90 power hardware photovoltaics (PVs) and bat-tery inverters. The applied DERMS algorithm is designed based on a real-time optimal power flow algorithm and im-plemented with acceleration design that performs fast dis-patch of simulated PVs and real physical hardware DER devices every 4 seconds.

distributed energy management system (DERMS)↗

Adaptive Control for Microgravity Vibration Isolation System

Most active vibration isolation systems that try to a provide quiescent acceleration environment for space science experiments have utilized linear design methods. In this paper, we address adaptive control augmentation of an existing classical controller that employs a high-gain acceleration feedback together with a low-gain position feedback to center the isolated platform. The control design feature includes parametric and dynamic uncertainties because the hardware of the isolation system is built as a payload-level isolator, and the acceleration Sensor exhibits a significant bias. A neural network is incorporated to adaptively compensate for the system uncertainties, and a high-pass filter is introduced to mitigate the effect of the measurement bias. Simulations show that the adaptive control improves the performance of the existing acceleration controller and keep the level of the isolated platform deviation to that of the existing control system.

Yang, Bong-Jun↗

AN INJECTION/EXTRACTION SCENARIO FOR EMMA

EMMA is an experiment to study beam dynamics in a linear non-scaling fixed-field alternating gradient accelerator (FFAG). It accelerates an electron beam from 10 to 20 MeV kinetic energy. To optimally perform these studies, one must be able to inject the beam at any energy within the machine's energy range. Furthermore, because we wish to study the behavior of large-emittance beams in such a machine, the injection systems must be able to inject the beam anywhere within a transverse phase space ellipse with a normalized acceptance of 3 mm, and the extraction systems must be able to extract from that same ellipse. I describe a computation of kicker and septum fields to achieve all of these requirements, and discuss how this interacts with the hardware constraints.

43 PARTICLE ACCELERATORS↗

DDCP framework

DDCP protocol software 1.0 This repository contains the C++ implementation of version 1.x of the Distributed Data Communications Protocol (DDCP). DDCP provides request/reply, feature discovery, data transfer, control, interrupt, and transaction support for communicating with accelerator instrumentation over UDP. The standard server port is 65000. The framework is a source dependency for services that communicate directly with DDCP hardware. It is not a deployable service by itself.

Joshi, Shreya [Fermi National Accelerator Laborato↗

SmartFuse: Reconfigurable Smart Switches to Accelerate Fused Collectives in HPC Applications

Communication switches have sometimes been augmented to process collectives (e.g., the IBM BlueGene project and the Mellanox SHArP switch). In this work, we find that there is a great acceleration opportunity through the further augmentation of switches to accelerate more complex functions that combine communication with computation. We consider three types of such functions. The first is fully-fused collectives built by fusing multiple existing collectives like Allreduce with Alltoall. The second is semi-fused collectives built by combining a collective with another computation. The third we refer to as higher-order collectives built by combining multiple computations and communications, such as to perform matrix-matrix multiply (PGEMM). In this work, we propose a framework called SmartFuse to accelerate fused collective functions. The core of SmartFuse is a reconfigurable smart switch to support these operations. The semi/fully fused collectives are implemented with a CGRAlike architecture, while higher-order collectives are implemented with a more specialized computational unit that can also schedule communication. Supporting our framework is software to evaluate and translate relevant parts of the input program, compile them into a control data flow graph, and then map this graph to the switch hardware. The proposed framework, once deployed, has the strong potential to accelerate existing HPC applications transparently by encapsulation within an MPI implementation. Experimental results show that this approach improves the performance of the PGEMM kernel, MINIFE, and AMG by, on average, 94%, 15%, and 13%, respectively.

Haghi, Pouya↗

Phaser.MRage: automated molecular replacement

The functionality of the molecular-replacement pipeline phaser.MRage is introduced and illustrated with examples. Phaser.MRage is a molecular-replacement automation framework that implements a full model-generation workflow and provides several layers of model exploration to the user. It is designed to handle a large number of models and can distribute calculations efficiently onto parallel hardware. In addition, phaser.MRage can identify correct solutions and use this information to accelerate the search. Firstly, it can quickly score all alternative models of a component once a correct solution has been found. Secondly, it can perform extensive analysis of identified solutions to find protein assemblies and can employ assembled models for subsequent searches. Thirdly, it is able to use a priori assembly information (derived from, for example, homologues) to speculatively place and score molecules, thereby customizing the search procedure to a certain class of protein molecule (for example, antibodies) and incorporating additional biological information into molecular replacement.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗