Search NASA⌕ Search

SEARCH · Search NASA

Results for “High-End Computing”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Data-driven glass/ceramic science research: Insights from the glass and ceramic and data science/informatics communities

Data-driven science and technology have helped achieve meaningful results in areas such as materials/drug discovery and health care, but efforts to apply high-end data science algorithms to the areas of glass and ceramics are still limited. Many glass and ceramic researchers are interested in enhancing their work by using more data and data analytics to efficiently develop better functional materials. Simultaneously, the data science community is looking for a way to access materials data resources to test and validate their advanced computational learning algorithms. To bring together the glass/ceramic and data science communities to address this issue, The American Ceramic Society (ACerS) convened a Glass/Ceramics Data Science Workshop on February 6, 2018, at Nexight Group offices in Silver Spring, Maryland. The workshop, sponsored by the National Institute for Standards and Technology (NIST) Advanced Manufacturing Technologies (AMTech) program, brought together a select group of 20 key leaders in the data science, informatics, and glass/ceramics communities to identify the greatest opportunities and mechanisms for facilitating increased collaboration and coordination between these communities. This article summarizes workshop discussions about the current challenges that limit interactions and collaboration between the glass/ceramic and data science communities, opportunities for a coordinated approach that leverages existing knowledge in both communities, and a clear path toward the enhanced use of data science technologies for functional glass and ceramic research and development.

data science, ceramics, informatics↗
NASA NTRS2000

Computer accelerated conceptual design and development of spacecraft

The Next Generation Payload Development Team (NPDT), also called Team I, at the Jet Propulsion Laboratory provides a customer with a state-of-the-art Concurrent Design and Analysis environment for the early Design stages and emphasizes a total Systems approach, and features Multi-Disciplinary design teams, and interconnected high-end Analysis and Design tools.

NPDT design payload spacecraft↗
DOE OSTI2020

CoREC: Scalable and Resilient In-memory Data Staging for In-situ Workflows

The dramatic increase in the scale of current and planned high-end HPC systems is leading new challenges, such as the growing costs of data movement and IO, and the reduced mean time between failures (MTBF) of system components. In-situ workflows, i.e., executing the entire application workflows on the HPC system, have emerged as an attractive approach to address data-related challenges by moving computations closer to the data, and staging-based frameworks have been effectively used to support in-situ workflows at scale. However, the resilience of these staging-based solutions has not been addressed, and they remain susceptible to expensive data failures. Furthermore, naive use of data resilience techniques such as n-way replication and erasure codes can impact latency and/or result in significant storage overheads. In this article, we present CoREC, a scalable and resilient in-memory data staging runtime for large-scale in-situ workflows. CoREC uses a novel hybrid approach that combines dynamic replication with erasure coding based on data access patterns. It also leverages multiple levels of replications and erasure coding to support diverse data resiliency requirements. Furthermore, the article presents optimizations for load balancing and conflict-avoiding encoding, and a low overhead, lazy data recovery scheme. We have implemented the CoREC runtime and have deployed with the DataSpaces staging service on leadership class computing machines and present an experimental evaluation in the article. Here, the experiments demonstrate that CoREC can tolerate in-memory data failures while maintaining low latency and sustaining high overall storage efficiency at large scales.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1999

MOD Tool (Microwave Optics Design Tool)

The Jet Propulsion Laboratory (JPL) is currently designing and building a number of instruments that operate in the microwave and millimeter-wave bands. These include MIRO (Microwave Instrument for the Rosetta Orbiter), MLS (Microwave Limb Sounder), and IMAS (Integrated Multispectral Atmospheric Sounder). These instruments must be designed and built to meet key design criteria (e.g., beamwidth, gain, pointing) obtained from the scientific goals for the instrument. These criteria are frequently functions of the operating environment (both thermal and mechanical). To design and build instruments which meet these criteria, it is essential to be able to model the instrument in its environments. Currently, a number of modeling tools exist. Commonly used tools at JPL include: FEMAP (meshing), NASTRAN (structural modeling), TRASYS and SINDA (thermal modeling), MACOS/IMOS (optical modeling), and POPO (physical optics modeling). Each of these tools is used by an analyst, who models the instrument in one discipline. The analyst then provides the results of this modeling to another analyst, who continues the overall modeling in another discipline. There is a large reengineering task in place at JPL to automate and speed-up the structural and thermal modeling disciplines, which does not include MOD Tool. The focus of MOD Tool (and of this paper) is in the fields unique to microwave and millimeter-wave instrument design. These include initial design and analysis of the instrument without thermal or structural loads, the automation of the transfer of this design to a high-end CAD tool, and the analysis of the structurally deformed instrument (due to structural and/or thermal loads). MOD Tool is a distributed tool, with a database of design information residing on a server, physical optics analysis being performed on a variety of supercomputer platforms, and a graphical user interface (GUI) residing on the user's desktop computer. The MOD Tool client is being developed using Tcl/Tk, which allows the user to work on a choice of platforms (PC, Mac, or Unix) after downloading the Tcl/Tk binary, which is readily available on the web. The MOD Tool server is written using Expect, and it resides on a Sun workstation. Client/server communications are performed over a socket, where upon a connection from a client to the server, the server spawns a child which is be dedicated to communicating with that client. The server communicates with other machines, such as supercomputers using Expect with the username and password being provided by the user on the client.

Katz, Daniel S.↗
DOE OSTI2019

A Classical-Quantum Hybrid Approach for Unsupervised Probabilistic Machine Learning

For training unsupervised probabilistic machine learning models, matrix computation and sample generation are the two key steps. While GPUs excel at matrix computation, they use pseudo-random numbers to generate samples. Contrarily, Adiabatic Quantum Processors (AQP) use quantum mechanical systems to generate samples accurately and quickly, but are not suited for matrix computation. We present a Classical-Quantum Hybrid Approach for training unsupervised probabilistic machine learning models, leveraging GPUs for matrix computations and the D-Wave quantum sampling library for sample generation. We compare this approach to classical and quantum approaches across four performance metrics. Our results indicate that while the hybrid approach–which uses one AQP and one GPU–outperforms quantum and one of the classical approaches, it performs comparably to the GPU approach, and is outperformed by the CPU approach, which uses 56 high-end CPUs. Lastly, we compare sampling on AQP versus sampling library and show that AQP performs better.

Date, Prasanna↗
NASA NTRS2000

Simulators for the X-38/CRV Parafoil and Re-Entry Phases

The X38/CRV is unique in several aspects: it does not afford the pilot a forward view through a window and it utilizes a parafoil in the final landing flight phase. As a result of some of these unique attributes the prototype on-board displays will need to provide enhanced situation awareness to aid a crew member in supervising the onboard GNC software to select a landing site, and possible obstacle avoidance during the final flight phase. In the ESA/ESTEC visualization prototype system the scene is visualized using MultiGen OpenFlight models on high-end SGI machines. The Parafoil Guidance Navigation and Control (PGNC) algorithms are being developed as a joint NASA/ESA venture. These algorithms will be used onboard the vehicle to create nominal flight trajectories for the vehicle to follow. These same algorithms are also used as parafoil simulators in our augmented situation awareness system we are developing. The output of the parafoil simulator is displayed on a Windows-based computer running the LandForm FlightVision software. The FlightVision software is used to create the synthetic environment displays and all the necessary HUD symbology. Maps, such as aeronautical charts, as well as satellite imagery are optionally overlaid on the 3D-terrain model to provide additional situation awareness for the crew.

SITUATIONAL AWARENESS↗
NASA NTRS1994

High Performance Computing at NASA

The speaker will give an overview of high performance computing in the U.S. in general and within NASA in particular, including a description of the recently signed NASA-IBM cooperative agreement. The latest performance figures of various parallel systems on the NAS Parallel Benchmarks will be presented. The speaker was one of the authors of the NAS (National Aerospace Standards) Parallel Benchmarks, which are now widely cited in the industry as a measure of sustained performance on realistic high-end scientific applications. It will be shown that significant progress has been made by the highly parallel supercomputer industry during the past year or so, with several new systems, based on high-performance RISC processors, that now deliver superior performance per dollar compared to conventional supercomputers. Various pitfalls in reporting performance will be discussed. The speaker will then conclude by assessing the general state of the high performance computing field.

Bailey, David H.↗
NASA NTRS1999

NASA HPCC Technology for Aerospace Analysis and Design

The Computational Aerosciences (CAS) Project is part of NASA's High Performance Computing and Communications Program. Its primary goal is to accelerate the availability of high-performance computing technology to the US aerospace community-thus providing the US aerospace community with key tools necessary to reduce design cycle times and increase fidelity in order to improve safety, efficiency and capability of future aerospace vehicles. A complementary goal is to hasten the emergence of a viable commercial market within the aerospace community for the advantage of the domestic computer hardware and software industry. The CAS Project selects representative aerospace problems (especially design) and uses them to focus efforts on advancing aerospace algorithms and applications, systems software, and computing machinery to demonstrate vast improvements in system performance and capability over the life of the program. Recent demonstrations have served to assess the benefits of possible performance improvements while reducing the risk of adopting high-performance computing technology. This talk will discuss past accomplishments in providing technology to the aerospace community, present efforts, and future goals. For example, the times to do full combustor and compressor simulations (of aircraft engines) have been reduced by factors of 320:1 and 400:1 respectively. While this has enabled new capabilities in engine simulation, the goal of an overnight, dynamic, multi-disciplinary, 3-dimensional simulation of an aircraft engine is still years away and will require new generations of high-end technology.

Schulbach, Catherine H.↗
DOE OSTI2020

Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect

High performance multi-GPU computing becomes an inevitable trend due to the ever-increasing demand on computation capability in emerging domains such as deep learning, big data and planet-scale simulations. However, the lack of deep understanding on how modern GPUs can be connected and the real impact of state-of-the-art interconnect technology on multi-GPU application performance become a hurdle. In this paper, we fill the gap by conducting a thorough evaluation on five latest types of modern GPU interconnects: PCIe, NVLink-V1, NVLink-V2, NVLink-SLI and NVSwitch, from six high-end servers and HPC platforms: NVIDIA P100-DGX-1, V100-DGX-1, DGX-2, OLCF’s SummitDev and Summit supercomputers, as well as an SLI-linked system with two NVIDIA Turing RTX-2080 GPUs. Based on the empirical evaluation, we have observed four new types of GPU communication network NUMA effects: three are triggered by NVLink’s topology, connectivity and routing, while one is caused by PCIe chipset design issue. These observations indicate that, for a multi-GPU application running in a multi-GPU node, choosing the right GPU combination can impose considerable impact on GPU communication efficiency, as well as an application’s overall performance. Our evaluation can be leveraged in building practical multi-GPU performance models, which are vital for GPU task allocation, scheduling and migration in a shared environment (e.g., AI cloud and HPC centers), as well as communication-oriented performance tuning.

Performance Evaluation, GPU, Interconnect, NUMA, P↗
DOE OSTI2025

CMIP6-based Dynamically Downscaled Hydroclimate Projection over the Conterminous US

This dataset presents a suite of downscaled hydro-climate projections over the conterminous United States (CONUS) based on multiple selected Global Climate Models (GCMs) from the Coupled Models Intercomparison Project phase 6 (CMIP6). The CMIP6 GCMs are downscaled dynamically using Regional Climate Model version 4 (RegCM4). Each ensemble member covers the 1980-2019 baseline and 2020-2059 near-future periods under the high-end (SSP585) emission scenario. This dataset is formulated to support the SECURE Water Act Section 9505 Assessment for the US Department of Energy (DOE) Water Power Technologies Office (WPTO). For further details on this dataset, please refer to Kao et al. (2022) and Rastogi et al. (2022).

13 HYDRO ENERGY↗
DOE OSTI2019

Towards Native Execution of Deep Learning on a Leadership-Class HPC System

Large parallel machines generally offer the best parallel performance with "native execution" that is achieved using codes developed with the optimized compilers, communication libraries, and runtimes offered on the machines. In this paper, we report and analyze performance results from native execution of deep learning on a leadership-class high-performance computing (HPC) system. Using our new code called DeepEx, we present a study of the parallel speed up and convergence rates of learning achieved with native parallel execution. In the trade-off between computational parallelism and synchronized convergence, we first focus on maximizing parallelism while still obtaining convergence. Scaling results are reported from execution on up to 15,000 GPUs using two scientific data sets from atom microscopy and protein folding applications, and also using the popular ImageNet data set. In terms of the traditional measure of parallel speed up, excellent scaling is observed up to 12,000 GPUs. Additionally, accounting for convergence rates of deep learning accuracy or error, a deep learning-specific metric called "learning speed up" is also tracked. The performance results indicate the need to evaluate parallel deep learning execution in terms of learning speed up, and point to additional directions for improved exploitation of high-end HPC systems.

Yoginath, Srikanth↗
NASA NTRS2000

A Linux Workstation for High Performance Graphics

The primary goal of this effort was to provide a low-cost method of obtaining high-performance 3-D graphics using an industry standard library (OpenGL) on PC class computers. Previously, users interested in doing substantial visualization or graphical manipulation were constrained to using specialized, custom hardware most often found in computers from Silicon Graphics (SGI). We provided an alternative to expensive SGI hardware by taking advantage of third-party, 3-D graphics accelerators that have now become available at very affordable prices. To make use of this hardware our goal was to provide a free, redistributable, and fully-compatible OpenGL work-alike library so that existing bodies of code could simply be recompiled. for PC class machines running a free version of Unix. This should allow substantial cost savings while greatly expanding the population of people with access to a serious graphics development and viewing environment. This should offer a means for NASA to provide a spectrum of graphics performance to its scientists, supplying high-end specialized SGI hardware for high-performance visualization while fulfilling the requirements of medium and lower performance applications with generic, off-the-shelf components and still maintaining compatibility between the two.

Geist, Robert↗
DOE OSTI2024

CMIP6-based Multi-model Hydroclimate Projection over the Conterminous US, Version 1.1

This dataset presents a suite of high-resolution downscaled hydro-climate projections over the conterminous United States (CONUS) based on multiple selected Global Climate Models (GCMs) from the Coupled Models Intercomparison Project phase 6 (CMIP6). The CMIP6 GCMs are downscaled using either statistical (DBCCA) or dynamical (RegCM) downscaling approaches based on two meteorological reference datasets (Daymet and Livneh). Subsequently, the downscaled precipitation, temperature, and wind speed are employed to drive two calibrated hydrologic models (VIC and PRMS), enabling the simulation of projected future hydrologic responses across the CONUS. Each ensemble member covers the 1980-2019 baseline and 2020-2059 near-future periods under the high-end (SSP585) emission scenario. Moreover, utilizing only DBCCA and Daymet, the projections are further extended to the 2060-2099 far-future period and across three additional emission scenarios (SSP370, SSP245, and SSP126). This dataset is formulated to support the SECURE Water Act Section 9505 Assessment for the US Department of Energy (DOE) Water Power Technologies Office (WPTO). For further details on this dataset, please refer to Kao et al. (2022) and Rastogi et al. (2022).

13 HYDRO ENERGY↗
DOE OSTI2021

Land Surface Modeling 2.0 for agricultural climate change impact assessments

Focus Area: This white paper addresses DOE AI4ESP focus area #2 by providing a sketch blueprint for a next generation, hybrid AI/process-based global Land Surface Modeling (LSM) framework to improve projections of climate change impacts on the land surface system including agriculture and the hydrological cycle. Science Challenge: Climate change impacts on agriculture are highly uncertain: -50% to +150% global production changes for major grains under high-end climate change, for example. The core challenge in land surface system predictability is the large gap between the scale at which the relevant biological processes act and the scale at which the risks need to be assessed. Conventional empirical and process-based modeling approaches are insufficient. A new multi-scale modeling paradigm which employs AI/ML to learn from new streams of remote sensing data and targeted ’gene-to-global’ simulations is needed.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Economic and embodied energy analysis of integrated circuit manufacturing processes

Integrated circuits (ICs) are the fundamental microelectronic building blocks of typical information and communication technology (ICT) devices such as laptops and smartphone. With the emergence of faster and cheaper low-power ICs for the growing ICT market, there is a limited information on their manufacturing energy and economic impacts owing to the lack of recurrent upgradation of proprietary IC manufacturing process data. In this work, economic and life cycle energy assessments (LCAs) of IC manufacturing and assembly processes were conducted using the latest bill of materials (BOM) manufacturing data in a state-of-the-art IC manufacturing cost software tool developed by IC Knowledge, LLC. IC manufacturing cost was estimated to be $\$$1.00-$\$$5.00/cm 2 ; the high-end cost represents the most advanced 3D NAND IC technology with the Wafer Level Chip Scale Package cost of $4/cm 2 . Total cumulative energy demand (CED) estimates of IC manufacturing using the OpenLCA software ranged from 9 to 38 MJ/cm 2 or 56–235 BJ/month with the largest share (~ 75%) from on-site energy. The IC manufacturing CED is projected to increase with the progress in IC technology node, which has increased by more than two times for technology node evolution from 110 to 14 nm. Furthermore, the representative detailed BOM data were considered to reduce the CED uncertainties of the estimated standard deviation of 35%- 42%.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

TiltEM User Manual

The ability to automate the scanning transmission electron microscope (S/TEM) is tantamount to addressing next generation artificial intelligence, machine learning, and materials modeling capabilities. Constant utilization of these high-end capital equipment purchases also serves the requirements of the Department of Energy (DOE) to be fiscally responsible to the public. The development of an automated multi-modal tilt series algorithm for dark field/bright field S/TEM imaging plus chemical identification with energy dispersive x-ray spectroscopy has been achieved at PNNL. A tilt series workflow has now been generated which allows for autonomous collection of imaging and compositional information simultaneously. This advancement is due in large part to a transition from the rigid and microscope specific JEOL hardware environment, to the more adaptable GMS environment. This has thereby led to a greater degree of flexibility in the application of this method across platforms in addition to substantial time savings to the user.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Scalable Data-Intensive Geocomputation: A Design for Real-Time Continental Flood Inundation Mapping

The convergence of data-intensive and extreme-scale computing enables an integrated software and data ecosystem for scientific discovery. Developments in this realm will fuel transformative research in data-driven interdisciplinary domains. Geocomputation provides computing paradigms in Geographic Information Systems (GIS) for interactive computing of geographic data, processes, models, and maps. Because GIS is data-driven, the computational scalability of a geocomputation workflow is directly related to the scale of the GIS data layers, their resolution and extent, as well as the velocity of the geo-located data streams to be processed. Unique in high user interactivity and low end-to-end latency requirements, geocomputation applications will dramatically benefit from the convergence of high-end data analytics (HDA) and high-performance computing (HPC). The application level challenge, however, is to identify and eliminate computational bottlenecks that arise along a geocomputation workflow. Indeed, poor scalability at any of the workflow components is detrimental to the entire end-to-end pipeline. Here, we study a large geocomputation use case in flood inundation mapping that handles multiple national-scale geospatial datasets and targets low end-to-end latency. We discuss benefits and challenges for harnessing both HDA and HPC for data-intensive geospatial data processing and intensive numerical modeling of geographic processes. We propose an HDA+HPC geocomputation architecture design that couples HDA (e.g., Spark)-based spatial data handling and HPC-based parallel data modeling. Key techniques for coupling HDA and HPC to bridge the two different software stacks are reviewed and discussed.

Liu, Yan↗
DOE OSTI2024

Unraveling the multi-step crystallization mechanism of polytetrafluoroethylene, modified polytetrafluoroethylene, and their nanocomposites with boron nitride nanobarbs: Experimental insights and theoretical analysis

The non-isothermal crystallization behavior and kinetics of polytetrafluoroethylene (PTFE) composites with boron nitride nanobarb (BNNB), a new generation nanostructure with unique surface morphology and mechanical “barbs” have been analyzed, understanding these properties is essential for their high-end applications as thermal interface materials (TIM) for microwave, 5G and microelectronic devices. The analysis of the crystallization parameters includes crystallization onset, peak and end temperatures, crystallization half-life and overall crystallinity of PTFE, modified PTFE and their BNNB composites. The results were further analyzed using theoretical models such as the combined Avrami-Ozawa model. It was found that BNNB supports crystallization in the modified PTFE but shows minimal effect on the crystallization of PTFE. Due to the limitation of the classical theoretical models used above in fully characterizing the multi-step crystallization process of PTFE, an in-depth analysis using the model-free advanced isoconversional computation was used to characterize the PTFE crystallization based on the evolution of activation energy with fractional crystallinity and for the first time with temperature. Three kinetic regions were identified in the crystallization mechanism. Here, this study investigated the molecular organization and microstructural evolution of PTFE, modified PTFE and their composites during non-isothermal crystallization using advanced X-ray scattering measurements. An insight into the changes undergone by the material's microstructural units including crystallite size and morphology, lamellar thickness and lamellar interfacial layer thickness, and crystallographic phase dynamics during non-isothermal cooling from the melt, was provided here in this work. The effect of copolymer modification of PTFE and the inclusion of pristine and functionalized BNNB (a thermally conductive and electrically insulating ceramic) are both new investigations that provide valuable knowledge for the development of materials with strong matrix-nanofiller interaction and guidance for optimizing sintering and cooling cycles, two key steps in PTFE processing that largely affect the material microstructural features. Overall, the result of the three-part investigation demonstrates that BNNB supports crystallization in the modified PTFE up to 20 wt% concentration and at low and high cooling rates typically used in the industrial processing of PTFE.

36 MATERIALS SCIENCE↗