Search NASA⌕ Search

SEARCH · Search NASA

Results for “Scientific 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 1,261 records · Page 70
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Arithmetic Primitives for Efficient Neuromorphic Computing

Neuromorphic computing is steadily gaining popularity in many scientific and engineering disciplines. However, one of the biggest problems that has prevented widespread usage of neuromorphic computing is the lack of efficient encoding methods. Traditional encoding methods such as binning, rate encoding, and temporal encoding are based on unary encoding and generate a large number of spikes for certain applications, making them less energy efficient. Lack of better encoding methods has also prevented preprocessing operations from being carried out on neuromorphic computers. As a result, over 99% of the time can be spent on data preprocessing and data transfer operations in some cases, leading to an inefficient workflow. In this paper, we present preliminary results that would enable us to efficiently encode data and perform basic arithmetic operations on neuromorphic computers. First, we present a neuromorphic approach for the two’s complement encoding of numbers and leverage it to devise addition and multiplication circuits, which could be used in preprocessing operations on neuromorphic computers. We test our approach on the SuperNeuroMAT simulator. Our results indicate that two’s complement is a highly efficient encoding method in terms of time, space, and energy complexity and that the addition and multiplication circuits produce accurate results on two numbers having arbitrary precision.

Wurm, Ahna↗
DOE OSTI2021

Accelerating Multigrid-based Hierarchical Scientific Data Refactoring on GPUs

Rapid growth in scientific data and a widening gap between computational speed and I/O bandwidth make it increasingly infeasible to store and share all data produced by scientific simulations. Instead, we need methods for reducing data volumes: ideally, methods that can scale data volumes adaptively so as to enable negotiation of performance and fidelity tradeoffs in different situations. Multigrid-based hierarchical data representations hold promise as a solution to this problem, allowing for flexible conversion between different fidelities so that, for example, data can be created at high fidelity and then transferred or stored at lower fidelity via logically simple and mathematically sound operations. However, the effective use of such representations has been hindered until now by the relatively high costs of creating, accessing, reducing, and otherwise operating on such representations. We describe here highly optimized data refactoring kernels for GPU accelerators that enable efficient creation and manipulation of data in multigrid-based hierarchical forms. We demonstrate that our optimized design can achieve up to 250 TB/s aggregated data refactoring throughput—83% of theoretical peak—on 1024 nodes of the Summit supercomputer. We showcase our optimized design by applying it to a large-scale scientific visualization workflow and the MGARD lossy compression software.

Data refactoring↗
DOE OSTI2021

Accelerating Multigrid-based Hierarchical Scientific Data Refactoring on GPUs

Rapid growth in scientific data and a widening gap between computational speed and I/O bandwidth make it increasingly infeasible to store and share all data produced by scientific simulations. Instead, we need methods for reducing data volumes: ideally, methods that can scale data volumes adaptively so as to enable negotiation of performance and fidelity tradeoffs in different situations. Multigrid-based hierarchical data representations hold promise as a solution to this problem, allowing for flexible conversion between different fidelities so that, for example, data can be created at high fidelity and then transferred or stored at lower fidelity via logically simple and mathematically sound operations. However, the effective use of such representations has been hindered until now by the relatively high costs of creating, accessing, reducing, and otherwise operating on such representations. We describe here highly optimized data refactoring kernels for GPU accelerators that enable efficient creation and manipulation of data in multigrid-based hierarchical forms. We demonstrate that our optimized design can achieve up to 250 TB/s aggregated data refactoring throughput—83% of theoretical peak—on 1024 nodes of the Summit supercomputer. We showcase our optimized design by applying it to a large-scale scientific visualization workflow and the MGARD lossy compression software.

Chen, Jieyang↗
DOE OSTI2020

Modular performance prediction for scientific workflows using Machine Learning

Scientific workflows provide an opportunity for declarative computational experiment design in an intuitive and efficient way. A distributed workflow is typically executed on a variety of resources, and it uses a variety of computational algorithms or tools to achieve the desired outcomes. Such a variety imposes additional complexity in scheduling these workflows on large scale computers. As computation becomes more distributed, insights into expected workload that a workflow presents become critical for effective resource allocation. In this paper, we present a modular framework that leverages Machine Learning for creating precise performance predictions of a workflow. The central idea is to partition a workflow in such a way that makes the task of forecasting each atomic unit manageable and gives us a way to combine the individual predictions efficiently. We recognize a combination of an executable and a specific physical resource as a single module. This gives us a handle to characterize workload and machine power as a single unit of prediction. Overall, our modular technique of creating atomic modules and deployment of longest-path approach to estimate workflow performance, allows the framework to adapt to highly complex nested directed acyclic workflows and scale to new scenarios, since it does not make assumptions of underlying workflow structure. We present performance estimation results of independent workflow modules executed on the XSEDE SDSC Comet cluster using various Machine Learning algorithms. The results provide insights into the behavior and effectiveness of different algorithms in the context of scientific workflow performance prediction.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Evaluating integration and performance of containerized climate applications on a Hewlett Packard Enterprise Cray system

Containers have taken over large swaths of cloud computing as the most convenient way of packaging and deploying applications. The features that containers offer for packaging and deploying applications translate to high performance computing (HPC) as well. At The National Oceanic and Atmospheric Administration, containers provide an easy way to build and distribute complex HPC applications, allowing faster collaboration, portability, and experiment computer environment reproducibility amongst the scientific community. The challenge arises when applications rely on message passing interface (MPI). This necessitates investigation into how to properly run these applications with their own unique requirements and produce performance on par with native runs. We investigate the MPI performance for benchmarks and containerized climate models for various containers covering selection of compiler and MPI library combinations from the Cray provided programming environments on the Cray XC supercomputer GAEA. Performance from the benchmarks and the climate models shows that for the most part containerized applications perform on par with the natively built applications when the system optimized Cray MPICH libraries are bound into the container, and the hybrid model containers have poor performance in comparison. We also describe several challenges and our solutions in running these containers, particularly challenges with heterogeneous jobs for the containerized model runs.

Abraham, Subil↗
DOE OSTI2024

Evaluating the potential of disaggregated memory systems for HPC applications

Summary Disaggregated memory is a promising approach that addresses the limitations of traditional memory architectures by enabling memory to be decoupled from compute nodes and shared across a data center. Cloud platforms have deployed such systems to improve overall system memory utilization, but performance can vary across workloads. High‐performance computing (HPC) is crucial in scientific and engineering applications, where HPC machines also face the issue of underutilized memory. As a result, improving system memory utilization while understanding workload performance is essential for HPC operators. Therefore, learning the potential of a disaggregated memory system before deployment is a critical step. This paper proposes a methodology for exploring the design space of a disaggregated memory system. It incorporates key metrics that affect performance on disaggregated memory systems: memory capacity, local and remote memory access ratio, injection bandwidth, and bisection bandwidth, providing an intuitive approach to guide machine configurations based on technology trends and workload characteristics. We apply our methodology to analyze thirteen diverse workloads, including AI training, data analysis, genomics, protein, fusion, atomic nuclei, and traditional HPC bookends. Our methodology demonstrates the ability to comprehend the potential and pitfalls of a disaggregated memory system and provides motivation for machine configurations. Our results show that eleven of our thirteen applications can leverage injection bandwidth disaggregated memory without affecting performance, while one pays a rack bisection bandwidth penalty and two pay the system‐wide bisection bandwidth penalty. In addition, we also show that intra‐rack memory disaggregation would meet the application's memory requirement and provide enough remote memory bandwidth.

Ding, Nan↗
DOE OSTI2020

Should Sea-Ice Modeling Tools Designed for Climate Research Be Used for Short-Term Forecasting?

In theory, the same sea-ice models could be used for both research and operations, but in practice, differences in scientific and software requirements and computational and human resources complicate the matter. Although sea-ice modeling tools developed for climate studies and other research applications produce output of interest to operational forecast users, such as ice motion, convergence, and internal ice pressure, the relevant spatial and temporal scales may not be sufficiently resolved. For instance, sea-ice research codes are typically run with horizontal resolution of more than 3 km, while mariners need information on scales less than 300 m. Certain sea-ice processes and coupled feedbacks that are critical to simulating the Earth system may not be relevant on these scales; and therefore, the most important model upgrades for improving sea-ice predictions might be made in the atmosphere and ocean components of coupled models or in their coupling mechanisms, rather than in the sea-ice model itself. This paper discusses some of the challenges in applying sea-ice modeling tools developed for research purposes for operational forecasting on short time scales, and highlights promising new directions in sea-ice modeling.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2018

Use of computational modeling combined with advanced visualization to develop strategies for the design of crop ideotypes to address food security

Sustainable crop production is a contributing factor to current and future food security. Innovative technologies are needed to design strategies that will achieve higher crop yields on less land and with fewer resources. Computational modeling coupled with advanced scientific visualization enables researchers to explore and interact with complex agriculture, nutrition, and climate data to predict how crops will respond to untested environments. These virtual observations and predictions can direct the development of crop ideotypes designed to meet future yield and nutritional demands. This review surveys modeling strategies for the development of crop ideotypes and scientific visualization technologies that have led to discoveries in “big data” analysis. Combined modeling and visualization approaches have been used to realistically simulate crops and to guide selection that immediately enhances crop quantity and quality under challenging environmental conditions. Lastly, this survey of current and developing technologies indicates that integrative modeling and advanced scientific visualization may help overcome challenges in agriculture and nutrition data as large-scale and multidimensional data become available in these fields.

3D crop modeling↗
DOE OSTI2019

Measurements and analytics of wide-area file transfers over dedicated connections

Distributed scientific and big-data computations are becoming increasingly dependent on access to remote files. Wide-area file transfers are supported by two basic schemes: (i) application-level tools, such as GridFTP, that provide transport services between file systems housed at geographically separated sites, and (ii) file systems mounted over wide-area networks, using mechanisms such as LNet routers that make them transparently available. In both cases, the file transfer performance critically depends on the configuration consisting of host, file, IO, and disk subsystems, which are complex by themselves, as well as on their complex compositions implemented using buffers and IO-network data transitions. We present extensive file transfer rate measurements collected over dedicated 10 Gbps connections with 0-366 ms round-trip times, using GridFTP and XDD file transfer tools, and Lustre file system extended over wide-area networks using LNet routers. Our test configurations are composed of: three types of host systems; XFS, Lustre, and ext3 file systems; and Ethernet and SONET wide-area connections. We present analytics based on the convexity-concavity of throughput profiles which provide insights into throughput and its superior or inferior trend compared to linear interpolations. We propose the utilization-concavity coefficient, a scalar metric that characterizes the overall performance of any file transfer method consisting of specific configuration and scheme. Our results enable performance optimizations by highlighting the significant roles of (i) buffer sizes and parallelism in GridFTP and XDD, and (ii) buffer utilization and credit mechanism in LNet routers.

Rao, Nageswara↗
DOE OSTI2018

ECP ALCC Quarterly Report (Oct-Dec 2017)

The scientific goal of ExaWind Exascale Computing Project (ECP) is to advance our fundamental understanding of the flow physics governing whole wind plant performance, including wake formation, complex terrain impacts, and turbine-turbine-interaction effects. Current methods for modeling wind plant performance fall short due to insufficient model fidelity and inadequate treatment of key phenomena, combined with a lack of computational power necessary to address the wide range of relevant length scales associated with wind plants. Thus, our ten-year exascale challenge is the predictive simulation of a wind plant composed of O(100) multi-MW wind turbines sited within a 100 km2 area with complex terrain, involving simulations with O(100) billion grid points. The project plan builds progressively from predictive petascale simulations of a single turbine, where the detailed blade geometry is resolved, meshes rotate and deform with blade motions, and atmospheric turbulence is realistically modeled, to a multi turbine array in complex terrain. The ALCC allocation will be used continually throughout the allocation period. In the first half of the allocation period, small (e.g., for testing Kokkos algorithms) and medium (e.g., 10K cores for highly resolved ABL simulations) sized jobs will be typical. In the second half of the allocation period, we will also have a number of large submittals for our resolved-turbine simulations. A challenge in the latter period is that small time step sizes will require long wall-clock times for statistically meaningful solutions. As such, we expect our allocation-hour burn rate to increase as we move through the allocation period.

17 WIND ENERGY↗
DOE OSTI2020

Time Series Dimension Reduction for Surrogate Models of Port Scanning Cyber Emulations

Surrogate model development is a key resource in the scientific modeling community for providing computational expedience when simulating complex systems without loss of great fidelity. The initial step to development of a surrogate model is identification of the primary governing components of the system. Principal component analysis (PCA) is a widely used data science technique that provides inspection of such driving factors, when the objective for modeling is to capture the greatest sources of variance inherent to a dataset. Although an efficient linear dimension reduction tool, PCA makes the fundamental assumption that the data is continuous and normally distributed. Thus, it provides ideal performance when these conditions are met. In the case for which cyber emulations provide realizations of a port scanning scenario, the data to be modeled follows a discrete time series function comprised of monotonically increasing piece-wise constant steps. The sources of variance are related to the timing and magnitude of these steps. Therefore, we consider using XPCA, an extension to PCA for continuous and discrete random variates. This report provides the documentation of the trade-offs between the PCA and XPCA linear dimension reduction algorithms, for the intended purpose to identify key components of greatest variance in our time series data. These components will ultimately provide the basis for future surrogate models of port scanning cyber emulations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Jan-Dec 2021 IC Project: w20_earthquake (Yearly Report) [Slides]

Large-scale simulations were conducted using the computational tool HOSS to investigate scientific aspects of the time reversal process. The main focus was the identification of damage/defects in wellbores for relevant subsurface applications.

58 GEOSCIENCES↗
NASA NTRS1979

High resolution spectrograph for the Space Telescope

The high resolution spectrograph (HRS) for ultraviolet astronomy with the Space Telescope will provide a spectral resolution of approximately 120,000 over a nominal wavelength range of 110-320 nm, together with a spatial resolution of about 0.25 arc seconds. The two detectors will consist of 512-element Digicons with cesium telluride and cesium iodide photocathodes, respectively. Photoelectrons in transit between the photocathodes and the diodes within the Digicons can be deflected in two axes with 12-bit resolution. This feature facilitates a design that emphasizes reliability since (once a hermetic seal is opened in orbit), only two moving parts, a grating carrousel and a shutter, are required for regular operation of the HRS. The instrument will be controlled by a computer in the spacecraft. The scientific objectives of the HRS investigation relate to interstellar matter in our own and nearby galaxies, physical processes of stellar mass loss and mass transfer, chemical abundances, bright quasars and Seyfert galaxy nuclei, and solar system phenomena.

Brandt, J. C.↗
NASA NTRS1990

Highly parallel computation

Highly parallel computing architectures are the only means to achieve the computation rates demanded by advanced scientific problems. A decade of research has demonstrated the feasibility of such machines and current research focuses on which architectures designated as multiple instruction multiple datastream (MIMD) and single instruction multiple datastream (SIMD) have produced the best results to date; neither shows a decisive advantage for most near-homogeneous scientific problems. For scientific problems with many dissimilar parts, more speculative architectures such as neural networks or data flow may be needed.

Denning, Peter J.↗
NASA NTRS1993

Interactive Forecasting with the National Weather Service River Forecast System

The National Weather Service River Forecast System (NWSRFS) consists of several major hydrometeorologic subcomponents to model the physics of the flow of water through the hydrologic cycle. The entire NWSRFS currently runs in both mainframe and minicomputer environments, using command oriented text input to control the system computations. As computationally powerful and graphically sophisticated scientific workstations became available, the National Weather Service (NWS) recognized that a graphically based, interactive environment would enhance the accuracy and timeliness of NWS river and flood forecasts. Consequently, the operational forecasting portion of the NWSRFS has been ported to run under a UNIX operating system, with X windows as the display environment on a system of networked scientific workstations. In addition, the NWSRFS Interactive Forecast Program was developed to provide a graphical user interface to allow the forecaster to control NWSRFS program flow and to make adjustments to forecasts as necessary. The potential market for water resources forecasting is immense and largely untapped. Any private company able to market the river forecasting technologies currently developed by the NWS Office of Hydrology could provide benefits to many information users and profit from providing these services.

Smith, George F.↗
NASA NTRS1995

Evaluation of Visualization Software

Visualization software is widely used in scientific and engineering research. But computed visualizations can be very misleading, and the errors are easy to miss. We feel that the software producing the visualizations must be thoroughly evaluated and the evaluation process as well as the results must be made available. Testing and evaluation of visualization software is not a trivial problem. Several methods used in testing other software are helpful, but these methods are (apparently) often not used. When they are used, the description and results are generally not available to the end user. Additional evaluation methods specific to visualization must also be developed. We present several useful approaches to evaluation, ranging from numerical analysis of mathematical portions of algorithms to measurement of human performance while using visualization systems. Along with this brief survey, we present arguments for the importance of evaluations and discussions of appropriate use of some methods.

Globus, Al↗
NASA NTRS1997

Three-Dimensional User Interfaces for Immersive Virtual Reality

The focus of this grant was to experiment with novel user interfaces for immersive Virtual Reality (VR) systems, and thus to advance the state of the art of user interface technology for this domain. Our primary test application was a scientific visualization application for viewing Computational Fluid Dynamics (CFD) datasets. This technology has been transferred to NASA via periodic status reports and papers relating to this grant that have been published in conference proceedings. This final report summarizes the research completed over the past year, and extends last year's final report of the first three years of the grant.

vanDam, Andries↗
NASA NTRS1997

Trenholm State (AL) Technical College High School Science Enrichment Program 1996-1997 Evaluation Report

This document presents findings based on a third-year evaluation of Trenholm State (AL) Technical College's National Aeronautics and Space Administration (NASA) - supported High School Science Enrichment Program (HSSEP). HSSEP is an external (to school) program for area students from groups that are underrepresented in the mathematics, science, engineering and technology (MSET) professions. In addition to gaining insight into scientific careers, HSSEP participants learn about and deliver presentations that focus on mathematics applications, scientific problem-solving and computer programming during a seven-week summer or 10-week Academic-Year Saturday session.

Ross, Elizabeth G.↗