SEARCH · Engineering Papers
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.
Acceptance test data included: voltage profiles; pressure increase or decrease; and response of the third electrode cell. A softening of the voltage profile was revealed, as well as a lowering of the discharge profile and a 10 percent loss of capacity over a 0 to 20 C temperature range.
On current multiprocessor architectures one must carefully distribute data in memory in order to achieve high performance. Process partitioning is the operation of rewriting an algorithm as a collection of tasks, each operating primarily on its own portion of the data, to carry out the computation in parallel. A semi-automatic approach to process partitioning is considered in which the compiler, guided by advice from the user, automatically transforms programs into such an interacting task system. This approach is illustrated with a picture processing example written in BLAZE, which is transformed into a task system maximizing locality of memory reference.
MERRA AS is a cyberinfrastructure resource that will combine iRODS-based Climate Data Server (CDS) capabilities with Coudera MapReduce to serve MERRA analytic products, store the MERRA reanalysis data collection in an HDFS to enable parallel, high-performance, storage-side data reductions, manage storage-side driver, mapper, reducer code sets and realized objects for users, and provide a library of commonly used spatiotemporal operations that can be composed to enable higher-order analyses.
The substantial increase in data volume and complexity expected from future experiments will require significant investment to prepare experimental algorithms. These algorithms include physics object reconstruction, calibrations, and processing of observational data. In addition, the changing computing architecture landscape, which will be primarily composed of heterogeneous resources, will continue to pose major challenges with regard to algorithmic migration. Portable tools need to be developed that can be shared among the frontiers (e.g., for code execution on different platforms) and opportunities, such as forums or cross-experimental working groups, need to be provided where experiences and lessons learned can be shared between experiments and frontiers. At the same time, individual experiments also need to invest considerable resources to develop algorithms unique to their needs (e.g., for facilities dedicated to the experiment), and ensure that their specific algorithms will be able to efficiently exploit external heterogeneous computing facilities. Common software tools represent a cost-effective solution, providing ready-to-use software solutions as well as a platform for R&D work. These are particularly important for small experiments which typically do not have dedicated resources needed to face the challenges imposed by the evolving computing technologies. Workforce development is a key concern across frontiers and experiments, and additional support is needed to provide career opportunities for researchers working in the field of experimental algorithm development. Finally, cross-discipline collaborations going beyond high-energy physics are a key ingredient to address the challenges ahead and more support for such collaborations needs to be created. This report targets future experiments, observations and experimental algorithm development for the next 10-15 years.
The method of parallel adaptive discretization of data is considered the most promising and allows the effective compression algorithms to be used for high information-capacity radio telemetry systems. An associative computer device (ACD), i.e., parallel computers based on associative memory units (AMU), are recommended for realization of this method. A detailed discussion of the problems of application of AMU is followed by description of a particular ACD and its recommended use.
Scientific discoveries rely heavily on efficient access, search, and management of massive data sets. Data management technologies have, for decades, provided foundational capabilities for scientific computing. Just as storage, input/output (I/O), and data management have been fundamental to simulation-based science for many years, so too are capable data-management technologies key to the success of today’s scientific workflows utilizing data intensive and machine learning (ML) techniques. The Department of Energy, Office of Science, Advanced Scientific Computing Research (ASCR) program has invested broadly in data-management research focused on high-performance computing (HPC) systems, from parallel file systems that store data to application software that makes these systems more productive. Still, advances in technology combined with growing diversity of supported science strongly motivate continued investment in this area. In January 2022, ASCR convened a workshop to identify priority research directions in the area of data management for high-performance and scientific computing. Attendees were challenged to identify promising approaches that would support the breadth of the DOE mission, including the explosion of artificial intelligence (AI) uses and the growing needs of experimental and observational science. Technological and science drivers were identified and considered as they relate to key aspects of data management such as interfaces, architectural design, and FAIR principles (Findable, Accessible, Interoperable, and Reusable). The thoughts of the workshop participants were distilled into a set of four priority research directions with the potential for high impact on DOE science. These research directions are summarized in the following pages.
The ParaScope parallel programming environment, developed to support scientific programming of shared-memory multiprocessors, includes a collection of tools that use global program analysis to help users develop and debug parallel programs. This paper focuses on ParaScope's compilation system, its parallel program editor, and its parallel debugging system. The compilation system extends the traditional single-procedure compiler by providing a mechanism for managing the compilation of complete programs. Thus, ParaScope can support both traditional single-procedure optimization and optimization across procedure boundaries. The ParaScope editor brings both compiler analysis and user expertise to bear on program parallelization. It assists the knowledgeable user by displaying and managing analysis and by providing a variety of interactive program transformations that are effective in exposing parallelism. The debugging system detects and reports timing-dependent errors, called data races, in execution of parallel programs. The system combines static analysis, program instrumentation, and run-time reporting to provide a mechanical system for isolating errors in parallel program executions. Finally, we describe a new project to extend ParaScope to support programming in FORTRAN D, a machine-independent parallel programming language intended for use with both distributed-memory and shared-memory parallel computers.
The laser velocimeter (autocovariance) buffer interface is a data acquisition subsystem designed specifically for the acquisition of data from a laser velocimeter. The subsystem acquires data from up to six laser velocimeter components in parallel, measures the times between successive data points for each of the components, establishes and maintains a coincident condition between any two or three components, and acquires data from other instrumentation systems simultaneously with the laser velocimeter data points. The subsystem is designed to control the entire data acquisition process based on initial setup parameters obtained from a host computer and to be independent of the computer during the acquisition. On completion of the acquisition cycle, the interface transfers the contents of its memory to the host under direction of the host via a single 16-bit parallel DMA channel.
NASA's Atmospheric Tomography Mission (ATom) seeks to understand the impact of anthropogenic air pollution on gases in the Earth's atmosphere. Four flight campaigns are being deployed on a seasonal basis to establish a continuous global-scale data set intended to improve the representation of chemically reactive gases in global atmospheric chemistry models. The Global Modeling Initiative (GMI), is creating chemical transport simulations on a global scale for each of the ATom flight campaigns. To meet the computational demands required to translate the GMI simulation data to grids associated with the flights from the ATom campaigns, the GMI ICARTT Processing Software (GMI-IPS) has been developed and is providing key functionality for data processing and analysis in this ongoing effort. The GMI-IPS is written in Python and provides computational kernels for data interpolation and visualization tasks on GMI simulation data. A key feature of the GMI-IPS, is its ability to read ICARTT files, a text-based file format for airborne instrument data, and extract the required flight information that defines regional and temporal grid parameters associated with an ATom flight. Perhaps most importantly, the GMI-IPS creates ICARTT files containing GMI simulated data, which are used in collaboration with ATom instrument teams and other modeling groups. The initial main task of the GMI-IPS is to interpolate GMI model data to the finer temporal resolution (1-10 seconds) of a given flight. The model data includes basic fields such as temperature and pressure, but the main focus of this effort is to provide species concentrations of chemical gases for ATom flights. The software, which uses parallel computation techniques for data intensive tasks, linearly interpolates each of the model fields to the time resolution of the flight. The temporally interpolated data is then saved to disk, and is used to create additional derived quantities. In order to translate the GMI model data to the spatial grid of the flight path as defined by the pressure, latitude, and longitude points at each flight time record, a weighted average is then calculated from the nearest neighbors in two dimensions (latitude, longitude). Using SciPya's Regular Grid Interpolator, interpolation functions are generated for the GMI model grid and the calculated weighted averages. The flight path points are then extracted from the ATom ICARTT instrument file, and are sent to the multi-dimensional interpolating functions to generate GMI field quantities along the spatial path of the flight. The interpolated field quantities are then written to a ICARTT data file, which is stored for further manipulation. The GMI-IPS is aware of a generic ATom ICARTT header format, containing basic information for all flight campaigns. The GMI-IPS includes logic to edit metadata for the derived field quantities, as well as modify the generic header data such as processing dates and associated instrument files. The ICARTT interpolated data is then appended to the modified header data, and the ICARTT processing is complete for the given flight and ready for collaboration. The output ICARTT data adheres to the ICARTT file format standards V1.1. The visualization component of the GMI-IPS uses Matplotlib extensively and has several functions ranging in complexity. First, it creates a model background curtain for the flight (time versus model eta levels) with the interpolated flight data superimposed on the curtain. Secondly, it creates a time-series plot of the interpolated flight data. Lastly, the visualization component creates averaged 2D model slices (longitude versus latitude) with overlaid flight track circles at key pressure levels. The GMI-IPS consists of a handful of classes and supporting functionality that have been generalized to be compatible with any ICARTT file that adheres to the base class definition. The base class represents a generic ICARTT entry, only defining a single time entry and 3D spatial positioning parameters. Other classes inherit from this base class; several classes for input ICARTT instrument files, which contain the necessary flight positioning information as a basis for data processing, as well as other classes for output ICARTT files, which contain the interpolated model data. Utility classes provide functionality for routine procedures such as: comparing field names among ICARTT files, reading ICARTT entries from a data file and storing them in data structures, and returning a reduced spatial grid based on a collection of ICARTT entries. Although the GMI-IPS is compatible with GMI model data, it can be adapted with reasonable effort for any simulation that creates Hierarchical Data Format (HDF) files. The same can be said of its adaptability to ICARTT files outside of the context of the ATom mission. The GMI-IPS contains just under 30,000 lines of code, eight classes, and a dozen drivers and utility programs. It is maintained with GIT source code management and has been used to deliver processed GMI model data for the ATom campaigns that have taken place to date.
A review was carried out of ISEE and Voyager spacecraft magnetometer data to determine if quasi-parallel bow shocks are really broad, disordered regions. The key parameter was the deceleration scale (thickness, Lp) across which random energy would need to increase and a localized electrostatic field (E) would be present. Lp would define the breadth of the shock and be associated with a plasma deceleration. The ISEE 1 satellite collected data on the electron density, bulk speed, magnetic intensity, and electron temperature in November 1977 during five traverses of the bow shock. Similar data were gathered from an interplanetary shock wave in 1981. The evidence supported the concept of a plasma deceleration across a thin layer (Lp) in both types of shocks. The layers were about 50 times (interplanetary) and 20 times (earth) thinner than surrounding magnetic fluctuation regions. It is asserted that the regions of deceleration, although much thinner, are the actual shocks and not the entire regions of magnetic fluctuations.
Summary Parallel I/O is a critical technique for moving data between compute and storage subsystems of supercomputers. With massive amounts of data produced or consumed by compute nodes, high‐performant parallel I/O is essential. I/O benchmarks play an important role in this process; however, there is a scarcity of I/O benchmarks representative of current workloads on HPC systems. Toward creating representative I/O kernels from real‐world applications, we have created h5bench , a set of I/O kernels that exercise hierarchical data format version 5 (HDF5) I/O on parallel file systems in numerous dimensions. Our focus on HDF5 is due to the parallel I/O library's heavy usage in various scientific applications running on supercomputing systems. The various tests benchmarked in the h5bench suite include I/O operations (read and write), data locality (arrays of basic data types and arrays of structures), array dimensionality (one‐dimensional arrays, two‐dimensional meshes, three‐dimensional cubes), I/O modes (synchronous and asynchronous). In this paper, we present the observed performance of h5bench executed along several of these dimensions on existing supercomputers (Cori and Summit) and pre‐exascale platforms (Perlmutter, Theta, and Polaris). h5bench measurements can be used to identify performance bottlenecks and their root causes and evaluate I/O optimizations. As the I/O patterns of h5bench are diverse and capture the I/O behaviors of various HPC applications, this study will be helpful to the broader supercomputing and I/O community.
Interactive three-dimensional graphics applications, such as terrain data representation and manipulation, require extensive arithmetic processing. Massively parallel machines are attractive for this application since they offer high computational rates, and grid connected architectures provide a natural mapping for grid based terrain models. Presented here are algorithms for data movement on the massive parallel processor (MPP) in support of pan and zoom functions over large data grids. It is an extension of earlier work that demonstrated real-time performance of graphics functions on grids that were equal in size to the physical dimensions of the MPP. When the dimensions of a data grid exceed the processing array size, data is packed in the array memory. Windows of the total data grid are interactively selected for processing. Movement of packed data is needed to distribute items across the array for efficient parallel processing. Execution time for data movement was found to exceed that for arithmetic aspects of graphics functions. Performance figures are given for routines written in MPP Pascal.
This paper discusses work done by JPL 's Parallel Applications Technologies Group in helping scientists access and visualize very large data sets through the use of multiple computing resources, such as parallel supercomputers, clusters, and grids These tools do one or more of the following tasks visualize local data sets for local users, visualize local data sets for remote users, and access and visualize remote data sets The tools are used for various types of data, including remotely sensed image data, digital elevation models, astronomical surveys, etc The paper attempts to pull some common elements out of these tools that may be useful for others who have to work with similarly large data sets.
Here, we discuss the implementation of a finite element method, used to numerically solve the Euler equations of compressible flows, using an asynchronous runtime system (RTS). The algorithm is implemented for distributed-memory machines, using stationary unstructured 3D meshes, combining data-, and task-parallelism on top of the Charm++ RTS. Charm++’s execution model is asynchronous by default, allowing arbitrary overlap of computation and communication. Task-parallelism allows scheduling parts of an algorithm independently of, or dependent on, each other. Built-in automatic load balancing enables continuous redistribution of computational load by migration of work units based on real-time CPU load measurement. The RTS also features automatic checkpointing, fault tolerance, resilience against hardware failure, and supports power-, and energy-aware computation. We demonstrate scalability up to 25 x 10 9 cells at $\mathscr{O}$10 4 compute cores and the benefits of automatic load balancing for irregular workloads. The full source code with documentation is available at https://quinoacomputing.org.
Telemetry enhancement techniques used by Voyager-2 to reduce telemetry transmission rates by over 50 percent compared to those used at Saturn, with negligible loss in information return, are described. The use of the Reed-Solomon encoder is discussed, and the principles and implementation of an Image Data Compressor algorithm for noiseless coding techniques are addressed. Parallel operation of the redundant Flight Data Subsystem processors is discussed.
NASA is working with the FAA to demonstrate the feasibility of pulse Doppler radar as a candidate airborne sensor to detect low altitude windshears. The need to provide the pilot with timely information about possible hazards has motivated a demand for real-time processing of a radar return. Investigated here is parallel processing as a means of accommodating the high data rates required. A PC based parallel computer, called the transputer, is used to investigate issues in real time concurrent processing of radar signals. A transputer network is made up of an array of single instruction stream processors that can be networked in a variety of ways. They are easily reconfigured and software development is largely independent of the particular network topology. The performance of the transputer is evaluated in light of the computational requirements. A number of algorithms have been implemented on the transputers in OCCAM, a language specially designed for parallel processing. These include signal processing algorithms such as the Fast Fourier Transform (FFT), pulse-pair, and autoregressive modelling, as well as routing software to support concurrency. The most computationally intensive task is estimating the spectrum. Two approaches have been taken on this problem, the first and most conventional of which is to use the FFT. By using table look-ups for the basis function and other optimizing techniques, an algorithm has been developed that is sufficient for real time. The other approach is to model the signal as an autoregressive process and estimate the spectrum based on the model coefficients. This technique is attractive because it does not suffer from the spectral leakage problem inherent in the FFT. Benchmark tests indicate that autoregressive modeling is feasible in real time.
Direct numerical simulation data for the lateral velocity derivative delta(u)/delta(y) at the centerline of a fully developed turbulent channel flow provide reasonable support for Wyngaard's analysis of the error involved in measuring this quantity using parallel hot wires. Numerical data in the wall region of the channel flow also provide a useful indication of how to select the separation between the wires. Justification for this choice is obtained by comparing several measured statistics of delta(u)/delta(y) with the corresponding numerical data.
Recent and prospective advances in parallel multiple introduction multiple data (MIMD) computers offer significant improvements in the range of structural problems that can be solved, as well as the speed of solutions. These improvements have their basis in the effective selection and implementation of algorithms exploiting parallel computation. Attention is presently given to the solution of the transient response calculations of an experimental MIMD computer designated the 'Finite Element Machine', including its algorithm and its results for representative one- and two-dimensional dynamic response test problems. A factor of 6.5 is noted for the computational speed improvement.