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.
Topics in Computational Structural Mechanics (CSM) are reviewed. CSM parallel structural methods, a transputer finite element solver, architectures for multiprocessor computers, and parallel eigenvalue extraction are among the topics discussed.
This paper describes a suggested design for an integrated information system for the proposed BIO-Plex (Bioregenerative Planetary Life Support Systems Test Complex) at Johnson Space Center (JSC), including distributed control systems, central control, networks, database servers, personal computers and workstations, applications software, and external communications. The system will have an open commercial computing and networking, architecture. The network will provide automatic real-time transfer of information to database server computers which perform data collection and validation. This information system will support integrated, data sharing applications for everything, from system alarms to management summaries. Most existing complex process control systems have information gaps between the different real time subsystems, between these subsystems and central controller, between the central controller and system level planning and analysis application software, and between the system level applications and management overview reporting. An integrated information system is vitally necessary as the basis for the integration of planning, scheduling, modeling, monitoring, and control, which will allow improved monitoring and control based on timely, accurate and complete data. Data describing the system configuration and the real time processes can be collected, checked and reconciled, analyzed and stored in database servers that can be accessed by all applications. The required technology is available. The only opportunity to design a distributed, nonredundant, integrated system is before it is built. Retrofit is extremely difficult and costly.
This report provides an overview and description of commands used in the Computational Materials mini-application, AladynPi. AladynPi is an extension of a previously released mini-application, Aladyn (https://github.com/nasa/aladyn; Yamakov, V.I., and Glaessgen, E.H., NASA/TM-2018-220104). Aladyn and AladynPi are basic molecular dynamics codes written in FORTRAN 2003, which are designed to demonstrate the use of adaptive neural networks (ANNs) in atomistic simulations. The role of ANNs is to efficiently reproduce the very complex energy landscape resulting from the atomic interactions in materials with the accuracy of the more expensive quantum mechanics-based calculations. The ANN is trained on a large set of atomic structures calculated using the density functional theory method. An input for the ANN is a set of structure coefficients, characterizing the local atomic environment of each atom, for which the atomic energy is obtained in the ANN inference process. In Aladyn, the ANN gives directly the energy of interatomic interactions. In AladynPi, the ANN gives optimized parameters for a predefined empirical function, known as bond-order-potential (BOP). The parameterized BOP function is then used to calculate the energy. AladynPi code is being released to serve as a training testbed for students and professors in academia to explore possible optimization algorithms for parallel computing on multicore central processing unit (CPU) computers or computers utilizing manycore architectures based on graphic processing units (GPUs). The effort is supported by the High Performance Computing incubator (HPCi) project at NASA Langley Research Center.
This paper provides an overview of the computational techniques used to characterize the viability of different lunar architectures and their ability to provide communication services to the lunar surface. This analysis was done with modern ray tracing techniques that allow for the computations to be done on Graphics Processing Unit (GPU) clusters for a high level of parallelism and severe reduction in computation time. The ray tracing computations were done with the GPU platform Compute Unified Device Architecture (CUDA) provided by NVIDIA which utilizes general-purpose computing on graphics processing units (GPGPU). This new method provides the advantage of being able to characterize a much larger portion of the lunar surface due to its computational efficiency as well as providing a more accurate representation of elevation angle limits instead of the typical and often inaccurate elevation angle mask. The Lunar surface can now be characterized with metrics such as contact time, outage time, and received data rate. With these metrics, different proposed Lunar architectures can be rapidly evaluated. This reduction in computation time not only leads to more accurate results but allows these results to be obtained in a time frame that allows for the complete characterization of the trade space. It is expected that these different architecture comparisons will lead to a conclusive determination of the optimal Lunar architecture and will allow for future Lunar missions to operate as close to real time as possible. In addition, this computation method can be used to recreate visibility figures generated by previous methods but with an increased level of accuracy.
This paper presents a methodology for enhancing community resilience through optimal renewable resource allocation and load scheduling in order to minimize unserved load and thermal discomfort. The proposed control architecture distributes the computational effort and is easier to be scaled up than traditional centralized control. The decentralized control architecture consists of two layers: The community operator layer (COL) allocates the limited amount of renewable energy resource according to the power flexibility of each building. The building agent layer (BAL) addresses the optimal load scheduling problem for each building with the allowable load determined by the COL. Both layers are formulated as a model predictive control (MPC) based optimization. Simulation scenarios are designed to compare different combinations of building weighting methods and objective functions to provide guidance for real-world deployment by community and microgrid operators. The results indicate that the impact of power flexibility is more prominent than the weighting factor to the resource allocation process. Allocation based purely on occupancy status could lead to an increase of PV curtailment. Further, it is necessary for the building agent to have multi-objective optimization to minimize unserved load ratio and maximize comfort simultaneously.
The conference presents papers on parallel architectures and the programming environment, parallel numerical algorithms, structural mechanics applications, and fluid dynamics applications. Topics include concurrent computer architecture, the state-of-the-art in highly parallel computer systems, supercomputer programming environments, uniquely parallel algorithms, the parallel solution of nonlinear elliptic equations, highly parallel banded systems solvers, and optimal mapping of irregular finite element domains to parallel processors. Consideration is also given to parallel processing in finite element structural analysis, heirarchical parallelism in a finite element CFD algorithm, and a parallelized elliptic solver for reacting flows.
This paper presents the JPL-developed Sequential Principal Component Analysis (SPCA) algorithm for feature extraction / image compression, based on "dominant-term selection" unsupervised learning technique that requires an order-of-magnitude lesser computation and has simpler architecture compared to the state of the art gradient-descent techniques. This algorithm is inherently amenable to a compact, low power and high speed VLSI hardware embodiment. The paper compares the lossless image compression performance of the JPL's SPCA algorithm with the state of the art JPEG2000, widely used due to its simplified hardware implementability. JPEG2000 is not an optimal data compression technique because of its fixed transform characteristics, regardless of its data structure. On the other hand, conventional Principal Component Analysis based transform (PCA-transform) is a data-dependent-structure transform. However, it is not easy to implement the PCA in compact VLSI hardware, due to its highly computational and architectural complexity. In contrast, the JPL's "dominant-term selection" SPCA algorithm allows, for the first time, a compact, low-power hardware implementation of the powerful PCA algorithm. This paper presents a direct comparison of the JPL's SPCA versus JPEG2000, incorporating the Huffman and arithmetic coding for completeness of the data compression operation. The simulation results show that JPL's SPCA algorithm is superior as an optimal data-dependent-transform over the state of the art JPEG2000. When implemented in hardware, this technique is projected to be ideally suited to future NASA missions for autonomous on-board image data processing to improve the bandwidth of communication.
Dense LU factorization is a prominent benchmark used to rank the performance of supercomputers. Many implementations use block-cyclic distributions of matrix blocks onto a two-dimensional process grid. The process grid dimensions drive a trade-off between communication and computation and are architecture- and implementation-sensitive. The critical panel factorization steps can be made less communication-bound by overlapping asynchronous collectives for pivoting with the computation of rank-k updates. By shifting the computation-communication trade-off, a modified block-cyclic distribution can beneficially exploit more available parallelism on the critical path, and reduce panel factorization's memory hierarchy contention on now-ubiquitous multicore architectures. During active panel factorization, rank-1 updates stream through memory with minimal reuse. In a column-major process grid, the performance of this access pattern degrades as too many streaming processors contend for access to memory. A block-cyclic mapping in the row-major order does not encounter this problem, but consequently sacrifices node and network locality in the critical pivoting steps. We introduce 'striding' to vary between the two extremes of row- and column-major process grids. The maximum available parallelism in the critical path work (active panel factorization, triangular solves, and subsequent broadcasts) is bounded by the length or width of the process grid. Increasing one dimension of the process grid decreases the number of distinct processes and nodes in the other dimension. To increase the harnessed parallelism in both dimensions, we start with a tall process grid. We then apply periodic 'rotation' to this grid to restore exploited parallelism along the row to previous levels. As a test-bed for further mapping experiments, we describe a dense LU implementation that allows a block distribution to be defined as a general function of block to processor. Other mappings can be tested wit...
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.
The solution of eigenproblems is often a key computational bottleneck that limits the tractable system size of numerical algorithms, among them electronic structure theory in chemistry and in condensed matter physics. Large eigenproblems can easily exceed the capacity of a single compute node, thus must be solved on distributed-memory parallel computers. We here present GPU-oriented optimizations of the ELPA two-stage tridiagonalization eigensolver (ELPA2). On top of cuBLAS-based GPU offloading, we add a CUDA kernel to speed up the back-transformation of eigenvectors, which can be the computationally most expensive part of the two-stage tridiagonalization algorithm. Furthermore, we benchmark the performance of this GPU-accelerated eigensolver on two hybrid CPU–GPU architectures, namely a compute cluster based on Intel Xeon Gold CPUs and NVIDIA Volta GPUs, and the Summit supercomputer based on IBM POWER9 CPUs and NVIDIA Volta GPUs. Consistent with previous benchmarks on CPU-only architectures, the GPU-accelerated two-stage solver exhibits a parallel performance superior to the one-stage counterpart. Finally, we demonstrate the performance of the GPU-accelerated eigensolver developed in this work for routine semi-local KS-DFT calculations comprising thousands of atoms.
Irregular applications are characterized by irregular data structures, control and communication patterns. Novel irregular high performance applications which deal with large data sets and require have recently appeared. Unfortunately, current high performance systems and software infrastructures executes irregular algorithms poorly. Only coordinated efforts by end user, area specialists and computer scientists that consider both the architecture and the software stack may be able to provide solutions to the challenges of modern irregular applications.
In this paper, an architecture for building Scalable And Mobile Environment For High-Performance Computing with spatial capabilities called SAME4HPC is described using cutting-edge technologies and standards such as Node.js, HTML5, ECMAScript 6, and PostgreSQL 9.4. Mobile devices are increasingly becoming powerful enough to run high-performance apps. At the same time, there exist a significant number of low-end and older devices that rely heavily on the server or the cloud infrastructure to do the heavy lifting. Our architecture aims to support both of these types of devices to provide high-performance and rich user experience. A cloud infrastructure consisting of OpenStack with Ubuntu, GeoServer, and high-performance JavaScript frameworks are some of the key open-source and industry standard practices that has been adopted in this architecture.
This Exascale Computing Project (ECP) milestone report summarizes the status of all 30 ECP Applications Development (AD) subprojects at the end of FY20. In October and November of 2020, a comprehensive assessment of AD projects was conducted by the ECP leadership. Reviews occurred virtually between October 27, 2020 and November 12, 2020. The review committee—consisting of the AD lead, deputy, and L3—was tasked with evaluating each subproject’s progress in porting their codes to early exascale architectures considered precursors to the planned exascale machines. This includes characterizing which modules have been ported to multi-accelerator nodes, initial performance analyses, the status of software integration, and a current vision of successes, obstacles, and next steps. As such, this report contains not only an accurate snapshot of each subproject’s current status but also represents an unprecedentedly broad account of experiences in porting large scientific applications to next-generation high-performance computing architectures.
The dynamic spatiotemporal distribution of light and micro climatic variables (wind speed, atmospheric CO 2 concentration, humidity, pressure, and air temperature) within the plant canopy as determined by the canopy architecture play a critical role in land-biosphere-atmosphere (LBA) photosynthetic carbon uptake, transpiratory water loss and energy partitioning. Vegetation models that include effects of sun and shade flecks, leaf temperature and energy balance partitioning between sensible and latent heat fluxes, and reduced turbulent mixing in dense vegetation canopies can accurately predict canopy performance, particularly its shaded leaves, which can constitute 80% of leaf area and contribute up to 50% of carbon update and 65% of water loss. However, current vegetation models with their bulk characterization of shaded leaves poorly represent the complex three dimensional (3D) canopy architecture are insufficient to capture the spatiotemporal dynamics of shaded leaves. Here, we propose to employ an x-ray computed tomography (XCT) imaging technique in combination with an automated, high throughput, image processing pipeline (3DArch, to be developed) to obtain an explicit 3D triangulated surface mesh of a plant canopy (Fig 1). 3DArch would provide a much needed technological jump in 3D LBA modeling where computer generated artificial 3D models suffer from lack of high resolution detailed canopy architecture parameters. The 3D canopy surface mesh output from 3DArch is coupled with an explicit 3D forward ray tracing model (fastTracer) to obtain a high resolution representation of the dynamic spatiotemporal light environment within the canopy over the course of a day (Fig 1). The results from the light attenuation model are then coupled with a process based multi-scale bio-physical canopy and leaf model of photosynthesis (PlantGro) to get fluxes of carbon, water and energy at the leaf and canopy scale, in addition to estimating whole plant carbon uptake, and water loss. Our proposed model framework would be the first of its kind to provide a breakthrough capability in the field of process-based plant modeling that bridges the key technological gap in shaded leaf modeling through explicit representation of 3D canopy architecture. Computer generated artificial 3D model canopy simulations on grasses show that the canopy light distribution does not follow an exponential behavior as assumed in most 1D vegetation models, but rather exhibits a heterogeneous behavior, with a small but significant portion of interior canopy leaves experiencing peak light levels due to sun flecks while the rest of the canopy receives substantially lower light levels. These results indicate a bias in traditional models that overestimates shaded leaf contribution towards whole canopy photosynthesis by up to 15% and underestimate transpiration by up to 12% with an associated increase in sensible heat fluxes since photosynthesis, transpiration and energy partitioning are tightly coupled processes. However, these test results need to be validated using the 3D architecture obtained from a real plant imaged in 3D using 3DArch, rather than an artificial model plant. Our proposed model framework would allow us to identify inefficiencies in canopy light distribution and prescribe optimal canopy architectures (leaf optical properties, leaf area, leaf angles, row spacing, planting density, etc.) to traditional and genetic engineering based crop breeders, for maximizing target functions such as light use efficiency, water use efficiency, drought tolerance, crop yield, crop resilience etc., with important applications in biofuel crops such as sorghum, and switchgrass. Our model can also be applied for designing optimal canopy architecture that increase surface albedo as a mitigation strategy for global warming and projections of crop yield for future food and water security under climate change.
Large language models (LLMs) have garnered significant attention in both the AI community and beyond. Among these, the Generative Pre-trained Transformer (GPT) has emerged as the dominant architecture, spawning numerous variants. However, these variants have undergone pre-training under diverse conditions, including variations in input data, data preprocessing, and training methodologies, resulting in a lack of controlled comparative studies. Here we meticulously examine two prominent open-sourced GPT architectures, GPT-NeoX and LLaMA, leveraging the computational power of Frontier, the world’s first Exascale supercomputer. Employing the same materials science text corpus and a comprehensive end-to-end pipeline, we conduct a comparative analysis of their training and downstream performance. Our efforts culminate in achieving state-of-the-art performance on a challenging materials science benchmark. Furthermore, we investigate the computation and energy efficiency, and propose a computationally efficient method for architecture design. To our knowledge, these pre-trained models represent the largest available for materials science. Our findings provide practical guidance for building LLMs on HPC platforms.
Pattern matching is a fundamental tool for answering complex graph queries. Unfortunately, existing solutions have limited capabilities: They do not scale to process large graphs and/or support only a restricted set of search templates or usage scenarios. Moreover, the algorithms at the core of the existing techniques are not suitable for today’s graph processing infrastructures relying on horizontal scalability and shared-nothing clusters, as most of these algorithms are inherently sequential and difficult to parallelize. In this article we present an algorithmic pipeline that bases pattern matching on constraint checking. The key intuition is that each vertex and edge participating in a match has to meet a set of constraints implicitly specified by the search template. These constraints can be verified independently and typically are less expensive to compute than searching the full template. The pipeline we propose generates these constraints and iterates over them to eliminate all the vertices and edges that do not participate in any match, thus reducing the background graph to a subgraph that is the union of all template matches—the complete set of all vertices and edges that participate in at least one match. Additional analysis can be performed on this annotated, reduced graph, such as full match enumeration, match counting, or computing vertex/edge centrality. Furthermore, a vertex-centric formulation for constraint checking algorithms exists, and this makes it possible to harness existing high-performance, vertex-centric graph processing frameworks. This technique (i) enables highly scalable pattern matching in metadata (labeled) graphs; (ii) supports arbitrary patterns with 100% precision; (iii) enables tradeoffs between precision and time-to-solution, while always selects all vertices and edges that participate in matches, thus offering 100% recall; and (iv) supports a set of popular data analytics scenarios. We implement our approach on top of HavoqGT, an open-source asynchronous graph processing framework, and demonstrate its advantages through strong and weak scaling experiments on massive scale real-world (up to 257 billion edges) and synthetic (up to 4.4 trillion edges) labeled graphs, respectively, and at scales (1,024 nodes / 36,864 cores), orders of magnitude larger than used in the past for similar problems. This article serves two purposes: First, it synthesises the knowledge accumulated during a long-term project. Second, it presents new system features, usage scenarios, optimizations, and comparisons with related work that strengthen the confidence that pattern matching based on iterative pruning via constraint checking is an effective and scalable approach in practice. The new contributions include the following: (i) We demonstrate the ability of the constraint checking approach to efficiently support two additional search scenarios that often emerge in practice, interactive incremental search and exploratory search. (ii) We empirically compare our solution with two additional state-of-the-art systems, Arabsque and TriAD. (iii) We show the ability of our solution to accommodate a more diverse range of datasets with varying properties, e.g., scale, skewness, label distribution, and match frequency. (iv) We introduce or extend a number of system features (e.g., work aggregation, load balancing, and the ability to cap the generated traffic) and design optimizations and demonstrate their advantages with respect to improving performance and scalability. (v) We present bottleneck analysis and insights into artifacts that influence performance. (vi) We present a theoretical complexity argument that motivates the performance gains we observe.
This paper describes an integrated distributed directory services (DDS) architecture as a fundamental component of KSC distributed computing systems. Specifically, an architecture for an integrated directory service based on DNS and X.500/LDAP has been suggested. The architecture supports using DNS in its traditional role as a name service and X.500 for other services. Specific designs were made in the integration of X.500 DDS for Public Key Certificates, Kerberos Security Services, Network-wide Login, Electronic Mail, WWW URLS, Servers, and other diverse network objects. Issues involved in incorporating the emerging Microsoft Active Directory Service MADS in KSC's X.500 were discussed.
A computer system includes an ensemble moving target defense architecture that protects the computer system against attack using one or more composable protection layers that change each churn cycle, thereby requiring an attacker to acquire information needed for an attack (e.g., code and pointers) and successfully deploy the attack, before the layers have changed state. Each layer may deploy a respective attack information asset protection providing multiple respective attack protections each churn cycle, wherein the respective attack information asset protections may differ.