Search NASA⌕ Search

SEARCH · Search NASA

Results for “Task based parallelism”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
NASA NTRS1987

Knowledge-based vision for space station object motion detection, recognition, and tracking

Computer vision, especially color image analysis and understanding, has much to offer in the area of the automation of Space Station tasks such as construction, satellite servicing, rendezvous and proximity operations, inspection, experiment monitoring, data management and training. Knowledge-based techniques improve the performance of vision algorithms for unstructured environments because of their ability to deal with imprecise a priori information or inaccurately estimated feature data and still produce useful results. Conventional techniques using statistical and purely model-based approaches lack flexibility in dealing with the variabilities anticipated in the unstructured viewing environment of space. Algorithms developed under NASA sponsorship for Space Station applications to demonstrate the value of a hypothesized architecture for a Video Image Processor (VIP) are presented. Approaches to the enhancement of the performance of these algorithms with knowledge-based techniques and the potential for deployment of highly-parallel multi-processor systems for these algorithms are discussed.

Symosek, P.↗
NASA NTRS1999

ADPAC v1.0: User's Manual

The overall objective of this study was to evaluate the effects of turbulence models in a 3-D numerical analysis on the wake prediction capability. The current version of the computer code resulting from this study is referred to as ADPAC v7 (Advanced Ducted Propfan Analysis Codes -Version 7). This report is intended to serve as a computer program user's manual for the ADPAC code used and modified under Task 15 of NASA Contract NAS3-27394. The ADPAC program is based on a flexible multiple-block and discretization scheme permitting coupled 2-D/3-D mesh block solutions with application to a wide variety of geometries. Aerodynamic calculations are based on a four-stage Runge-Kutta time-marching finite volume solution technique with added numerical dissipation. Steady flow predictions are accelerated by a multigrid procedure. Turbulence models now available in the ADPAC code are: a simple mixing-length model, the algebraic Baldwin-Lomax model with user defined coefficients, the one-equation Spalart-Allmaras model, and a two-equation k-R model. The consolidated ADPAC code is capable of executing in either a serial or parallel computing mode from a single source code.

Hall, Edward J.↗
DOE OSTI2025

Distributed Cross-Channel Hierarchical Aggregation for Foundation Models

Vision-based scientific foundation models hold significant promise for advancing scientific discovery and innovation. This potential stems from their ability to aggregate images from diverse sources—such as varying physical groundings or data acquisition systems—and to learn spatio-temporal correlations using transformer architectures. However, tokenizing and aggregating images can be compute-intensive, a challenge not fully addressed by current distributed methods. In this work, we introduce the Distributed Cross-Channel Hierarchical Aggregation (D-CHAG) approach designed for datasets with a large number of channels across image modalities. Our method is compatible with any model-parallel strategy and any type of vision transformer architecture, significantly improving computational efficiency. We evaluated D-CHAG on hyperspectral imaging and weather forecasting tasks. When integrated with tensor parallelism and model sharding, our approach achieved up to a 75% reduction in memory usage and more than doubled sustained throughput on up to 1,024 AMD GPUs on the Frontier Supercomputer.

Tsaris, Aristeidis (aris) [ORNL] (ORCID:0000000277↗
NASA NTRS2001

Efficiency Improvements to the Displacement Based Multilevel Structural Optimization Algorithm

Multilevel Structural Optimization (MSO) continues to be an area of research interest in engineering optimization. In the present project, the weight optimization of beams and trusses using Displacement based Multilevel Structural Optimization (DMSO), a member of the MSO set of methodologies, is investigated. In the DMSO approach, the optimization task is subdivided into a single system and multiple subsystems level optimizations. The system level optimization minimizes the load unbalance resulting from the use of displacement functions to approximate the structural displacements. The function coefficients are then the design variables. Alternately, the system level optimization can be solved using the displacements themselves as design variables, as was shown in previous research. Both approaches ensure that the calculated loads match the applied loads. In the subsystems level, the weight of the structure is minimized using the element dimensions as design variables. The approach is expected to be very efficient for large structures, since parallel computing can be utilized in the different levels of the problem. In this paper, the method is applied to a one-dimensional beam and a large three-dimensional truss. The beam was tested to study possible simplifications to the system level optimization. In previous research, polynomials were used to approximate the global nodal displacements. The number of coefficients of the polynomials equally matched the number of degrees of freedom of the problem. Here it was desired to see if it is possible to only match a subset of the degrees of freedom in the system level. This would lead to a simplification of the system level, with a resulting increase in overall efficiency. However, the methods tested for this type of system level simplification did not yield positive results. The large truss was utilized to test further improvements in the efficiency of DMSO. In previous work, parallel processing was applied to the subsystems level, where the derivative verification feature of the optimizer NPSOL had been utilized in the optimizations. This resulted in large runtimes. In this paper, the optimizations were repeated without using the derivative verification, and the results are compared to those from the previous work. Also, the optimizations were run on both, a network of SUN workstations using the MPICH implementation of the Message Passing Interface (MPI) and on the faster Beowulf cluster at ICASE, NASA Langley Research Center, using the LAM implementation of UP]. The results on both systems were consistent and showed that it is not necessary to verify the derivatives and that this gives a large increase in efficiency of the DMSO algorithm.

Plunkett, C. L.↗
NASA NTRS1990

Development of microcomputer-based mental acuity tests for repeated-measures studies

The purpose of this report is to detail the development of the Automated Performance Test System (APTS), a computer battery of mental acuity tests that can be used to assess human performance in the presence of toxic elements and environmental stressors. There were four objectives in the development of APTS. First, the technical requirements for developing APTS followed the tenets of the classical theory of mental tests which requires that tests meet set criteria like stability and reliability (the lack of which constitutes insensitivity). To be employed in the study of the exotic conditions of protracted space flight, a battery with multiple parallel forms is required. The second criteria was for the battery to have factorial multidimensionality and the third was for the battery to be sensitive to factors known to compromise performance. A fourth objective was for the tests to converge on the abilities entailed in mission specialist tasks. A series of studies is reported in which candidate APTS tests were subjected to an examination of their psychometric properties for repeated-measures testing. From this work, tests were selected that possessed the requisite metric properties of stability, reliability, and factor richness. In addition, studies are reported which demonstrate the predictive validity of the tests to holistic measures of intelligence.

Kennedy, R. S.↗
NASA NTRS2012

JELC-LITE: Unconventional Instructional Design for Special Operations Training

Current special operations staff training is based on the Joint Event Life Cycle (JELC). It addresses operational level tasks in multi-week, live military exercises which are planned over a 12 to 18 month timeframe. As the military experiences changing global mission sets, shorter training events using distributed technologies will increasingly be needed to augment traditional training. JELC-Lite is a new approach for providing relevant training between large scale exercises. This new streamlined, responsive training model uses distributed and virtualized training technologies to establish simulated scenarios. It keeps proficiency levels closer to optimal levels -- thereby reducing the performance degradation inherent in periodic training. It can be delivered to military as well as under-reached interagency groups to facilitate agile, repetitive training events. JELC-Lite is described by four phases paralleling the JELC, differing mostly in scope and scale. It has been successfully used with a Theater Special Operations Command and fits well within the current environment of reduced personnel and financial resources.

Friedman, Mark↗
DOE OSTI2026

HydraGNN v5.0

HydraGNN v5.0 expands the code base into a more portable, scalable, and flexible framework for scientific graph learning, with particular strength in atomistic machine-learning interatomic potentials and large-scale distributed training. The release adds Fully Sharded Data Parallel (FSDP) support alongside existing DDP and DeepSpeed paths, including FSDP-aware checkpointing and optimizer integration, and introduces a configurable multi-precision training workflow supporting FP32, BF16, and FP64 across GPUs and Intel XPUs. For atomistic modeling, HydraGNN v5.0 strengthens its MLIP capabilities through dynamic graph construction at every forward pass, energy-conserving force prediction via automatic differentiation, and per-atom energy loss formulations, while extending EGNN models to properly handle periodic boundary conditions. The release also broadens model expressiveness through graph-level attribute conditioning, adds new multi-task and model-parallel extensions such as MACE support and encoder/decoder branch optimization, and expands application coverage with integrated examples for datasets including OC25, Nabla2-DFT, QCML, Open Polymers 2026, and OPF. In parallel, HydraGNN v5.0 improves production readiness through performance optimizations for large-scale runs, stratified sampling and linear-regression preprocessing utilities, and tested installation scripts for DOE supercomputers including Frontier, Aurora, Perlmutter, and Andes. Overall, the release advances HydraGNN as a robust software platform for scalable graph neural networks across materials science, chemistry, and scientific machine learning workflows

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗
NASA NTRS1995

Displacement based multilevel structural optimization

Multidisciplinary design optimization (MDO) is expected to play a major role in the competitive transportation industries of tomorrow, i.e., in the design of aircraft and spacecraft, of high speed trains, boats, and automobiles. All of these vehicles require maximum performance at minimum weight to keep fuel consumption low and conserve resources. Here, MDO can deliver mathematically based design tools to create systems with optimum performance subject to the constraints of disciplines such as structures, aerodynamics, controls, etc. Although some applications of MDO are beginning to surface, the key to a widespread use of this technology lies in the improvement of its efficiency. This aspect is investigated here for the MDO subset of structural optimization, i.e., for the weight minimization of a given structure under size, strength, and displacement constraints. Specifically, finite element based multilevel optimization of structures (here, statically indeterminate trusses and beams for proof of concept) is performed. In the system level optimization, the design variables are the coefficients of assumed displacement functions, and the load unbalance resulting from the solution of the stiffness equations is minimized. Constraints are placed on the deflection amplitudes and the weight of the structure. In the subsystems level optimizations, the weight of each element is minimized under the action of stress constraints, with the cross sectional dimensions as design variables. This approach is expected to prove very efficient, especially for complex structures, since the design task is broken down into a large number of small and efficiently handled subtasks, each with only a small number of variables. This partitioning will also allow for the use of parallel computing, first, by sending the system and subsystems level computations to two different processors, ultimately, by performing all subsystems level optimizations in a massively parallel manner on separate processors. It is expected that the subsystems level optimizations can be further improved through the use of controlled growth, a method which reduces an optimization to a more efficient analysis with only a slight degradation in accuracy. The efficiency of all proposed techniques is being evaluated relative to the performance of the standard single level optimization approach where the complete structure is weight minimized under the action of all given constraints by one processor and to the performance of simultaneous analysis and design which combines analysis and optimization into a single step. It is expected that the present approach can be expanded to include additional structural constraints (buckling, free and forced vibration, etc.) or other disciplines (passive and active controls, aerodynamics, etc.) for true MDO.

Striz, Alfred G.↗
NASA NTRS1997

Structural Verification of the Space Shuttle's External Tank Super LightWeight Design: A Lesson in Innovation

The Super LightWeight Tank (SLWT) team was tasked with a daunting challenge from the outset: boost the payload capability of the Shuttle System by safely removing 7500 lbs. from the existing 65,400 lb. External Tank (ET). Tools they had to work with included a promising new Aluminum Lithium alloy, the concept of a more efficient structural configuration for the Liquid Hydrogen (LH2) tank, and a highly successful, mature Light Weight Tank (LWT) program. The 44 month schedule which the SLWT team was given for the task was ambitious by any measure. During this time the team had to not only design, build, and verify the new tank, but they also had to move a material from the early stages of development to maturity. The aluminum lithium alloy showed great promise, with an approximately 29% increase in yield strength, 15% increase in ultimate strength, 5 deg/O increase in modulus and 5 deg/O decrease in density when compared to the current 2219 alloy. But processes had to be developed and brought under control, manufacturing techniques perfected, properties characterized, and design allowable generated. Because of the schedule constraint, this material development activity had to occur in parallel with design and manufacturing. Initial design was performed using design allowable believed to be achievable with the Aluminum Lithium alloy system, but based on limited test data. Preliminary structural development tests were performed with material still in the process of iteration. This parallel path approach posed obvious challenges and risks, but also allowed a unique opportunity for interaction between the structures and materials disciplines in the formulation of the material.

Otte, Neil↗
NASA NTRS2008

PyPele Rewritten To Use MPI

A computer program known as PyPele, originally written as a Pythonlanguage extension module of a C++ language program, has been rewritten in pure Python language. The original version of PyPele dispatches and coordinates parallel-processing tasks on cluster computers and provides a conceptual framework for spacecraft-mission- design and -analysis software tools to run in an embarrassingly parallel mode. The original version of PyPele uses SSH (Secure Shell a set of standards and an associated network protocol for establishing a secure channel between a local and a remote computer) to coordinate parallel processing. Instead of SSH, the present Python version of PyPele uses Message Passing Interface (MPI) [an unofficial de-facto standard language-independent application programming interface for message- passing on a parallel computer] while keeping the same user interface. The use of MPI instead of SSH and the preservation of the original PyPele user interface make it possible for parallel application programs written previously for the original version of PyPele to run on MPI-based cluster computers. As a result, engineers using the previously written application programs can take advantage of embarrassing parallelism without need to rewrite those programs.

Hockney, George↗
NASA NTRS1972

Study of solid rocket motors for a space shuttle booster. Appendix D: Recovery and reuse 156-inch diameter solid rocket motor booster

The baseline for a space shuttle configuration utilizing two parallel-burn, 156-in.-diameter SRMs with three segments and techroll seal movable nozzles is presented. The concept and general economic benefits of SRM recovery are equally valid for the series-burn SRMs, provided that those SRMs are also designed for the same strength, stiffness, segmentation, and interchangeability as the present design, and that those SRMs are also recovered as individual units. Feasibility studies were initiated to investigate SRM recoverability. These studies were based upon recovery of the SRM boosters for the Titan 3C. Ground rules precluded SRM modification that required significant changes in motor qualification or schedule. Even with this restriction, the study determined that the recoverable booster concept was completely feasible, both technically and economically. Parachute recovery has been selected as the best method, principally because it can accomplish the task with a minimum development cost and time to achieve operational recovery status. This system affords the highest probability for achieving large cost reductions.

Source record↗
NASA NTRS1986

Optimal design of structures with multiple design variables per group and multiple loading conditions on the personal computer

A finite element based programming system for minimum weight design of a truss-type structure subjected to displacement, stress, and lower and upper bounds on design variables is presented. The programming system consists of a number of independent processors, each performing a specific task. These processors, however, are interfaced through a well-organized data base, thus making the tasks of modifying, updating, or expanding the programming system much easier in a friendly environment provided by many inexpensive personal computers. The proposed software can be viewed as an important step in achieving a 'dummy' finite element for optimization. The programming system has been implemented on both large and small computers (such as VAX, CYBER, IBM-PC, and APPLE) although the focus is on the latter. Examples are presented to demonstrate the capabilities of the code. The present programming system can be used stand-alone or as part of the multilevel decomposition procedure to obtain optimum design for very large scale structural systems. Furthermore, other related research areas such as developing optimization algorithms (or in the larger level: a structural synthesis program) for future trends in using parallel computers may also benefit from this study.

Nguyen, D. T.↗
NASA NTRS1992

Moving formal methods into practice. Verifying the FTPP Scoreboard: Results, phase 1

This report documents the Phase 1 results of an effort aimed at formally verifying a key hardware component, called Scoreboard, of a Fault-Tolerant Parallel Processor (FTPP) being built at Charles Stark Draper Laboratory (CSDL). The Scoreboard is part of the FTPP virtual bus that guarantees reliable communication between processors in the presence of Byzantine faults in the system. The Scoreboard implements a piece of control logic that approves and validates a message before it can be transmitted. The goal of Phase 1 was to lay the foundation of the Scoreboard verification. A formal specification of the functional requirements and a high-level hardware design for the Scoreboard were developed. The hardware design was based on a preliminary Scoreboard design developed at CSDL. A main correctness theorem, from which the functional requirements can be established as corollaries, was proved for the Scoreboard design. The goal of Phase 2 is to verify the final detailed design of Scoreboard. This task is being conducted as part of a NASA-sponsored effort to explore integration of formal methods in the development cycle of current fault-tolerant architectures being built in the aerospace industry.

Srivas, Mandayam↗
NASA NTRS2022

Balancing Predictive and Reactive Science Planning for Mars 2020 Perseverance

The design of the science planning process for a space science mission needs to find a balance between operational and resource constraints and scientific decision-making. Science planning has previously been characterized as either predictive or reactive. Predictive science planning is needed when constraints drive science activities to be planned far in advance. For example, a combination of long one-way light time plus high-stakes science decisions drove the Cassini-Huygens mission to Saturn to have an extremely predictive planning process. On the other extreme, reactive science planning is needed when constraints drive science activities to be planned based on the results of the previous plan. For example, the Mars Exploration Rover mission interacted with the surface of Mars, and so the planning team needed to know the state of the rover at the end of each planning cycle before starting the next cycle. Operational and resource constraints that require management on intermediate timescales has led to the development of a science planning process between these two extremes. For example, the Mars Science Laboratory is a technically complex rover and has a parallel predictive process that allows the operations team to manage engineering constraints several days in advance while maintaining the reactive tactical planning process similar to that of MER. The Mars 2020 Perseverance rover is a technically complex rover in the MSL style, but has an added layer of science complexity: it is tasked with collecting a returnable cache of scientifically valuable samples of Mars within prime mission. Thus, the science planning process also needs to accommodate high-stakes longer-term science decisions in the style of Cassini. In order to balance the push-pull of these constraints, we have developed a science campaign-focused operational paradigm for Mars 2020 Perseverance that allows for both predictive planning to accommodate technological complexity and high-stakes science decisions as well as reactive planning to accommodate the realities of interacting with the martian surface. This paradigm influenced the design of operational processes and operational tools.

Spanovich, Nicole↗
NASA NTRS1995

Searching for patterns in remote sensing image databases using neural networks

We have investigated a method, based on a successful neural network multispectral image classification system, of searching for single patterns in remote sensing databases. While defining the pattern to search for and the feature to be used for that search (spectral, spatial, temporal, etc.) is challenging, a more difficult task is selecting competing patterns to train against the desired pattern. Schemes for competing pattern selection, including random selection and human interpreted selection, are discussed in the context of an example detection of dense urban areas in Landsat Thematic Mapper imagery. When applying the search to multiple images, a simple normalization method can alleviate the problem of inconsistent image calibration. Another potential problem, that of highly compressed data, was found to have a minimal effect on the ability to detect the desired pattern. The neural network algorithm has been implemented using the PVM (Parallel Virtual Machine) library and nearly-optimal speedups have been obtained that help alleviate the long process of searching through imagery.

Paola, Justin D.↗
DOE OSTI2026

Classic and Quantum Task-Based Intelligent Runtime for QIRs Running on Multiple QPUs

High-performance computing systems are rapidly evolving into heterogeneous platforms that fuse quantum accelerators with traditional classical processing units (CPUs) and graphical processing units (GPUs). This convergence calls for runtimes capable of managing both classical and quantum workloads in a unified manner. We introduce an intelligent, task-based runtime that marries the Intelligent RuntIme System (IRIS) asynchronous scheduler with a quantum programming stack through the Quantum Intermediate Representation Execution Engine (QIR-EE). Our design allows programs written in the quantum intermediate representation (QIR) to be dispatched concurrently to a variety of back-ends, including multiple quantum simulators and nascent quantum processors, enabling genuine hybrid execution on a single node. To illustrate its practicality, we partition a 4-qubit and 20-qubit circuit into three sub-circuits using quantum circuit cutting via the QCut library. Each sub-circuit is simulated independently by the QIR-EE driver within IRIS, after which a classical post-processing step merges the simulation results to recover the outcome of the original full-circuit computation. This case study demonstrates how finer task granularity can enable the parallel execution and lower the simulation burden per quantum task while preserving overall accuracy, highlighting the feasibility of our hybrid approach.

Miniskar, Narasinga Rao [ORNL] (ORCID:000000018259↗
DOE OSTI2025

Knowledge Oriented Graph Unified Transformer (KOGUT) v0.1

KOGUT — Knowledge Oriented Graph Unified Transformer KOGUT implements the Relational Graph Transformer (RelGT) architecture for knowledge graph link prediction in biological domains, with a primary focus on microbial growth media prediction. While the original RelGT (arXiv:2505.10960) targets relational tables, time series, and multi-table databases, KOGUT adapts this architecture for heterogeneous biological knowledge graphs, providing first-in-class AI predictive models for microbial cultivation. Key Adaptations Beyond Original RelGT: - Knowledge Graph Focus: Applied to biological KGs with semantic node types (taxa, chemicals, media, phenotypes, environments) versus generic relational database tables, trained on the KG-Microbe knowledge graph (1.3M entities, 2.9M edges, 24 relation types). - Multimodal Node Encoding: Integrates node labels, categories, descriptions, and synonyms from KG metadata through learned embedding layers—adapting relational column features to graph node attributes with textual semantics. - Extended K-Hop Subgraph Strategy: Optimized neighborhood sampling (3-hop default, configurable up to 200 nodes) tuned for sparse biological networks, building on the original local-global attention framework with biological relation preservation. - Biolink Predicate Preservation: Type-specific transformations for 24 biological edge semantics (occurs_in, consumes, produces, has_phenotype, subclass_of) beyond standard relational foreign keys, enabling multi-relation link prediction. - Inductive Learning Support: Enables zero-shot predictions for novel taxa through feature-based embeddings (temperature, oxygen requirements, gram stain, cell shape), extending the original transductive relational benchmark scope to uncultured microorganisms. CheapSOTA Performance Optimizations (This Distribution): - VQ-EMA Centroid Attention: Vector quantization with exponential moving average for improved global context modeling (+5-10% MRR improvement). - HDF5 Precomputed Data Loading: One-time preprocessing of k-hop subgraphs to eliminate redundant graph traversals (2-5× training speedup). - Distributed Data Parallel Training: Multi-GPU support for scaling to larger knowledge graphs (tested on 4× NVIDIA A100 GPUs at NERSC Perlmutter). - Mixed Precision Training: Automatic mixed precision (AMP) for memory efficiency and faster training. Advantages Over Standard Knowledge Graph Embedding Models: Combines RelGT's proven multi-element tokenization (features, type, hop, structure) with graph-native biological representations, enabling interpretable link prediction across heterogeneous entities that standard embedding models (TransE, RotatE, ComplEx) and table-based transformers cannot directly model. Achieves near-perfect performance on microbial growth media prediction (MRR: 0.9966, Precision@1: 0.9932, Hit@10: 1.0000) while maintaining explainability through attention-based reasoning over biological pathways. Training Data: - KG-Microbe merged knowledge graph: 1,379,337 nodes, 2,960,472 edges - 24 biological relation types including taxonomic hierarchies, metabolic interactions, phenotype associations, and environmental relationships - Primary prediction task: Growth media suitability for microbial taxa (biolink:occurs_in, 50K edges) - Multi-relation capability: Predicts links for any of the 24 relation types, including chemical consumption/production, phenotype associations, and taxonomic classification Citation: Original RelGT Architecture: Dwivedi et al., "Relational Graph Transformer", arXiv:2505.10960, 2025 KOGUT Implementation: Knowledge Oriented Graph Unified Transformer for Microbial Growth Media Prediction Developed at Lawrence Berkeley National Laboratory (LBNL) Trained on NERSC Perlmutter supercomputer

Joachimiak, Marcin [Lawrence Berkeley National Lab↗
NASA NTRS1996

Paradise: A Parallel Information System for EOSDIS

The Paradise project was begun-in 1993 in order to explore the application of the parallel and object-oriented database system technology developed as a part of the Gamma, Exodus. and Shore projects to the design and development of a scaleable, geo-spatial database system for storing both massive spatial and satellite image data sets. Paradise is based on an object-relational data model. In addition to the standard attribute types such as integers, floats, strings and time, Paradise also provides a set of and multimedia data types, designed to facilitate the storage and querying of complex spatial and multimedia data sets. An individual tuple can contain any combination of this rich set of data types. For example, in the EOSDIS context, a tuple might mix terrain and map data for an area along with the latest satellite weather photo of the area. The use of a geo-spatial metaphor simplifies the task of fusing disparate forms of data from multiple data sources including text, image, map, and video data sets.

DeWitt, David↗