Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel optimization”

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 469 records · Page 26

RingX: Scalable Parallel Attention for Long-Context Learning on HPC

The attention mechanism has become foundational for remarkable AI breakthroughs since the introduction of the Transformer, driving the demand for increasingly longer context to power frontier models such as large-scale reasoning language models and high-resolution image/video generators. However, its quadratic computational and memory complexities present substantial challenges. Current state-of-the-art parallel attention methods, such as ring attention, are widely adopted for long-context training but utilize a point-to-point communication strategy that fails to fully exploit the capabilities of modern HPC network architectures. In this work, we propose ringX, a scalable family of parallel attention methods optimized explicitly for HPC systems. By enhancing workload partitioning, refining communication patterns, and improving load balancing, ringX achieves up to 3.4 × speedup compared to conventional ring attention on the Frontier supercomputer. Optimized for both bi-directional and causal attention mechanisms, ringX demonstrates its effectiveness through training benchmarks of a Vision Transformer (ViT) on a climate dataset and a Generative Pre-Trained Transformer (GPT) model, Llama3 8B. Our method attains an end-to-end training speedup of approximately 1.5 × in both scenarios. To our knowledge, the achieved 38% model FLOPs utilization (MFU) for training Llama3 8B with a 1M-token sequence length on 4,096 GPUs represents one of the highest training efficiencies reported for long-context learning on HPC systems. Our code implementation is available at https://github.com/jqyin/ringX-attention.

Yin, Junqi [ORNL] (ORCID:0000000338435520)↗

RX-PSA

This code is built on top of the ML-PSA utility and implements the ability to implement a multi-fidelity parallel simulated annealing optimization for a range of engineering problems. RX-PSA provides specializations to interact with modern nuclear reactor codes such as VERA to perform assembly and core optimization in a robust way. RX-PSA also provides LWR specific objective functions and constraints to provide a straightforward user interface that reactor designers are familiar with.

Collins, BenjaminS.↗

Wavefront shaping with a Hadamard basis for scattering soil imaging

Here, soil is a scattering medium that inhibits imaging of plant-microbial-mineral interactions that are essential to plant health and soil carbon sequestration. However, optical imaging in the complex medium of soil has been stymied by the seemingly intractable problems of scattering and contrast. Here, we develop a wavefront shaping method based on adaptive stochastic parallel gradient descent optimization with a Hadamard basis to focus light through soil mineral samples. Our approach allows a sparse representation of the wavefront with reduced dimensionality for the optimization. We further divide the used Hadamard basis set into subsets and optimize a certain subset at once. Simulation and experimental optimization results demonstrate our method has an approximately seven times higher convergence rate and overall better performance compared to that with optimizing all pixels at once. The proposed method can benefit other high-dimensional optimization problems in adaptive optics and wavefront shaping.

47 OTHER INSTRUMENTATION↗

Enabling High Performance Application I/O

This work provides software that enables scientific applications to more efficiently access available storage resources at different levels of interfaces. We developed scalable techniques and optimizations for PVFS parallel file systems, MPI I/O, and parallel netCDF I/O library. These implementations were evaluated using production application I/O kernels as well as popular I/O benchmarks and demonstrated promising results. The software developed under this work has been made available to the public via MCS, ANL web sites.

97 MATHEMATICS AND COMPUTING↗

Exago TM Users Manual: Version 1.0

The Exascale Grid Optimization (ExaGOTM) toolkit is an open source package for solving large-scale power grid optimization problems on parallel and distributed architectures, particularly targeted for exascale machines with heteregenous architectures (GPU). This manual is a guide to ExaGO's working including installation, formulation, and usage.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Scientific Data Management Integrated Software Infrastructure Center

This work provides software that enables scientific applications to more efficiently access available storage resources at different levels of interfaces. We developed scalable techniques and optimizations for PVFS parallel file systems, MPI I/O, and parallel netCDF I/O library. These implementations were evaluated using production application I/O kernels as well as popular I/O benchmarks and demonstrated promising results. The software developed under this work has been made available to the public via MCS, ANL web sites.

97 MATHEMATICS AND COMPUTING↗

Hierarchial parallel computer architecture defined by computational multidisciplinary mechanics

The goal is to develop an architecture for parallel processors enabling optimal handling of multi-disciplinary computation of fluid-solid simulations employing finite element and difference schemes. The goals, philosphical and modeling directions, static and dynamic poly trees, example problems, interpolative reduction, the impact on solvers are shown in viewgraph form.

Padovan, Joe↗

Modeling and new equipment definition for the vibration isolation box equipment system

Our MSAD-funded research project is to provide numerical modeling support for the VIBES (Vibration Isolation Box Experiment System) which is an IML2 flight experiment being built by the Japanese research team of Dr. H. Azuma of the Japanese National Aerospace Laboratory. During this reporting period, the following have been accomplished: A semi-consistent mass finite element projection algorithm for 2D and 3D Boussinesq flows has been implemented on Sun, HP And Cray Platforms. The algorithm has better phase speed accuracy than similar finite difference or lumped mass finite element algorithms, an attribute which is essential for addressing realistic g-jitter effects as well as convectively-dominated transient systems. The projection algorithm has been benchmarked against solutions generated via the commercial code FIDAP. The algorithm appears to be accurate as well as computationally efficient. Optimization and potential parallelization studies are underway. Our implementation to date has focused on execution of the basic algorithm with at most a concern for vectorization. The initial time-varying gravity Boussinesq flow simulation is being set up. The mesh is being designed and the input file is being generated. Some preliminary 'small mesh' cases will be attempted on our HP9000/735 while our request to MSAD for supercomputing resources is being addressed. The Japanese research team for VIBES was visited, the current set up and status of the physical experiment was obtained and ongoing E-Mail communication link was established.

Sani, Robert L.↗

Using parallel banded linear system solvers in generalized eigenvalue problems

Subspace iteration is a reliable and cost effective method for solving positive definite banded symmetric generalized eigenproblems, especially in the case of large scale problems. This paper discusses an algorithm that makes use of two parallel banded solvers in subspace iteration. A shift is introduced to decompose the banded linear systems into relatively independent subsystems and to accelerate the iterations. With this shift, an eigenproblem is mapped efficiently into the memories of a multiprocessor and a high speed-up is obtained for parallel implementations. An optimal shift is a shift that balances total computation and communication costs. Under certain conditions, we show how to estimate an optimal shift analytically using the decay rate for the inverse of a banded matrix, and how to improve this estimate. Computational results on iPSC/2 and iPSC/860 multiprocessors are presented.

Zhang, Hong↗

Using parallel banded linear system solvers in generalized eigenvalue problems

Subspace iteration is a reliable and cost effective method for solving positive definite banded symmetric generalized eigenproblems, especially in the case of large scale problems. This paper discusses an algorithm that makes use of two parallel banded solvers in subspace iteration. A shift is introduced to decompose the banded linear systems into relatively independent subsystems and to accelerate the iterations. With this shift, an eigenproblem is mapped efficiently into the memories of a multiprocessor and a high speedup is obtained for parallel implementations. An optimal shift is a shift that balances total computation and communication costs. Under certain conditions, we show how to estimate an optimal shift analytically using the decay rate for the inverse of a banded matrix, and how to improve this estimate. Computational results on iPSC/2 and iPSC/860 multiprocessors are presented.

DISTRIBUTED MEMORY MULTIPROCES↗

NASA Image eXchange (NIX)

This paper discusses the technical aspects of and the project background for the NASA Image exchange (NIX). NIX, which provides a single entry point to search selected image databases at the NASA Centers, is a meta-search engine (i.e., a search engine that communicates with other search engines). It uses these distributed digital image databases to access photographs, animations, and their associated descriptive information (meta-data). NIX is available for use at the following URL: http://nix.nasa.gov./NIX, which was sponsored by NASAs Scientific and Technical Information (STI) Program, currently serves images from seven NASA Centers. Plans are under way to link image databases from three additional NASA Centers. images and their associated meta-data, which are accessible by NIX, reside at the originating Centers, and NIX utilizes a virtual central site that communicates with each of these sites. Incorporated into the virtual central site are several protocols to support searches from a diverse collection of database engines. The searches are performed in parallel to ensure optimization of response times. To augment the search capability, browse functionality with pre-defined categories has been built into NIX, thereby ensuring dissemination of 'best-of-breed' imagery. As a final recourse, NIX offers access to a help desk via an on-line form to help locate images and information either within the scope of NIX or from available external sources.

vonOfenheim. William H. C.↗

Optimizing the NASA Technical Report Server

The NASA Technical Report Server (NTRS), a World Wide Web report distribution NASA technical publications service, is modified for performance enhancement, greater protocol support, and human interface optimization. Results include: Parallel database queries, significantly decreasing user access times by an average factor of 2.3; access from clients behind firewalls and/ or proxies which truncate excessively long Uniform Resource Locators (URLs); access to non-Wide Area Information Server (WAIS) databases and compatibility with the 239-50.3 protocol; and a streamlined user interface.

Nelson, Michael L.↗

NASA Tech Briefs, April 2009

Topics covered include: Direct-Solve Image-Based Wavefront Sensing; Use of UV Sources for Detection and Identification of Explosives; Using Fluorescent Viruses for Detecting Bacteria in Water; Gradiometer Using Middle Loops as Sensing Elements in a Low-Field SQUID MRI System; Volcano Monitor: Autonomous Triggering of In-Situ Sensors; Wireless Fluid-Level Sensors for Harsh Environments; Interference-Detection Module in a Digital Radar Receiver; Modal Vibration Analysis of Large Castings; Structural/Radiation-Shielding Epoxies; Integrated Multilayer Insulation; Apparatus for Screening Multiple Oxygen-Reduction Catalysts; Determining Aliasing in Isolated Signal Conditioning Modules; Composite Bipolar Plate for Unitized Fuel Cell/Electrolyzer Systems; Spectrum Analyzers Incorporating Tunable WGM Resonators; Quantum-Well Thermophotovoltaic Cells; Bounded-Angle Iterative Decoding of LDPC Codes; Conversion from Tree to Graph Representation of Requirements; Parallel Hybrid Vehicle Optimal Storage System; and Anaerobic Digestion in a Flooded Densified Leachbed.

Source record↗

Aladyn - Adaptive Neural Network Molecular Dynamics Simulation Code: Computational Materials Mini-Application

This report provides an overview and commands description of the Computational Materials mini-application, Aladyn. Aladyn is a simple molecular dynamics code written in FORTRAN 2008, which is designed to demonstrate the use of adaptive neural networks (ANNs) in atomistic simulations. The role of ANNs is to reproduce the very complex energy landscape resulting from the atomic interactions in materials with the accuracy of quantum mechanics-based energy calculations. The ANN is trained on a large set of atomic structures calculated using the density functional theory (DFT) method. The Aladyn 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 many core architectures based on graphic processing units (GPUs). The effort is related to the High Performance Computing Incubator (HPCI) project at NASA Langley Research Center.

Yamakov, Vesselin I.↗

AladynPi – Adaptive Neural Network Molecular Dynamics Simulation Code with Physically Informed Potential: Computational Materials Mini-Application

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.

Yamakov, Vesselin I.↗

Dynamic Modeling, Trajectory Optimization, and Linear Control of Cable-Driven Parallel Robots for Automated Panelized Building Retrofits

The construction industry faces a growing need for automation to reduce costs, improve accuracy and productivity, and address labor shortages. One area that stands to benefit significantly from automation is panelized prefabricated building envelope retrofits, which can improve a building’s energy efficiency in heating and cooling interior spaces. In this paper, we propose using cable-driven parallel robots (CDPRs), which can effectively lift and handle large objects, to install these panels. However, implementing CDPRs presents significant challenges because of their nonlinear dynamics, complex trajectory planning, and precise control requirements. To tackle these challenges, this work focuses on a new application of established control and trajectory optimization theories in a CDPR simulation of a building envelope retrofit under real-world conditions. We first model the dynamics of CDPRs, highlighting the critical role of damping in system behavior. Building on this dynamic model, we formulate a trajectory optimization problem to generate feasible and efficient motion plans for the robot under operational and environmental constraints. Given the high precision required in the construction industry, accurately tracking the optimized trajectory is essential. However, challenges such as partial observability and external vibrations complicate this task. To address these issues, a Linear Quadratic Gaussian control framework is applied, enabling the robot to track the optimized trajectories with precision. Simulation results show that the proposed controller enables precise end effector positioning with errors under 4 mm, even in the presence of external wind disturbances. Through comprehensive simulations, our approach allows for an in-depth exploration of the system’s nonlinear dynamics, trajectory optimization, and control strategies under controlled yet highly realistic conditions. The results demonstrate the feasibility of CDPRs for automating panel installation and provide insights into their practical deployment.

CDPR↗

Automated Work Package: Initial Wireless Communication Platform Design, Development, and Evaluation

The Department of Energy's Light Water Reactor Sustainability Program is developing the scientific basis to ensure long-term reliability, productivity, safety, and security of the nuclear power industry in the United States. The Instrumentation, Information, and Control (II and C) pathway of the program aims to increase the role of advanced II and C technologies to achieve this objective. One of the pathway efforts at Idaho National Laboratory (INL) is to improve the work packages execution process by replacing the expensive, inefficient, bulky, complex, and error-prone paper-based work orders with automated work packages (AWPs). An AWP is an automated and dynamic presentation of the work package designed to guide the user through the work process. It is loaded on a mobile device, such as a tablet, and is capable of communicating with plant equipment and systems to acquire plant and procedure states. The AWP replaces those functions where a computer is more efficient and reliable than a human. To enable the automatic acquisition of plant data, it is necessary to design and develop a prototype platform for data exchange between the field instruments and the AWP mobile devices. The development of the platform aims to reveal issues and solutions generalizable to large-scale implementation of a similar system. Topics such as bandwidth, robustness, response time, interference, and security are usually associated with wireless communication. These concerns, along with other requirements, are listed in an earlier INL report. Specifically, the targeted issues and performance aspects in this work are relevant to the communication infrastructure from the perspective of promptness, robustness, expandability, and interoperability with different technologies. The development of a prompt system entailed significant performance optimization, including the use of parallel processing, parallel communication, modularity, noise filtering, and frequency tuning. A robust system was achieved by enforcing a persistent continuous data exchange that automatically detects and conveys a failure of any link or component in any part of the system, and that automatically restores the communication once the link or component is restored. An expandable topology was enabled by modularity and load sharing. The number of servers, mobile devices, and field instruments is not limited from a system structure point of view. The system interoperability was achieved by enforcing the independence of the field communication application from the mobile device application. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Parallel Directionally Split Solver Based on Reformulation of Pipelined Thomas Algorithm

In this research an efficient parallel algorithm for 3-D directionally split problems is developed. The proposed algorithm is based on a reformulated version of the pipelined Thomas algorithm that starts the backward step computations immediately after the completion of the forward step computations for the first portion of lines This algorithm has data available for other computational tasks while processors are idle from the Thomas algorithm. The proposed 3-D directionally split solver is based on the static scheduling of processors where local and non-local, data-dependent and data-independent computations are scheduled while processors are idle. A theoretical model of parallelization efficiency is used to define optimal parameters of the algorithm, to show an asymptotic parallelization penalty and to obtain an optimal cover of a global domain with subdomains. It is shown by computational experiments and by the theoretical model that the proposed algorithm reduces the parallelization penalty about two times over the basic algorithm for the range of the number of processors (subdomains) considered and the number of grid nodes per subdomain.

Povitsky, A.↗