SEARCH · Search NASA

Results for “Parallelization Strategy”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 343 records · Page 19

All sources NASA NTRS DOE OSTI

NASA NTRS1988

Retargeting of existing FORTRAN program and development of parallel compilers

The software models used in implementing the parallelizing compiler for the B-HIVE multiprocessor system are described. The various models and strategies used in the compiler development are: flexible granularity model, which allows a compromise between two extreme granularity models; communication model, which is capable of precisely describing the interprocessor communication timings and patterns; loop type detection strategy, which identifies different types of loops; critical path with coloring scheme, which is a versatile scheduling strategy for any multicomputer with some associated communication costs; and loop allocation strategy, which realizes optimum overlapped operations between computation and communication of the system. Using these models, several sample routines of the AIR3D package are examined and tested. It may be noted that automatically generated codes are highly parallelized to provide the maximized degree of parallelism, obtaining the speedup up to a 28 to 32-processor system. A comparison of parallel codes for both the existing and proposed communication model, is performed and the corresponding expected speedup factors are obtained. The experimentation shows that the B-HIVE compiler produces more efficient codes than existing techniques. Work is progressing well in completing the final phase of the compiler. Numerous enhancements are needed to improve the capabilities of the parallelizing compiler.

Agrawal, Dharma P.↗

DOE OSTI2021

An experimental comparison of a space-time multigrid method with PFASST for a reaction-diffusion problem

We consider two parallel-in-time approaches applied to a (reaction) diffusion problem, possibly non-linear. In particular, we consider PFASST (Parallel Full Approximation Scheme in Space and Time) and space-time multigrid strategies. For both approaches, we start from an integral formulation of the continuous time dependent problem. Then, a collocation form for PFASST and a discontinuous Galerkin discretization in time for the space-time multi-grid are employed, resulting in the same discrete solution at the time nodes. Strong and weak scaling of both multilevel strategies are compared for varying orders of the temporal discretization. Moreover, we investigate the respective convergence behavior for non-linear problems and highlight quantitative differences in execution times

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Enabling Modular Autonomous Feedback‐Loops in Materials Science through Hierarchical Experimental Laboratory Automation and Orchestration

Abstract Materials acceleration platforms (MAPs) operate on the paradigm of integrating combinatorial synthesis, high‐throughput characterization, automatic analysis, and machine learning. Within a MAP, one or multiple autonomous feedback loops may aim to optimize materials for certain functional properties or to generate new insights. The scope of a given experiment campaign is defined by the range of experiment and analysis actions that are integrated into the experiment framework. Herein, the authors present a method for integrating many actions within a hierarchical experimental laboratory automation and orchestration (HELAO) framework. They demonstrate the capability of orchestrating distributed research instruments that can incorporate data from experiments, simulations, and databases. HELAO interfaces laboratory hardware and software distributed across several computers and operating systems for executing experiments, data analysis, provenance tracking, and autonomous planning. Parallelization is an effective approach for accelerating knowledge generation provided that multiple instruments can be effectively coordinated, which the authors demonstrate with parallel electrochemistry experiments orchestrated by HELAO. Efficient implementation of autonomous research strategies requires device sharing, asynchronous multithreading, and full integration of data management in experimental orchestration, which to the best of the authors’ knowledge, is demonstrated for the first time herein.

36 MATERIALS SCIENCE↗

DOE OSTI2022

Energy alignment manipulation at the C 60 /TiO 2 (110) interface using a blanket molecular dipole approach

In this work, modifying the energy alignment between the frontier levels of a chromophore and the band edges of a semiconductor substrate using a “blanket layer” of molecular dipoles is explored. The electronic structure, measured with ultraviolet and x-ray photoemission spectroscopy, of C 60 deposited directly onto the TiO 2 (110) surface is compared with that of C 60 deposited onto the surface covered by a blanket layer of the custom-designed helical peptide Z-(Aib) 6 -Ipa, which has a large dipole moment of 18.6 D oriented along its molecular axis and pointing toward the substrate. The C 60 HOMO level is shifted 600 meV to deeper binding energy in the presence of the blanket layer, in good agreement with what is expected from a simple parallel plate capacitor model. These results demonstrate a simple and versatile strategy for controlling energy level alignment at organic/inorganic interfaces.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2021

Ultra-Fast Vertical Ordering of Lamellar Block Copolymer Films on Unmodified Substrates

To utilize the full potential of block copolymer (BCP) thin films for use in technological devices ranging from ion conduction membranes, transistors to nanowire array antennas, rapid self- assembly of lamellar block copolymers (l-BCPs) with vertically oriented lamellar domains on a variety of unmodified substrates is needed. l-BCPs have an inherently larger interfacial area for transport compared to their cylindrical counterpart. Our observations demonstrate that the as-cast weakly ordered vertically oriented state of l-BCP films of polystyrene-block-poly(methyl methacrylate) (PS-b-PMMA) from directional evaporation of select solvents, act as “seed templates” for their ultra-fast evolution (~30 s) into well-ordered vertically oriented nanostructures, using a thermal gradient-based Cold Zone Annealing (CZA) technique. Furthermore, vertical lamellae are obtained on unmodified substrates, Quartz and Kapton, and the kinetics of l-BCP ordering is much faster by CZA as compared to the isotropic oven annealing. The rapid ordering kinetics of vertical l-BCPs is tested and found applicable to different molecular weights and film thicknesses ranging from 20 nm to 480 nm, which ultimately flip over to their equilibrium parallel morphology at upper limits of annealing times. This rapid ordering strategy for vertical orientation of l-BCPs using roll-to-roll compatible CZA would be highly relevant for fundamental studies of interfacial transport as well as for industrial applications from membranes to nanowires.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2011

Comparative metagenomic, phylogenetic and physiological analyses of soil microbial communities across nitrogen gradients

Terrestrial ecosystems are receiving elevated inputs of nitrogen (N) from anthropogenic sources and understanding how these increases in N availability affect soil microbial communities is critical for predicting the associated effects on belowground ecosystems. We used a suite of approaches to analyze the structure and functional characteristics of soil microbial communities from replicated plots in two long-term N fertilization experiments located in contrasting systems. Pyrosequencingbased analyses of 16S rRNA genes revealed no significant effects of N fertilization on bacterial diversity, but significant effects on community composition at both sites; copiotrophic taxa (including members of the Proteobacteria and Bacteroidetes phyla) typically increased in relative abundance in the high N plots, with oligotrophic taxa (mainly Acidobacteria) exhibiting the opposite pattern. Consistent with the phylogenetic shifts under N fertilization, shotgun metagenomic sequencing revealed increases in the relative abundances of genes associated with DNA/RNA replication, electron transport and protein metabolism, increases that could be resolved even with the shallow shotgun metagenomic sequencing conducted here (average of 75 000 reads per sample). We also observed shifts in the catabolic capabilities of the communities across the N gradients that were significantly correlated with the phylogenetic and metagenomic responses, indicating possible linkages between the structure and functioning of soil microbial communities. Overall, our results suggest that N fertilization may, directly or indirectly, induce a shift in the predominant microbial life-history strategies, favoring a more active, copiotrophic microbial community, a pattern that parallels the often observed replacement of K-selected with r-selected plant species with elevated N.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2014

Asymmetry and non-random orientation of the inflight effective beam pattern in the WMAP data

Tentative evidence for statistical anisotropy in the Wilkinson Microwave Anisotropy Probe data was alleged to be due to 'insufficient handling of beam asymmetries'. In this paper, we investigate this issue and develop a method to estimate the shape of the inflight effective beam, particularly the asymmetry and azimuthal orientation. We divide the whole map into square patches and exploit the information in the Fourier space. For patches containing bright extragalactic point sources, we can directly estimate their shapes, from which the inflight effective beam can be estimated. For those without, we estimate the pattern from iso-power contours in two-dimensional Fourier space. We show that the inflight effective beam convolving the signal is indeed non-symmetric for most of the sky, and it is not randomly oriented. Around the ecliptic poles, however, the asymmetry is smaller due to the averaging effect from different orientations of the beam from the scan strategy. The orientations of the effective beam with significant asymmetry are parallel to the lines of ecliptic longitude. In the foreground-cleaned Internal Linear Combination map, however, the systematics caused by beam effect is significantly lessened.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2016

A high performance cost-effective digital complex correlator for an X-band polarimetry survey

The detailed knowledge of the Milky Way radio emission is important to characterize galactic foregrounds masking extragalactic and cosmological signals. The update of the global sky models describing radio emissions over a very large spectral band requires high sensitivity experiments capable of observing large sky areas with long integration times. Here, we present the design of a new 10 GHz (X-band) polarimeter digital backend to map the polarization components of the galactic synchrotron radiation field of the Northern Hemisphere sky. The design follows the digital processing trends in radio astronomy and implements a large bandwidth (1 GHz) digital complex cross-correlator to extract the Stokes parameters of the incoming synchrotron radiation field. The hardware constraints cover the implemented VLSI hardware description language code and the preliminary results. The implementation is based on the simultaneous digitized acquisition of the Cartesian components of the two linear receiver polarization channels. The design strategy involves a double data rate acquisition of the ADC interleaved parallel bus, and field programmable gate array device programming at the register transfer mode. The digital core of the back-end is capable of processing 32 Gbps and is built around an Altera field programmable gate array clocked at 250 MHz, 1 GSps analog to digital converters and a clock generator. The control of the field programmable gate array internal signal delays and a convenient use of its phase locked loops provide the timing requirements to achieve the target bandwidths and sensitivity. This solution is convenient for radio astronomy experiments requiring large bandwidth, high functionality, high volume availability and low cost. Of particular interest, this correlator was developed for the Galactic Emission Mapping project and is suitable for large sky area polarization continuum surveys. The solutions may also be adapted to be used at signal processing subsystem levels for large projects like the square kilometer array testbeds.

79 ASTRONOMY AND ASTROPHYSICS↗

NASA NTRS1992

Unstructured mesh algorithms for aerodynamic calculations

The use of unstructured mesh techniques for solving complex aerodynamic flows is discussed. The principle advantages of unstructured mesh strategies, as they relate to complex geometries, adaptive meshing capabilities, and parallel processing are emphasized. The various aspects required for the efficient and accurate solution of aerodynamic flows are addressed. These include mesh generation, mesh adaptivity, solution algorithms, convergence acceleration, and turbulence modeling. Computations of viscous turbulent two-dimensional flows and inviscid three-dimensional flows about complex configurations are demonstrated. Remaining obstacles and directions for future research are also outlined.

Mavriplis, D. J.↗

NASA NTRS1992

Unstructured mesh algorithms for aerodynamic calculations

Mavriplis, D. J.↗

NASA NTRS1996

A General-Purpose Optimization Engine for Multi-Disciplinary Design Applications

A general purpose optimization tool for multidisciplinary applications, which in the literature is known as COMETBOARDS, is being developed at NASA Lewis Research Center. The modular organization of COMETBOARDS includes several analyzers and state-of-the-art optimization algorithms along with their cascading strategy. The code structure allows quick integration of new analyzers and optimizers. The COMETBOARDS code reads input information from a number of data files, formulates a design as a set of multidisciplinary nonlinear programming problems, and then solves the resulting problems. COMETBOARDS can be used to solve a large problem which can be defined through multiple disciplines, each of which can be further broken down into several subproblems. Alternatively, a small portion of a large problem can be optimized in an effort to improve an existing system. Some of the other unique features of COMETBOARDS include design variable formulation, constraint formulation, subproblem coupling strategy, global scaling technique, analysis approximation, use of either sequential or parallel computational modes, and so forth. The special features and unique strengths of COMETBOARDS assist convergence and reduce the amount of CPU time used to solve the difficult optimization problems of aerospace industries. COMETBOARDS has been successfully used to solve a number of problems, including structural design of space station components, design of nozzle components of an air-breathing engine, configuration design of subsonic and supersonic aircraft, mixed flow turbofan engines, wave rotor topped engines, and so forth. This paper introduces the COMETBOARDS design tool and its versatility, which is illustrated by citing examples from structures, aircraft design, and air-breathing propulsion engine design.

Patnaik, Surya N.↗

NASA NTRS1987

Mapping between parallel processor structures and programs

This paper reports some ongoing research efforts at Stanford in allocation of parallel processing resources. Both processor structures and program structures have their own characteristics. Resource allocation binds the two structures during program execution. The mapping problem determines what processor structure and program structure may be combined to obtain maximum speedup. Three approaches to this mapping problem are considered. Two important factors, granularity and interaction delay, are also considered. A new hierarchical approach to structure definition is outlined. Effective and efficient tools are necessary for the study of the mapping problem. A fast turn-around simulation environment developed for investigating partition strategies for distributed computations and a computationally efficient method to predict performance of parallel processor structures are described.

Ngai, Tin-Fook↗

NASA NTRS1988

Evaluation of the benefits and feasibility of on-orbit repair by comparison with operations in an analogous environment - How is the Freedom Space Station like an oceanographic expedition?

Equipment maintenance and logistics strategies followed on the R/S Thompson, an oceanographic research vessel, are described, and parallels are drawn between the problems and solutions of an oceanographic expedition and those of a space station mission. Presumably oceanic expeditions, which have been conducted for over 150 years, have developed effective methods of equipment maintenance. Similarities are found in relative budget and equipment maintenance problems, but few similarities are found in solutions to these problems. It is speculated that the high relative cost of on-orbit work is responsible, and that development of significantly more effective component level fault diagnosis equipment and repair equipment could enable application of oceanographic equipment maintenance strategies, enhancing safety and speeding laboratory work while giving significant cost reduction.

Lewis, William C.↗

NASA NTRS2002

Load Balancing Strategies for Multi-Block Overset Grid Applications

The multi-block overset grid method is a powerful technique for high-fidelity computational fluid dynamics (CFD) simulations about complex aerospace configurations. The solution process uses a grid system that discretizes the problem domain by using separately generated but overlapping structured grids that periodically update and exchange boundary information through interpolation. For efficient high performance computations of large-scale realistic applications using this methodology, the individual grids must be properly partitioned among the parallel processors. Overall performance, therefore, largely depends on the quality of load balancing. In this paper, we present three different load balancing strategies far overset grids and analyze their effects on the parallel efficiency of a Navier-Stokes CFD application running on an SGI Origin2000 machine.

Djomehri, M. Jahed↗

DOE OSTI2025

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)↗

NASA NTRS1996

Object-Oriented Implementation of the NAS Parallel Benchmarks using Charm++

This report describes experiences with implementing the NAS Computational Fluid Dynamics benchmarks using a parallel object-oriented language, Charm++. Our main objective in implementing the NAS CFD kernel benchmarks was to develop a code that could be used to easily experiment with different domain decomposition strategies and dynamic load balancing. We also wished to leverage the object-orientation provided by the Charm++ parallel object-oriented language, to develop reusable abstractions that would simplify the process of developing parallel applications. We first describe the Charm++ parallel programming model and the parallel object array abstraction, then go into detail about each of the Scalar Pentadiagonal (SP) and Lower/Upper Triangular (LU) benchmarks, along with performance results. Finally we conclude with an evaluation of the methodology used.

Krishnan, Sanjeev↗

DOE OSTI2017

Tuning HDF5 subfiling performance on parallel file systems

Subfiling is a technique used on parallel file systems to reduce locking and contention issues when multiple compute nodes interact with the same storage target node. Subfiling provides a compromise between the single shared file approach that instigates the lock contention problems on parallel file systems and having one file per process, which results in generating a massive and unmanageable number of files. In this paper, we evaluate and tune the performance of recently implemented subfiling feature in HDF5. In specific, we explain the implementation strategy of subfiling feature in HDF5, provide examples of using the feature, and evaluate and tune parallel I/O performance of this feature with parallel file systems of the Cray XC40 system at NERSC (Cori) that include a burst buffer storage and a Lustre disk-based storage. We also evaluate I/O performance on the Cray XC30 system, Edison, at NERSC. Our results show performance benefits of 1.2X to 6X performance advantage with subfiling compared to writing a single shared HDF5 file. We present our exploration of configurations, such as the number of subfiles and the number of Lustre storage targets to storing files, as optimization parameters to obtain superior I/O performance. Based on this exploration, we discuss recommendations for achieving good I/O performance as well as limitations with using the subfiling feature.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2011

Coding for Parallel Links to Maximize the Expected Value of Decodable Messages

When multiple parallel communication links are available, it is useful to consider link-utilization strategies that provide tradeoffs between reliability and throughput. Interesting cases arise when there are three or more available links. Under the model considered, the links have known probabilities of being in working order, and each link has a known capacity. The sender has a number of messages to send to the receiver. Each message has a size and a value (i.e., a worth or priority). Messages may be divided into pieces arbitrarily, and the value of each piece is proportional to its size. The goal is to choose combinations of messages to send on the links so that the expected value of the messages decodable by the receiver is maximized. There are three parts to the innovation: (1) Applying coding to parallel links under the model; (2) Linear programming formulation for finding the optimal combinations of messages to send on the links; and (3) Algorithms for assisting in finding feasible combinations of messages, as support for the linear programming formulation. There are similarities between this innovation and methods developed in the field of network coding. However, network coding has generally been concerned with either maximizing throughput in a fixed network, or robust communication of a fixed volume of data. In contrast, under this model, the throughput is expected to vary depending on the state of the network. Examples of error-correcting codes that are useful under this model but which are not needed under previous models have been found. This model can represent either a one-shot communication attempt, or a stream of communications. Under the one-shot model, message sizes and link capacities are quantities of information (e.g., measured in bits), while under the communications stream model, message sizes and link capacities are information rates (e.g., measured in bits/second). This work has the potential to increase the value of data returned from spacecraft under certain conditions.

Klimesh, Matthew A.↗