Large Scale Integral Equation Modeling Using Scalable Parallel Processing
(See abstract).
speed matrix solvers↗
SEARCH · Search NASA
Results for “parallel integration”
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.
Large-Scale Transport Responses to Tropospheric Circulation Changes Using GEOS-5
The mean age since air was last at the Northern Hemisphere midlatitude surface is a fundamental property of tropospheric transport. Recent comparisons among chemistry climate models, however, reveal that there are large differences in the mean age among models and that these differences are most likely related to differences in tropical (parameterized) convection. Here we use aquaplanet simulations of the Goddard Earth Observing System Model Version 5 (GEOS-5) to explore the sensitivity of the mean age to changes in the tropical circulation. Tropical circulation changes are forced by prescribed localized off-equatorial warm sea surface temperature anomalies that (qualitatively) reproduce the convection and circulation differences among the comprehensive models. Idealized chemical species subject to prescribed OH loss are also integrated in parallel in order to illustrate the impact of tropical transport changes on interhemispheric constituent transport.
Orbe, Clara↗
LibERI—A portable and performant multi-GPU accelerated library for electron repulsion integrals via OpenMP offloading and standard language parallelism
A portable and performant graphics processing unit (GPU)-accelerated library for electron repulsion integral (ERI) evaluation, named LibERI, has been developed and implemented via directive-based (e.g., OpenMP and OpenACC) and standard language parallelism (e.g., Fortran DO CONCURRENT). Offloaded ERIs consist of integrals over low and high contraction s, p, and d functions using the rotated-axis and Rys quadrature methods. GPU codes are factorized based on previous developments with two layers of integral screening and quartet presorting. In this work, the density screening is moved to the GPU to enhance the computational efficacy for large molecular systems. Here, the L-shells in the Pople basis set are also separated into pure S and P shells to increase the ERI homogeneity and reduce atomic operations and the memory footprint. LibERI is compatible with any quantum chemistry drivers supporting the MolSSI Driver Interface. Benchmark calculations of LibERI interfaced with the GAMESS software package were carried out on various GPU architectures and molecular systems. The results show that the LibERI performance is comparable to other state-of-the-art GPU-accelerated codes (e.g., TeraChem and GMSHPC) and, in some cases, outperforms conventionally developed ERI CUDA kernels (e.g., QUICK) while fully maintaining portability.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Barotropic instability of weakly non-parallel zonal flows
Integrations of the linear stability problem, in the present numerical investigation of weakly nonparallel zonal flows barotropic instability having localized intense shear regions, reveal the existence of unstable localized wave packets. The spatial structure and eigenfrequencies of these packets depend on two parameters measuring the degree of supercriticality and the zonal length scale of the shear region. It is found that instability structure is defined by conditions ensuring the decay of the wave packet at infinity, and the transition from long to short waves across a turning point region that is controlled by nonparallel effects.
Merkine, L.-O.↗
OVERAERO-MPI: Parallel Overset Aeroelasticity Code
An overset modal structures analysis code was integrated with a parallel overset Navier-Stokes flow solver to obtain a code capable of static aeroelastic computations. The new code was used to compute the static aeroelastic deformation of an arrow-wing-body geometry and a complex, full aircraft configuration. For the simple geometry, the results were similar to the results obtained with the ENSAERO code and the PVM version of OVERAERO. The full potential of this code suite was illustrated in the complex, full aircraft computations.
Gee, Ken↗
Parallel-Processing Equalizers for Multi-Gbps Communications
Architectures have been proposed for the design of frequency-domain least-mean-square complex equalizers that would be integral parts of parallel- processing digital receivers of multi-gigahertz radio signals and other quadrature-phase-shift-keying (QPSK) or 16-quadrature-amplitude-modulation (16-QAM) of data signals at rates of multiple gigabits per second. Equalizers as used here denotes receiver subsystems that compensate for distortions in the phase and frequency responses of the broad-band radio-frequency channels typically used to convey such signals. The proposed architectures are suitable for realization in very-large-scale integrated (VLSI) circuitry and, in particular, complementary metal oxide semiconductor (CMOS) application- specific integrated circuits (ASICs) operating at frequencies lower than modulation symbol rates. A digital receiver of the type to which the proposed architecture applies (see Figure 1) would include an analog-to-digital converter (A/D) operating at a rate, fs, of 4 samples per symbol period. To obtain the high speed necessary for sampling, the A/D and a 1:16 demultiplexer immediately following it would be constructed as GaAs integrated circuits. The parallel-processing circuitry downstream of the demultiplexer, including a demodulator followed by an equalizer, would operate at a rate of only fs/16 (in other words, at 1/4 of the symbol rate). The output from the equalizer would be four parallel streams of in-phase (I) and quadrature (Q) samples.
Gray, Andrew↗
Role of the Controller in an Integrated Pilot-Controller Study for Parallel Approaches
Closely spaced parallel runway operations have been found to increase capacity within the National Airspace System but poor visibility conditions reduce the use of these operations [1]. Previous research examined the concepts and procedures related to parallel runways [2][4][5]. However, there has been no investigation of the procedures associated with the strategic and tactical pairing of aircraft for these operations. This study developed and examined the pilot s and controller s procedures and information requirements for creating aircraft pairs for closely spaced parallel runway operations. The goal was to achieve aircraft pairing with a temporal separation of 15s (+/- 10s error) at a coupling point that was 12 nmi from the runway threshold. In this paper, the role of the controller, as examined in an integrated study of controllers and pilots, is presented. The controllers utilized a pairing scheduler and new pairing interfaces to help create and maintain aircraft pairs, in a high-fidelity, human-in-the loop simulation experiment. Results show that the controllers worked as a team to achieve pairing between aircraft and the level of inter-controller coordination increased when the aircraft in the pair belonged to different sectors. Controller feedback did not reveal over reliance on the automation nor complacency with the pairing automation or pairing procedures.
Verma, Savvy↗
A parallel row-based algorithm for standard cell placement with integrated error control
A new row-based parallel algorithm for standard-cell placement targeted for execution on a hypercube multiprocessor is presented. Key features of this implementation include a dynamic simulated-annealing schedule, row-partitioning of the VLSI chip image, and two novel approaches to control error in parallel cell-placement algorithms: (1) Heuristic Cell-Coloring; (2) Adaptive Sequence Length Control.
Sargent, Jeff S.↗
Parallel-in-Time Solution of Allen-Cahn Equations by Integrating Operator Learning into the Parareal Method
While recent advances in deep learning have shown promising efficiency gains in solving time-dependent partial differential equations (PDEs), matching the accuracy of conventional numerical solvers still remains a challenge. One strategy to improve the accuracy of deep learning-based solutions for time-dependent PDEs is to use the learned model as the coarse propagator in the Parareal method and a traditional numerical method as the fine solver. However, successful integration of deep learning into the Parareal method requires consistency between the coarse and fine solvers, particularly for PDEs exhibiting rapid changes such as sharp transitions. Here, to ensure this consistency, we propose using convolutional neural networks (CNNs) to learn the fully discrete time-stepping operator defined by the same numerical scheme employed as the fine solver. We demonstrate the effectiveness of the proposed method in solving the classical and mass-conservative Allen–Cahn (AC) equations. Through iterative updates in the Parareal algorithm, our approach achieves a significant computational speedup compared to traditional fine solvers while converging to high-accuracy solutions. Our results highlight that the proposed hybrid Parareal algorithm effectively accelerates simulations, particularly when implemented on multiple GPUs, and converges to the desired accuracy in only a few iterations. Another advantage of our method is that the CNN model is trained on trajectory-based data generated from random initial conditions, such that the trained model can be used to solve the AC equations with various initial conditions without retraining. This work demonstrates the potential of integrating neural network methods into parallel-in-time frameworks for efficient and accurate simulations of time-dependent PDEs.
97 MATHEMATICS AND COMPUTING↗
Enhancing Scalability for FUN3D Rotorcraft Simulations with Yoga: an Overset Grid Assembler
FUN3D, an unstructured grid Navier-Stokes CFD code is capable of overset grid simu- lations, but does not have an internal method for assembling an overset grid system from a group of component grids. FUN3D currently relies on the third party codes Suggar++ and DiRTlib to perform domain assembly and provide intergrid connectivity for overset simulations. Rotorcraft simulations with moving, deforming blades require domain assembly and mesh deformation at each time step. For these simulations, the three primary drivers of computational cost for each time step are: deforming the mesh, performing domain assembly, and performing subiterations of the flow solver. FUN3D exhibits strong and weak scalability for the flow solver subiterations and the mesh deformation. However, FUN3D is currently hardwired directly to the serial version of Suggar++, which has a fixed cost for a given mesh system. Therefore, domain assembly begins to dominate the total cost of each time step as grid systems become larger. An integrated method for parallel domain assembly is presented that addresses scalability for large grid systems. Restructuring within FUN3D to accommodate integrated domain assembly is also discussed, which could enable use of the parallel Suggar++ library.
Cameron T Druyor↗
Opus: A Coordination Language for Multidisciplinary Applications
Data parallel languages, such as High Performance fortran, can be successfully applied to a wide range of numerical applications. However, many advanced scientific and engineering applications are multidisciplinary and heterogeneous in nature, and thus do not fit well into the data parallel paradigm. In this paper we present Opus, a language designed to fill this gap. The central concept of Opus is a mechanism called ShareD Abstractions (SDA). An SDA can be used as a computation server, i.e., a locus of computational activity, or as a data repository for sharing data between asynchronous tasks. SDAs can be internally data parallel, providing support for the integration of data and task parallelism as well as nested task parallelism. They can thus be used to express multidisciplinary applications in a natural and efficient way. In this paper we describe the features of the language through a series of examples and give an overview of the runtime support required to implement these concepts in parallel and distributed environments.
Chapman, Barbara↗
Integrated sensor with frame memory and programmable resolution for light adaptive imaging
An image sensor operable to vary the output spatial resolution according to a received light level while maintaining a desired signal-to-noise ratio. Signals from neighboring pixels in a pixel patch with an adjustable size are added to increase both the image brightness and signal-to-noise ratio. One embodiment comprises a sensor array for receiving input signals, a frame memory array for temporarily storing a full frame, and an array of self-calibration column integrators for uniform column-parallel signal summation. The column integrators are capable of substantially canceling fixed pattern noise.
Zhou, Zhimin↗
Implementing clips on a parallel computer
The C language integrated production system (CLIPS) is a forward chaining rule based language to provide training and delivery for expert systems. Conceptually, rule based languages have great potential for benefiting from the inherent parallelism of the algorithms that they employ. During each cycle of execution, a knowledge base of information is compared against a set of rules to determine if any rules are applicable. Parallelism also can be employed for use with multiple cooperating expert systems. To investigate the potential benefits of using a parallel computer to speed up the comparison of facts to rules in expert systems, a parallel version of CLIPS was developed for the FLEX/32, a large grain parallel computer. The FLEX implementation takes a macroscopic approach in achieving parallelism by splitting whole sets of rules among several processors rather than by splitting the components of an individual rule among processors. The parallel CLIPS prototype demonstrates the potential advantages of integrating expert system tools with parallel computers.
Riley, Gary↗
An integrated runtime and compile-time approach for parallelizing structured and block structured applications
Scientific and engineering applications often involve structured meshes. These meshes may be nested (for multigrid codes) and/or irregularly coupled (called multiblock or irregularly coupled regular mesh problems). A combined runtime and compile-time approach for parallelizing these applications on distributed memory parallel machines in an efficient and machine-independent fashion was described. A runtime library which can be used to port these applications on distributed memory machines was designed and implemented. The library is currently implemented on several different systems. To further ease the task of application programmers, methods were developed for integrating this runtime library with compilers for HPK-like parallel programming languages. How this runtime library was integrated with the Fortran 90D compiler being developed at Syracuse University is discussed. Experimental results to demonstrate the efficacy of our approach are presented. A multiblock Navier-Stokes solver template and a multigrid code were experimented with. Our experimental results show that our primitives have low runtime communication overheads. Further, the compiler parallelized codes perform within 20 percent of the code parallelized by manually inserting calls to the runtime library.
Agrawal, Gagan↗
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↗
Feasibility study of silicon nitride protection of plastic encapsulated semiconductors
The application of low temperature silicon nitride protective layers on wire bonded integrated circuits mounted on lead frame assemblies is reported. An evaluation of the mechanical and electrical compatibility of both plasma nitride and photochemical silicon nitride (photonitride) passivations (parallel evaluations) of integrated circuits which were then encapsulated in plastic is described. Photonitride passivation is compatible with all wire bonded lead frame assemblies, with or without initial chip passivation. Plasma nitride passivation of lead frame assemblies is possible only if the chip is passivated before lead frame assembly. The survival rate after the environmental test sequence of devices with a coating of plasma nitride on the chip and a coating of either plasma nitride or photonitride over the assembled device is significantly greater than that of devices assembled with no nitride protective coating over either chip or lead frame.
Peters, J. W.↗
Integrating Cache Performance Modeling and Tuning Support in Parallelization Tools
With the resurgence of distributed shared memory (DSM) systems based on cache-coherent Non Uniform Memory Access (ccNUMA) architectures and increasing disparity between memory and processors speeds, data locality overheads are becoming the greatest bottlenecks in the way of realizing potential high performance of these systems. While parallelization tools and compilers facilitate the users in porting their sequential applications to a DSM system, a lot of time and effort is needed to tune the memory performance of these applications to achieve reasonable speedup. In this paper, we show that integrating cache performance modeling and tuning support within a parallelization environment can alleviate this problem. The Cache Performance Modeling and Prediction Tool (CPMP), employs trace-driven simulation techniques without the overhead of generating and managing detailed address traces. CPMP predicts the cache performance impact of source code level "what-if" modifications in a program to assist a user in the tuning process. CPMP is built on top of a customized version of the Computer Aided Parallelization Tools (CAPTools) environment. Finally, we demonstrate how CPMP can be applied to tune a real Computational Fluid Dynamics (CFD) application.
Waheed, Abdul↗
Mutual impedance of parallel and perpendicular coplanar surface monopoles
One dimensional integral formulas are derived for mutual impedance of arbitrary size, coplanar, parallel, and perpendicular surface monopoles. The integrals in formulas are expressed as exponential integrals where possible. The mutual impedance expression for parallel monopoles is a summation of exponential integrals and one-dimensional integrals. For perpendicular monopoles, the mutual impedance is in closed form, containing exponential integrals only. The final expressions are in a form suitable for numerical computation. Since the expressions contain at most one-dimensional integrals, they can be utilized to reduce the matrix filling time in the moment method formulations, especially when inhomogeneous sectioning is preferred. Additionally, they can be used in rectangular surface patch modeling of conducting surfaces with edges which are at an angle to the surface patches, providing the angle is small. To this end, the expressions were utilized in the moment method analysis of linearly tapered slot antennas. Very good accuracy was obtained with a reduction in computer time.
Koksal, Adnan↗