Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel computing algorithms”

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 1,027 records · Page 57

Calculating potential energy curves with fixed-node diffusion Monte Carlo: CO and N 2

This study reports on the prospect for the routine use of Quantum Monte Carlo (QMC) for the electronic structure problem, applying fixed-node Diffusion Monte Carlo (DMC) to generate highly accurate Born-Oppenheimer potential energy curves (PECs) for small molecular systems. The singlet ground electronic states of CO and N 2 were used as test cases. The PECs obtained by DMC employing multiconfigurational trial wavefunctions were compared with those obtained by conventional high-accuracy electronic structure methods such as multireference configuration interaction and/or the best available empirical spectroscopic curves. The goal was to test whether a straightforward procedure using available QMC codes could be applied robustly and reliably. Results obtained with DMC codes were found to be in close agreement with the benchmark PECs, and the n 3 scaling with the number of electrons (compared with n 7 or worse for conventional high-accuracy quantum chemistry) could be advantageous depending on the system size. Due to a large pre-factor in the scaling, for the small systems tested here, it is currently still much more computationally intensive to compute PECs with QMC. Nevertheless, QMC algorithms are particularly well-suited to large-scale parallelization and are therefore likely to become more relevant for future massively parallel hardware architectures.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (distributed parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

graph algorithms, high performance comptuing↗

Chance-Constrained Energy Management System for Power Grids With High Proliferation of Renewables and Electric Vehicles

This paper proposes a two-stage energy management system (EMS) for power grids with massive integration of electric vehicles (EVs) and renewable energy resources. The first stage economic dispatch determines the optimal operating points of charging stations and battery swapping stations (BSS) for EVs under plug-in and battery swapping modes, respectively. The proposed stochastic model predictive control (SMPC) problem in this stage is characterized through a chance-constrained optimization formulation that can effectively capture the system and the forecast uncertainties. A distributed algorithm, the alternating direction method of multipliers (ADMM), is applied to accelerate the optimization computation through parallel computing. The second stage is aimed in coordinating the EV charging mechanisms to continuously follow the first-stage solutions, i.e., the target operating points, and meeting the EV customers' charging demands captured via the Advanced Metering Infrastructure (AMI). In this work, the proposed solution offers a holistic control strategy for large-scale centralized power grids in which the aggregated individual parameters are predictable and the system dynamics do not vary sharply within a short time-interval.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Polynomial Preconditioned Arnoldi with Stability Control

Polynomial preconditioning can improve the convergence of the Arnoldi method for computing eigenvalues. Such preconditioning significantly reduces the cost of orthogonalization; for difficult problems, it can also reduce the number of matrix-vector products. Parallel computations can particularly benefit from the reduction of communication-intensive operations. Additoinally, the GMRES algorithm provides a simple and effective way of generating the preconditioning polynomial. For some problems high degree polynomials are especially effective, but they can lead to stability problems that must be mitigated. A two-level “double polynomial preconditioning” strategy provides an effective way to generate high-degree preconditioners.

97 MATHEMATICS AND COMPUTING↗

PyBioNetFit

Systems biology models written in the BioNetGen language often contain parameters that must be fit based on experimental data. PyBioNetFit is a software tool designed to fit parameters of BioNetGen models. The user is expected to provide a BioNetGen model that contains unknown parameters, along with one or more text files containing experimental data. PyBioNetFit will perform a series of calls to the BioNetGen simulator using different parameter sets, to identify the parameter set that best fits the data. The parameter search is dictated by the user's choice of one of several metaheuristic optimization algorithms, including differential evolution, particle swarm optimization, scatter search, and simulated annealing. The software supports parallelized computing on multi-core computers and on computing clusters. We expect this software to be a useful tool for researchers designing BioNetGen models in collaboration with experimentalists.

Mitra, Eshan↗

Analytical study of mixing and reacting three-dimensional supersonic combustor flow fields

An analytical investigation is presented of mixing and reacting hydrogen jets injected from multiple orifices transverse and parallel to a supersonic airstream. The COMOC computer program, based upon a finite-element solution algorithm, was developed to solve the governing equations for three-dimensional, turbulent, reacting, boundary-region, and confined flow fields. The computational results provide a three-dimensional description of the velocity, temperature, and species-concentration fields downstream of hydrogen injection. Detailed comparisons between cold-flow data and results of the computational analysis have established validity of the turbulent-mixing model based on the elementary mixing-length hypothesis. A method is established to initiate computations for reacting flow fields based upon cold-flow correlations and the appropriate experimental parameters of Mach number, injector spacing, and pressure ratio. Key analytical observations on mixing and combustion efficiency for reacting flows are presented and discussed.

Baker, A. J.↗

Motion detection in astronomical and ice floe images

Two approaches are presented for establishing correspondence between small areas in pairs of successive images for motion detection. The first one, based on local correlation, is used on a pair of successive Voyager images of the Jupiter which differ mainly in locally variable translations. This algorithm is implemented on a sequential machine (VAX 780) as well as the Massively Parallel Processor (MPP). In the case of the sequential algorithm, the pixel correspondence or match is computed on a sparse grid of points using nonoverlapping windows (typically 11 x 11) by local correlations over a predetermined search area. The displacement of the corresponding pixels in the two images is called the disparities to cubic surfaces. The disparities at points where the error between the computed values and the surface values exceeds a particular threshold are replaced by the surface values. A bilinear interpolation is then used to estimate disparities at all other pixels between the grid points. When this algorithm was applied at the red spot in the Jupiter image, the rotating velocity field of the storm was determined. The second method of motion detection is applicable to pairs of images in which corresponding areas can experience considerable translation as well as rotation.

Manohar, M.↗

Algorithms and Application of Sparse Matrix Assembly and Equation Solvers for Aeroacoustics

An algorithm for symmetric sparse equation solutions on an unstructured grid is described. Efficient, sequential sparse algorithms for degree-of-freedom reordering, supernodes, symbolic/numerical factorization, and forward backward solution phases are reviewed. Three sparse algorithms for the generation and assembly of symmetric systems of matrix equations are presented. The accuracy and numerical performance of the sequential version of the sparse algorithms are evaluated over the frequency range of interest in a three-dimensional aeroacoustics application. Results show that the solver solutions are accurate using a discretization of 12 points per wavelength. Results also show that the first assembly algorithm is impractical for high-frequency noise calculations. The second and third assembly algorithms have nearly equal performance at low values of source frequencies, but at higher values of source frequencies the third algorithm saves CPU time and RAM. The CPU time and the RAM required by the second and third assembly algorithms are two orders of magnitude smaller than that required by the sparse equation solver. A sequential version of these sparse algorithms can, therefore, be conveniently incorporated into a substructuring for domain decomposition formulation to achieve parallel computation, where different substructures are handles by different parallel processors.

Watson, W. R.↗

Path Planning: Differential Dynamic Programming and Model Predictive Path Integral Control on VTOL Aircraft

This paper explores two optimal control approaches, widely used in robotics, to establish their viability as real-time trajectory planners for vehicle configurations envisioned for the emerging aviation sector of Urban Air Mobility (UAM). Differential Dynamic Programming (DDP) enables planning over highly nonlinear dynamics using second-order approximations along a nominal trajectory, and displays quadratic convergence to a local solution. Model Predictive Path Integral (MPPI) is a stochastic sampling-based algorithm that can optimize for general cost criteria, including potentially highly nonlinear formulations, and supports parallel computation through the use of modern GPU hardware. In this work, DDP and MPPI were implemented using model predictive control (MPC), and the results indicate they are able to successfully transition the aircraft over different flight envelopes and generate trajectories unique to UAM vehicles.

Differential Dynamic Programming↗

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (Distributed Parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve an optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively, the performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

Sattar, Naw Safrin↗

The correlation study of parallel feature extractor and noise reduction approaches

This paper presents literature reviews that show variety of techniques to develop parallel feature extractor and finding its correlation with noise reduction approaches for low light intensity images. Low light intensity images are normally displayed as darker images and low contrast. Without proper handling techniques, those images regularly become evidences of misperception of objects and textures, the incapability to section them. The visual illusions regularly clues to disorientation, user fatigue, poor detection and classification performance of humans and computer algorithms. Noise reduction approaches (NR) therefore is an essential step for other image processing steps such as edge detection, image segmentation, image compression, etc. Parallel Feature Extractor (PFE) meant to capture visual contents of images involves partitioning images into segments, detecting image overlaps if any, and controlling distributed and redistributed segments to extract the features. Working on low light intensity images make the PFE face challenges and closely depend on the quality of its pre-processing steps. Some papers have suggested many well established NR as well as PFE strategies however only few resources have suggested or mentioned the correlation between them. This paper reviews best approaches of the NR and the PFE with detailed explanation on the suggested correlation. This finding may suggest relevant strategies of the PFE development. With the help of knowledge based reasoning, computational approaches and algorithms, we present the correlation study between the NR and the PFE that can be useful for the development and enhancement of other existing PFE.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining

Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace existing Deep Neural Networks (DNNs). Despite the remarkable triumphs, the prolonged turnaround time of Transformer models is a widely recognized roadblock. The variety of sequence lengths imposes additional computing overhead where inputs need to be zero-padded to the maximum sentence length in the batch to accommodate the parallel computing platforms. This paper targets the field-programmable gate array (FPGA) and proposes a coherent sequence length adaptive algorithm–hardware co-design for Transformer acceleration. Particularly, we develop a hardware-friendly sparse attention operator and a length-aware hardware resource scheduling algorithm. The proposed sparse attention operator brings the complexity of attention-based models down to linear complexity and alleviates the off-chip memory traffic. The proposed length-aware resource hardware scheduling algorithm dynamically allocates the hardware resources to fill up the pipeline slots and eliminates bubbles for NLP tasks. Experiments show that our design has very small accuracy loss and has 80.2 × and 2.6 × speedup compared to CPU and GPU implementation, and 4 × higher energy efficiency than state-of-the-art GPU accelerator optimized via CUBLAS GEMM.

Peng, Hongwu↗

Parallel processing implementations of a contextual classifier for multispectral remote sensing data

Contextual classifiers are being developed as a method to exploit the spatial/spectral context of a pixel to achieve accurate classification. Classification algorithms such as the contextual classifier typically require large amounts of computation time. One way to reduce the execution time of these tasks is through the use of parallelism. The applicability of the CDC flexible processor system and of a proposed multimicroprocessor system (PASM) for implementing contextual classifiers is examined.

Siegel, H. J.↗

A PETSc Parallel-in-Time Solver based on MGRIT algorithm

We address the development of a modular implementation of the MGRIT (MultiGrid-In-Time) algorithm to solve linear and nonlinear systems that arise from the discretization of evolutionary models with a parallel-in-time approach in the context of the PETSc (the Portable, Extensible Toolkit for Scientific computing) library. Our aim is to give the opportunity of predicting the performance gain achievable when using the MGRIT approach instead of the Time Stepping integrator (TS). To this end, we analyze the performance parameters of the algorithm that provide a-priori the best number of processing elements and grid levels to use to address the scaling of MGRIT, regarded as a parallel iterative algorithm proceeding along the time dimension.

Mele, Valeria↗

Performance of GeantV EM Physics Models

The recent progress in parallel hardware architectures with deeper vector pipelines or many-cores technologies brings opportunities for HEP experiments to take advantage of SIMD and SIMT computing models. Launched in 2013, the GeantV project studies performance gains in propagating multiple particles in parallel, improving instruction throughput and data locality in HEP event simulation on modern parallel hardware architecture. Due to the complexity of geometry description and physics algorithms of a typical HEP application, performance analysis is indispensable in identifying factors limiting parallel execution. In this report, we will present design considerations and preliminary computing performance of GeantV physics models on coprocessors (Intel Xeon Phi and NVidia GPUs) as well as on mainstream CPUs.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Direct pore-level modeling of incompressible fluid flow in porous media

We present a dynamic particle-based model for direct pore-level modeling of incompressible viscous fluid flow in disordered porous media. The model is capable of simulating flow directly in three-dimensional high-resolution micro-CT images of rock samples. It is based on moving particle semi-implicit (MPS) method. We modify this technique in order to improve its stability for flow in porous media problems. Using the micro-CT image of a rock sample, the entire medium, i.e., solid and fluid, is discretized into particles. The incompressible Navier-Stokes equations are then solved for each particle using the MPS summations. The model handles highly irregular fluid-solid boundaries effectively. An algorithm to split and merge fluid particles is also introduced. To handle the computational load, we present a parallel version of the model that runs on distributed memory computer clusters. The accuracy of the model is validated against the analytical, numerical, and experimental data available in the literature. The validated model is then used to simulate both unsteady- and steady-state flow of an incompressible fluid directly in a representative elementary volume (REV) size micro-CT image of a naturally-occurring sandstone with 3.398 {mu}m resolution. We analyze the quality and consistency of the predicted flow behavior and calculate absolute permeability using the steady-state flow rate.

97 MATHEMATICS AND COMPUTING↗

Distributed parallel processing applied to an implicit multigrid Euler/Navier-Stokes algorithm

An implicit multigrid algorithm for the solution of the Euler and Navier-Stokes equations has been implemented within the framework of multiple block-structured grids in which the physical domain is spatially decomposed into several blocks and the solution is advanced in parallel on each block. Utilities have been developed to implement such a scheme in a distributed computing environment. The multi-block algorithm is designed so that the explicit residual calculation is identical to that of single-block scheme, and therefore converged solutions for both schemes must be the same. To accelerate convergence, synchronous and asynchronous multigrid strategies are implemented. Significant speedups have been achieved in a multiple processor environment, while convergence rates similar to those of the single-block scheme are observed.

Tysinger, T. L.↗