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 1,423 records · Page 79

Virtual Time III, Part 3: Throttling and Message Cancellation

This is Part 3 of a trio of papers that unify in a natural way the two historically distinct parallel discrete event synchronization paradigms, optimistic and conservative, combining the best properties of both into a single framework called Unified Virtual Time (UVT). In this part, we survey the synchronization effects that can be achieved by restricting to corner cases the relationships permitted among the control variables, GVT, CVT, TVT, and LVT, which were defined in Part 1. Here we also survey various throttling policies from the literature and describe how they can be implemented in UVT by controlling the value of TVT, including policies that can take advantage of rollback in addition to LP blocking. A significant result is a new category of efficient and higher precision throttling algorithms for optimistic execution that are based on optimistic lookahead, defined in a way that is symmetric to what we now call the conservative lookahead information that is traditionally used for conservative synchronization. Finally, we present a novel algorithm allowing the choice between lazy and aggressive cancellation to be made on a message-by-message basis using either external logic expressed in the model code, or policy code internal to the simulator, or a mixture of both.

throttling↗

Low-synch Gram–Schmidt with delayed reorthogonalization for Krylov solvers

The parallel strong-scaling of iterative methods is often determined by the number of global reductions at each iteration. Low-synch Gram-Schmidt algorithms are applied here to the Arnoldi algorithm to reduce the number of global reductions and therefore to improve the parallel strong-scaling of iterative solvers for nonsymmetric matrices such as the GMRES and the Krylov-Schur iterative methods. In the Arnoldi context, the factorization is "left-looking" and processes one column at a time. Among the methods for generating an orthogonal basis for the Arnoldi algorithm, the classical Gram-Schmidt algorithm, with reorthogonalization (CGS2) requires three global reductions per iteration. A new variant of CGS2 that requires only one reduction per iteration is presented and applied to the Arnoldi algorithm. Delayed CGS2 (DCGS2) employs the minimum number of global reductions per iteration (one) for a one-column at-a-time algorithm. The main idea behind the new algorithm is to group global reductions by rearranging the order of operations. DCGS2 must be carefully integrated into an Arnoldi expansion or a GMRES solver. Numerical stability experiments assess robustness for Krylov-Schur eigenvalue computations. Performance experiments on the ORNL Summit supercomputer then establish the superiority of DCGS2 over CGS2.

97 MATHEMATICS AND COMPUTING↗

Coupled cluster theory on modern heterogeneous supercomputers

This study examines the computational challenges in elucidating intricate chemical systems, particularly through ab-initio methodologies. This work highlights the Divide-Expand-Consolidate (DEC) approach for coupled cluster (CC) theory—a linear-scaling, massively parallel framework—as a viable solution. Detailed scrutiny of the DEC framework reveals its extensive applicability for large chemical systems, yet it also acknowledges inherent limitations. To mitigate these constraints, the cluster perturbation theory is presented as an effective remedy. Attention is then directed towards the CPS (D-3) model, explicitly derived from a CC singles parent and a doubles auxiliary excitation space, for computing excitation energies. The reviewed new algorithms for the CPS (D-3) method efficiently capitalize on multiple nodes and graphical processing units, expediting heavy tensor contractions. As a result, CPS (D-3) emerges as a scalable, rapid, and precise solution for computing molecular properties in large molecular systems, marking it an efficient contender to conventional CC models.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Efficient algorithms and implementations of entropy-based moment closures for rarefied gases

We present efficient algorithms and implementations of the 35-moment system equipped with the maximum-entropy closure in the context of rarefied gases. While closures based on the principle of entropy maximization have been shown to yield very promising results for moderately rarefied gas flows, the computational cost of these closures is in general much higher than for closure theories with explicit closed-form expressions of the closing fluxes, such as Grad's classical closure. Following a similar approach as Garrett et al. (2015) , we investigate efficient implementations of the computationally expensive numerical quadrature method used for the moment evaluations of the maximum-entropy distribution by exploiting its inherent fine-grained parallelism with the parallelism offered by multi-core processors and graphics cards. We show that using a single graphics card as an accelerator allows speed-ups of two orders of magnitude when compared to a serial CPU implementation. To accelerate the time-to-solution for steady-state problems, we propose a new semi-implicit time discretization scheme. The resulting nonlinear system of equations is solved with a Newton type method in the Lagrange multipliers of the dual optimization problem in order to reduce the computational cost. Additionally, fully explicit time-stepping schemes of first and second order accuracy are presented. We investigate the accuracy and efficiency of the numerical schemes for several numerical test cases, including a steady-state shock-structure problem.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Development of a Reactive Force Field for Simulating Photoinitiated Acrylate Polymerization

Light-driven and photo-curable polymer based additive manufacturing (AM) has enormous potential due to its excellent resolution and precision. Acrylated radical chain-growth polymerized resins are widely used in photopolymer AM due to their fast kinetics, and often serve as a departure point for developing other resin materials for photopolymer-based AM technologies. For successful control of the photopolymer resins, the molecular basis of the acrylate free-radical polymerization has to be understood in detail. We present an optimized reactive force field (ReaxFF) for molecular dynamics (MD) simulations of acrylate polymer resins that captures radical polymerization thermodynamics and kinetics. The force field is trained against an extensive training set including density functional theory (DFT) calculations of reaction pathways along the radical polymerization from methyl acrylate to methyl butyrate, bond dissociation energies, and structures and partial charges of several molecules and radicals. We also found that it was critical to train the force field against an incorrect, nonphysical reaction pathway observed in simulations that used parameters not optimized for acrylate polymerization. As a result, the parameterization process utilizes a parallelized search algorithm, and the resulting model can describe polymer resin formation, crosslinking density, conversion rate, and residual monomers of the complex acrylate mixtures.

36 MATERIALS SCIENCE↗

On-demand data analytics in HPC environments at leadership computing facilities: Challenges and experiences

Scaling-up scientific data analysis and machine learning algorithms for data-driven discovery is a grand challenge that we face today. Despite the growing need for analysis from science domains that are generating `Big Data' from instruments and simulations, building high-performance analytical workflows of data-intensive algorithms have been daunting because: (i) the `Big Data' hardware and software architecture landscape is constantly evolving, (ii) newer architectures impose new programming models, and (iii) data-parallel kernels of analysis algorithms and their performance facets on different architectures are poorly understood. To address these problems, we have: (i) identified scalable data-parallel kernels of popular data analysis algorithms, (ii) implemented `Mini-Apps' of those kernels using different programming models (e.g. Map Reduce, MPI, etc.), (iii) benchmarked and validated the performance of the kernels in diverse architectures. In this paper, we discuss two of those Mini-Apps and show the execution of principal component analysis built as a workflow of the Mini-Apps. We show that Mini-Apps enable scientists to (i) write domain-specific data analysis code that scales on most HPC hardware and (ii) and offers the ability (most times with over a 10x speed-up) to analyze data sizes 100 times the size of what off-the-shelf desktop/workstations of today can handle.

Harney, John↗

Scaling Deep Learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors—including NVIDIA, Intel, AMD, and IBM—have architectural road maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. Here, this article provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Our evaluation consists of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. We use sequentially equivalent implementations to maintain iso-accuracy between parallel and sequential DL models. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling—sometimes encouraged by restricted GPU memory—NVLink is less important.

97 MATHEMATICS AND COMPUTING↗

High Energy Electromagnetic Particle Transportation on the GPU

We present massively parallel high energy electromagnetic particle transportation through a finely segmented detector on a Graphics Processing Unit (GPU). Simulating events of energetic particle decay in a general-purpose high energy physics (HEP) detector requires intensive computing resources, due to the complexity of the geometry as well as physics processes applied to particles copiously produced by primary collisions and secondary interactions. The recent advent of hardware architectures of many-core or accelerated processors provides the variety of concurrent programming models applicable not only for the high performance parallel computing, but also for the conventional computing intensive application such as the HEP detector simulation. The components of our prototype are a transportation process under a non-uniform magnetic field, geometry navigation with a set of solid shapes and materials, electromagnetic physics processes for electrons and photons, and an interface to a framework that dispatches bundles of tracks in a highly vectorized manner optimizing for spatial locality and throughput. Core algorithms and methods are excerpted from the Geant4 toolkit, and are modified and optimized for the GPU application. Program kernels written in C/C++ are designed to be compatible with CUDA and OpenCL and with the aim to be generic enough for easy porting to future programming models and hardware architectures. To improve throughput by overlapping data transfers with kernel execution, multiple CUDA streams are used. Issues with floating point accuracy, random numbers generation, data structure, kernel divergences and register spills are also considered. Performance evaluation for the relative speedup compared to the corresponding sequential execution on CPU is presented as well.

Canal, P.↗

Scale-Dependent Fracture-Matrix Interactions and Their Impact on Radionuclide Transport: Development of efficient particle-tracking methods

Matrix Diffusion and Adsorption within a rock matrix are important mechanisms for retarding transport of radionuclides in fractured rock. Due to computational limitations and difficulties in characterizing complex subsurface systems, diffusive exchange between a fracture network and surrounding rock matrix is often modeled using simplified conceptual representations. There is significant uncertainty in “effective” parameters used in these models, such as the “effective matrix diffusivity”. Often, these parameters are estimated by fitting sparse breakthrough data, and estimated values fall outside meaningful ranges, because simplified interpretive models do not consider complex three-dimensional flow. There is limited understanding of the relationship between the effective parameters and rock mass characteristics including network structure and matrix properties. There is also evidence for an apparent scale-dependence in “effective matrix diffusion” coefficients. These observations raise questions on whether fracture-matrix interaction parameters estimated from small-scale tracer tests can be used for predicting radionuclide fate and transport at the scale of DOE field sites. High-resolution three-dimensional Discrete-Fracture-Network-Matrix (DFNM) models based on well-defined local scale transport equations can help to address some of these questions. Due to tremendous advances in computational technology over the last 10 years, DFNM modeling in relatively large domains is now feasible. The overarching objective of our research is to use DFNM modeling to improve fundamental understanding of how effective parameters in conceptual models are related to fracture network structure and matrix properties. An advanced three-dimensional DFNM model is being developed, which combines upscaled particle-tracking algorithms for fracture-matrix interaction and a parallel fracture-network flow simulator. The particle-tracking algorithms allow complexity in flow fields at different scales, and track transport across fracture-matrix interfaces based on rigorous local approximations to the transport equations. This modeling approach can incorporate aperture variability, multi-scale preferential flow and matrix heterogeneity. We developed efficient particle-tracking methods for handling matrix diffusion and adsorption on fracture walls and demonstrated their efficiency for use within the context of large-scale complex fracture network models with variability in apertures across a network of fractures and within individual fractures.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Segmented slant hole collimator for stationary cardiac SPECT: Monte Carlo simulations

Purpose: This work is a preliminary study of a stationary cardiac SPECT system. The goal of this research is to propose a stationary cardiac SPECT system using segmented slant-hole collimators and to perform computer simulations to test the feasibility. Compared to the rotational SPECT, a stationary system has a benefit of acquiring temporally consistent projections. The most challenging issue in building a stationary system is to provide sufficient projection view-angles. Methods: A GATE (GEANT4 application for tomographic emission) Monte Carlo model was developed to simulate a two-detector stationary cardiac SPECT that uses segmented slant-hole collimators. Each detector contains seven segmented slant-hole sections that slant to a common volume at the rotation center. Consequently, 14 view-angles over 180° were acquired without any gantry rotation. The NCAT phantom was used for data generation and a tailored maximum-likelihood expectation-maximization algorithm was used for image reconstruction. Effects of limited number of view-angles and data truncation were carefully evaluated in the paper. Results: Simulation results indicated that the proposed segmented slant-hole stationary cardiac SPECT system is able to acquire sufficient data for cardiac imaging without a loss of image quality, even when the uptakes in the liver and kidneys are high. Seven views are acquired simultaneously at each detector, leading to 5-fold sensitivity gain over the conventional dual-head system at the same total acquisition time, which in turn increases the signal-to-noise ratio by 19%. The segmented slant-hole SPECT system also showed a good performance in lesion detection. In our prototype system, a short hole-length was used to reduce the dead zone between neighboring collimator segments. The measured sensitivity gain is about 17-fold over the conventional dual-head system. Conclusions: The GATE Monte Carlo simulations confirm the feasibility of the proposed stationary cardiac SPECT system with segmented slant-hole collimators. The proposed collimator consists of combined parallel and slant holes, and the image on the detector is not reduced in size.

60 APPLIED LIFE SCIENCES↗

Pararhombi: Parallel Implementation of 3-D Seismic Wave Propagation in Orthorhombic Media

Many earth materials and minerals are seismically anisotropic; however, due to the weakness of anisotropy and for simplicity, the earth is often approximated as an isotropic medium. Specific circumstances, such as in shales, tectonic fabrics, or oriented fractures, for example, require the use of anisotropic simulations in order to accurately model the earth. This report details the development of a new massively parallel 3-D full seismic waveform simulation algorithm within the principle coordinate system of an orthorhombic material, which is a specific form of anisotropy common in layered, fractured media. The theory and implementation of Pararhombi is described along with verification of the code against other solutions.

58 GEOSCIENCES↗

Manycore Parallel Computing for a Hybridizable Discontinuous Galerkin Nested Multigrid Method

In this work, we present a parallel computing strategy for a hybridizable discontinuous Galerkin (HDG) nested geometric multigrid (GMG) solver. Parallel GMG solvers require a combination of coarse-grain and fine-grain parallelism to improve time-to-solution performance. In this work we focus on fine-grain parallelism. We use Intel's second generation Xeon Phi (Knights Landing) manycore processor. The GMG method achieves ideal convergence rates of 0.2 or less, for high polynomial orders. A matrix free (assembly free) technique is exploited to save considerable memory usage and increase arithmetic intensity. HDG enables static condensation, and due to the discontinuous nature of the discretization, we developed a matrix vector multiply routine that does not require any costly synchronizations or barriers. Our algorithm is able to attain 80% of peak bandwidth performance for higher order polynomials. This is possible due to the data locality inherent in the HDG method. Very high performance is realized for high order schemes, due to good arithmetic intensity, which declines as the order is reduced.

97 MATHEMATICS AND COMPUTING↗

Multilevel Convergence Analysis of Multigrid-Reduction-in-Time

This study presents a multilevel convergence framework for multigrid-reduction-in-time (MGRIT) as a generalization of previous two-grid estimates. The framework provides a priori upper bounds on the convergence of MGRIT V- and F-cycles, with different relaxation schemes, by deriving the respective residual and error propagation operators. The residual and error operators are functions of the time-stepping operator, analyzed directly and bounded in the norm, both numerically and analytically. We present various upper bounds of different computational cost and varying sharpness. These upper bounds are complemented by proposing analytic formulae for the approximate convergence factor of V-cycle algorithms that take the number of fine grid time points, the temporal coarsening factors, and the eigenvalues of the time-stepping operator as parameters. The paper concludes with supporting numerical investigations of parabolic (anisotropic diffusion) and hyperbolic (wave equation) model problems. We assess the sharpness of the bounds and the quality of the approximate convergence factors. Observations from these numerical investigations demonstrate the value of the proposed multilevel convergence framework for estimating MGRIT convergence a priori and for the design of a convergent algorithm. We further highlight that observations in the literature are captured by the theory, including that two-level Parareal and multilevel MGRIT with F-relaxation do not yield scalable algorithms and the benefit of a stronger relaxation scheme. An important observation is that with increasing numbers of levels MGRIT convergence deteriorates for the hyperbolic model problem, while constant convergence factors can be achieved for the diffusion equation. The theory also indicates that L-stable Runge--Kutta schemes are more amendable to multilevel parallel-in-time integration with MGRIT than A-stable Runge--Kutta schemes.

97 MATHEMATICS AND COMPUTING↗

An inertia-free filter line-search algorithm for large-scale nonlinear programming

We present a filter line-search algorithm that does not require inertia information of the linear system. This feature enables the use of a wide range of linear algebra strategies and libraries, which is essential to tackle large-scale problems on modern computing architectures. The proposed approach performs curvature tests along the search step to detect negative curvature and to trigger convexification. We prove that the approach is globally convergent and we implement the approach within a parallel interior-point framework to solve large-scale and highly nonlinear problems. Our numerical tests demonstrate that the inertia-free approach is as efficient as inertia detection via symmetric indefinite factorizations. We also demonstrate that the inertia-free approach can lead to reductions in solution time because it reduces the amount of convexification needed.

Chiang, Nai-Yuan↗

Path-accelerated stochastic molecular dynamics: Parallel-in-time integration using path integrals

Massively parallel computer architectures create new opportunities for the performance of long-time scale molecular dynamics (MD) simulations. Here, we introduce the path-accelerated molecular dynamics method that takes advantage of distributed computing to reduce the wall-clock time of MD simulation via parallelization with respect to stochastic MD time steps. The marginal distribution for the time evolution of a system is expressed in terms of a path integral, enabling the use of path sampling techniques to numerically integrate MD trajectories. By parallelizing the evaluation of the path action with respect to time and by initializing the path configurations from a nonequilibrium distribution, the algorithm enables significant speedups in terms of the length of MD trajectories that can be integrated in a given amount of wall-clock time. The method is demonstrated for Brownian dynamics, although it is generalizable to other stochastic equations of motion including open systems. We apply the method to two simple systems, a harmonic oscillator and a Lennard-Jones liquid, and we show that in comparison to the conventional Euler integration scheme for Brownian dynamics, the new method can reduce the wall-clock time for integrating trajectories of a given length by more than three orders of magnitude in the former system and more than two in the latter. This new method for parallelizing MD in the dimension of time can be trivially combined with algorithms for parallelizing the MD force evaluation to achieve further speedup.

Rosa-Raíces, Jorge L.↗

Preparing sparse solvers for exascale computing

Sparse solvers provide essential functionality for a wide variety of scientific applications. Highly parallel sparse solvers are essential for continuing advances in high-fidelity, multi-physics and multi-scale simulations, especially as we target exascale platforms. This paper describes the challenges, strategies and progress of the US Department of Energy Exascale Computing project towards providing sparse solvers for exascale computing platforms. We address the demands of systems with thousands of high-performance node devices where exposing concurrency, hiding latency and creating alternative algorithms become essential. The efforts described here are works in progress, highlighting current success and upcoming challenges.

97 MATHEMATICS AND COMPUTING↗