Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel methods”

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 829 records · Page 46
All sourcesNASA NTRSDOE OSTI
DOE OSTI2013

Radiative signatures of the relativistic Kelvin-Helmholtz instability

We present a particle-in-cell simulation of the relativistic Kelvin-Helmholtz Instability (KHI) that for the first time delivers angularly resolved radiation spectra of the particle dynamics during the formation of the KHI. This enables studying the formation of the KHI with unprecedented spatial, angular and spectral resolution. Our results are of great importance for understanding astrophysical jet formation and comparable plasma phenomena by relating the particle motion observed in the KHI to its radiation signature. The innovative methods presented here on the implementation of the particle-in-cell algorithm on graphic processing units can be directly adapted to any many-core parallelization of the particle-mesh method. With these methods we see a peak performance of 7.176 PFLOP/s (double-precision) plus 1.449 PFLOP/s (single-precision), an efficiency of 96% when weakly scaling from 1 to 18432 nodes, an efficiency of 68.92% and a speed up of 794 (ideal: 1152) when strongly scaling from 16 to 18432 nodes.

42 ENGINEERING↗
DOE OSTI2022

Compressed basis GMRES on high-performance graphics processing units

Krylov methods provide a fast and highly parallel numerical tool for the iterative solution of many large-scale sparse linear systems. To a large extent, the performance of practical realizations of these methods is constrained by the communication bandwidth in current computer architectures, motivating the investigation of sophisticated techniques to avoid, reduce, and/or hide the message-passing costs (in distributed platforms) and the memory accesses (in all architectures). This article leverages Ginkgo’s memory accessor in order to integrate a communication-reduction strategy into the (Krylov) GMRES solver that decouples the storage format (i.e., the data representation in memory) of the orthogonal basis from the arithmetic precision that is employed during the operations with that basis. Given that the execution time of the GMRES solver is largely determined by the memory accesses, the cost of the datatype transforms can be mostly hidden, resulting in the acceleration of the iterative step via a decrease in the volume of bits being retrieved from memory. Together with the special properties of the orthonormal basis (whose elements are all bounded by 1), this paves the road toward the aggressive customization of the storage format, which includes some floating-point as well as fixed-point formats with mild impact on the convergence of the iterative process. We develop a high-performance implementation of the “compressed basis GMRES” solver in the Ginkgo sparse linear algebra library using a large set of test problems from the SuiteSparse Matrix Collection. We demonstrate robustness and performance advantages on a modern NVIDIA V100 graphics processing unit (GPU) of up to 50% over the standard GMRES solver that stores all data in IEEE double-precision.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2013

A domain decomposition method for pseudo-spectral electromagnetic simulations of plasmas

Pseudo-spectral electromagnetic solvers (i.e. representing the fields in Fourier space) have extraordinary precision. In particular, Haber et al. presented in 1973 a pseudo-spectral solver that integrates analytically the solution over a finite time step, under the usual assumption that the source is constant over that time step. Yet, pseudo-spectral solvers have not been widely used, due in part to the difficulty for efficient parallelization owing to global communications associated with global FFTs on the entire computational domains. A method for the parallelization of electromagnetic pseudo-spectral solvers is proposed and tested on single electromagnetic pulses, and on Particle-In-Cell simulations of the wakefield formation in a laser plasma accelerator. The method takes advantage of the properties of the Discrete Fourier Transform, the linearity of Maxwell’s equations and the finite speed of light for limiting the communications of data within guard regions between neighboring computational domains. Although this requires a small approximation, test results show that no significant error is made on the test cases that have been presented. The proposed method opens the way to solvers combining the favorable parallel scaling of standard finite-difference methods with the accuracy advantages of pseudo-spectral methods.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2019

PASTA: A Parallel Sparse Tensor Algorithm Benchmark Suite

Tensor methods have gained increasingly attention from various applications, including machine learning, quantum chemistry, healthcare analytics, social network analysis, data mining, and signal processing, to name a few. Sparse tensors and their algorithms become critical to further improve the performance of these methods and enhance the interpretability of their output. This work presents a sparse tensor algorithm benchmark suite (PASTA) for single- and multi-core CPUs. To the best of our knowledge, this is the first benchmark suite for sparse tensor world. PASTA targets on: 1) helping application users to evaluate different computer systems using its representative computational workloads; 2) providing insights to better utilize existed computer architecture and systems and inspiration for the future design. This benchmark suite will be publicly released.

HPC, sparse tensor, benchmark↗
NASA NTRS1987

Parallel Algorithm Solves Coupled Differential Equations

Numerical methods adapted to concurrent processing. Algorithm solves set of coupled partial differential equations by numerical integration. Adapted to run on hypercube computer, algorithm separates problem into smaller problems solved concurrently. Increase in computing speed with concurrent processing over that achievable with conventional sequential processing appreciable, especially for large problems.

Hayashi, A.↗
DOE OSTI2014

Scaling Semantic Graph Databases in Size and Performance

In this paper we present SGEM, a full software system for accelerating large-scale semantic graph databases on commodity clusters. Unlike current approaches, SGEM addresses semantic graph databases by only employing graph methods at all the levels of the stack. On one hand, this allows exploiting the space efficiency of graph data structures and the inherent parallelism of graph algorithms. These features adapt well to the increasing system memory and core counts of modern commodity clusters. On the other hand, however, these systems are optimized for regular computation and batched data transfers, while graph methods usually are irregular and generate fine-grained data accesses with poor spatial and temporal locality. Our framework comprises a SPARQL to data parallel C compiler, a library of parallel graph methods and a custom, multithreaded runtime system. We introduce our stack, motivate its advantages with respect to other solutions and show how we solved the challenges posed by irregular behaviors. We present the result of our software stack on the Berlin SPARQL benchmarks with datasets up to 10 billion triples (a triple corresponds to a graph edge), demonstrating scaling in dataset size and in performance as more nodes are added to the cluster.

Aggregation↗
DOE OSTI2013

Theoretical Plasma Physics

Lattice Boltzmann algorithms are a mesoscopic method to solve problems in nonlinear physics which are highly parallelized – unlike the direction solution of the original problem. These methods are applied to both fluid and magnetohydrodynamic turbulence. By introducing entropic constraints one can enforce the positive definiteness of the distribution functions and so be able to simulate fluids at high Reynolds numbers without numerical instabilities. By introducing a vector distribution function for the magnetic field one can enforce the divergence free condition on the magnetic field automatically, without the need of divergence cleaning as needed in most direct numerical solutions of the resistive magnetohydrodynamic equations. The principal reason for the high parallelization of lattice Boltzmann codes is that they consist of a kinetic collisional relaxation step (which is purely local) followed by a simple shift of the relaxed data to neighboring lattice sites. In large eddy simulations, the closure schemes are highly nonlocal – the most famous of these schemes is that due to Smagorinsky. Under a lattice Boltzmann representation the Smagorinsky closure is purely local – being simply a particular moment on the perturbed distribution fucntions. After nonlocal fluid moment models were discovered to represent Landau damping, it was found possible to model these fluid models using an appropriate lattice Boltzmann algorithm. The close to ideal parallelization of the lattice Boltzmann codes permitted us to be Gordon Bell finalists on using the Earth Simulation in Japan. We have also been involved in the radio frequency propagation of waves into a tokamak and into a spherical overdense tokamak plasma. Initially we investigated the use of a quasi-optical grill for the launching of lower hybrid waves into a tokamak. It was found that the conducting walls do not prevent the rods from being properly irradiated, the overloading of the quasi-optical grill is not severe with the electric field only being about three times higher than in the ideal case. Moreover, the quasi-optical grill was significantly fewer structural elements that the multijunction grill. Nevertheless there has not been much interest from experimental fusion groups to implementing these structures. Hence we have returned to optimizing the multijunction grill so that the large number of coupling matrix elements can be efficiently evaluated using symmetry arguments. In overdense plasmas, the standard electromagnetic waves cannot propagate into the plasma center, but are reflected at the plasma edge. By optimizing mode conversion processes (in particular, the O-X-B wave propagation of Ordinary Mode converting to an Extraordinary mode which then converts into an electrostatic Bernstein wave) one can excite within the plasma an electrostatic Bernstein wave that does not suffer density cutoffs and is absorbed on the electron cyclotron harmonics. Finally we have started looking at other mesoscopic lattice algorithms that involve unitary collision and streaming steps. Because these algorithms are unitary they can be run on quantum computers when they become available – unlike their computational cousin of lattice Boltzmann which is a purely classical code. These quantum lattice gas algorithms have been tested successfully on exact analytic soliton collision solution. These calculations are hoped to be able to study Bose Einstein condensed atomic gases and their ground states in an optical lattice.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS2005

Making Macroscopic Assemblies of Aligned Carbon Nanotubes

A method of aligning and assembling single-wall carbon nanotubes (SWNTs) to fabricate macroscopic structures has been invented. The method entails suspending SWNTs in a fluid, orienting the SWNTs by use of a magnetic and/or electric field, and then removing the aligned SWNTs from suspension in such a way as to assemble them while maintaining the alignment. SWNTs are essentially tubular extensions of fullerene molecules. It is desirable to assemble aligned SWNTs into macroscopic structures because the common alignment of the SWNTs in such a structure makes it possible to exploit, on a macroscopic scale, the unique mechanical, chemical, and electrical properties that individual oriented SWNTs exhibit at the molecular level. Because of their small size and high electrical conductivity, carbon nanotubes, and especially SWNTs, are useful for making electrical connectors in integrated circuits. Carbon nanotubes can be used as antennas at optical frequencies, and as probes in scanning tunneling microscopes, atomic-force microscopes, and the like. Carbon nanotubes can be used with or instead of carbon black in tires. Carbon nanotubes are useful as supports for catalysts. Ropes of SWNTs are metallic and, as such, are potentially useful in some applications in which electrical conductors are needed - for example, they could be used as additives in formulating electrically conductive paints. Finally, macroscopic assemblies of aligned SWNTs can serve as templates for the growth of more and larger structures of the same type. The great variety of tubular fullerene molecules and of the structures that could be formed by assembling them in various ways precludes a complete description of the present method within the limits of this article. It must suffice to present a typical example of the use of one of many possible variants of the method to form a membrane comprising SWNTs aligned substantially parallel to each other in the membrane plane. The apparatus used in this variant of the method (see figure) includes a reservoir containing SWNTs dispersed in a suspending agent (for example, dimethylformamide) and a reservoir containing a suitable solvent (for example, water mixed with a surfactant). By use of either pressurized gas supplied from upstream or suction from downstream, the suspension of SWNTs and the solvent are forced to mix and flow into a tank. A filter inside the tank contains pores small enough to prevent the passage of most SWNTs, but large enough to allow the passage of molecules of the solvent and suspending agent. The filter is oriented perpendicular to the flow path. A magnetic field parallel to the plane of the filter is applied. The success of the method is based on the tendency of SWNTs to become aligned with their longitudinal axes parallel to an applied magnetic field. The alignment energy of an SWNT increases with the length of the SWNT and the magnetic-field strength. In order to obtain an acceptably small degree of statistical deviation of SWNTs of a given length from alignment with a magnetic field, one must make the field strong enough so that the thermal energy associated with rotation of an SWNT away from alignment is less than the alignment energy.

Smalley, Richard E.↗
NASA NTRSDate not supplied

Performance Optimization Methods for a Memory-Bound, Unstructured-Grid CFD Application on Massively Parallel GPU Platforms

Computational performance of the FUN3D unstructured-grid computational fluid dynamics (CFD) application on massively parallel GPU environments is memory-bound and highly dependent upon efficient reads from and atomic updates to the irregular cell-, edge-, and node-based data structures. In this talk, we present recent efforts into optimizing select performance-critical kernels on NVIDIA Tesla V100 and A100 GPUs and AMD CDNA MI100 GPUs. A novel use of L2 cache residency controls and asynchronous loads into on-chip shared memory are explored on the A100 GPU for the sparse iterative solver, which is dominated by mixed-precision, sparse matrix vector multiplication. Demonstrations show that these methods improve global memory bandwidth utilization by 13.5% on the A100 GPU. Several techniques are also presented that use registers and/or shared memory to facilitate array transposition and aggregation which combine to reduce the frequency and increase the cache efficiency of floating-point atomic updates to the irregular data structures. These methods are demonstrated to improve the kernel throughput by nearly 500% on select kernels on the AMD MI100 over atomic updates directly to global memory. Overall, both V100 and A100 GPUs outperformed the MI100 GPU on kernels dominated by double-precision atomic updates; however, the techniques demonstrated here reduced the performance gap and improved the MI100 performance.

GPU CPU unstructured CFD memory↗
DOE OSTI2017

Shock waves simulated using the dual domain material point method combined with molecular dynamics

Here in this work we combine the dual domain material point method with molecular dynamics in an attempt to create a multiscale numerical method to simulate materials undergoing large deformations with high strain rates. In these types of problems, the material is often in a thermodynamically nonequilibrium state, and conventional constitutive relations or equations of state are often not available. In this method, the closure quantities, such as stress, at each material point are calculated from a molecular dynamics simulation of a group of atoms surrounding the material point. Rather than restricting the multiscale simulation in a small spatial region, such as phase interfaces, or crack tips, this multiscale method can be used to consider nonequilibrium thermodynamic effects in a macroscopic domain. This method takes the advantage that the material points only communicate with mesh nodes, not among themselves; therefore molecular dynamics simulations for material points can be performed independently in parallel. The dual domain material point method is chosen for this multiscale method because it can be used in history dependent problems with large deformation without generating numerical noise as material points move across cells, and also because of its convergence and conservation properties. In conclusion, to demonstrate the feasibility and accuracy of this method, we compare the results of a shock wave propagation in a cerium crystal calculated using the direct molecular dynamics simulation with the results from this combined multiscale calculation.

36 MATERIALS SCIENCE↗
NASA NTRS1994

Dependability analysis of parallel systems using a simulation-based approach

The analysis of dependability in large, complex, parallel systems executing real applications or workloads is examined in this thesis. To effectively demonstrate the wide range of dependability problems that can be analyzed through simulation, the analysis of three case studies is presented. For each case, the organization of the simulation model used is outlined, and the results from simulated fault injection experiments are explained, showing the usefulness of this method in dependability modeling of large parallel systems. The simulation models are constructed using DEPEND and C++. Where possible, methods to increase dependability are derived from the experimental results. Another interesting facet of all three cases is the presence of some kind of workload of application executing in the simulation while faults are injected. This provides a completely new dimension to this type of study, not possible to model accurately with analytical approaches.

Sawyer, Darren Charles↗
DOE OSTI2022

Electron‐Scale Reconnection in Three‐Dimensional Shock Turbulence

Abstract Magnetic reconnection has been observed in the transition region of quasi‐parallel shocks. In this work, the particle‐in‐cell method is used to simulate three‐dimensional reconnection in a quasi‐parallel shock. The shock transition region is turbulent, leading to the formation of reconnecting current sheets with various orientations. Two reconnection sites with weak and strong guide fields are studied, and it is shown that reconnection is fast and transient. Reconnection sites are characterized using diagnostics including electron flows and magnetic flux transport. In contrast to two‐dimensional simulations, weak guide field reconnection is realized. Furthermore, the current sheets in these events form in a direction almost perpendicular to those found in two‐dimensional simulations, where the reconnection geometry is constrained.

58 GEOSCIENCES↗
NASA NTRS1972

Variance reduction in Monte Carlo analysis of rarefied gas diffusion.

The problem of rarefied diffusion between parallel walls is solved using the Monte Carlo method. The diffusing molecules are evaporated or emitted from one of the two parallel walls and diffuse through another molecular species. The Monte Carlo analysis treats the diffusing molecule as undergoing a Markov random walk, and the local macroscopic properties are found as the expected value of the random variable, the random walk payoff. By biasing the transition probabilities and changing the collision payoffs, the expected Markov walk payoff is retained but its variance is reduced so that the Monte Carlo result has a much smaller error.

Perlmutter, M.↗
DOE OSTI2016

Introduction to Numerical Methods [Slides]

These are slides for a lecture for the Parallel Computing Summer Research Internship at the National Security Education Center. This gives an introduction to numerical methods. Repetitive algorithms are used to obtain approximate solutions to mathematical problems, using sorting, searching, root finding, optimization, interpolation, extrapolation, least squares regression, Eigenvalue problems, ordinary differential equations, and partial differential equations. Many equations are shown. Discretizations allow us to approximate solutions to mathematical models of physical systems using a repetitive algorithm and introduce errors that can lead to numerical instabilities if we are not careful.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1991

Collecting address traces from parallel computers

Trace driven simulation is a well-established method of performance analysis for single processor computer systems. However, efficient and accurate memory address tracing for parallel computer systems is not well understood. In this paper we present a critical survey of recently implemented approaches to address tracing and highlight the issues specific to collection of traces for both shared and distributed memory parallel computers. These issues include potential distortion of the relative ordering of events by the address tracing activity, realistic interleaving of addresses generated by multiple processors, and I/O and storage problems associated with collecting traces for large parallel systems. The strengths and weaknesses of the parallel tracing approaches are described.

Stunkel, Craig B.↗
DOE OSTI2014

Pole EXpansion and Selected Inversion (PEXSI)

The Pole EXpansion and Selected Inversion method (PEXSI) is a fast method for evaluating certain selected elements of a matrix function. PEXSI is highly scalable on distributed memory parallel machines. For sparse matrices, the PEXSI method can be more efficient than the widely used diagonalization method for evaluating matrix functions, especially when a relatively large number of eigenpairs are needed to be computed in the diagonalization methond

Source record↗
DOE OSTI2017

Modern gyrokinetic particle-in-cell simulation of fusion plasmas on top supercomputers

The Gyrokinetic Toroidal Code at Princeton (GTC-P) is a highly scalable and portable particle-in-cell (PIC) code. It solves the 5D Vlasov-Poisson equation featuring efficient utilization of modern parallel computer architectures at the petascale and beyond. Motivated by the goal of developing a modern code capable of dealing with the physics challenge of increasing problem size with sufficient resolution, new thread-level optimizations have been introduced as well as a key additional domain decomposition. GTC-P's multiple levels of parallelism, including inter-node 2D domain decomposition and particle decomposition, as well as intra-node shared memory partition and vectorization have enabled pushing the scalability of the PIC method to extreme computational scales. In this paper, we describe the methods developed to build a highly parallelized PIC code across a broad range of supercomputer designs. This particularly includes implementations on heterogeneous systems using NVIDIA GPU accelerators and Intel Xeon Phi (MIC) co-processors and performance comparisons with state-of-the-art homogeneous HPC systems such as Blue Gene/Q. New discovery science capabilities in the magnetic fusion energy application domain are enabled, including investigations of Ion-Temperature-Gradient (ITG) driven turbulence simulations with unprecedented spatial resolution and long temporal duration. Performance studies with realistic fusion experimental parameters are carried out on multiple supercomputing systems spanning a wide range of cache capacities, cache-sharing configurations, memory bandwidth, interconnects and network topologies. Furthermore, these performance comparisons using a realistic discovery-science-capable domain application code provide valuable insights on optimization techniques across one of the broadest sets of current high-end computing platforms worldwide.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

Massively-parallel Lagrangian particle code and applications

Massively-parallel, distributed-memory algorithms for the Lagrangian particle hydrodynamic method (Samulyak et al., 2018) have been developed, verified, and implemented. The key component of parallel algorithms is a particle management module that includes a parallel construction of octree databases, dynamic adaptation and refinement of octrees, and particle migration between parallel subdomains. The particle management module is based on the p4est (parallel forest of k-trees) library. The massively-parallel Lagrangian particle code has been applied to a variety of fundamental science and applied problems. A summary of Lagrangian particle code applications to the injection of impurities into thermonuclear fusion devices and to the simulation of supersonic hydrogen jets in support of laser-plasma wakefield acceleration research has also been presented.

97 MATHEMATICS AND COMPUTING↗