Search NASA⌕ Search

SEARCH · Search NASA

Results for “high performance parallel computing”

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 847 records · Page 47
All sourcesNASA NTRSDOE OSTI
NASA NTRS2007

Reusable, Extensible High-Level Data-Distribution Concept

A framework for high-level specification of data distributions in data-parallel application programs has been conceived. [As used here, distributions signifies means to express locality (more specifically, locations of specified pieces of data) in a computing system composed of many processor and memory components connected by a network.] Inasmuch as distributions exert a great effect on the performances of application programs, it is important that a distribution strategy be flexible, so that distributions can be adapted to the requirements of those programs. At the same time, for the sake of productivity in programming and execution, it is desirable that users be shielded from such error-prone, tedious details as those of communication and synchronization. As desired, the present framework enables a user to refine a distribution type and adjust it to optimize the performance of an application program and conceals, from the user, the low-level details of communication and synchronization. The framework provides for a reusable, extensible, data-distribution design, denoted the design pattern, that is independent of a concrete implementation. The design pattern abstracts over coding patterns that have been found to be commonly encountered in both manually and automatically generated distributed parallel programs. The following description of the present framework is necessarily oversimplified to fit within the space available for this article. Distributions are among the elements of a conceptual data-distribution machinery, some of the other elements being denoted domains, index sets, and data collections (see figure). Associated with each domain is one index set and one distribution. A distribution class interface (where "class" is used in the object-oriented-programming sense) includes operations that enable specification of the mapping of an index to a unit of locality. Thus, "Map(Index)" specifies a unit, while "LocalLayout(Index)" specifies the local address within that unit. The distribution class can be extended to enable specification of commonly used distributions or novel user-defined distributions. A data collection can be defined over a domain. The term "data collection" in this context signifies, more specifically, an abstraction of mappings from index sets to variables. Since the index set is distributed, the addresses of the variables are also distributed.

James, Mark↗
NASA NTRS1993

Algorithm and code development for unsteady three-dimensional Navier-Stokes equations

In the last two decades, there have been extensive developments in computational aerodynamics, which constitutes a major part of the general area of computational fluid dynamics. Such developments are essential to advance the understanding of the physics of complex flows, to complement expensive wind-tunnel tests, and to reduce the overall design cost of an aircraft, particularly in the area of aeroelasticity. Aeroelasticity plays an important role in the design and development of aircraft, particularly modern aircraft, which tend to be more flexible. Several phenomena that can be dangerous and limit the performance of an aircraft occur because of the interaction of the flow with flexible components. For example, an aircraft with highly swept wings may experience vortex-induced aeroelastic oscillations. Also, undesirable aeroelastic phenomena due to the presence and movement of shock waves occur in the transonic range. Aeroelastically critical phenomena, such as a low transonic flutter speed, have been known to occur through limited wind-tunnel tests and flight tests. Aeroelastic tests require extensive cost and risk. An aeroelastic wind-tunnel experiment is an order of magnitude more expensive than a parallel experiment involving only aerodynamics. By complementing the wind-tunnel experiments with numerical simulations the overall cost of the development of aircraft can be considerably reduced. In order to accurately compute aeroelastic phenomenon it is necessary to solve the unsteady Euler/Navier-Stokes equations simultaneously with the structural equations of motion. These equations accurately describe the flow phenomena for aeroelastic applications. At Ames a code, ENSAERO, is being developed for computing the unsteady aerodynamics and aeroelasticity of aircraft and it solves the Euler/Navier-Stokes equations. The purpose of this contract is to continue the algorithm enhancements of ENSAERO and to apply the code to complicated geometries. During the last year, the geometric capability of the code was extended to simulate transonic flows, a wing with oscillating control surface. Single-grid and zonal approaches were tested. For the zonal approach, a new interpolation technique was introduced. The key development of the algorithm was an interface treatment between moving zones for a control surface using the virtual-zone concept. The work performed during the period, 1 Apr. 1992 through 31 Mar. 1993 is summarized. Additional details on the various aspects of the study are given in the Appendices.

Obayashi, Shigeru↗
DOE OSTI2019

Tail queues: A multi-threaded matching architecture

As we approach exascale, computational parallelism will have to drastically increase in order to meet throughput targets. Many–core architectures have exacerbated this problem by trading reduced clock speeds, core complexity, and computation throughput for increasing parallelism. This presents two major challenges for communication libraries such as MPI: the library must leverage the performance advantages of thread level parallelism and avoid the scalability problems associated with increasing the number of processes to that scale. Hybrid programming models, such as MPI+X, have been proposed to address these challenges. MPI THREAD MULTIPLE is MPI's thread safe mode. While there has been work to optimize it, it largely remains non–performant in most implementations. While current applications avoid MPI multithreading due to performance concerns, it is expected to be utilized in future applications. One of the major synchronous data structures required by MPI is the matching engine. In this paper, we present a parallel matching algorithm that can improve MPI matching for multithreaded applications. We then perform a feasibility study to demonstrate the performance benefit of the technique.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2001

Accelerating Demand Paging for Local and Remote Out-of-Core Visualization

This paper describes a new algorithm that improves the performance of application-controlled demand paging for the out-of-core visualization of data sets that are on either local disks or disks on remote servers. The performance improvements come from better overlapping the computation with the page reading process, and by performing multiple page reads in parallel. The new algorithm can be applied to many different visualization algorithms since application-controlled demand paging is not specific to any visualization algorithm. The paper includes measurements that show that the new multi-threaded paging algorithm decreases the time needed to compute visualizations by one third when using one processor and reading data from local disk. The time needed when using one processor and reading data from remote disk decreased by up to 60%. Visualization runs using data from remote disk ran about as fast as ones using data from local disk because the remote runs were able to make use of the remote server's high performance disk array.

Ellsworth, David↗
DOE OSTI2018

OpenMP in VASP: Threading and SIMD

Abstract The Vienna Ab initio Simulation Package (VASP) is a widely used electronic structure code that originally exploits process‐level parallelism through the Message Passing Interface (MPI) for work distribution within and across nodes. Architectural changes of modern parallel processors urge programmers to address thread‐ and data‐level parallelism as well to benefit most from the available compute resources within a node. We describe for VASP how to approach for an MPI + OpenMP parallelization including data‐level parallelism through OpenMP SIMD constructs together with a generic high‐level vector coding scheme. We can demonstrate an improved scalability of VASP and more than 20% gain over the MPI‐only version as well as a 2× increased performance of collective operations using the multiple‐endpoint MPI feature. The high‐level vector coding scheme applied to VASP's general gradient approximation routine gives up 9× performance gain on AVX512 platforms with the Intel compiler.

Wende, Florian↗
DOE OSTI2021

PRISMS-Fatigue computational framework for fatigue analysis in polycrystalline metals and alloys

Abstract The PRISMS-Fatigue open-source framework for simulation-based analysis of microstructural influences on fatigue resistance for polycrystalline metals and alloys is presented here. The framework uses the crystal plasticity finite element method as its microstructure analysis tool and provides a highly efficient, scalable, flexible, and easy-to-use ICME community platform. The PRISMS-Fatigue framework is linked to different open-source software to instantiate microstructures, compute the material response, and assess fatigue indicator parameters. The performance of PRISMS-Fatigue is benchmarked against a similar framework implemented using ABAQUS. Results indicate that the multilevel parallelism scheme of PRISMS-Fatigue is more efficient and scalable than ABAQUS for large-scale fatigue simulations. The performance and flexibility of this framework is demonstrated with various examples that assess the driving force for fatigue crack formation of microstructures with different crystallographic textures, grain morphologies, and grain numbers, and under different multiaxial strain states, strain magnitudes, and boundary conditions.

Chemistry↗
NASA NTRS1995

Supersonic civil airplane study and design: Performance and sonic boom

Since aircraft configuration plays an important role in aerodynamic performance and sonic boom shape, the configuration of the next generation supersonic civil transport has to be tailored to meet high aerodynamic performance and low sonic boom requirements. Computational fluid dynamics (CFD) can be used to design airplanes to meet these dual objectives. The work and results in this report are used to support NASA's High Speed Research Program (HSRP). CFD tools and techniques have been developed for general usages of sonic boom propagation study and aerodynamic design. Parallel to the research effort on sonic boom extrapolation, CFD flow solvers have been coupled with a numeric optimization tool to form a design package for aircraft configuration. This CFD optimization package has been applied to configuration design on a low-boom concept and an oblique all-wing concept. A nonlinear unconstrained optimizer for Parallel Virtual Machine has been developed for aerodynamic design and study.

Cheung, Samson↗
DOE OSTI2019

Nonconforming Mesh Refinement for High-Order Finite Elements

In this study, we propose a general algorithm for nonconforming adaptive mesh refinement (AMR) of unstructured meshes in high-order finite element codes. Our focus is on $h$-refinement with a fixed polynomial order. The algorithm handles triangular, quadrilateral, hexahedral, and prismatic meshes of arbitrarily high-order curvature, for any order finite element space in the de Rham sequence. We present a flexible data structure for meshes with hanging nodes and a general procedure to construct the conforming interpolation operator, both in serial and in parallel. The algorithm and data structure allow anisotropic refinement of tensor product elements in two and three dimensions and support unlimited refinement ratios of adjacent elements. We report numerical experiments verifying the correctness of the algorithms and perform a parallel scaling study to show that we can adapt meshes containing billions of elements and run efficiently on 393,000 parallel tasks. Finally, we illustrate the integration of dynamic AMR into a high-order Lagrangian hydrodynamics solver.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Speeding up Particle Track Reconstruction in the CMS Detector using a Vectorized and Parallelized Kalman Filter Algorithm

Building particle tracks is the most computationally intense step of event reconstruction at the LHC. With the increased instantaneous luminosity and associated increase in pileup expected from the High-Luminosity LHC, the computational challenge of track finding and fitting requires novel solutions. The current track reconstruction algorithms used at the LHC are based on Kalman filter methods that achieve good physics performance. By adapting the Kalman filter techniques for use on many-core SIMD architectures such as the Intel Xeon and Intel Xeon Phi and (to a limited degree) NVIDIA GPUs, we are able to obtain significant speedups and comparable physics performance. New optimizations, including a dedicated post-processing step to remove duplicate tracks, have improved the algorithm's performance even further. Here we report on the current structure and performance of the code and future plans for the algorithm.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Distributed-Memory Sparse Deep Neural Network Inference Using Global Arrays

Partitioned Global Address Space (PGAS) models exhibit tremendous promise in developing efficient and productive distributed-memory parallel applications. They have been used extensively in scientific computations due to conveniently offering a ``shared-memory''-like model and convenient interfaces that separate communication with synchronization. Traditionally, PGAS communication models have been applied to dense/contiguously distributed data, but most modern applications depict varied levels of sparsity. Existing PGAS models require certain adaptations to support distributed sparse computations, since associated computations often require matrix arithmetic, in addition to data movement. The Global Arrays toolkit from Pacific Northwest National Laboratory (PNNL) is one of the earliest PGAS models to combine one-sided data communication and distributed matrix operations and is still used in the popular NWChem quantum chemistry suite. Recently, we have expanded the Global Arrays toolkit to support common sparse operations, like sparse matrix-dense matrix multiplies (SpMM), sparse matrix-sparse matrix multiplication (SpGEMM) and Sampled Dense-Dense Matrix Multiplication (SDDMM). As it turns out, these operations are the bedrock of sparse Deep Learning (DL); sparse deep neural networks and Graph Neural Networks (GNNs) have gained increasing attention recently in achieving speedups on training and inference with reduced memory footprints. Unlike scientific applications in High Performance Computing (HPC), modern (distributed-memory capable) DL toolkits often rely on non-standardized and closed-source vendor software optimizations, creating challenges in software-hardware co-design at scale. Our goal is to support a variety of distributed-memory sparse matrix operations and helper functions in the newly created Sparse Global Arrays (SGA), such that it is possible to build portable and productive Machine Learning scenarios for algorithm/software and hardware codesign purposes. Contemporary data-parallel schemes for training/inference are undergoing a major overhaul since model replication limits scalability and causes resource inefficiencies. As such, we have adopted tensor parallelism in decomposing the model and inputs, to mitigate memory issues. Current implementation is built on top of MPI and uses CPUs to maximize the portability across the platforms.

Distributed computing, machine learning↗
NASA NTRS1993

Turbulence modeling of free shear layers for high-performance aircraft

The High Performance Aircraft (HPA) Grand Challenge of the High Performance Computing and Communications (HPCC) program involves the computation of the flow over a high performance aircraft. A variety of free shear layers, including mixing layers over cavities, impinging jets, blown flaps, and exhaust plumes, may be encountered in such flowfields. Since these free shear layers are usually turbulent, appropriate turbulence models must be utilized in computations in order to accurately simulate these flow features. The HPCC program is relying heavily on parallel computers. A Navier-Stokes solver (POVERFLOW) utilizing the Baldwin-Lomax algebraic turbulence model was developed and tested on a 128-node Intel iPSC/860. Algebraic turbulence models run very fast, and give good results for many flowfields. For complex flowfields such as those mentioned above, however, they are often inadequate. It was therefore deemed that a two-equation turbulence model will be required for the HPA computations. The k-epsilon two-equation turbulence model was implemented on the Intel iPSC/860. Both the Chien low-Reynolds-number model and a generalized wall-function formulation were included.

Sondak, Douglas L.↗
NASA NTRS1995

VLSI Processor For Vector Quantization

Pixel intensities in each kernel compared simultaneously with all code vectors. Prototype high-performance, low-power, very-large-scale integrated (VLSI) circuit designed to perform compression of image data by vector-quantization method. Contains relatively simple analog computational cells operating on direct or buffered outputs of photodetectors grouped into blocks in imaging array, yielding vector-quantization code word for each such block in sequence. Scheme exploits parallel-processing nature of vector-quantization architecture, with consequent increase in speed.

Tawel, Raoul↗
DOE OSTI2019

A massively-parallel, unstructured overset method to simulate moving bodies in turbulent flows

An unstructured overset method capable of performing direct numerical simulation (DNS) and large eddy simulation (LES) of many (O(10 5 )) moving bodies, utilizing many computational cores (O(10 5 )), in turbulent, incompressible fluid flow is presented. Unstructured meshes are attached to bodies and placed within a fixed background domain. Body meshes are allowed to arbitrarily overlap and move throughout the domain. Within each mesh a high resolution, unstructured, non-dissipative finite volume method is used to solve for the flow field. Boundary conditions for each mesh are provided by interpolation from flow solutions on overlapping meshes. When many unstructured meshes of different resolution overlap, care is required in the connection between the different flow solutions. An interpolant is created which seeks to preserve volume conservation of flow quantities between meshes regardless of overlapping mesh differences. An implicit fractional step method is used for time advancement, requiring the calculation of a predicted fluid velocity and corrector pressure field. For the predictor step, the resulting interpolation is directly introduced into the implicit equations for the predicted flow field. For the corrected pressure field, the continuity between meshes is weakly enforced using a penalty formulation. The pressure formulation is symmetric, positive-definite and non-singular resulting in a formulation which is readily solvable using traditional iterative matrix inversion techniques. An Arbitrary Euler-Lagrangian (ALE) method coupled to a 6 degrees of freedom rigid body equation system (6-DOF) is used for body motion. For rotation, a quaternion representation is used to solve Euler's equations of rigid body motion. A linear spring damper model, which uses geometry information readily available from the overset assembly process, is used for collisions. Validation of the method for canonical flow fields is presented including assessment of order of accuracy and kinetic energy conservation properties. Particle-resolved direct numerical simulation (PR-DNS) of single particles in various flow fields are presented for validation. PR-DNS results of 50,000 spherical particles freely moving within turbulent channel flow are shown as a demonstration of the method at full scale. LES results of a marine propeller under crashback conditions are shown to demonstrate the ability to simulate highly unsteady turbulent flows over complex, moving geometries.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1995

Implementation and Characterization of Three-Dimensional Particle-in-Cell Codes on Multiple-Instruction-Multiple-Data Massively Parallel Supercomputers

A three-dimensional electrostatic particle-in-cell (PIC) plasma simulation code has been developed on coarse-grain distributed-memory massively parallel computers with message passing communications. Our implementation is the generalization to three-dimensions of the general concurrent particle-in-cell (GCPIC) algorithm. In the GCPIC algorithm, the particle computation is divided among the processors using a domain decomposition of the simulation domain. In a three-dimensional simulation, the domain can be partitioned into one-, two-, or three-dimensional subdomains ("slabs," "rods," or "cubes") and we investigate the efficiency of the parallel implementation of the push for all three choices. The present implementation runs on the Intel Touchstone Delta machine at Caltech; a multiple-instruction-multiple-data (MIMD) parallel computer with 512 nodes. We find that the parallel efficiency of the push is very high, with the ratio of communication to computation time in the range 0.3%-10.0%. The highest efficiency (> 99%) occurs for a large, scaled problem with 64(sup 3) particles per processing node (approximately 134 million particles of 512 nodes) which has a push time of about 250 ns per particle per time step. We have also developed expressions for the timing of the code which are a function of both code parameters (number of grid points, particles, etc.) and machine-dependent parameters (effective FLOP rate, and the effective interprocessor bandwidths for the communication of particles and grid points). These expressions can be used to estimate the performance of scaled problems--including those with inhomogeneous plasmas--to other parallel machines once the machine-dependent parameters are known.

Lyster, P. M.↗
DOE OSTI2025

Implementation of a Mesh refinement algorithm into the quasi-static PIC code QuickPIC

Plasma-based acceleration (PBA) has emerged as a promising candidate for the accelerator technology used to build a future linear collider and/or an advanced light source. In PBA, a trailing or witness particle beam is accelerated in the plasma wave wakefield (WF) created by a laser or particle beam driver. The WF is often nonlinear and involves the crossing of plasma particle trajectories in real space and thus particle-in-cell methods are used. The distance over which the drive beam evolves is several orders of magnitude larger than the wake wavelength. This large disparity in length scales is amenable to the quasi-static approach. Three-dimensional (3D), quasi-static (QS), particle-in-cell (PIC) codes, e.g., QuickPIC, have been shown to provide high fidelity simulation capability with 2-4 orders of magnitude speedup over 3D fully explicit PIC codes. In PBA, the witness beam needs to be matched to the focusing forces of the WF to reduce the emittance growth. In some linear collider designs, the matched spot size of the witness beam can be 2 to 3 orders of magnitude smaller than the spot size (and wavelength) of the wakefield. Such an additional disparity in length scales is ideal for mesh refinement where the WF within the witness beam is described on a finer mesh than the rest of the WF. A mesh refinement scheme is described that has been implemented into the 3D QS PIC code, QuickPIC. Very fine (high) resolution is used in a small spatial region that includes the witness beam and progressively coarser resolutions in the rest of the simulation domain. A fast multigrid Poisson solver has been implemented for the field solve on the refined meshes and a Fast Fourier Transform (FFT) based Poisson solver is used for the coarse mesh. The code has been parallelized with both MPI and OpenMP, and the parallel scalability has also been improved by using pipelining. A preliminary adaptive mesh refinement technique is described to optimize the computational time for simulations with an evolving witness beam size. Several test problems are used to verify that the mesh refinement algorithm provides accurate results. Additionally, the results are benchmarked against highly resolved simulations exhibiting near-azimuthal symmetry, performed using QPAD—a novel hybrid QS PIC code that uses a PIC description in the coordinates (r, ct – z) and a gridless description in the azimuthal angle, Φ.

Linear collider↗
DOE OSTI2021

PAGANI: a parallel adaptive GPU algorithm for numerical integration

We present a new adaptive parallel algorithm for the challenging problem of multi-dimensional numerical integration on massively parallel architectures. Adaptive algorithms have demonstrated the best performance, but efficient many-core utilization is difficult to achieve because the adaptive work-load can vary greatly across the integration space and is impossible to predict a priori. Existing parallel algorithms utilize sequential computations on independent processors, which results in bottlenecks due to the need for data redistribution and processor synchronization. Our algorithm employs a high-throughput approach in which all existing sub-regions are processed and sub-divided in parallel. Repeated sub-region classification and filtering improves upon a brute-force approach and allows the algorithm to make efficient use of computation and memory resources. A CUDA implementation shows orders of magnitude speedup over the fastest open-source CPU method and extends the achievable accuracy for difficult integrands. Our algorithm typically outperforms other existing deterministic parallel methods.

Sakiotis, Ioannis↗
DOE OSTI2023

Characterizing the performance of node-aware strategies for irregular point-to-point communication on heterogeneous architectures

Supercomputer architectures are trending toward higher computational throughput due to the inclusion of heterogeneous compute nodes. These multi-GPU nodes increase on-node computational efficiency, while also increasing the amount of data to be communicated and the number of potential data flow paths. In this work, we characterize the performance of irregular point-to-point communication with MPI on heterogeneous compute environments through performance modeling, demonstrating the limitations of standard communication strategies for both device-aware and staging-through-host communication techniques. Presented models suggest staging communicated data through host processes then using node-aware communication strategies for high inter-node message counts. Notably, the models also predict that node-aware communication utilizing all available CPU cores to communicate inter-node data leads to the most performant strategy when communicating with a high number of nodes. Furthermore, model validation is provided via a case study of irregular point-to-point communication patterns in distributed sparse matrix–vector products. Importantly, we include a discussion on the implications model predictions have on communication strategy design for emerging supercomputer architectures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Protein Molecular Dynamics Simulations with Approximate QM: What Can We Learn?

Classical force fields are essential for computer simulations of proteins and are typically parameterized to reproduce secondary and tertiary structure of isolated proteins. However, while protein-protein interactions are ubiquitous in nature, they are not considered in parameterization efforts and are far less understood than isolated proteins. A better characterization of intermolecular interactions is widely recognized as a key to revolutionizing drug and therapeutic developments with high-throughput computational screening. Urgently needed is a critical assessment of the performance of modern protein force fields against first-principles electronic structure methods and experiments. In a daring step toward this goal, we here describe a comparison of peptide folding dynamics as predicted by a molecular mechanics force field on the one hand and by an approximate electronic structure quantum mechanical (QM) method based on density-functional tight-binding (DFTB) on the other. We further compare the dynamics from straightforward DFTB simulations with a near-linear scaling version of DFTB for massively parallel computation based on the fragment molecular orbital (FMO-DFTB) method. We illustrate differences between the phenomenology of the folding dynamics from these three methods for a small model peptide, as well as charge polarization and dynamic fluctuations, point out possible correlations and implications for force field developers, and discuss the lessons learned that might become applicable to future predictive high-throughput computer screening for personalized neoantigen cancer therapy.

Irle, Stephan↗