Search NASA⌕ Search

SEARCH · Search NASA

Results for “graphics processing unit”

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 307 records · Page 17

Accelerated finite element elastodynamic simulations using the GPU

An approach is developed to perform explicit time domain finite element simulations of elastodynamic problems on the graphical processing unit, using Nvidia's CUDA. Of critical importance for this problem is the arrangement of nodes in memory, allowing data to be loaded efficiently and minimising communication between the independently executed blocks of threads. The initial stage of memory arrangement is partitioning the mesh; both a well established ‘greedy’ partitioner and a new, more efficient ‘aligned’ partitioner are investigated. A method is then developed to efficiently arrange the memory within each partition. The software is applied to three models from the fields of non-destructive testing, vibrations and geophysics, demonstrating a memory bandwidth of very close to the card's maximum, reflecting the bandwidth-limited nature of the algorithm. Comparison with Abaqus, a widely used commercial CPU equivalent, validated the accuracy of the results and demonstrated a speed improvement of around two orders of magnitude. A software package, Pogo, incorporating these developments, is released open source, downloadable from (http://www.pogo-fea.com/) to benefit the community. -- Highlights: •A novel memory arrangement approach is discussed for finite elements on the GPU. •The mesh is partitioned then nodes are arranged efficiently within each partition. •Models from ultrasonics, vibrations and geophysics are run. •The code is significantly faster than an equivalent commercial CPU package. •Pogo, the new software package, is released open source.

58 GEOSCIENCES↗

A new limiting procedure for discontinuous Galerkin methods applied to compressible multiphase flows with shocks and interfaces

Although the Discontinuous Galerkin (dg) method has seen widespread use for compressible flow problems in a single fluid with constant material properties, it has yet to be implemented in a consistent fashion for compressible multiphase flows with shocks and interfaces. Specifically, it is challenging to design a scheme that meets the following requirements: conservation, high-order accuracy in smooth regions and non-oscillatory behavior at discontinuities (in particular, material interfaces). Following the interface-capturing approach of Abgrall [1], we model flows of multiple fluid components or phases using a single equation of state with variable material properties; discontinuities in these properties correspond to interfaces. Here, to represent compressible phenomena in solids, liquids, and gases, we present our analysis for equations of state belonging to the Mie–Grüneisen family. Within the dg framework, we propose a conservative, high-order accurate, and non-oscillatory limiting procedure, verified with simple multifluid and multiphase problems. We show analytically that two key elements are required to prevent spurious pressure oscillations at interfaces and maintain conservation: (i) the transport equation(s) describing the material properties must be solved in a non-conservative weak form, and (ii) the suitable variables must be limited (density, momentum, pressure, and appropriate properties entering the equation of state), coupled with a consistent reconstruction of the energy. Further, we introduce a physics-based discontinuity sensor to apply limiting in a solution-adaptive fashion. We verify this approach with one- and two-dimensional problems with shocks and interfaces, including high pressure and density ratios, for fluids obeying different equations of state to illustrate the robustness and versatility of the method. Lastly, the algorithm is implemented on parallel graphics processing units (gpu) to achieve high speedup.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Accelerating population balance-Monte Carlo simulation for coagulation dynamics from the Markov jump model, stochastic algorithm and GPU parallel computing

This paper proposes a comprehensive framework for accelerating population balance-Monte Carlo (PBMC) simulation of particle coagulation dynamics. By combining Markov jump model, weighted majorant kernel and GPU (graphics processing unit) parallel computing, a significant gain in computational efficiency is achieved. The Markov jump model constructs a coagulation-rule matrix of differentially-weighted simulation particles, so as to capture the time evolution of particle size distribution with low statistical noise over the full size range and as far as possible to reduce the number of time loopings. Here three coagulation rules are highlighted and it is found that constructing appropriate coagulation rule provides a route to attain the compromise between accuracy and cost of PBMC methods. Further, in order to avoid double looping over all simulation particles when considering the two-particle events (typically, particle coagulation), the weighted majorant kernel is introduced to estimate the maximum coagulation rates being used for acceptance–rejection processes by single-looping over all particles, and meanwhile the mean time-step of coagulation event is estimated by summing the coagulation kernels of rejected and accepted particle pairs. The computational load of these fast differentially-weighted PBMC simulations (based on the Markov jump model) is reduced greatly to be proportional to the number of simulation particles in a zero-dimensional system (single cell). Finally, for a spatially inhomogeneous multi-dimensional (multi-cell) simulation, the proposed fast PBMC is performed in each cell, and multiple cells are parallel processed by multi-cores on a GPU that can implement the massively threaded data-parallel tasks to obtain remarkable speedup ratio (comparing with CPU computation, the speedup ratio of GPU parallel computing is as high as 200 in a case of 100 cells with 10 000 simulation particles per cell). These accelerating approaches of PBMC are demonstrated in a physically realistic Brownian coagulation case. The computational accuracy is validated with benchmark solution of discrete-sectional method. The simulation results show that the comprehensive approach can attain very favorable improvement in cost without sacrificing computational accuracy.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

GPU-advanced 3D electromagnetic simulations of superconductors in the Ginzburg–Landau formalism

Ginzburg–Landau theory is one of the most powerful phenomenological theories in physics, with particular predictive value in superconductivity. The formalism solves coupled nonlinear differential equations for both the electronic and magnetic responsiveness of a given superconductor to external electromagnetic excitations. With order parameter varying on the short scale of the coherence length, and the magnetic field being long-range, the numerical handling of 3D simulations becomes extremely challenging and time-consuming for realistic samples. Here we show precisely how one can employ graphics-processing units (GPUs) for this type of calculations, and obtain physics answers of interest in a reasonable time-frame – with speedup of over 100× compared to best available CPU implementations of the theory on a 256{sup 3} grid.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

A Monte Carlo volumetric-ray-casting estimator for global fluence tallies on GPUs

A Monte Carlo fluence estimator has been designed to take advantage of the computational power of graphical processing units (GPUs). This new estimator, termed the volumetric-ray-casting estimator, is an extension of the expectation estimator. It can be used as a replacement of the track-length estimator for the estimation of global fluence. Calculations for this estimator are performed on the GPU while the Monte Carlo random walk is performed on the central processing unit (CPU). This method lowers the implementation cost for GPU acceleration of existing Monte Carlo particle transport codes as there is little modification of the particle history logic flow. Three test problems have been evaluated to assess the performance of the volumetric-ray-casting estimator for neutron transport on GPU hardware in comparison to the standard track-length estimator on CPU hardware. Evaluation of neutron transport through air in a criticality accident scenario showed that the volumetric-ray-casting estimator achieved 23 times the performance of the track-length estimator using a single core CPU paired with a GPU and 15 times the performance of the track-length estimator using an eight core CPU paired with a GPU. Finally, simulation of a pressurized water reactor fuel assembly showed that the performance improvement was 6 times within the fuel and 7 times within the control rods using an eight core CPU paired with a single GPU.

74 ATOMIC AND MOLECULAR PHYSICS↗

Stabilized bases for high-order, interpolation semi-Lagrangian, element-based tracer transport

In a computational fluid model of the atmosphere, the advective transport of trace species, or tracers, can be computationally expensive. For efficiency, models often use semi-Lagrangian advection methods. High-order interpolation semi-Lagrangian (ISL) methods, in particular, can be extremely efficient, if the problem of property preservation specific to them can be addressed. Atmosphere models often use geometrically and logically nonuniform grids for efficiency and, as a result, element-based discretizations. Such grids and discretizations make stability a particular problem for ISL methods. Generally, high-order, element-based ISL methods that use the natural polynomial interpolant associated with a nodal finite-element discretization are unstable. Here, we derive new bases having order of accuracy up to nine, with positive nodal weights, that stabilize the element-based ISL method. We use these bases to construct the linear advection operator in the property-preserving Interpolation Semi-Lagrangian Element-based Transport (Islet) method. Then we discuss key software implementation details. Finally, we show performance results for the Energy Exascale Earth System Model's atmosphere dynamical core, comparing the original and new transport methods. These simulations used up to 27,600 Graphical Processing Units (GPU) on the Oak Ridge Leadership Computing Facility's Summit supercomputer.

97 MATHEMATICS AND COMPUTING↗

Accelerating high-order continuum kinetic plasma simulations using multiple GPUs

Kinetic plasma simulations solve the Vlasov-Poisson or Vlasov-Maxwell equations to evolve scalar-variable distribution functions in position-velocity phase space and vector-variable electromagnetic fields in configuration space. The immense computational cost of evolving high-dimensional variables, and their large number of degrees of freedom, often limits the utility of continuum kinetic simulations and presents a challenge when it comes to accurately simulating real-world physical phenomena. To address this challenge, we present techniques that accelerate and minimize the computational work required for a scalable Vlasov-Poisson solver. We show theoretical hardware compute and communication bounds for solving a fourth-order finite-volume Vlasov-Poisson system. These bounds are then used to inform and evaluate the design of performance portable algorithms for a multiple graphics processing unit (GPU) accelerated version of the Vlasov-Poisson solver VCK-CPU [1]. We demonstrate that the multi-GPU Vlasov solver implementation, VCK-GPU, simultaneously minimizes required inter-process data transfer while also being bounded by the machine network performance limits. This results in an overall strong scaling speedup per timestep of up to 40x in three-dimensional phase space (one position, two velocity coordinates) and 54x in four dimensional phase space (two position, two velocity coordinates) and a 341x increase in simulation throughput of the GPU accelerated code over the existing CPU code. The GPU code is also able to weak scale up to 256 compute nodes and 1024 GPUs. In conclusion, we demonstrate that the improved compute performance enables exploring configurations which were previously computationally infeasible, including resolving fine-scale distribution function filamentation and multi-species dynamics with realistic electron-proton mass ratios.

Continuum kinetics↗

Hardware acceleration for HPS algorithms in two and three dimensions

We provide a flexible, open-source framework for hardware acceleration, namely massively-parallel execution on general-purpose graphics processing units (GPUs), applied to the hierarchical Poincaré–Steklov (HPS) family of algorithms for building fast direct solvers for linear elliptic partial differential equations. To take full advantage of the power of hardware acceleration, we propose two variants of HPS algorithms to improve performance on two- and three-dimensional problems. In the two-dimensional setting, we introduce a novel recomputation strategy that minimizes costly data transfers to and from the GPU; in three dimensions, we modify and extend the adaptive discretization technique of Geldermans and Gillman [1] to greatly reduce peak memory usage. We provide an open-source implementation of these methods written in JAX, a high-level accelerated linear algebra package, which allows for the first integration of a high-order fast direct solver with automatic differentiation tools. We conclude with extensive numerical examples showing our methods are fast and accurate on two- and three-dimensional problems.

Fast direct solvers↗

A case study of CUDA FORTRAN and OpenACC for an atmospheric climate kernel

The porting of a key kernel in the tracer advection routines of the Community Atmosphere Model – Spectral Element (CAM-SE) to use Graphics Processing Units (GPUs) using OpenACC is considered in comparison to an existing CUDA FORTRAN port. The development of the OpenACC kernel for GPUs was substantially simpler than that of the CUDA port. Also, OpenACC performance was about 1.5× slower than the optimized CUDA version. Particular focus is given to compiler maturity regarding OpenACC implementation for modern FORTRAN, and it is found that the Cray implementation is currently more mature than the PGI implementation. Still, for the case that ran successfully on PGI, the PGI OpenACC runtime was slightly faster than Cray. The results show encouraging performance for OpenACC implementation compared to CUDA while also exposing some issues that may be necessary before the implementations are suitable for porting all of CAM-SE. Furthermore, most notable are that GPU shared memory should be used by future OpenACC implementations and that derived type support should be expanded.

54 ENVIRONMENTAL SCIENCES↗

Kernel fusion in atomistic spin dynamics simulations on Nvidia GPUs using tensor core

In atomistic spin dynamics simulations, the time cost of constructing the space- and time-displaced pair correlation function in real space increases quadratically as the number of spins N, leading to significant computational effort. The GEMM subroutine can be adopted to accelerate the calculation of the dynamical spin-spin correlation function, but the computational cost of simulating large spin systems (>40000 spins) on CPUs remains expensive. In this work, we perform the simulation on the graphics processing unit (GPU), a hardware solution widely used as an accelerator for scientific computing and deep learning. Here we show that GPUs can accelerate the simulation up to 25-fold compared to multi-core CPUs when using the GEMM subroutine on both. To hide memory latency, we fuse the element-wise operation into the GEMM kernel using CUTLASS that can improve the performance by 26% ~ 33% compared to implementation based on cuBLAS. Furthermore, we perform the on-the-fly calculation in the epilogue of the GEMM subroutine to avoid saving intermediate results on global memory, which makes the large-scale atomistic spin dynamics simulation feasible and affordable.

97 MATHEMATICS AND COMPUTING↗

A new efficient grain growth model using a random Gaussian-sampled mode filter

This paper presents the use of a Gaussian neighborhood mode filter for predicting grain growth in a manner similar to the solutions obtained by a Monte Carlo Potts model. This flexible grain growth model can quickly utilize modern, computationally optimized data science strategies on graphics processing units to simulate grain growth up to 100 times faster than the state-of-the-art, publicly available Monte Carlo Potts model. We show that, given the correct neighborhood, the mode filter can replicate normal grain growth in two or three dimensions. In addition, the paper briefly demonstrates the ability to model limited anisotropic in grain boundary energy and mobility. Anisotropic grain boundary energy is modeled by defining a weighted mode filter operation. Anisotropic grain boundary mobility is modeled by scaling and orienting the Gaussian neighborhood in a particular direction.

Anisotropy↗

Optimized fluid dynamics for heavy ion collisions

The (viscous) anisotropic hydrodynamic approach, especially after perturbative inclusion of all residual viscous terms, has been shown to dramatically outperform viscous hydrodynamics in several simplified situations for which exact solutions exist but which share with realistic expansion scenarios the problem of large dissipative currents. Here we will report on the present status of applying viscous anisotropic hydrodynamics in a highly efficient simulation of the full three-dimensional quark-gluon plasma. Results from accelerated 3+1-dimensional viscous hydrodynamic simulations using graphics processing units will be compared to the anisotropic frameworks.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Parallel accelerated vector similarity calculations for genomics applications

The surge in availability of genomic data holds promise for enabling determination of genetic causes of observed individual traits, with applications to problems such as discovery of the genetic roots of phenotypes, be they molecular phenotypes such as gene expression or metabolite concentrations, or complex phenotypes such as diseases. However, the growing sizes of these datasets and the quadratic, cubic or higher scaling characteristics of the relevant algorithms pose a serious computational challenge necessitating use of leadership scale computing. In this study we describe a new approach to performing vector similarity metrics calculations, suitable for parallel systems equipped with graphics processing units (GPUs) or Intel Xeon Phi processors. Our primary focus is the Proportional Similarity metric applied to Genome Wide Association Studies (GWAS) and Phenome Wide Association Studies (PheWAS). We describe the implementation of the algorithms on accelerated processors, methods used for eliminating redundant calculations due to symmetries, and techniques for efficient mapping of the calculations to many-node parallel systems. Finally, results are presented demonstrating high per-node performance and parallel scalability with rates of more than five quadrillion (5 × 10 15 ) elementwise comparisons achieved per second on the ORNL Titan system. In a companion paper we describe corresponding techniques applied to calculations of the Custom Correlation Coefficient for comparative genomics applications.

59 BASIC BIOLOGICAL SCIENCES↗

Parallel accelerated Custom Correlation Coefficient calculations for genomics applications

The massive quantities of genomic data being made available through gene sequencing techniques are enabling breakthroughs in genomic science in many areas such as medical advances in the diagnosis and treatment of diseases. Analyzing this data, however, is a computational challenge insofar as the computational costs of the relevant algorithms can grow with quadratic, cubic or higher complexity—leading to the need for leadership scale computing. In this paper we describe a new approach to calculations of the Custom Correlation Coefficient (CCC) between Single Nucleotide Polymorphisms (SNPs) across a population, suitable for parallel systems equipped with graphics processing units (GPUs) or Intel Xeon Phi processors. We describe the mapping of the algorithms to accelerated processors, techniques used for eliminating redundant calculations due to symmetries, and strategies for efficient mapping of the calculations to many-node parallel systems. Results are presented demonstrating high per-node performance and near-ideal parallel scalability with rates of more than nine quadrillion (9 × 10 15 ) elementwise comparisons achieved per second with the latest optimized code on the ORNL Titan system, this being orders of magnitude faster than rates achieved using other codes and platforms as reported in the literature. Also it is estimated that as many as 90 quadrillion (90 × 10 15 ) comparisons per second may be achievable on the upcoming ORNL Summit system, an additional 10X performance increase. Finally, in a companion paper we describe corresponding techniques applied to calculations of the Proportional Similarity metric for comparative genomics applications.

97 MATHEMATICS AND COMPUTING↗

A parallel strategy for density functional theory computations on accelerated nodes

Using the Löwdin orthonormalization of tall-skinny matrices as a proxy-app for wavefunction-based Density Functional Theory solvers, we investigate a distributed memory parallel strategy focusing on Graphics Processing Unit (GPU)-accelerated nodes as available on some of the top ranked supercomputers at the present time. Here we present numerical results in the strong limit regime, as it is particularly relevant for First-Principles Molecular Dynamics. We also examine how matrix product-based iterative solvers provide a competitive alternative to dense eigensolvers on GPUs, allowing to push the strong scaling limit of these computations to a larger number of distributed tasks. Our strategy, which relies on replicated Gram matrices and efficient collective communications using the NCCL library, leads to a time-to-solution under 0.5 s for the Löwdin orthonormalization of a tall-skinny matrix of 3000 columns on Summit at Oak Ridge Leadership Facility (OLCF). Given the similarity in computational operations between one iteration of a DFT solver and this proxy-app, this shows the possibility of solving accurately the DFT equations well under a minute for 3000 electronic wave functions, and thus perform First-Principles molecular dynamics of physical systems much larger than traditionally solved on CPU systems.

97 MATHEMATICS AND COMPUTING↗

Iterative methods in GPU-resident linear solvers for nonlinear constrained optimization

Linear solvers are major computational bottlenecks in a wide range of decision support and optimization computations. The challenges become even more pronounced on heterogeneous hardware, where traditional sparse numerical linear algebra methods are often inefficient. For example, methods for solving ill-conditioned linear systems have relied on conditional branching, which degrades performance on hardware accelerators such as graphical processing units (GPUs). To improve the efficiency of solving ill-conditioned systems, our computational strategy separates computations that are efficient on GPUs from those that need to run on traditional central processing units (CPUs). Our strategy maximizes the reuse of expensive CPU computations. Iterative methods, which thus far have not been broadly used for ill-conditioned linear systems, play an important role in our approach. In particular, we extend ideas from Arioli et al., (2007) to implement iterative refinement using inexact LU factors and flexible generalized minimal residual (FGMRES), with the aim of efficient performance on GPUs. In conclusion, we focus on solutions that are effective within broader application contexts, and discuss how early performance tests could be improved to be more predictive of the performance in a realistic environment.

97 MATHEMATICS AND COMPUTING↗

SPH modeling of biomass granular flow: Theoretical implementation and experimental validation

The commercialization of biomass-derived energy is impeded by flowability challenges arising from the feeding and handling of granular biomass materials in full-scale biorefineries. To overcome these obstacles, a robust and accurate model to simulate the flow of granular biomass is indispensable. However, conventional mesh-based numerical codes are limited by inherent mesh distortion in simulating large deformation that commonly occurs in granular biomass handling. Here, in this study, we propose a graphics processing unit (GPU)-accelerated meshless Smoothed Particle Hydrodynamics (SPH) code to model the flow of granular biomass materials. A modified void ratio-based mass conversation, a hybrid particle-to-particle/surface frictional boundary treatment, and a hypoplastic constitutive model are implemented. Four numerical examples, an elastic block sliding on inclined planes, sand column collapse, Angle of Repose, and axial compression tests for pine chips, were simulated using the developed SPH code. The results demonstrate good agreement between numerical predictions and analytical and experimental data for all four examples, validating the SPH code and increasing confidence that it can be applied to simulate more complex granular biomass handling processes, such as hopper feeding or auger conveyance.

09 BIOMASS FUELS↗

A High-Performance Discrete-Element Framework for Simulating Flow and Jamming of Moisture Bearing Biomass Feedstocks

We developed and verified a high-performance open-source discrete element method (DEM) solver with simultaneously-supported feedstock-specific interaction models, including bonded-sphere, liquid bridge, cohesion, and non-linear contact models. Our solver uses parallel data structures on hybrid central and graphics processing unit (CPU/GPU) architectures, with favorable strong scaling performance observed for large problem sizes comprised of (100 M particles), and 4X single-node GPU speedup. The particles for corn stover feedstock were conceptualized and calibrated based on experimental measurements and results. Sensitivity analyses demonstrate that the mass flow rate from a wedge hopper is governed primarily by moisture content, friction coefficient, and cohesion energy density. The model is used to reproduce experimentally observed hopper jamming results, highlighting that the experimental no-flow trends can only be achieved by using non-spherical particles, liquid bridge and cohesion models, highlighting the importance of using concurrent feedstock specialized models for the effective representation of biomass material handling problems.

bioenergy↗