Search NASA⌕ Search

SEARCH · Search NASA

Results for “Linear systems solvers”

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 37 records · Page 2

Solving linear equations with messenger-field and conjugate gradient techniques: An application to CMB data analysis

We discuss linear system solvers invoking a messenger-field and compare them with (preconditioned) conjugate gradient approaches. We show that the messenger-field techniques correspond to fixed point iterations of an appropriately preconditioned initial system of linear equations. We then argue that a conjugate gradient solver applied to the same preconditioned system, or equivalently a preconditioned conjugate gradient solver using the same preconditioner and applied to the original system, will in general ensure at least a comparable and typically better performance in terms of the number of iterations to convergence and time-to-solution. We illustrate our conclusions with two common examples drawn from the cosmic microwave background (CMB) data analysis: Wiener filtering and map-making. In addition, and contrary to the standard lore in the CMB field, we show that the performance of the preconditioned conjugate gradient solver can depend significantly on the starting vector. In conclusion, this observation seems of particular importance in the cases of map-making of high signal-to-noise ratio sky maps and therefore should be of relevance for the next generation of CMB experiments.

79 ASTRONOMY AND ASTROPHYSICS↗

Final Report - Subcontract B6183769

During my visit to LLNL during July 5{15, 2016, we worked on linear system solvers. The two level hierarchical solver that initiated our study was developed to solve linear system arising from hp adaptive finite element calculations, and is implemented in the PLTMG software package, version 12 [1]. This preconditioner typically requires 3-20% of the space used by the stiffness matrix for higher order elements. It has multigrid like convergence rates for a wide variety of PDEs (self-adjoint positive definite elliptic equations, convection dominated convection-diffusion equations, and highly inde nite Helmholtz equations, among others). The convergence rate is not independent of the polynomial degree p as p ! 1, but but remains strong for p 9, which is the highest polynomial degree allowed in PLTMG, due to limitations of numerical quadrature formulae. A more complete description of the method and some numerical experiments illustrating its effectiveness appear in [2]. Like traditional geometric multilevel methods, this scheme relies on extensive knowledge of the underlying finite element space in order to construct both the smoother and the coarse grid correction components.

97 MATHEMATICS AND COMPUTING↗

Final Report - Subcontract B623760

During my visit to LLNL during July 17{27, 2017, I worked on linear system solvers. The two level hierarchical solver that initiated our study was developed to solve linear systems arising from hp adaptive finite element calculations, and is implemented in the PLTMG software package, version 12. This preconditioner typically requires 3-20% of the space used by the stiffness matrix for higher order elements. It has multigrid like convergence rates for a wide variety of PDEs (self-adjoint positive de nite elliptic equations, convection dominated convection-diffusion equations, and highly indefinite Helmholtz equations, among others). The convergence rate is not independent of the polynomial degree p as p ! 1, but but remains strong for p 9, which is the highest polynomial degree allowed in PLTMG, due to limitations of the numerical quadrature rules implemented in the software package. A more complete description of the method and some numerical experiments illustrating its effectiveness appear in. Like traditional geometric multilevel methods, this scheme relies on knowledge of the underlying finite element space in order to construct the smoother and the coarse grid correction.

97 MATHEMATICS AND COMPUTING↗

Final Report - Subcontract B629114

During my visits to LLNL August 20-24, 2018, and September 10-14, 2018, I worked on linear system solvers. The two level hierarchical solver that initiated our study was developed to solve linear systems arising from $hp$ adaptive finite element calculations, and is implemented in the PLTMG software package, version 13. This preconditioner typically requires 3 – 20% of the space used by the stiffness matrix for higher order elements. It has multigrid like convergence rates for a wide variety of PDEs (self-adjoint positive definite elliptic equations, convection dominated convection-diffusion equations, and highly indefinite Helmholtz equations, among others). The convergence rate is not independent of the polynomial degree $p$ as $p → ∞$, but but remains strong for $p ≤$ 9, which is the highest polynomial degree allowed in PLTMG , due to limitations of the numerical quadrature rules implemented in the software package. A more complete description of the method and some numerical experiments illustrating its effectiveness appear. Like traditional geometric multilevel methods, this scheme relies on knowledge of the underlying finite element space in order to construct the smoother and the coarse grid correction.

97 MATHEMATICS AND COMPUTING↗

Subcontract B635525 (Final Report)

During my visits to LLNL July 8–12 and July 22–26, 2019, I worked on linear system solvers. The two level hierarchical solver that initiated our study was developed to solve linear systems arising from $\textit{hp}$ adaptive finite element calculations, and is implemented in the $\textit{PLTMG}$ software package, version 13. This preconditioner typically requires 3–20% of the space used by the stiffness matrix for higher order elements. It has multigrid like convergence rates for a wide variety of PDEs (self-adjoint positive definite elliptic equations, convection dominated convection-diffusion equations, and highly indefinite Helmholtz equations, among others). The convergence rate is not independent of the polynomial degree $\textit{p}$ as $\textit{p} → ∞$, but remains strong for $\textit{p}$ ≤ 9, which is the highest polynomial degree allowed in $\textit{PLTMG}$, due to limitations of the numerical quadrature rules implemented in the soft- ware package. A more complete description of the method and some numerical experiments illustrating its effectiveness appear in. Like traditional geometric multilevel methods, this scheme relies on knowledge of the underlying finite element space in order to construct the smoother and the coarse grid correction.

97 MATHEMATICS AND COMPUTING↗

Low Precision and Efficient Programming Languages for Sustainable AI: Final Report for the Summer Project of 2024

This document contains all relevant material generated during the authors' summer internship at NREL in 2024. This report shows how to improve energy efficiency of a few code samples by using low-precision data types combined with mixed-precision algorithms. The main applications considered here are (i) linear system solvers using mixed precision, and (ii) neural networks using mixed precision. This report also discusses how programming languages affect energy consumption of algorithms, energy metrics for a code and tools, and the available current software and hardware infrastructure.

97 MATHEMATICS AND COMPUTING↗

An Efficient Multicore Implementation of a Novel HSS-Structured Multifrontal Solver Using Randomized Sampling

Here, we present a sparse linear system solver that is based on a multifrontal variant of Gaussian elimination and exploits low-rank approximation of the resulting dense frontal matrices. We use hierarchically semiseparable (HSS) matrices, which have low-rank off-diagonal blocks, to approximate the frontal matrices. For HSS matrix construction, a randomized sampling algorithm is used together with interpolative decompositions. The combination of the randomized compression with a fast ULV HSS factoriz ation leads to a solver with lower computational complexity than the standard multifrontal method for many applications, resulting in speedups up to 7 fold for problems in our test suite. The implementation targets many-core systems by using task parallelism with dynamic runtime scheduling. Numerical experiments show performance improvements over state-of-the-art sparse direct solvers. The implementation achieves high performance and good scalability on a range of modern shared memory parallel systems, including the Intel Xeon Phi (MIC). The code is part of a software package called STRUMPACK - STRUctured Matrices PACKage, which also has a distributed memory component for dense rank-structured matrices.

97 MATHEMATICS AND COMPUTING↗

A Flexible CUDA LU-based Solver for Small, Batched Linear Systems

This chapter presents the implementation of a batched CUDA solver based on LU factorization for small linear systems. This solver may be used in applications such as reactive flow transport models, which apply the Newton-Raphson technique to linearize and iteratively solve the sets of non linear equations that represent the reactions for ten of thousands to millions of physical locations. The implementation exploits somewhat counterintuitive GPGPU programming techniques: it assigns the solution of a matrix (representing a system) to a single CUDA thread, does not exploit shared memory and employs dynamic memory allocation on the GPUs. These techniques enable our implementation to simultaneously solve sets of systems with over 100 equations and to employ LU decomposition with complete pivoting, providing the higher numerical accuracy required by certain applications. Other currently available solutions for batched linear solvers are limited by size and only support partial pivoting, although they may result faster in certain conditions. We discuss the code of our implementation and present a comparison with the other implementations, discussing the various tradeoffs in terms of performance and flexibility. This work will enable developers that need batched linear solvers to choose whichever implementation is more appropriate to the features and the requirements of their applications, and even to implement dynamic switching approaches that can choose the best implementation depending on the input data.

bached linear solvers↗

Numerical homogenization of concrete microstructures without explicit meshes

Life management of electric hydro or nuclear power plants requires to estimate long-term concrete properties on facilities, for obvious safety and serviceability reasons. Decades-old structures are foreseen to be operational for several more decades. As a large number of different concrete formulations are found in EDF facilities, empirical models based on many experiments cannot be an option for a large fleet of power plant buildings. To build predictive models, homogenization techniques offer an appealing alternative. To properly upscale creep, especially at long term, a rather precise description of the microstructure is required. However, the complexity of the morphology of concrete poses several challenges. In particular, concrete is formulated to maximize the packing density of the granular skeleton, leading to aggregates spanning several length scales with small inter particle spacings. Thus, explicit meshing of realistic concrete microstructures is either out of reach of current meshing algorithms or would produce a number of degrees of freedom far higher than the current generic FEM codes capabilities. This paper proposes a method to deal with complex matrix-inclusions microstructures such as the ones encountered at the mortar or concrete scales, without explicitly meshing them. The microstructure is superimposed to an independent mesh, which is a regular Cartesian grid. This inevitably yields so called 'gray elements', spanning across multiple phases. As the reliability of the estimate of the effective properties highly depends on the behavior affected to these gray elements, special attention is paid to them. As far as the question of the solvers is concerned, generic FEM codes are found to lack efficiency: they cannot reach high enough levels of discretization with classical free meshes, and they do not take advantage of the regular structure of the mesh. Thus, a specific finite differences/finite volumes solver has been developed. At first, generic off-the-shelf linear system solvers were used. To further improve the efficiency in terms of memory requirements, specific variants of the preconditioned conjugate gradient were implemented. This allowed to homogenize the conductivity of a concrete-like microstructure using more than 10{sup 9} degrees of freedom on a rather common hardware for 2010 (a PC embedding 48 GB of RAM). Taking benefit of the properties of the regular Cartesian grid we have also investigated a multi-level method to improve the CPU efficiency of the code.

36 MATERIALS SCIENCE↗

Current possibilities and future opportunities for erasure coded computations

The key capability established through the research funded by this award are erasure coded computations for linear systems, in serial and in parallel. This capability enables powerful efficient and scalable alternatives to existing linear system solvers in fault-prone computational systems.

97 MATHEMATICS AND COMPUTING↗

Higher Order, Hybrid BEM/FEM Methods Applied to Antenna Modeling

In this presentation, the authors address topics relevant to higher order modeling using hybrid BEM/FEM formulations. The first of these is the limitation on convergence rates imposed by geometric modeling errors in the analysis of scattering by a dielectric sphere. The second topic is the application of an Incomplete LU Threshold (ILUT) preconditioner to solve the linear system resulting from the BEM/FEM formulation. The final tOpic is the application of the higher order BEM/FEM formulation to antenna modeling problems. The authors have previously presented work on the benefits of higher order modeling. To achieve these benefits, special attention is required in the integration of singular and near-singular terms arising in the surface integral equation. Several methods for handling these terms have been presented. It is also well known that achieving ~he high rates of convergence afforded by higher order bases may als'o require the employment of higher order geometry models. A number of publications have described the use of quadratic elements to model curved surfaces. The authors have shown in an EFIE formulation, applied to scattering by a PEC .sphere, that quadratic order elements may be insufficient to prevent the domination of modeling errors. In fact, on a PEC sphere with radius r = 0.58 Lambda(sub 0), a quartic order geometry representation was required to obtain a convergence benefi.t from quadratic bases when compared to the convergence rate achieved with linear bases. Initial trials indicate that, for a dielectric sphere of the same radius, - requirements on the geometry model are not as severe as for the PEC sphere. The authors will present convergence results for higher order bases as a function of the geometry model order in the hybrid BEM/FEM formulation applied to dielectric spheres. It is well known that the system matrix resulting from the hybrid BEM/FEM formulation is ill -conditioned. For many real applications, a good preconditioner is required to obtain usable convergence from an iterative solver. The authors have examined the use of an Incomplete LU Threshold (ILUT) preconditioner . to solver linear systems stemming from higher order BEM/FEM formulations in 2D scattering problems. Although the resulting preconditioner provided aD excellent approximation to the system inverse, its size in terms of non-zero entries represented only a modest improvement when compared with the fill-in associated with a sparse direct solver. Furthermore, the fill-in of the preconditioner could not be substantially reduced without the occurrence of instabilities. In addition to the results for these 2D problems, the authors will present iterative solution data from the application of the ILUT preconditioner to 3D problems.

Fink, P. W.↗

Integration Strategies for Efficient Multizone Chemical Kinetics Models

Three integration strategies are developed and tested for the stiff, ordinary differential equation (ODE) integrators used to solve the fully coupled multizone chemical kinetics model. Two of the strategies tested are found to provide more than an order of magnitude of improvement over the original, basic level of usage for the stiff ODE solver. One of the faster strategies uses a decoupled, or segregated, multizone model to generate an approximate Jacobian. This approach yields a 35-fold reduction in the computational cost for a 20 zone model. Using the same approximate Jacobian as a preconditioner for an iterative Krylov-type linear system solver, the second improved strategy achieves a 75-fold reduction in the computational cost for a 20 zone model. The faster strategies achieve their cost savings with no significant loss of accuracy. The pressure, temperature and major species mass fractions agree with the solution from the original integration approach to within six significant digits; and the radical mass fractions agree with the original solution to within four significant digits. The faster strategies effectively change the cost scaling of the multizone model from cubic to quadratic, with respect to the number of zones. As a consequence of the improved scaling, the 40 zone model offers more than a 250-fold cost savings over the basic calculation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Domain decomposition approaches for accelerating contour integration eigenvalue solvers for symmetric eigenvalue problems

This work discusses techniques for computing a few selected eigenvalue–eigenvector pairs of large and sparse symmetric matrices. A recently developed class of techniques to solve this type of problems is based on integrating the matrix resolvent operator along a complex contour that encloses the interval containing the eigenvalues of interest. This paper considers such contour integration techniques from a domain decomposition viewpoint and proposes two schemes. The first scheme can be seen as an extension of domain decomposition linear system solvers in the framework of contour integration methods for eigenvalue problems, such as FEAST. The second scheme focuses on integrating the resolvent operator primarily along the interface region defined by adjacent subdomains. A parallel implementation of the proposed schemes is described, and results on distributed computing environments are reported. These results show that domain decomposition approaches can lead to reduced run times and improved scalability.

97 MATHEMATICS AND COMPUTING↗

Neutronics Modeling of the High Flux Isotope Reactor using COMSOL

The High Flux Isotope Reactor located at the Oak Ridge National Laboratory is a versatile 85 MWth research reactor with cold and thermal neutron scattering, materials irradiation, isotope production, and neutron activation analysis capabilities. HFIR staff members are currently in the process of updating the thermal hydraulic and reactor transient modeling methodologies. COMSOL Multiphysics has been adopted for the thermal hydraulic analyses and has proven to be a powerful finite-element-based simulation tool for solving multiple physics-based systems of partial and ordinary differential equations. Modeling reactor transients is a challenging task because of the coupling of neutronics, heat transfer, and hydrodynamics. This paper presents a preliminary COMSOL-based neutronics study performed by creating a two-dimensional, two-group, diffusion neutronics model of HFIR to study the spatially-dependent, beginning-of-cycle fast and thermal neutron fluxes. The 238-group ENDF/B-VII neutron cross section library and NEWT, a two-dimensional, discrete-ordinates neutron transport code within the SCALE 6 code package, were used to calculate the two-group neutron cross sections required to solve the diffusion equations. The two-group diffusion equations were implemented in the COMSOL coefficient form PDE application mode and were solved via eigenvalue analysis using a direct (PARDISO) linear system solver. A COMSOL-provided adaptive mesh refinement algorithm was used to increase the number of elements in areas of largest numerical error to increase the accuracy of the solution. The flux distributions calculated by means of COMSOL/SCALE compare well with those calculated with benchmarked three-dimensional MCNP and KENO models, a necessary first step along the path to implementing two- and three-dimensional models of HFIR in COMSOL for the purpose of studying the spatial dependence of transient-induced behavior in the reactor core.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Multigrid deflation for Lattice QCD

Computing the trace of the inverse of large matrices is typically addressed through statistical methods. Deflating out the lowest eigenvectors or singular vectors of the matrix reduces the variance of the trace estimator. This work summarizes our efforts to reduce the computational cost of computing the deflation space while achieving the desired variance reduction for Lattice QCD applications. Previous efforts computed the lower part of the singular spectrum of the Dirac operator by using an eigensolver preconditioned with a multigrid linear system solver. Despite the improvement in performance in those applications, as the problem size grows the runtime and storage demands of this approach will eventually dominate the stochastic estimation part of the computation. In this work, we propose to compute the deflation space in one of the following two ways. First, by using an inexact eigensolver on the Hermitian, but maximally indefinite, operator. Second, by exploiting the fact that the multigrid prolongator for this operator is rich in components toward the lower part of the singular spectrum. We show experimentally that the inexact eigensolver can approximate the lower part of the spectrum even for ill-conditioned operators. Also, the deflation based on the multigrid prolongator is more efficient to compute and apply, and, despite its limited ability to approximate the fine level spectrum, it obtains similar variance reduction on the trace estimator as deflating with approximate eigenvectors from the fine level operator.

97 MATHEMATICS AND COMPUTING↗

Subsurface Transport Over Multiple Phases Demonstration Software

The STOMP simulator is a suite of numerical simulators developed by Pacific Northwest National Laboratory for addressing problems involving coupled multifluid hydrologic, thermal, geochemical, and geomechanical processes in the subsurface. The simulator has been applied to problems concerning environmental remediation, environmental stewardship, carbon sequestration, conventional petroleum production, and the production of unconventional hydrocarbon fuels. The simulator is copyrighted by Battelle Memorial Institute, and is available outside of PNNL via use agreements. To promote the open exchange of scientific ideas the simulator is provided as source code. A demonstration version of the simulator has been developed, which will provide potential new users with an executable (not source code) implementation of the software royalty free. Demonstration versions will be offered via the STOMP website for all currently available operational modes of the simulator. The demonstration versions of the simulator will be configured with the direct banded linear system solver and have a limit of 1,000 active grid cells. This will provide potential new users with an opportunity to apply the code to simple problems, including many of the STOMP short course problems, without having to pay a license fee. Users will be required to register on the STOMP website prior to receiving an executable.

Source record↗

Scalability under a Power Bound using the GREMLINs Framework

With the move towards exascale, system and software developers will have to deal with issues of extreme parallelism. The system properties affected most by the increase in node and core count are the shared resources on node and across the system. The increase in parallelism leads to reduced memory and bandwidth when regarding individual cores. Since power is a limiting factor for supercomputers, and power is not fully utilized in current systems, overprovisioning compute resources is a viable approach to maximized power utilization. To maximize system performance in regard to these changing conditions, it is necessary to understand how resource restrictions impact performance and system behavior. For the purpose of understanding anticipated system properties the GREMLINs Framework was developed. The framework gives the opportunity to add power restrictions, hinder memory properties and introduce faults to study resilience, among others. These features give the opportunity to use current petascale technology to study problems system designers and software developers will have to face when moving towards exascale and beyond. This work describes the initial release of the GREMLINs Framework, developed for this work, and shows how it can be used to study the scaling behavior of proxy applications. These proxy applications represent a selection of HPC workloads important to the scientific community. The proxy applications studied are AMG2013, an algebraic multi-grid linear system solver, CoMD, a classical molecular dynamics proxy application and NEKBONE, an application that uses a high order spectral element method to solve the Navier-Stokes equations. The main interest of these studies lies in analysis regarding their power behavior at scale under a power bound. These findings show how the GREMLINs Framework can help systems and software designers to attain better application performance and can also be used as basis for CPU power balancing tools to use power more efficiently.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

FY2022 Q4: Demonstrate multi-turbine simulation with hybrid-structured/unstructured-moving-grid software stack running primarily on GPUs and propose improvements for successful KPP-2 [Poster]

Milestone accomplishments staged the ExaWind team for successful completion of KPP-2 challenge problem in FY23, which requires the simulation on Frontier of at least four MW-scale turbines in an atmospheric boundary layer with at least 20B gridpoints. The ExaWind project and software stack is many faceted, with team members working on multiple areas, including linear-system solvers (Trilinos, hypre, AMReX), overset meshes, turbulence modeling, and in situ visualization, all with an aim for high fidelity predictions and performance portability. This milestone marks significant improvements on many fronts and provides the team with a pathway to exascale wind farm simulations in FY23.

17 WIND ENERGY↗