Search NASA⌕ Search

SEARCH · Search NASA

Results for “LU decomposition”

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 19 records

GSoFa: Scalable Sparse Symbolic LU Factorization on GPUs

Decomposing a matrix $\mathbf {A}$ into a lower matrix $\mathbf {L}$ and an upper matrix $\mathbf {U}$, which is also known as LU decomposition, is an essential operation in numerical linear algebra. For a sparse matrix, LU decomposition often introduces more nonzero entries in the $\mathbf {L}$ and $\mathbf {U}$ factors than in the original matrix. A symbolic factorization step is needed to identify the nonzero structures of $\mathbf {L}$ and $\mathbf {U}$ matrices. Attracted by the enormous potentials of the Graphics Processing Units (GPUs), an array of efforts have surged to deploy various LU factorization steps except for the symbolic factorization, to the best of our knowledge, on GPUs. This article introduces gSoFa, the first GPU-based symbolic factorization design with the following three optimizations to enable scalable LU symbolic factorization for nonsymmetric pattern sparse matrices on GPUs. First, here we introduce a novel fine-grained parallel symbolic factorization algorithm that is well suited for the Single Instruction Multiple Thread (SIMT) architecture of GPUs. Second, we tailor supernode detection into a SIMT friendly process and strive to balance the workload, minimize the communication and saturate the GPU computing resources during supernode detection. Third, we introduce a three-pronged optimization to reduce the excessive space consumption problem faced by multi-source concurrent symbolic factorization. Taken together, gSoFa achieves up to 31× speedup from 1 to 44 Summit nodes (6 to 264 GPUs) and outperforms the state-of-the-art CPU project, on average, by 5×. Notably, gSoFa also achieves up to 47 percent of the peak memory throughput of a V100 GPU in the Summit Supercomputer.

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↗

Accelerating Subsurface Transport Simulation on Heterogeneous Clusters

Reactive transport numerical models simulate chemical and microbiological reactions that occur along a flowpath. These models have to compute reactions for a large number of locations. They solve the set of ordinary differential equations (ODEs) that describes the reaction for each location through the Newton-Raphson technique. This technique involves computing a Jacobian matrix and a residual vector for each set of equation, and then solving iteratively the linearized system by performing Gaussian Elimination and LU decomposition until convergence. STOMP, a well known subsurface flow simulation tool, employs matrices with sizes in the order of 100x100 elements and, for numerical accuracy, LU factorization with full pivoting instead of the faster partial pivoting. Modern high performance computing systems are heterogeneous machines whose nodes integrate both CPUs and GPUs, exposing unprecedented amounts of parallelism. To exploit all their computational power, applications must use both the types of processing elements. For the case of subsurface flow simulation, this mainly requires implementing efficient batched LU-based solvers and identifying efficient solutions for enabling load balancing among the different processors of the system. In this paper we discuss two approaches that allows scaling STOMP's performance on heterogeneous clusters. We initially identify the challenges in implementing batched LU-based solvers for small matrices on GPUs, and propose an implementation that fulfills STOMP's requirements. We compare this implementation to other existing solutions. Then, we combine the batched GPU solver with an OpenMP-based CPU solver, and present an adaptive load balancer that dynamically distributes the linear systems to solve between the two components inside a node. We show how these approaches, integrated into the full application, provide speed ups from 6 to 7 times on large problems, executed on up to 16 nodes of a cluster with two AMD Opteron 6272 and a Tesla M2090 per node.

GPU↗

Efficient Scalable Parallel Higher Order Direct MoM-SIE Method With Hierarchically Semiseparable Structures for 3-D Scattering

A novel fast scalable parallel algorithm is proposed for the solution of large 3-D scattering problems based on: 1) the double (geometrical and current-approximation) higher order (DHO) method of moments (MoM) in the surface integral equation (SIE) formulation and 2) a direct solver for dense linear systems utilizing hierarchically semiseparable (HSS) structures. Namely, an HSS matrix representation is used for compression, factorization, and solution of the system matrix. In addition, a rank-revealing QR decomposition for memory compression is used, with a stopping criterion in terms of the relative rank tolerance value. One method for geometrical preprocessing of the scatterers based on the cobblestone distance sorting technique is employed in order to enhance the HSS algorithm accuracy and parallelization. Numerical examples show how the accuracy of the DHO HSS-MoM-SIE method is easily controllable by using the relative tolerance for the matrix compression. Furthermore, the examples demonstrate low memory consumption, as well as much faster simulation time, when compared to the direct LU decomposition. The method enables dramatically faster monostatic scattering computations than iterative solvers and reduced number of unknowns when compared to low-order discretizations. Finally, great scalability of the algorithm is demonstrated on more than one thousand processes.

97 MATHEMATICS AND COMPUTING↗

Constructing efficient substructure-based preconditioners for BEM systems of equations

In this work, a generic substructuring algorithm is employed to construct global block-diagonal preconditioners for BEM systems of equations. In this strategy, the allowable fill-in positions are those on-diagonal block matrices corresponding to each BE subregion. As these subsystems are independently assembled, the preconditioner for a particular BE model, after the LU decomposition of all subsystem matrices, is easily formed. So as to highlight the efficiency of the preconditioning proposed, the Bi-CG solver, which presents a quite erratic convergence behavior, is considered. In the particular applications of this paper, 3D representative volume elements (RVEs) of carbon-nanotube (CNT) composites are analyzed. The models contain up to several tens of thousands of degrees of freedom. The efficiency and relevance of the preconditioning technique is also discussed in the context of developing general (parallel) BE codes.

36 MATERIALS SCIENCE↗

Predicting Flow in Fracture Networks With Quantum Algorithms

Uncertainty quantification plays a crucial role in the modeling of subsurface flow. For instance, uncertainties in the properties of geologic fracture networks significantly impact flow, requiring numerous simulations to accurately estimate quantities of interest. However, each simulation is computationally expensive because it requires solving a large linear system to capture features that involve both small and large fractures. An example is in percolation, where the interaction of many small fractures (which cumulatively can have a large surface area) with the rock matrix must be modeled precisely. Quantum computing is an emerging tool with the potential to address this issue. Quantum algorithms offer a significant speedup in solving linear systems, achieving efficiencies that are challenging to match with classical approaches. These classical approaches include direct solvers, such as LU decomposition, and iterative methods, notably preconditioned conjugate gradient, commonly used in subsurface modeling to solve large sparse systems. However, applying quantum algorithms to geologic fracture flow requires careful attention to algorithmic and problem-specific constraints to fully realize this quantum advantage. In this work we describe a quantum algorithm for generalized Monte Carlo applications with a quadratic speedup over the classical approaches which can be combined with the quantum speedup, currently under investigation, for solving quantum linear systems for subsurface flow. We show that for quantum algorithms the computational cost of estimating a quantity of interest for a statistical ensemble of networks is roughly the same as that of a single realization, essentially implying that one can get uncertainty quantification for free.

58 GEOSCIENCES↗

Designing Scalable PGAS Communication Subsystems on Cray Gemini Interconnect

The Cray Gemini Interconnect has been recently introduced as a next generation network architecture for building multi-petaflop supercomputers. Cray XE6 systems including LANL Cielo, NERSC Hopper, ORNL Titan and proposed NCSA BlueWaters leverage the Gemini Interconnect as their primary Interconnection network. At the same time, programming models such as the Message Passing Interface (MPI) and Partitioned Global Address Space (PGAS) models such as Unified Parallel C (UPC) and Co-Array Fortran (CAF) have become available on these systems. Global Arrays is a popular PGAS model used in a variety of application domains including hydrodynamics, chemistry and visualization. Global Arrays uses Aggregate Re- mote Memory Copy Interface (ARMCI) as the communication runtime system for Remote Memory Access communication. This paper presents a design, implementation and performance evaluation of scalable and high performance communication subsystems on Cray Gemini Interconnect using ARMCI. The design space is explored and time-space complexities of commu- nication protocols for one-sided communication primitives such as contiguous and uniformly non-contiguous datatypes, atomic memory operations (AMOs) and memory synchronization is presented. An implementation of the proposed design (referred as ARMCI-Gemini) demonstrates the efficacy on communication primitives, application kernels such as LU decomposition and full applications such as Smooth Particle Hydrodynamics (SPH) application.

ARMCI↗

Improving the Accuracy of the Chebyshev Rational Approximation Method Using Substeps

The Chebyshev Rational Approximation Method (CRAM) for solving the decay and depletion of nuclides is shown to have a remarkable decrease in error when advancing the system with the same time step and microscopic reaction rates as the previous step. This property is exploited here to achieve high accuracy in any end-of-step solution by dividing a step into equidistant sub-steps. The computational cost of identical substeps can be reduced significantly below that of an equal number of regular steps, as the LU decompositions for the linear solves required in CRAM only need to be formed on the first substep. The improved accuracy provided by substeps is most relevant in decay calculations, where there have previously been concerns about the accuracy and generality of CRAM. Lastly, with substeps, CRAM can solve any decay or depletion problem with constant microscopic reaction rates to an extremely high accuracy for all nuclides with concentrations above an arbitrary limit.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

Final Report, Center for Programming Models for Scalable Parallel Computing: Co-Array Fortran, Grant Number DE-FC02-01ER25505

The major accomplishment of this project is the production of CafLib, an 'object-oriented' parallel numerical library written in Co-Array Fortran. CafLib contains distributed objects such as block vectors and block matrices along with procedures, attached to each object, that perform basic linear algebra operations such as matrix multiplication, matrix transpose and LU decomposition. It also contains constructors and destructors for each object that hide the details of data decomposition from the programmer, and it contains collective operations that allow the programmer to calculate global reductions, such as global sums, global minima and global maxima, as well as vector and matrix norms of several kinds. CafLib is designed to be extensible in such a way that programmers can define distributed grid and field objects, based on vector and matrix objects from the library, for finite difference algorithms to solve partial differential equations. A very important extra benefit that resulted from the project is the inclusion of the co-array programming model in the next Fortran standard called Fortran 2008. It is the first parallel programming model ever included as a standard part of the language. Co-arrays will be a supported feature in all Fortran compilers, and the portability provided by standardization will encourage a large number of programmers to adopt it for new parallel application development. The combination of object-oriented programming in Fortran 2003 with co-arrays in Fortran 2008 provides a very powerful programming model for high-performance scientific computing. Additional benefits from the project, beyond the original goal, include a programto provide access to the co-array model through access to the Cray compiler as a resource for teaching and research. Several academics, for the first time, included the co-array model as a topic in their courses on parallel computing. A separate collaborative project with LANL and PNNL showed how to extend the co-array model to other languages in a small experimental version of Co-array Python. Another collaborative project defined a Fortran 95 interface to ARMCI to encourage Fortran programmers to use the one-sided communication model in anticipation of their conversion to the co-array model later. A collaborative project with the Earth Sciences community at NASA Goddard and GFDL experimented with the co-array model within computational kernels related to their climate models, first using CafLib and then extending the co-array model to use design patterns. Future work will build on the design-pattern idea with a redesign of CafLib as a true object-oriented library using Fortran 2003 and as a parallel numerical library using Fortran 2008.

97 MATHEMATICS AND COMPUTING↗

BiGlobal Secondary Instabilities of Roughness-Induced Transient Growth

Roughness-induced transient disturbances distort laminar boundary layers and can lead to premature transition if the roughness is of sufficient height and shape. If transition does occur, it does so through a high-frequency "secondary" instability of the roughness wake. A BiGlobal secondaryinstability code has been developed to solve the stability problem downstream of roughness. The code implements multiple solvers for incompressible/compressible, inviscid/viscous, and temporal/spatial stability. High-order finite differences, sparse matrix linear algebra, LU decomposition, and Arnoldi iterations are used to solve the resulting generalized eigenvalue problem. The code has been used to evaluate the stability properties of experimental roughness-induced transient growth on a flat-plate at low-speed and a slightly blunted cone at M∞= 6. The resulting mode shapes, growth rates, and spatial N-factors show excellent agreement with experimental data. The viscous mode shapes show the best agreement with the experimental disturbance profiles. Yet, execution time can be reduced by an order-of-magnitude by using the inviscid solvers with only modest differences in growth rates.

BiGlobal↗

An efficient solution of low-frequency magnetic problems with voltage sources using all-frequency stable formulation

The modeling and simulation of magnetic problems at low frequencies are considered in this paper. When excited with a voltage source, conduction current is induced in the circuit of interest, which generates the magnetic field. This type of problems is modeled using the all-frequency stable formulation, which employs the potential description of fields with an inhomogeneous Coulomb gauge. With the aid of the stable formulation, the low-frequency breakdown problem is circumvented and both electric and magnetic fields can be solved in a single simulation. To solve large magnetic problems efficiently, it is necessary to employ an iterative solver with an efficient preconditioner. In this work, a preconditioner based on the incomplete LU decomposition is constructed and applied in a wide frequency range. Several numerical examples are given to demonstrate the performance of the proposed method.

Mekonnen, Minyechil↗

Power/Performance Trade-offs of Small Batched LU Based Solvers on GPUs

In this paper we propose and analyze a set of batched linear solvers for small matrices on Graphic Processing Units (GPUs), evaluating the various alternatives depending on the size of the systems to solve. We discuss three different solutions that operate with different level of parallelization and GPU features. The first, exploiting the CUBLAS library, manages matrices of size up to 32x32 and employs Warp level (one matrix, one Warp) parallelism and shared memory. The second works at Thread-block level parallelism (one matrix, one Thread-block), still exploiting shared memory but managing matrices up to 76x76. The third is Thread level parallel (one matrix, one thread) and can reach sizes up to 128x128, but it does not exploit shared memory and only relies on the high memory bandwidth of the GPU. The first and second solution only support partial pivoting, the third one easily supports partial and full pivoting, making it attractive to problems that require greater numerical stability. We analyze the trade-offs in terms of performance and power consumption as function of the size of the linear systems that are simultaneously solved. We execute the three implementations on a Tesla M2090 (Fermi) and on a Tesla K20 (Kepler).

GPGPU↗

A hierarchical butterfly LU preconditioner for two-dimensional electromagnetic scattering problems involving open surfaces

This paper introduces a hierarchical interpolative decomposition butterfly-LU factorization (H-IDBF-LU) preconditioner for solving two-dimensional electric-field integral equations (EFIEs) in electromagnetic scattering problems of perfect electrically conducting objects with open surfaces. H-IDBF-LU leverages the interpolative decomposition butterfly factorization (IDBF) to compress dense blocks of the discretized EFIE operator to expedite its application; this compressed operator also serves as an approximate LU factorization of the EFIE operator leading to an efficient preconditioner in iterative solvers. Both the memory requirement and computational cost of the H-IDBF-LU solver scale as $O$($N$ log 2 $N$) in one iteration; the total number of iterations required for a reasonably good accuracy scales as $O$(1) to O(log 2 $N$) in all of our numerical tests. The efficacy and accuracy of the proposed preconditioned iterative solver are demonstrated via its application to a broad range of scatterers involving up to 100 million unknowns.

Liu, Yang↗

A continuous analogue of the tensor-train decomposition

We develop new approximation algorithms and data structures for representing and computing with multivariate functions using the functional tensor-train (FT), a continuous extension of the tensor-train (TT) decomposition. The FT represents functions using a tensor-train ansatz by replacing the three-dimensional TT cores with univariate matrix-valued functions. The main contribution of this paper is a framework to compute the FT that employs adaptive approximations of univariate fibers, and that is not connected to any tensorized discretization. The algorithm can be coupled with any univariate linear or nonlinear approximation procedure. We demonstrate that this approach can generate multivariate function approximations that are several orders of magnitude more accurate, for the same cost, than those based on the conventional approach of compressing the coefficient tensor of a tensor-product basis. Our approach is in the spirit of other continuous computation packages such as Chebfun, and yields an algorithm which requires the computation of “continuous” matrix factorizations such as the LU and QR decompositions of vector-valued functions. To support these developments, we describe continuous versions of an approximate maximum-volume cross approximation algorithm and of a rounding algorithm that re-approximates an FT by one of lower ranks. We demonstrate that our technique improves accuracy and robustness, compared to TT and quantics-TT approaches with fixed parameterizations, of high-dimensional integration, differentiation, and approximation of functions with local features such as discontinuities and other nonlinearities.

42 ENGINEERING↗

Linear solvers for power grid optimization problems: A review of GPU-accelerated linear solvers

The linear equations that arise in interior methods for constrained optimization are sparse symmetric indefinite, and they become extremely ill-conditioned as the interior method converges. These linear systems present a challenge for existing solver frameworks based on sparse LU or LDL T decompositions. Here, we benchmark five well known direct linear solver packages on CPU- and GPU-based hardware, using matrices extracted from power grid optimization problems. The achieved solution accuracy varies greatly among the packages. None of the tested packages delivers significant GPU acceleration for our test cases. For completeness of the comparison we include results for MA57, which is one of the most efficient and reliable CPU solvers for this class of problem.

97 MATHEMATICS AND COMPUTING↗

On performance of Krylov smoothing for fully-coupled AMG preconditioners for VMS resistive MHD

Here, this study explores the performance and scaling of a GMRES Krylov method employed as a smoother for an algebraic multigrid (AMG) preconditioned Newton- Krylov solution approach applied to a fully-implicit variational multiscale (VMS) nite element (FE) resistive magnetohydrodynamics (MHD) formulation. In this context a Newton iteration is used for the nonlinear system and a Krylov (GMRES) method is employed for the linear subsystems. The efficiency of this approach is critically dependent on the scalability and performance of the AMG preconditioner for the linear solutions and the performance of the smoothers play a critical role. Krylov smoothers are considered in an attempt to reduce the time and memory requirements of existing robust smoothers based on additive Schwarz domain decomposition (DD) with incomplete LU factorization solves on each subdomain. Three time dependent resistive MHD test cases are considered to evaluate the method. The results demonstrate that the GMRES smoother can be faster due to a decrease in the preconditioner setup time and a reduction in outer GMRESR solver iterations, and requires less memory (typically 35% less memory for global GMRES smoother) than the DD ILU smoother.

97 MATHEMATICS AND COMPUTING↗