Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel algorithms”

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 1,297 records · Page 72

High-performance algorithm to calculate spin- and parity-dependent nuclear level densities

A new algorithm for calculating the spin- and parity-dependent shell-model nuclear level densities using the moments method in the proton-neutron formalism is presented. A new, parallelized code based on this algorithm was developed and tested using up to 4000 cores for a set of nuclei from the sd-, pf-, and pf+g{sub 9/2}-model spaces. By comparing the nuclear level densities at low excitation energy for a given nucleus calculated in two model spaces, such as pf and pf+g{sub 9/2}, one can estimate the ground-state energy in the larger model space, which is not accessible to direct shell-model calculations due to the unmanageable dimension. Examples for the ground-state energies of for {sup 64}Ge and {sup 68}Se in the pf+g{sub 9/2} model space are presented.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Optimization of Condensed Matter Physics Application with OpenMP Tasking Model

The Density Matrix Renormalization Group (DMRG++) is a condensed matter physics application used to study superconductivity properties of materials. It’s main computations consist of calculating hamiltonian matrix which requires sparse matrix-vector multiplications. This paper presents task-based parallelization and optimization strategies of the Hamiltonian algorithm. The algorithm is implemented as a mini-application in C++ and parallelized with OpenMP. The optimization leverages tasking features, such as dependencies or priorities included in the OpenMP standard 4.5. The code refactoring targets performance as much as programmability. The optimized version achieves a speedup of 8.0× with 8 threads and 20.5× with 40 threads on a Power9 computing node while reducing the memory consumption to 90 MB with respect to the original code, by adding less than ten OpenMP directives.

Criado, Joel↗

Accelerated fast iterative shrinkage thresholding algorithms for sparsity-regularized cone-beam CT image reconstruction

Purpose: The development of iterative image reconstruction algorithms for cone-beam computed tomography (CBCT) remains an active and important research area. Even with hardware acceleration, the overwhelming majority of the available 3D iterative algorithms that implement nonsmooth regularizers remain computationally burdensome and have not been translated for routine use in time-sensitive applications such as image-guided radiation therapy (IGRT). In this work, two variants of the fast iterative shrinkage thresholding algorithm (FISTA) are proposed and investigated for accelerated iterative image reconstruction in CBCT. Methods: Algorithm acceleration was achieved by replacing the original gradient-descent step in the FISTAs by a subproblem that is solved by use of the ordered subset simultaneous algebraic reconstruction technique (OS-SART). Due to the preconditioning matrix adopted in the OS-SART method, two new weighted proximal problems were introduced and corresponding fast gradient projection-type algorithms were developed for solving them. We also provided efficient numerical implementations of the proposed algorithms that exploit the massive data parallelism of multiple graphics processing units. Results: The improved rates of convergence of the proposed algorithms were quantified in computer-simulation studies and by use of clinical projection data corresponding to an IGRT study. The accelerated FISTAs were shown to possess dramatically improved convergence properties as compared to the standard FISTAs. For example, the number of iterations to achieve a specified reconstruction error could be reduced by an order of magnitude. Volumetric images reconstructed from clinical data were produced in under 4 min. Conclusions: The FISTA achieves a quadratic convergence rate and can therefore potentially reduce the number of iterations required to produce an image of a specified image quality as compared to first-order methods. We have proposed and investigated accelerated FISTAs for use with two nonsmooth penalty functions that will lead to further reductions in image reconstruction times while preserving image quality. Moreover, with the help of a mixed sparsity-regularization, better preservation of soft-tissue structures can be potentially obtained. The algorithms were systematically evaluated by use of computer-simulated and clinical data sets.

60 APPLIED LIFE SCIENCES↗

Cholesky-based experimental design for Gaussian process and kernel-based emulation and calibration.

Gaussian processes and other kernel-based methods are used extensively to construct approximations of multivariate data sets. The accuracy of these approximations is dependent on the data used. This paper presents a computationally efficient algorithm to greedily select training samples that minimize the weighted L p error of kernel-based approximations for a given number of data. The method successively generates nested samples, with the goal of minimizing the error in high probability regions of densities specified by users. The algorithm presented is extremely simple and can be implemented using existing pivoted Cholesky factorization methods. Training samples are generated in batches which allows training data to be evaluated (labeled) in parallel. For smooth kernels, the algorithm performs comparably with the greedy integrated variance design but has significantly lower complexity. Numerical experiments demonstrate the efficacy of the approach for bounded, unbounded, multi-modal and non-tensor product densities. We also show how to use the proposed algorithm to efficiently generate surrogates for inferring unknown model parameters from data using Bayesian inference.

97 MATHEMATICS AND COMPUTING↗

Implementation of the Lanczos eigen-solver for the CSI code on high performance computers

The focus of this research is to implement a Lanczos algorithm for the Control-Structure Integration (CSI) code which can exploit both parallel and vector capabilities provided by modern, high performance computers. A partial restoring orthogonality scheme is also developed and incorporated into the basic Lanczos algorithm. The numerical performance of the proposed parallel-vector Lanczos algorithm is demonstrated by solving for the frequencies and mode shapes of the Phase Zero CSI model. The superior performance of the Lanczos algorithm is illustrated in tabular form.

Nguyen, Duc T.↗

Provably optimal parallel transport sweeps on regular grids

We have found provably optimal algorithms for full-domain discrete-ordinate transport sweeps on regular grids in 3D Cartesian geometry. We describe these algorithms and sketch a 'proof that they always execute the full eight-octant sweep in the minimum possible number of stages for a given P{sub x} x P{sub y} x P{sub z} partitioning. Computational results demonstrate that our optimal scheduling algorithms execute sweeps in the minimum possible stage count. Observed parallel efficiencies agree well with our performance model. An older version of our PDT transport code achieves almost 80% parallel efficiency on 131,072 cores, on a weak-scaling problem with only one energy group, 80 directions, and 4096 cells/core. A newer version is less efficient at present-we are still improving its implementation - but achieves almost 60% parallel efficiency on 393,216 cores. These results conclusively demonstrate that sweeps can perform with high efficiency on core counts approaching 10{sup 6}. (authors)

97 MATHEMATICS AND COMPUTING↗

Parallel computing strategies for block multigrid implicit solution of the Euler equations

A multigrid diagonal implicit algorithm has been developed to solve the three-dimensional Euler equations of inviscid compressible flow on block-structured grids. An improved method of advancing the multigrid cycle has been examined with respect to convergence rates, accuracy, and efficiency. In this method, the multigrid cycle is advanced independently in each of the blocks, and the information exchange between the blocks is done using buffer arrays, allowing for the asynchronous updating of interface boundary conditions. This updating scheme is used to eliminate the convergence problems found in a previous implementation of the algorithm while retaining its potential for efficient parallel execution. Results are computed for transonic flows past wings and include pressure distributions to verify the accuracy of the scheme and convergence histories to demonstrate the efficiency of the method. Efficiencies that were obtained using a modest number of processors in parallel are also presented and discussed.

Yadlin, Yoram↗

Dynamically Scheduled Region-Based Image Compositing

Algorithms for sort-last parallel volume rendering on large distributed memory machines usually divide a dataset equally across all nodes for rendering. Depending on the features that a user wants to see in a dataset, all the nodes will rarely finish rendering at the same time. Here, existing compositing algorithms do not often take this into consideration, which can lead to significant delays when nodes that are compositing wait for other nodes that are still rendering. In this paper, we present an image compositing algorithm that uses spatial and temporal awareness to dynamically schedule the exchange of regions in an image and progressively composite images as they become available. Running on the Edison supercomputer at NERSC, we show that a scheduler-based algorithm with awareness of the spatial contribution from each rendering node can outperform traditional image compositing algorithms.

97 MATHEMATICS AND COMPUTING↗

Improved Multi-Partition Method for Line-Based Iteration Schemes

Regular 3-dimensional multi-partitioning has been shown to be an efficient domain decomposition method for the parallelization of ADI-type algorithms on MIMD architectures. This paper discusses further improvements that can be made to the scheme that increase the granularity and reduce the communication density. These improvements, which are illustrated by simulation and parallel benchmark results, make multi-partitioning the method of choice on systems with relatively poor communication capabilities, such as networks of workstations, or on massively parallel machines with very fast processors, such as the IBM SP2.

Smith, Merritt H.↗

Convergence of the multigrid reduction in time algorithm for the linear elasticity equations

This paper presents some recent advances for parallel-in-time methods applied to linear elasticity. With recent computer architecture changes leading to stagnant clock speeds, but ever increasing numbers of cores, future speedups will be available through increased concurrency. Thus, sequential algorithms, such as time stepping, will suffer a bottleneck. This paper explores multigrid reduction in time (MGRIT) for an important application area, linear elasticity. Previously, efforts at parallel-in-time for elasticity have experienced difficulties, for example, the beating phenomenon. As a result, practical parallel-in-time algorithms for this application area currently do not exist. This paper proposes some solutions made possible by MGRIT (e.g., slow temporal coarsening and FCF-relaxation) and, more importantly, a different formulation of the problem that is more amenable to parallel-in-time methods. Using a recently developed convergence theory for MGRIT and Parareal, we show that the changed formulation of the problem avoids the instability issues and allows the reduction of the error using two temporal grids. We then extend our approach to the multilevel case, where we demonstrate how slow temporal coarsening improves convergence. Finally, the paper ends with supporting numerical results showing a practical algorithm enjoying speedup benefits over the sequential algorithm.

97 MATHEMATICS AND COMPUTING↗

LDRD Report: Scheduling Irregular Algorithms

This LDRD project was a campus exec fellowship to fund (in part) Donald Nguyen’s PhD research at UT-Austin. His work has focused on parallel programming models, and scheduling irregular algorithms on shared-memory systems using the Galois framework. Galois provides a simple but powerful way for users and applications to automatically obtain good parallel performance using certain supported data containers. The naïve user can write serial code, while advanced users can optimize performance by advanced features, such as specifying the scheduling policy. Galois was used to parallelize two sparse matrix reordering schemes: RCM and Sloan. Such reordering is important in high-performance computing to obtain better data locality and thus reduce run times.

97 MATHEMATICS AND COMPUTING↗

Accurate modeling of switched reluctance machine based on hybrid trained WNN

According to the strong nonlinear electromagnetic characteristics of switched reluctance machine (SRM), a novel accurate modeling method is proposed based on hybrid trained wavelet neural network (WNN) which combines improved genetic algorithm (GA) with gradient descent (GD) method to train the network. In the novel method, WNN is trained by GD method based on the initial weights obtained per improved GA optimization, and the global parallel searching capability of stochastic algorithm and local convergence speed of deterministic algorithm are combined to enhance the training accuracy, stability and speed. Based on the measured electromagnetic characteristics of a 3-phase 12/8-pole SRM, the nonlinear simulation model is built by hybrid trained WNN in Matlab. The phase current and mechanical characteristics from simulation under different working conditions meet well with those from experiments, which indicates the accuracy of the model for dynamic and static performance evaluation of SRM and verifies the effectiveness of the proposed modeling method.

97 MATHEMATICS AND COMPUTING↗

Discrete Event Execution with One-Sided and Two-Sided GVT Algorithms on 216,000 Processor Cores

Global virtual time (GVT) computation is a key determinant of the efficiency and runtime dynamics of parallel discrete event simulations (PDES), especially on large-scale parallel platforms. Here, three execution modes of a generalized GVT computation algorithm are studied on high-performance parallel computing systems: (1) a synchronous GVT algorithm that affords ease of implementation, (2) an asynchronous GVT algorithm that is more complex to implement but can relieve blocking latencies, and (3) a variant of the asynchronous GVT algorithm to exploit one-sided communication in extant supercomputing platforms. Performance results are presented of implementations of these algorithms on up to 216,000 cores of a Cray XT5 system, exercised on a range of parameters: optimistic and conservative synchronization, fine- to medium-grained event computation, synthetic and non-synthetic applications, and different lookahead values. Performance of up to 54 billion events executed per second is registered. Detailed PDES-specific runtime metrics are presented to further the understanding of tightly-coupled discrete event dynamics on massively parallel platforms.

Perumalla, Kalyan S↗

Performance Models for the Spike Banded Linear System Solver

With availability of large-scale parallel platforms comprised of tens-of-thousands of processors and beyond, there is significant impetus for the development of scalable parallel sparse linear system solvers and preconditioners. An integral part of this design process is the development of performance models capable of predicting performance and providing accurate cost models for the solvers and preconditioners. There has been some work in the past on characterizing performance of the iterative solvers themselves. In this paper, we investigate the problem of characterizing performance and scalability of banded preconditioners. Recent work has demonstrated the superior convergence properties and robustness of banded preconditioners, compared to state-of-the-art ILU family of preconditioners as well as algebraic multigrid preconditioners. Furthermore, when used in conjunction with efficient banded solvers, banded preconditioners are capable of significantly faster time-to-solution. Our banded solver, the Truncated Spike algorithm is specifically designed for parallel performance and tolerance to deep memory hierarchies. Its regular structure is also highly amenable to accurate performance characterization. Using these characteristics, we derive the following results in this paper: (i) we develop parallel formulations of the Truncated Spike solver, (ii) we develop a highly accurate pseudo-analytical parallel performance model for our solver, (iii) we show excellent predication capabilities of our model – based on which we argue the high scalability of our solver. Our pseudo-analytical performance model is based on analytical performance characterization of each phase of our solver. These analytical models are then parameterized using actual runtime information on target platforms. An important consequence of our performance models is that they reveal underlying performance bottlenecks in both serial and parallel formulations. All of our results are validated on diverse heterogeneous multiclusters – platforms for which performance prediction is particularly challenging. Finally, we provide predict the scalability of the Spike algorithm using up to 65,536 cores with our model. In this paper we extend the results presented in the Ninth International Symposium on Parallel and Distributed Computing.

Manguoglu, Murat↗

Algorithms and software for solving finite element equations on serial and parallel architectures

The primary objective was to compare the performance of state-of-the-art techniques for solving sparse systems with those that are currently available in the Computational Structural Mechanics (MSC) testbed. One of the first tasks was to become familiar with the structure of the testbed, and to install some or all of the SPARSPAK package in the testbed. A brief overview of the CSM Testbed software and its usage is presented. An overview of the sparse matrix research for the Testbed currently employed in the CSM Testbed is given. An interface which was designed and implemented as a research tool for installing and appraising new matrix processors in the CSM Testbed is described. The results of numerical experiments performed in solving a set of testbed demonstration problems using the processor SPK and other experimental processors are contained.

Chu, Eleanor↗

Algorithms and software for solving finite element equations on serial and parallel architectures

Over the past 15 years numerous new techniques have been developed for solving systems of equations and eigenvalue problems arising in finite element computations. A package called SPARSPAK has been developed by the author and his co-workers which exploits these new methods. The broad objective of this research project is to incorporate some of this software in the Computational Structural Mechanics (CSM) testbed, and to extend the techniques for use on multiprocessor architectures.

George, Alan↗