Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel algorithm”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
NASA NTRS1993

Real-time trajectory optimization on parallel processors

A parallel algorithm has been developed for rapidly solving trajectory optimization problems. The goal of the work has been to develop an algorithm that is suitable to do real-time, on-line optimal guidance through repeated solution of a trajectory optimization problem. The algorithm has been developed on an INTEL iPSC/860 message passing parallel processor. It uses a zero-order-hold discretization of a continuous-time problem and solves the resulting nonlinear programming problem using a custom-designed augmented Lagrangian nonlinear programming algorithm. The algorithm achieves parallelism of function, derivative, and search direction calculations through the principle of domain decomposition applied along the time axis. It has been encoded and tested on 3 example problems, the Goddard problem, the acceleration-limited, planar minimum-time to the origin problem, and a National Aerospace Plane minimum-fuel ascent guidance problem. Execution times as fast as 118 sec of wall clock time have been achieved for a 128-stage Goddard problem solved on 32 processors. A 32-stage minimum-time problem has been solved in 151 sec on 32 processors. A 32-stage National Aerospace Plane problem required 2 hours when solved on 32 processors. A speed-up factor of 7.2 has been achieved by using 32-nodes instead of 1-node to solve a 64-stage Goddard problem.

Psiaki, Mark L.↗
DOE OSTI2020

Reducing Communication in Graph Neural Network Training

Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse connectivity information of the data. GNNs represent this connectivity as sparse matrices, which have lower arithmetic intensity and thus higher communication costs compared to dense matrices, making GNNs harder to scale to high concurrencies than convolutional or fully-connected neural networks. Here, we introduce a family of parallel algorithms for training GNNs and show that they can asymptotically reduce communication compared to previous parallel GNN training methods. We implement these algorithms, which are based on 1D, 1. 5D, 2D, and 3D sparse-dense matrix multiplication, using torch.distributed on GPU-equipped clusters. Our algorithms optimize communication across the full GNN training pipeline. We train GNNs on over a hundred GPUs on multiple datasets, including a protein network with over a billion edges.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

A Shift Selection Strategy for Parallel Shift-Invert Spectrum Slicing in Symmetric Self-Consistent Eigenvalue Computation

The central importance of large scale eigenvalue problems in scientific computation necessitates the development massively parallel algorithms for their solution. Recent advances in dense numerical linear algebra have enabled the routine treatment of eigenvalue problems with dimensions on the order of hundreds of thousands on the world's largest supercomputers. In cases where dense treatments are not feasible, Krylov subspace methods offer an attractive alternative due to the fact that they do not require storage of the problem matrices. However, demonstration of scalability of either of these classes of eigenvalue algorithms on computing architectures capable of expressing excessive parallelism is non-trivial due to communication requirements and serial bottlenecks, respectively. In this work, we introduce the SISLICE method: a parallel shift-invert algorithm for the solution of the symmetric self-consistent field (SCF) eigenvalue problem. The SISLICE method drastically reduces the communication requirement of current parallel shift-invert eigenvalue algorithms through various shift selection and migration techniques based on density of states estimation and k-means clustering, respectively. This work demonstrates the robustness and parallel performance of the SISLICE method on a representative set of SCF eigenvalue problems and outlines research directions which will be explored in future work.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

DPP-PMRF: Rethinking Optimization for a Probabilistic Graphical Model Using Data-Parallel Primitives

We present a new parallel algorithm for probabilistic graphical model optimization. The algorithm relies on data-parallel primitives (DPPs), which provide portable performance over hardware architecture. We evaluate results on CPUs and GPUs for an image segmentation problem. Compared to a serial baseline, we observe runtime speedups of up to 13X (CPU) and 44X (GPU). We also compare our performance to a reference, OpenMP-based algorithm, and find speedups of up to 7X (CPU).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Hybrid Parallel Contour Trees, Version 1.0

A common operation in scientific visualization is to compute and render a contour of a data set. Given a function of the form f : R^d -> R, a level set is defined as an inverse image f^-1(h) for an isovalue h, and a contour is a single connected component of a level set. The Reeb graph can then be defined to be the result of contracting each contour to a single point, and is well defined for Euclidean spaces or for general manifolds. For simple domains, the graph is guaranteed to be a tree, and is called the contour tree. Analysis can then be performed on the contour tree in order to identify isovalues of particular interest, based on various metrics, and render the corresponding contours, without having to know such isovalues a priori. This code is intended to be the first data-parallel algorithm for computing contour trees. Our implementation will use the portable data-parallel primitives provided by Nvidia’s Thrust library, allowing us to compile our same code for both GPUs and multi-core CPUs. Native OpenMP and purely serial versions of the code will likely also be included. It will also be extended to provide a hybrid data-parallel / distributed algorithm, allowing scaling beyond a single GPU or CPU.

Sewell, Christopher↗
DOE OSTI2017

Hybrid Parallel Contour Trees, Version 1.0

A common operation in scientific visualization is to compute and render a contour of a data set. Given a function of the form f : R^d -> R, a level set is defined as an inverse image f^-1(h) for an isovalue h, and a contour is a single connected component of a level set. The Reeb graph can then be defined to be the result of contracting each contour to a single point, and is well defined for Euclidean spaces or for general manifolds. For simple domains, the graph is guaranteed to be a tree, and is called the contour tree. Analysis can then be performed on the contour tree in order to identify isovalues of particular interest, based on various metrics, and render the corresponding contours, without having to know such isovalues a priori. This code is intended to be the first data-parallel algorithm for computing contour trees. Our implementation will use the portable data-parallel primitives provided by Nvidia’s Thrust library, allowing us to compile our same code for both GPUs and multi-core CPUs. Native OpenMP and purely serial versions of the code will likely also be included. It will also be extended to provide a hybrid data-parallel / distributed algorithm, allowing scaling beyond a single GPU or CPU.

Sewell, Christopher↗
NASA NTRS1992

A balanced submatrix merging algorithm for multiprocessor architectures

In this article, a parallel algorithm which applies Givens rotations to selectively annihilate k(k + 1)/2 nonzero elements from two k x n(k not more than n) upper trapezoidal submatrices is described. The new algorithm is suitable for implementation on either a pair of directly connected local-memory processors or two clusters of multiple tightly-coupled processors. Analyses show that in both cases the proposed algorithms achieve optimal speed-up by balancing the work load distribution and masking interprocessor or intercluster communication by computation if k is much small than n. In the context of solving large scale least squares problems, this submatrix merging step is repetitively needed during the entire computation and, furthermore, there are usually many pairs of such submatrices to be merged with each submatrix stored in the memory of a processor or a cluster of processors. The proposed algorithm can be applied to each pair of submatrices concurrently, and thus parallelizes an important step in solving the least squares problems.

Chu, Eleanor↗
NASA NTRS1994

An architecture for real-time vision processing

To study the feasibility of developing an architecture for real time vision processing, a task queue server and parallel algorithms for two vision operations were designed and implemented on an i860-based Mercury Computing System 860VS array processor. The proposed architecture treats each vision function as a task or set of tasks which may be recursively divided into subtasks and processed by multiple processors coordinated by a task queue server accessible by all processors. Each idle processor subsequently fetches a task and associated data from the task queue server for processing and posts the result to shared memory for later use. Load balancing can be carried out within the processing system without the requirement for a centralized controller. The author concludes that real time vision processing cannot be achieved without both sequential and parallel vision algorithms and a good parallel vision architecture.

Chien, Chiun-Hong↗
NASA NTRS1998

High Rate Digital Demodulator ASIC

The architecture of High Rate (600 Mega-bits per second) Digital Demodulator (HRDD) ASIC capable of demodulating BPSK and QPSK modulated data is presented in this paper. The advantages of all-digital processing include increased flexibility and reliability with reduced reproduction costs. Conventional serial digital processing would require high processing rates necessitating a hardware implementation in other than CMOS technology such as Gallium Arsenide (GaAs) which has high cost and power requirements. It is more desirable to use CMOS technology with its lower power requirements and higher gate density. However, digital demodulation of high data rates in CMOS requires parallel algorithms to process the sampled data at a rate lower than the data rate. The parallel processing algorithms described here were developed jointly by NASA's Goddard Space Flight Center (GSFC) and the Jet Propulsion Laboratory (JPL). The resulting all-digital receiver has the capability to demodulate BPSK, QPSK, OQPSK, and DQPSK at data rates in excess of 300 Mega-bits per second (Mbps) per channel. This paper will provide an overview of the parallel architecture and features of the HRDR ASIC. In addition, this paper will provide an over-view of the implementation of the hardware architectures used to create flexibility over conventional high rate analog or hybrid receivers. This flexibility includes a wide range of data rates, modulation schemes, and operating environments. In conclusion it will be shown how this high rate digital demodulator can be used with an off-the-shelf A/D and a flexible analog front end, both of which are numerically computer controlled, to produce a very flexible, low cost high rate digital receiver.

Ghuman, Parminder↗
NASA NTRS1990

Parallel homotopy curve tracking on a hypercube

An investigation is conducted to find good parallel algorithms for solving systems of nonlinear equations using probability-one homotopy methods. Particular attention is paid to algorithms for the hypercube. Methods for one of the most computationally expensive steps of the homotopy approach, the computation of the kernel of the Jacobian matrix of the homotopy map, are studied. General nonlinear systems of equations with small and dense Jacobian matrices are considered, however, polynomial systems are not, since their structure leads to different strategies for parallelism. The mathematics behind the homotopy algorithm is summarized and the use of orthogonal factorizations is discussed. Parallel algorithms for orthogonal factorizations and triangular system solving are described. Computational results are presented and discussed.

Chakraborty, A.↗
DOE OSTI2017

The Parareal Method for Solving Space-Dependent Neutron Kinetics Equations in Hexagonal-z Geometry

Neutron kinetics plays an important role in reactor safety and analysis. The backward Euler method is the most widely used time integration method in the calculation of space-dependent nuclear reactor kinetics. Xia (2006) used this method to discretize the derivative of flux, and adopted the analytic integration to discretize the delayed neutron precursor concentrations. Diagonally Implicit Runge-Kutta (DIRK) method owns high accuracy and excellent stability, and it was applied in the rectangle core for calculating core the nuclear reactor kinetics by Wenbo Zhao (2013). Recently, DIRK was applied to the neutron kinetics for hexagonal-z geometry application (CAI, 2016). As solving the neutron kinetics equations is very time-consuming and the number of available cores continues to increase with parallel architectures evolving, parallel algorithms need to be designed in order to effectively utilize the available resources. However, it is difficult to parallel in time axis because the later moment is strongly dependent on the previous moment. Some methods have been proposed to parallel in time algorithm over the last decades. One of the famous methods to realize time parallelism is the Parareal algorithm (Lions, 2001), which offers a promising approach to increase the degree of concurrency. More than one decade from this method first proposed, this method has been studied and applied in the many fields of applied mathematics, physics, chemistry, parallel computing, etc. Fischer (2014 applied the Parareal method in the field of the Navier-Stokes Equations. Baudron (2014) combined the Parareal method with finite element method to solve the neutron kinetics equations, where the Parareal method was implemented based on the implicit Euler method or method. In this paper, the Parareal method is studied in the hexagonal-z geometry with the help of DIRK developed for neutron kinetics equations (CAI, 2016)

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
NASA NTRS1989

Eigensolution of finite element problems in a completely connected parallel architecture

A parallel algorithm is presented for the solution of the generalized eigenproblem in linear elastic finite element analysis. The algorithm is based on a completely connected parallel architecture in which each processor is allowed to communicate with all other processors. The algorithm is successfully implemented on a tightly coupled MIMD parallel processor. A finite element model is divided into m domains each of which is assumed to process n elements. Each domain is then assigned to a processor or to a logical processor (task) if the number of domains exceeds the number of physical processors. The effect of the number of domains, the number of degrees-of-freedom located along the global fronts, and the dimension of the subspace on the performance of the algorithm is investigated. For a 64-element rectangular plate, speed-ups of 1.86, 3.13, 3.18, and 3.61 are achieved on two, four, six, and eight processors, respectively.

Akl, F.↗
DOE OSTI2018

Parallel Nonnegative CP Decomposition of Dense Tensors

The CP tensor decomposition is a low-rank approximation of a tensor. We present a distributed-memory parallel algorithm and implementation of an alternating optimization method for computing a CP decomposition of dense tensors that can enforce nonnegativity of the computed low-rank factors. The principal task is to parallelize the Matricized-Tensor Times Khatri-Rao Product (MTTKRP) bottleneck subcomputation. The algorithm is computation efficient, using dimension trees to avoid redundant computation across MTTKRPs within the alternating method. Our approach is also communication efficient, using a data distribution and parallel algorithm across a multidimensional processor grid that can be tuned to minimize communication. We benchmark our software on synthetic as well as hyperspectral image and neuroscience dynamic functional connectivity data, demonstrating that our algorithm scales well to 100s of nodes (up to 4096 cores) and is faster and more general than the currently available parallel software.

Ballard, Grey↗
NASA NTRS1995

Parallel adaptive mesh refinement within the PUMAA3D Project

To enable the solution of large-scale applications on distributed memory architectures, we are designing and implementing parallel algorithms for the fundamental tasks of unstructured mesh computation. In this paper, we discuss efficient algorithms developed for two of these tasks: parallel adaptive mesh refinement and mesh partitioning. The algorithms are discussed in the context of two-dimensional finite element solution on triangular meshes, but are suitable for use with a variety of element types and with h- or p-refinement. Results demonstrating the scalability and efficiency of the refinement algorithm and the quality of the mesh partitioning are presented for several test problems on the Intel DELTA.

Freitag, Lori↗
DOE OSTI2011

Data-Parallel Mesh Connected Components Labeling and Analysis

We present a data-parallel algorithm for identifying and labeling the connected sub-meshes within a domain-decomposed 3D mesh. The identification task is challenging in a distributed-memory parallel setting because connectivity is transitive and the cells composing each sub-mesh may span many or all processors. Our algorithm employs a multi-stage application of the Union-find algorithm and a spatial partitioning scheme to efficiently merge information across processors and produce a global labeling of connected sub-meshes. Marking each vertex with its corresponding sub-mesh label allows us to isolate mesh features based on topology, enabling new analysis capabilities. We briefly discuss two specific applications of the algorithm and present results from a weak scaling study. We demonstrate the algorithm at concurrency levels up to 2197 cores and analyze meshes containing up to 68 billion cells.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Acceleration of the Particle Swarm Optimization for Peierls–Nabarro modeling of dislocations in conventional and high-entropy alloys

Dislocations are among the most important defects in determining the mechanical properties of both conventional alloys and high-entropy alloys. The Peierls-Nabarro model supplies an efficient pathway to their geometries and mobility. The difficulty in solving the integro-differential Peierls-Nabarro equation is how to effectively avoid the local minima in the energy landscape of a dislocation core. Among the other methods to optimize the dislocation core structures, we choose the algorithm of Particle Swarm Optimization, an algorithm that simulates the social behaviors of organisms. By employing more particles (bigger swarm) and more iterative steps (allowing them to explore for longer time), the local minima can be effectively avoided. But this would require more computational cost. The advantage of this algorithm is that it is readily parallelized in modern high computing architecture. We demonstrate the performance of our parallelized algorithm scales linearly with the number of employed cores.

36 MATERIALS SCIENCE↗
DOE OSTI2013

Scalable Domain Decomposed Monte Carlo Particle Transport

In this dissertation, we present the parallel algorithms necessary to run domain decomposed Monte Carlo particle transport on large numbers of processors (millions of processors). Previous algorithms were not scalable, and the parallel overhead became more computationally costly than the numerical simulation.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS1991

Parallel computation of manipulator inverse dynamics

In this article, parallel computation of manipulator inverse dynamics is investigated. A hierarchical graph-based mapping approach is devised to analyze the inherent parallelism in the Newton-Euler formulation at several computational levels, and to derive the features of an abstract architecture for exploitation of parallelism. At each level, a parallel algorithm represents the application of a parallel model of computation that transforms the computation into a graph whose structure defines the features of an abstract architecture, i.e., number of processors, communication structure, etc. Data-flow analysis is employed to derive the time lower bound in the computation as well as the sequencing of the abstract architecture. The features of the target architecture are defined by optimization of the abstract architecture to exploit maximum parallelism while minimizing architectural complexity. An architecture is designed and implemented that is capable of efficient exploitation of parallelism at several computational levels. The computation time of the Newton-Euler formulation for a 6-degree-of-freedom (dof) general manipulator is measured as 187 microsec. The increase in computation time for each additional dof is 23 microsec, which leads to a computation time of less than 500 microsec, even for a 12-dof redundant arm.

Fijany, Amir↗