skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Parallel Algorithms and Patterns

Abstract

This is a powerpoint presentation on parallel algorithms and patterns. A parallel algorithm is a well-defined, step-by-step computational procedure that emphasizes concurrency to solve a problem. Examples of problems include: Sorting, searching, optimization, matrix operations. A parallel pattern is a computational step in a sequence of independent, potentially concurrent operations that occurs in diverse scenarios with some frequency. Examples are: Reductions, prefix scans, ghost cell updates. We only touch on parallel patterns in this presentation. It really deserves its own detailed discussion which Gabe Rockefeller would like to develop.

Authors:
 [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1258365
Report Number(s):
LA-UR-16-24227
DOE Contract Number:
AC52-06NA25396
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Computer Science; Parallel algorithms; reproducible global sums; hash algorithms; prefix scans

Citation Formats

Robey, Robert W. Parallel Algorithms and Patterns. United States: N. p., 2016. Web. doi:10.2172/1258365.
Robey, Robert W. Parallel Algorithms and Patterns. United States. doi:10.2172/1258365.
Robey, Robert W. 2016. "Parallel Algorithms and Patterns". United States. doi:10.2172/1258365. https://www.osti.gov/servlets/purl/1258365.
@article{osti_1258365,
title = {Parallel Algorithms and Patterns},
author = {Robey, Robert W.},
abstractNote = {This is a powerpoint presentation on parallel algorithms and patterns. A parallel algorithm is a well-defined, step-by-step computational procedure that emphasizes concurrency to solve a problem. Examples of problems include: Sorting, searching, optimization, matrix operations. A parallel pattern is a computational step in a sequence of independent, potentially concurrent operations that occurs in diverse scenarios with some frequency. Examples are: Reductions, prefix scans, ghost cell updates. We only touch on parallel patterns in this presentation. It really deserves its own detailed discussion which Gabe Rockefeller would like to develop.},
doi = {10.2172/1258365},
journal = {},
number = ,
volume = ,
place = {United States},
year = 2016,
month = 6
}

Technical Report:

Save / Share:
  • One of the significant problems which must be addressed if we are to realize the computing potential offered by parallel architectures has to do with developing a better understanding of the relationship between parallel algorithms and parallel architectures. In this paper, research on the mapping of algorithms to reconfigurable parallel architectures is presented. The thrust of this work is in identifying those characteristics of parallel algorithms that have the greatest effect on their execution, and in identifying a correspondence between those characteristics and the characteristics of parallel architectures. The context of this work is in the design of an Intelligentmore » Operating System for the PASM reconfigurable multimicroprocessor system. The task of the Intelligent Operating System will be to direct the selection and scheduling of algorithms and the configuring of the architecture for the execution of an image understanding system.« less
  • A learning algorithm based on genetic algorithms for asymmetric neural networks with an arbitrary structure is presented. It is suited for the learning of temporal patterns and leads to stable neural networks with feedback.
  • Two domain-by-domain algorithms, suitable for coarse-grained parallel processing analysis of the transient structural dynamics equation, are investigated for accuracy. The application under specific consideration is the analysis of three-dimensional frame structures subjected to time-varying loading. The domain-by-domain approaches attempt to include the advantageous aspects of both conditionally stable explicit algorithms, which require no simultaneous solutions of equations and employ simple communication, and unconditionally stable implicit algorithms, which permit large time steps. The alternating group explicit algorithm is developed for finite-element analysis, and its accuracy is investigated for a linear formulation. The group implicit algorithm is extended to nonlinear finite elementmore » analysis, and its accuracy is investigated for the frame-dynamics application. Both algorithms are shown to provide inadequate accuracy for practical time-step sizes.« less
  • In recent years many researchers have investigated the use of Markov random fields (MRFs) for computer vision. They can be applied for example in the output of the visual processes to reconstruct surfaces from sparse and noisy depth data, or to integrate early vision processes to label physical discontinuities. Drawbacks of MRFs models have been the computational complexity of the implementation and the difficulty in estimating the parameters of the model. This paper derives deterministic approximations to MRFs models. One of the considered models is shown to give in a natural way the graduate non convexity (GNC) algorithm. This modelmore » can be applied to smooth a field preserving its discontinuities. A new model is then proposed: it allows the gradient of the field to be enhanced at the discontinuities and smoothed elsewhere. All the theoretical results are obtained in the framework of the mean field theory, that is a well known statistical mechanics technique. A fast, parallel, and iterative algorithm to solve the deterministic equations of the two models is presented, together with experiments on synthetic and real images. The algorithm is applied to the problem of surface reconstruction is in the case of sparse data. A fast algorithm is also described that solves the problem of aligning the discontinuities of different visual models with intensity edges via integration.« less
  • The authors study efficient deterministic executions of parallel algorithms on restartable fail-stop CRCW PRAMs. They allow the PRAM processors to be subject to arbitrary stop failures and restarts, that are determined by on-line adversary, and that result in loss of private memory but do not affect shared memory. For this model, they define and justify the complexity measures of: completed work, where processors are charged for completed fixed-size update cycles, and overhead ratio, which amortizes the work over necessary work and failures. We observe that P = N restartable fail-stop processors, the Write-All problem requires omega(N log N) completed work,more » and this lower bound holds even under the additional assumption that processors can read and locally process the entire shared memory at unit cost. Under this unrealistic assumption they have a matching upperbound. The lower bound also applies to the expected completed work of randomized algorithms that are subject to on line adversaries. Finally, they describe a simple on-line adversary that causes inefficiency in many randomized algorithms.« less