Asynchronous Parareal Time Discretization For Partial Differential Equations

  title={Asynchronous Parareal Time Discretization For Partial Differential Equations},
  author={Fr{\'e}d{\'e}ric Magoul{\`e}s and Guillaume Gbikpi Benissan},
Asynchronous iterations have been investigated more and more for both scaling and fault-resilience purposes on high performance computing platforms. While so far, they have been exclusively applied within space domain decomposition frameworks, this paper advocates a novel application direction targeting time-decomposed time-parallel approaches. Specifically, an asynchronous iterative model is derived from the Parareal scheme, for which convergence and speedup analysis are then conducted. It… 
Reducing the effect of global synchronization in delayed gradient methods for symmetric linear systems
This paper explores the cyclic formulations of lagged gradient methods and s-dimensional methods for reducing global synchronizations and concludes that these formulations perform better than traditional methods in view of both iteration count and computing time.
Asynchronous time-parallel method based on Laplace transform
An original asynchronous Laplace transform method formalized for quasilinear problems based on the well-known Gaver–Stehfest algorithm is proposed and several interesting properties compared with the classical algorithms are shown.
Parallel asynchronous algorithms: A survey
The principle of implementation of these parallel asynchronous iterative methods is described for subdomain method without overlapping and for sub domain method with overlapping; the use of load balancing approach for asynchronous parallel algorithms is also discussed.
Protocol-free asynchronous iterations termination
It is shown that, when one arbitrarily takes the local components of a global solution vector, an upper bound can be established on the difference between a residual error evaluation from this global vector and the inconsistent residual error evaluated without synchronizing the involved computing processes.
Recent Developments in Iterative Methods for Reducing Synchronization
  • Qinmeng Zou, F. Magoulès
  • Computer Science
    2019 18th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES)
  • 2019
This paper aims at providing a brief overview of recent advances in parallel iterative methods for solving large-scale problems by referring the reader to the related references for more details on the derivation, implementation, performance, and analysis of these techniques.
Using Asynchronous Simulation Approach for Interactive Simulation
The hypothesis is that get partial results faster is better than getting synchronized and final results to take a decision, in a interactive simulation context.


Scheduling of tasks in the parareal algorithm
It is suggested that the parareal algorithm is a promising approach to solving long time evolution problems, particularly when the goal is simulation of longer times using more processors, and exhibits characteristics that make it particularly suitable for execution on heterogeneous computational grids.
Fault Tolerance in the Parareal Method
It is demonstrated how the parareal algorithm may be made resilient towards Silent-Data-Corruption errors by viewing it as a point-iterative method, locally monitoring the residual between consecutive iterations so to discard potentially corrupt iterations.
Asynchronous multilevel adaptive methods for solving partial differential equations on multiprocessors: basic ideas
The asynchronous fast adaptive composite grid method (AFAC) is developed here as a method that can process refinement levels in parallel while maintaining full multilevel convergence speeds.
Asynchronous Iterations of Parareal Algorithm for Option Pricing Models
This paper presents an original model of asynchronous variant based on the parareal scheme, applied to the European option pricing problem and shows the convergence performance and computational efficiency of such a method.
Time‐decomposed parallel time‐integrators: theory and feasibility studies for fluid, structure, and fluid–structure applications
This methodology parallelizes the time-loop of a time- dependent partial differential equation solver without interfering with its sequential or parallel space-computations for time-dependent problems with a few degrees of freedom such as those arising in robotics and protein folding applications.
Asynchronous optimized Schwarz methods with and without overlap
An asynchronous version of the optimized Schwarz method for the solution of differential equations on a parallel computational environment is studied and it is shown to converge when the optimal artificial interface conditions are used.
Some aspects of parallel and distributed iterative algorithms - A survey,
Abstract We consider iterative algorithms of the form x := f ( x ), executed by a parallel or distributed computing system. We first consider synchronous executions of such iterations and study their
Asynchronous Iterative Methods for Multiprocessors
A class of asynchronous iterative methods is presented for solving a system of equations corresponding to a parallel implementation on a multiprocessor system with no synchronization between cooperating processes to show clearly the advantage of purely asynchronous Iterative methods.
JACK2: An MPI-based communication library with non-blocking synchronization for asynchronous iterations
This paper addresses the design of a communication library which particularly targets distributed iterative computing, including randomly executed asynchronous iterations, and provides an efficient exact approach to compute global convergence residual norms, by means of non-blocking synchronization.
Analysis of the Parareal Time-Parallel Time-Integration Method
New convergence results that show superlinear convergence of the parareal algorithm when used on bounded time intervals, and linear convergence for unbounded intervals are shown.