D. P. Bertsekas and J. N. Tistiklis. Parallel and Distributed Computing: Numerical Methods. Athena Scientific, 1989. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Reducing Synchronization Overhead in Parallel Simulation - Ulana Legedza William (1996) (15 citations) (Correct)
....In contrast, radix represents applications in which communication is more frequent and irregular. By varying parameters of both applications, we were able to experiment with a wide range of computation to communication ratios. 6.2. 1 SOR SOR is a stencil computation that iteratively solves PDE s [4]. Each iteration of the algorithm performs a relaxation function on a grid of points. This function requires only the value of the point to be updated and the values of adjacent points. Subblocks of this grid are distributed among the processors of the parallel machine. During each iteration, each ....
Bertsekas and Tsitsiklis. Parallel and Distributed Computing: Numerical Methods. Prentice Hall, Englewood Cliffs, NJ, 1989.
Run-Time Thread Management for Large-Scale Distributed-Memory.. - Nussbaum (1993) (3 citations) (Correct)
....[9] as a means of propagating threads throughout the machine. Their description is a rather brief part of a larger picture and gives no specific details. However, the settling time for Jacobi Relaxation is proportional to the square of the diameter of the mesh upon which the relaxation takes place [3]. More sophisticated relaxation techniques, such as Multigrid methods [3] achieve much better convergence times at the expense of the locality achieved by simple diffusion methods. The XTM algorithm presented by this thesis can be thought of as the multigrid version of diffusion scheduling. We ....
....is a rather brief part of a larger picture and gives no specific details. However, the settling time for Jacobi Relaxation is proportional to the square of the diameter of the mesh upon which the relaxation takes place [3] More sophisticated relaxation techniques, such as Multigrid methods [3], achieve much better convergence times at the expense of the locality achieved by simple diffusion methods. The XTM algorithm presented by this thesis can be thought of as the multigrid version of diffusion scheduling. We implemented both the simple diffusion scheduling algorithm described here ....
[Article contains additional citation context not shown here]
Dimitri P. Bertsekas and John N. Tsitsiklis. Parallel and Distributed Computing: Numerical Methods. Prentice Hall, 1989.
Fast Convergence to Wardrop Equilibria - Adaptive Sampling Methods (Correct)
No context found.
D. P. Bertsekas and J. N. Tistiklis. Parallel and Distributed Computing: Numerical Methods. Athena Scientific, 1989.
Adaptive Routing with Stale Information - Fischer, Vöcking (2005) (1 citation) (Correct)
No context found.
Dimitri P. Bertsekas and John N. Tistiklis. Parallel and Distributed Computing: Numerical Methods. Athena Scientific, 1989.
Reducing Synchronization Overhead in Parallel Simulation - Legedza (1995) (15 citations) (Correct)
No context found.
Bertsekas and Tsitsikus. Parallel and Distributed Computing Numerical Methods. 70
Analysis of Simple Algorithms for Dynamic Load Balancing - Alanyali, Hajek (1997) (8 citations) (Correct)
No context found.
Bertsekas, D.P., and Tsitsiklis, J.N. (1989). Parallel and Distributed Computing --- Numerical Methods. Prentice-Hall.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC