Publication View

Partial Differential Equations on the Intel Touchstone Delta Supercomputer (2008)

Abstract
Evolutionary partial differential actuations are usually solved by discretization in time and space, and by applying a marching in time procedure to data and algorithms potentially parallelized in the spatial domain.--2 In a cleparture from such a strictly. sequential temporal paradigm, we have developed the concept of-_.. — tinle~~rgll~l__~~orithms, which allow the marching in time to be fully parallelized. This is achieved by using a transforma-tion based on the eigenvalue-eigenvector decomposition of the matrices resulting from the discretization process. Since these matrices are involved in the time stepping iterations, the resulting diagonalization yields ‘(time parallel ” algorithms, i.e., algorithms that pos-sess a highly decoupled temporal structure, and hence can be efficiently implemented on emerging massively parallel MIMD architectures with a minimum of communication and synchronization overhead. Specifically, our algorithms have been implemented on the Intel Touchstone Delta supercomputer. We have illustrated our approach on a two-dimensional heat equation, and have demonstrated that a linear speedup can be achieved and main-tained, even for a very large number of processor nodes. 1.

Publication details
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=?doi=10.1.1.116.3428
Source http://trs-new.jpl.nasa.gov/dspace/bitstream/2014/35639/1/93-1360.pdf
Contributors CiteSeerX
Repository CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type text
Language English
Relation 10.1.1.36.4672