# Grid'5000 experiment

## GREMLINS (Networking)

### Conducted by

Christophe Denis### Description

Numerical applications in different scientific domains (biology mechanics, geophysics, ..) need a more and more increasing computational power in order to simulate phenomena close to the reality. They use more often existing sparse linear system librairies and tools which are efficient on sequential machines, on parallel computers or on PC-clusters. There exists in labs unused local computational power via PC's or PC clusters which can be federated into into an heteregenous and distributed grid. The grid computing seems to be a cheap answer of the computational power demand. Unfortunately, the heterogeneity of the machines and the variability of the interconnection networks bring new algorithmic problems. The goal of this project is to define new algorithmic schemes to solve sparse linear systems on heterogeneous and distributed clusters. Those algorithms will be implemented in a library which will be freely available for the scientific community. The communications being penalizing on such distributed clusters, the new algorithms will have to be coarse grained in order to minimize the former. To achieve this goal, the multisplitting method which consists in decomposing the linear system into several sub-systems will be used. In this method, the resolution takes an iterative form by applying on each processor a sequential method (direct or iterative) to solve its sub-system until the global result becomes stable. This method can be used either in synchronous or in asynchronous mode. In the latter mode, processors work independently and use the last received data from their neighbours in their computations. However, this method is only applicable to some matrices with a particular spectral radius. To avoid this restriction, we aim at studying the influence of pre-processing techniques such as reordering,load balancing and pre-conditioning methods.### Status

in progress### Resources

*Nodes involved:*>1000*Sites involved:*>3*Minimum walltime:*1h*Batch mode:*yes*CPU bound:*no*Memory bound:*no*Storage bound:*no*Network bound:*yes*Interlink bound:*yes

### Tools used

No information### Results

Not yet
*Shared by: Christophe Denis*

*Last update: 0000-00-00 00:00:00*

*Experiment #204*