References of "Huard, Guillaume"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailScheduling Instructions on Hierarchical Machines
Blachot, Florent; Huard, Guillaume; Pecero, Johnatan UL et al

in 2010 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW) (2010, April 23)

The aim of this work is to study the problem of scheduling fine grain task graphs on hierarchical distributed systems with communication delay. We consider as a case study how to schedule the instructions ... [more ▼]

The aim of this work is to study the problem of scheduling fine grain task graphs on hierarchical distributed systems with communication delay. We consider as a case study how to schedule the instructions on a processor that implements incomplete bypass ( ST200). We show first how this problem can be expressed as scheduling unitary tasks on a hierarchical architecture with heavy communications between clustered units. The proposed analysis is generic and can be extended to other challenging problems like scheduling in clusters of multi-cores. Our main result is an approximation algorithm based on list scheduling whose approximation ratio is the minimum of two expressions, the first one depends on the number of clusters while the second one depends on the communication delay. Experiments run on random graphs and on structured graphs demonstrate the effectiveness of the proposed approach. [less ▲]

Detailed reference viewed: 75 (0 UL)
Full Text
See detailIV Grid Plugtests: composing dedicated tools to run an application efficiently on Grid'5000
Besseron, Xavier UL; Danjean, Vincent; Gautier, Thierry et al

Presentation (2008, February 12)

Exploiting efficiently the resources of whole Grid'5000 with the same application requires to solve several issues: 1) resources reservation; 2) application's processes deployment; 3) application's tasks ... [more ▼]

Exploiting efficiently the resources of whole Grid'5000 with the same application requires to solve several issues: 1) resources reservation; 2) application's processes deployment; 3) application's tasks scheduling. For the IV Grid Plugtests, we used a dedicated tool for each issue to solve. The N-Queens contest rules imposed ProActive for the resources reservations (issue 1). Issue 2 was solved using TakTuk which allows to deploy a large set of remote nodes. Deployed nodes take part in the deployment using an adaptive algorithm that makes it very efficient. For the 3rd issue, we wrote our application with Athapascan API whose model is based on the concepts of tasks and shared data. The application is described as a data-flow graph using the Shared and Fork keywords. This high level abstraction of hardware gives us an efficient execution with the Kaapi runtime engine using a work-stealing scheduling algorithm to balance the workload between all the distributed processes. [less ▲]

Detailed reference viewed: 21 (1 UL)