Name
Title | ||
|---|---|---|
Impact of the Scheduling Strategy in Heterogeneous Systems That Provide Co-Scheduling. |
Abstract | ||
|---|---|---|
In recent years, the number of processing units per compute node has been increasing. In order to utilize all or most of the available resources of a high-performance computing cluster, at least some of its nodes will have to be shared by several applications at the same time. Yet, even if jobs are co-scheduled on a node, it can happen that high performance resources remain idle, although there are jobs that could make use of them (e. g. if the resource was temporarily blocked when the job was started). Heterogeneous schedulers, which schedule tasks for dierent devices, can bind jobs to resources in a way that can signicantly reduce the idle time. Typically, those schedulers make their decisions based on a static strategy. In this paper, we investigate the impact if a heterogeneous scheduler allows modications of the strategies at runtime. |
Year | Venue | DocType |
|---|---|---|
2016 | COSH@HiPEAC | Conference |
Citations | PageRank | References |
1 | 0.35 | 7 |
Authors | ||
8 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tim Süß | 1 | 50 | 10.80 |
| Nils Döring | 2 | 1 | 0.35 |
| Ramy Gad | 3 | 10 | 2.35 |
| Lars Nagel | 4 | 76 | 13.58 |
| André Brinkmann | 5 | 403 | 34.79 |
| dustin feld | 6 | 7 | 2.53 |
| Eric Schröder | 7 | 1 | 0.35 |
| Thomas Soddemann | 8 | 1 | 0.35 |