PARSE: A Tool for Parallel Application Run Time Sensitivity Evaluation
ICPADS '06 Proceedings of the 12th International Conference on Parallel and Distributed Systems - Volume 1
A network performance sensitivity metric for parallel applications
International Journal of High Performance Computing and Networking
Thread Tranquilizer: Dynamically reducing performance variation
ACM Transactions on Architecture and Code Optimization (TACO) - HIPEAC Papers
A network performance sensitivity metric for parallel applications
ISPA'07 Proceedings of the 5th international conference on Parallel and Distributed Processing and Applications
There goes the neighborhood: performance degradation due to nearby jobs
SC '13 Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis
| Hi-index | 0.00 |
Highly variable parallel application execution time is apersistent issue in cluster computing environments, and canbe particularly acute in systems composed of Networks ofWorkstations (NOWs). We are looking at this issue in termsof consistency. In particular, we are focusing on networkperformance. Before we can use techniques from fault managementto attain consistency, this paper presents our preliminaryanalysis of run-time variability from logs and experiments,exposing important issues related to systemic inconsistencyin NOW clusters. The characterization of applicationsensitivity can be used to set network performancegoals, thereby defining operational requirements. Networkperformance depends on the virtual topology imposed bythe scheduler's allocation of nodes and the communicationpatterns of the set of running applications. Therefore it isimportant to look at both the network and the cluster's centralizednode mapper (scheduler) as critical subsystems.