Sciweavers

474 search results - page 60 / 95
» Search-based Job Scheduling for Parallel Computer Workloads
Sort
View
CLUSTER
2003
IEEE
15 years 7 months ago
Improving Performance of a Dynamic Load Balancing System by Using Number of Effective Tasks
Efficient resource usage is a key to achieving better performance in cluster systems. Previously, most research in this area has focused on balancing the load of each node to use...
Min Choi, Jung-Lok Yu, Hojoong Kim, Seung Ryoul Ma...
JSSPP
1995
Springer
15 years 5 months ago
The ANL/IBM SP Scheduling System
During the past ve years scientists discovered that modern UNIX workstations connected with ethernet and ber networks could provide enough computational performance to compete wit...
David A. Lifka
JSSPP
1995
Springer
15 years 5 months ago
Time Space Sharing Scheduling and Architectural Support
In this paper, we describe a new job scheduling class, called \Time Space Sharing Scheduling" (TSSS) for dynamically partitionable parallel machines. As an instance of TSSS, ...
Atsushi Hori, Takashi Yokota, Yutaka Ishikawa, Shu...
ICCS
2004
Springer
15 years 7 months ago
Using Runtime Measurements and Historical Traces for Acquiring Knowledge in Parallel Applications
Abstract. A new approach for acquiring knowledge of parallel applications regarding resource usage and for searching similarity on workload traces is presented. The main goal is to...
Luciano José Senger, Marcos José San...
HPDC
2006
IEEE
15 years 8 months ago
On the Harmfulness of Redundant Batch Requests
Most parallel computing resources are controlled by batch schedulers that place requests for computation in a queue until access to compute nodes is granted. Queue waiting times a...
Henri Casanova