Eitan Frachtenberg, Fabrizio Petrini, Juan Fernandez, Scott Pakin, and Salvador Coll. STORM: Lightning-fast resource management. In SC '02: Proceedings of the IEEE/ACM SC2002. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Parallel Job Scheduling Under Dynamic Workloads - Eitan Frachtenberg Dror (2003) (1 citation) Self-citation (Frachtenberg Petrini Fernandez) (Correct)
No context found.
Eitan Frachtenberg, Fabrizio Petrini, Juan Fernandez, Scott Pakin, and Salvador Coll. STORM: Lightning-fast resource management. In Supercomputing 2002.
Scalable Collective Communication on the ASCI Q Machine - Fabrizio Petrini Juan (2003) (1 citation) Self-citation (Frachtenberg Petrini Fernandez Coll) (Correct)
No context found.
E. Frachtenberg, F. Petrini, J. Fernandez, S. Pakin, and S. Coll. STORM: Lightning-Fast Resource Management. In Proceedings of IEEE/ACM Supercomputing 2002.
Flexible CoScheduling: Mitigating Load Imbalance.. - Frachtenberg.. (2003) (3 citations) Self-citation (Frachtenberg Petrini Fernandez) (Correct)
....mode. But this can block other jobs. The proposed scheduler will prevent each job from wasting too many system resources, and the overall system efficiency and responsiveness will be improved. We demonstrate this methodology with a streamlined implementation on a resource manager, called STORM [6]. The key innovation behind STORM is a software architecture that enables resource management to exploit low level network features. As a consequence of this design, STORM can enact scheduling decisions, such as a global context switch or a heartbeat, in a few hundreds of microseconds across ....
....The main motivation behind FCS is the improvement of overall system performance in the presence of heterogeneous hardware or software, by using dynamic measurement of applications communication patterns and classification of applications into distinct types. FCS is implemented on top of STORM [6], which allows both for global synchronization through scalable global context switch messages (heartbeats) and local scheduling by a daemon run on every node, based on their locally collected information. 2.1. Process Classification FCS employs dynamic process classification and schedules ....
[Article contains additional citation context not shown here]
E. Frachtenberg, F. Petrini, J. Fernandez, S. Pakin, and S. Coll, "STORM: Lightning-Fast Resource Management ". In Supercomputing 2002.
Flexible CoScheduling: Mitigating Load Imbalance.. - Frachtenberg.. (2002) (3 citations) Self-citation (Frachtenberg Petrini Fernandez) (Correct)
....mode. But this can block other jobs. The proposed scheduler will prevent each job from wasting too many system resources, and the overall system efficiency and responsiveness will be improved. We demonstrate this methodology with a streamlined implementation on a resource manager, called STORM [5]. The key innovation behind STORM is a software architecture that enables resource management to exploit low level network features. As a consequence of this design STORM can enact scheduling decisions, such as a global context switch or a heartbeat, in a few hundreds of microseconds across ....
....by using dynamic measurement of applications communication patterns and classification of applications into distinct types. The scheduler can then make better local scheduling decisions based on the class information of different processes and applications. FCS is implemented on top of STORM [5], which allows both for global synchronization through scalable global context switch messages (heartbeats) and local scheduling by a daemon run on every node, based on their locally collected information. 2.1. Process Classification FCS employs dynamic process classification and schedules ....
[Article contains additional citation context not shown here]
Eitan Frachtenberg, Fabrizio Petrini, Juan Fernandez, Scott Pakin, and Salvador Coll. STORM: Lightning-Fast Resource Management. In Supercomputing 2002.
Flexible CoScheduling: Dealing with Load Imbalance .. - Frachtenberg.. Self-citation (Frachtenberg Petrini Fernandez) (Correct)
....mode. But this can block other jobs. The proposed scheduler will prevent each job from wasting too many system resources, and the overall system efficiency and responsiveness will be improved. We demonstrate this methodology with a streamlined implementation on a resource manager, called STORM [5]. The key innovation behind STORM is a software architecture that enables resource management to exploit low level network features. As a consequence of this design STORM can enact scheduling decisions, such as a global context switch or a heartbeat, in a few hundreds of microseconds across ....
....by using dynamic measurement of applications communication patterns and classification of applications to distinct types. The scheduler can then make better local scheduling decisions based on the class information of different processes and applications. FCS is implemented on top of STORM [5], which allows both for global synchronization through scalable global context switch messages (heartbeats) and local scheduling by a daemon run on every node, based on their locally collected information. 2.1. Process Classification FCS employs dynamic process classification and schedules ....
[Article contains additional citation context not shown here]
Eitan Frachtenberg, Fabrizio Petrini, Juan Fernandez, Scott Pakin, and Salvador Coll. STORM: Lightning-Fast Resource Management. In Supercomputing 2002.
Developing Custom Firmware for the Red Storm - Seastar Network Interface (Correct)
No context found.
Eitan Frachtenberg, Fabrizio Petrini, Juan Fernandez, Scott Pakin, and Salvador Coll. STORM: Lightning-fast resource management. In SC '02: Proceedings of the IEEE/ACM SC2002.
Fast Scalable File Distribution Over Infiniband* - Dennis Dalessand Ro (Correct)
No context found.
E. Frachtenberg, F. Petrini, J. Fernandez , S. Pakin, S. Coll. STORM: Lightning - Fast Resource Managemen t . In Proceedingsof the IEEE/ACM SC2002 Conference, 2002. B. Callaghan , B. Pawlowski, P. Staubach. NFS Version 3 Protocol Specification. June 1995 available via http: / / www . cse.ohio - sta t e.edu / cg i - bin / rfc / rfc1813 . h t m l .
Parallel Job Scheduling - A Status Report - Feitelson, Rudolph, al. (2004) (1 citation) (Correct)
No context found.
E. Frachtenberg, F. Petrini, J. Fernandez, S. Pakin, and S. Coll, "STORM: lightning-fast resource management ". In Supercomputing, Nov 2002.
Efficient and Scalable Barrier over Quadrics and Myrinet - With New Nic-Based (2004) (Correct)
No context found.
E. Frachtenberg, F. Petrini, J. Fernandez, S. Pakin, and S. Coll. STORM: Lightning-Fast Resource Management. In Proceedings of the Supercomputing '02, Baltimore, MD, November 2002.
SLURM: Simple Linux Utility for Resource Management - Jette, Yoo, Grondona (2002) (2 citations) (Correct)
No context found.
E. Frachtenberg, F. Petrini, et al. Storm: Lightning-fast resource management. In Proceedings of SuperComputing, 2002.
The Supercomputer Industry in Light of the Top500 Data - Feitelson (Correct)
No context found.
E. Frachtenberg, F. Petrini, J. Fernandez, S. Pakin, and S. Coll, "STORM: lightningfast resource management ". In SC2002.
SLURM: Simple Linux Utility for Resource Management - Morris Jette And (2002) (2 citations) (Correct)
No context found.
Frachtenberg, E., et al.: STORM: Lightning-Fast Resource Management. In: Proceedings of SuperComputing 2002, Baltimore, MD (2002) Available from http://www.cs.huji.ac.il/ etcs/papers/sc02.pdf.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC