Rocks Clusters and Object Storage
Recorded: June 27, 2005
Speakers: Steve Jones, Stanford University and Larry Jones, Panasas, Inc
Researchers at Stanford's Institute for Computational and Mathematical Engineering (ICME) use HPC as part of a comprehensive research program. These systems are used to better predict flutter and limit cycle oscillations for modern aircraft, to better understand the impact of turbulent flow on jet engines, and to develop computational methodologies that can be expected to facilitate the design of naval systems with lower signature levels. Their research can lead to improvements in the performance and safety of aircraft, reduction of engine noise, which will improve the quality of life for people living near airports, and new underwater navigation systems.
To accomplish this, ICME needed a cluster to tackle large-scale simulations of flow/structure interaction, aeroacoustic, and elasto-acoustic scattering problems. Join us in discussing how ICME utilized the 164-node Nivation Linux cluster and object-based storage to create a system that is easy to integrate and manage, scalable, and delivers extremely high bandwidth and random I/O.
- Hear the challenges ICME faced in building a cluster capable of handling complex mathematical simulations
- Learn how object storage systems, like those of Panasas, break I/O bottlenecks hindering cluster performance
- Hear Steve Jones' personal experience in managing large scale Rock clusters and the integration of the Panasas ActiveScale Storage Cluster
- Understand how the joint solution helped accelerate time to results
To view the webinar recording, please fill out the information form below.
New WebEx Users
If you have not previously participated in a WebEx event, viewing the presentation online will automatically set up the viewer for you. However if you prefer to download the presentation and view it offline, you will first need to download the WebEx viewer.
Downloading the WebEx viewer
|
 |
|
|
|
|
