The SuperComputing Conference 2010 was held in New Orleans, Louisiana (USA) this year. Caltech Booth showed different network centric and data intensive transfer demonstrations to the visiting researchers.
An international team of physicists, computer scientists, and network engineers led by the California Institute of Technology (Caltech) and partners from the University of Michigan, Fermilab, Brookhaven National Laboratory, CERN, San Diego (UCSD), Florida (UF and FIU), Brazil (Rio de Janeiro State University, UERJ, and State Universities of São Paulo, USP), Korea (Kyungpook National University, KISTI) and Estonia (NICPB), joined forces for a collaborative and effective massive data transfers during the SuperComputing 2010 (SC10) conference, more details
DYNES Collaborative Demonstration
DYNES is a nationwide cyber-instrument spanning approx 40 US universities and 14 Internet2 connectors. DYNES team includes Internet2, Caltech, Univ of Michigan and Vanderbilt Univ. During SC2010, Caltech, Internet2 and Vanderbilt demonstrated how DYNES Instrument can be quickly deployed among different participants. DYNES data transfer is based on Caltech’s FDT based circuit initiation and data transfer software and was successfully tested during the SC2010 and demonstrated through MonALISA monitoring platform, more details
40GE Network Demonstration
Caltech HEP team started testing the 40GE NICs from Mellanox before SC10, a detailed presentation on the 40GE network testing with results is available for download.
Force10 Networks released their first 40GE 1U top of the rack switch just before SC2010, Caltech received the switch with pre-alpha version however the testing was very successful (100% port utilization) with 4 10GE links going over the 100GE Internet2LONI-StarLight, more details
GLIF / GOLE Demonstration
The Global Lambda Integrated Facility (GLIF) community successfully demonstrated a pilot implementation of an automated multi-domain lightpath provisioning system during SC10. Caltech Tier2 had a perfSONAR node installed which was accessible to other participants via the Fenius path creation tool for different domains. USLHCNet provided dynamic Vlans between StarLight-MANLAN, StarLight-CERNLight and MANLAN-StarLight, more details
New Records in 2009
The focus of SC09 exhibit was the HEP team’s record-breaking demonstration of storage-to-storage data transfer over wide area networks from two racks of servers and a network switch-router on the exhibit floor. The high-energy physics team’s demonstration “Moving Towards Terabit/sec Transfers of Scientific Datasets: The LHC Challenge” achieved a bi-directional peak throughput of 119 gigabits per second (Gbps) and a data flow of more than 110 Gbps that could be sustained indefinitely among clusters of servers on the show floor and at Caltech, Michigan, San Diego, Florida, Fermilab, Brookhaven, CERN, Brazil, Korea, and Estonia.
Following the Bandwidth Challenge the team continued its tests and demonstrated a world-record data transfer between the Northern and Southern hemispheres, sustaining 8.26 Gbps on each of two 10 Gbps links linking São Paulo and Miami.
In 2008, High Energy Physicists Created Record for Network Data Transfer
110 Gbps Sustained Rates Among Storage Systems Over Wide Area Networks, and 200 Gbps Metro Data Rates on Next Generation Optical Links, Set New Standards for Networks and Computing Clusters
This work is made possible by the strong support of the
US Department of Energy Office of Science and the National Science Foundation.