SC16: INDIS Workshop

"Innovating the Network for Data Intensive Science (INDIS)"

homehttp://sne.science.uva.nl/
http://uva.nl/

The 3nd International Workshop on Innovating the Network for Data Intensive Science (INDIS) 2016, in conjunction with SC16: IEEE/ACM International Conference for High Performance Computing, Networking, Storage and Analysis, in Salt Lake City, Utah, on November 13, 2016, 9h00 17h00.

Workshop website: https://scinet.supercomputing.org/workshop/node/8

Workshop Scope:

Science is making the transition from Data-poor to Data-rich. Where in the past only limited experimental data was compared to big amounts of simulation-generated data at Supercomputing centers, we now see those centers transform into big data stream processing nodes. Wide area networks are now an integral and essential part of the data driven Supercomputing ecosystem connecting information-sources, data-stores, processing, simulation, and visualization and user communities together. Further networks are required to connect research instruments such as photon sources, and large visualization displays.

Networks for data-intensive science have more extreme requirements than general-purpose networks.  These requirements closely impact the design of processor interconnects in supercomputers/cluster computers, but they also impact campus networks, regional networks and national backbone networks.

The developments in network technology are tremendous. Speeds of many 100s of Gigabit and deep programmability of network infrastructure are now common. This enables a fundamentally different approach of integrating networks in Supercomputing applications.

This workshop encourages research papers that address one or more of these needs that are essential in the scientific discovery process. This workshop will also serve as a platform for participants in SCinet to present experimental papers on their latest designs and solutions. SCinet is the high-speed network engine of the SC conference. This network is state of the art, connects many demonstrators of big science data processing infrastructures at the highest line speeds, deploys the newest technologies available, and demonstrates novel functionality. The show floor network connects to many laboratories and universities worldwide using high-bandwidth connections.

This workshop brings together SCinet engineers and network researchers to share challenges and potential solutions. Their novel ideas will allow future SCinets to stretch their deployed technologies and further drive new network research. We invite papers that propose new and novel techniques that increase the capacity and functionality of scientific computing and wide-area networks.

Program:

Time Title Speaker(s) Chair
09:00 Welcome Cees de Laat (lead INDIS, UvA)
Brian Tierney (lead NRE, LBNL)
de Laat/Tierney
09:01
09:05
Introduction SCinet
SCinet Architecture
Corby Schmitz (Chair SCinet, ANL)
Marc Lyonnais (lead SCinet Architecture, CIENA),
Nick Buraglio (NRE team member, ESnet)
de Laat/Tierney
09:20
NRE Themes presentations
Applications - Joe Mambretti
Architecture - Joaquin Chung
Control Plane - Gerben van Malenstein
DATA - Harvey Newman
Monitoring - Yan Luo
Security - Jordi Ros-Giralt
Tierney
09:40
SCinet innovation panel led by Cees de Laat Joe Mambretti, Joaquin Chung, Gerben van Malenstein,
Harvey Newman, Yan Luo, Jordi Ros-Giralt
de Laat/Tierney
10:00
Coffee break

10:30 Keynote 1: SDN futures, virtualisation, predictable performance Yatish Kumar (Corsa) de Laat
11:00 TechTalk 1: TCP tuning Brian Tierney (LBNL) de Laat/Tierney
11:20
P1: High-Performance Virtualized SDN Switches for Experimental Network Testbeds Richard Cziva; Jerry Sobieski; Yatish Kumar de Laat/Tierney
11:40
TechTalk 2: Towards Terabit data distribution.
Harvey Newman (CALTECH) de Laat/Tierney
12:00
P2: Network Measurement for 100Gbps Links Using Multicore Processors
Xiaoban Wu; Peilong Li, PhD; Yongyi Ran, PhD; Yan Luo, PhD de Laat/Tierney
12:20 Lunch

13:30 Welcome, overview, state of the union Paola Grosso & Malathi Veeraraghavan
13:40 P3: Advance Reservation Access Control Using Software-Defined Networking and Tokens
Joaquin Chung, MSc.; Eun-Sung Jung; Rajkumar Kettimuthu; Nageswara Rao; Ian Foster; Russ Clark; Henry Owen Grosso/Veeraraghavan
14:00 P4: Energy-Efficient Data Transfers in Radio Astronomy with Software UDP RDMA Przemyslaw Lenkiewicz, Ph.D.; P. Chris Broekema; Bernard Metzler, Ph.D. Grosso/Veeraraghavan
14:20 P5: Enabling Intent to Configure Scientific Networks for High Performance Demands
Mariam Kiran; Eric Pouyoul; Anu Mercian; Brian Tierney; Chin Guok; Inder Monga
Grosso/Veeraraghavan
14:40 P6: mdtmFTP and Its Evaluation on ESNET SDN Testbed Liang Zhang, Ph.D.; Wenji Wu, Ph.D.; Phil Demar; Eric Pouyoul Grosso/Veeraraghavan
15:00 Tea break

15:30 Keynote 2: Transforming Research & Education Through Unusual Collaborations Dr. Wang, Kuang-Ching (U-Clemson) Grosso/Veeraraghavan
16:00 P7: SDN-managed Network Architecture for GridFTP Transfers
Deepak Nadig Anantha; Zhe Zhang; Byrav Ramamurthy, PhD; Brian Bockelman, PhD; Garhan Attebury; David Swanson, PhD Grosso/Veeraraghavan
16:20 P8: Maximizing the Performance of Scientific Data Transfer by Optimizing the Interface Between Parallel File Systems and Advanced Research Networks Nicholas Lombard Mills; Frank A Feltus, Ph.D.; Walter B Ligon III, Ph.D. Grosso/Veeraraghavan
16:40 P9: CoreFlow: Enriching Bro security events using network traffic monitoring data Ralph Koning; Nick Buraglio; Cees de Laat; Paola Grosso Grosso/Veeraraghavan
17:00 P10: Towards Bridging the Gap between Peak and Average Loads on Science Networks Sam Nickolay; Eun-Sung Jung; Rajkumar Kettimuthu; Ian Foster Grosso/Veeraraghavan
17:20 Wrap-up and conclusion Paola Grosso & Malathi Veeraraghavan
17:30 End


Workshop Organizers:

  • Cees de Laat: Professor System and Network Engineering, University of Amsterdam, The Netherlands.
  • Brian L. Tierney: Staff Scientist and Group Leader of the ESnet Advanced Network Technologies Group at Lawrence Berkeley National Laboratory.
  • Paola Grosso: Assistant professor in the System and Network Engineering (SNE) group at the University of Amsterdam, The Netherlands.
  • Malathi Veeraraghavan: Professor, Charles L. Brown Dept. of Electrical and Computer Engineering, and Associate Director, Infrastructure and Services, Data Science Institute, University of Virginia.

Liaisons:

  • Mehmet Balman: Liaison to the NDM committee, VMware Inc. & Lawrence Berkeley National Laboratory, USA.
  • Sylvia Kuijpers: Liaison to communications, SURFnet, The Netherlands, SCinet team-member INDIS.

Program Committee:

  • Pavan Balaji, Argonne National Laboratory and Northwestern University, USA
  • Mehmet Balman, VMware Inc. & Lawrence Berkeley National Laboratory, USA
  • Virginia Bedford, US Army Corps of Engineers, USA
  • Surendra Byna, Lawrence Berkeley National Laboratory, USA
  • Jerry Chou, National Tsing Hua University, Taiwan
  • Zhihui Du, Tsinghua University, China
  • Kartik Gopalan, State University of New York at Binghamton, USA
  • Paola Grosso, University of Amsterdam, The Netherlands.
  • Zhiyi Huang, University of Otago, New Zealand
  • Raj Kettimuthu, Argonne National Laboratory and University of Chicago, USA
  • Cees de Laat, University of Amsterdam, The Netherlands.
  • Jinoh Kim, Texas A&M University-Commerce, USA
  • Siva Kulasekaran, Texas Advanced Computing Center, USA
  • Kate Mace, ESnet, USA
  • Manish Parashar, Rutgers University, USA
  • Eric Pouyoul, Energy Sciences Network and Lawrence Berkeley Lab, USA
  • Corby Schmitz, Argonne National Lab/ Loyola University, Chicago, USA
  • Jennifer Schopf, Indiana University, USA
  • Martin Swany, Indiana University, USA
  • Brian L. Tierney, ESnet, Lawrence Berkeley National Laboratory, USA
  • Malathi Veeraraghavan, University of Virginia, USA
  • Venkat Vishwanath, Argonne National Laboratory, USA
  • Linda Winkler, Arogonne National Lab
  • Wenji Wu, Fermilab, USA
  • Lei Xia, LinkedIn, USA
  • Esma Yildirim, Fatih University, Turkey
  • Yufei Ren,  IBM, Watson, USA
  • Matthew J Zekauskas: Senior researcher, Internet2, USA
*** Please forward to anyone who might be interested ***