InTheLoop | 11.04.2013
ESnet’s Greg Bell Talks About Software-Defined Networking and Why It Matters
On the heels of a recent demonstration project, ESnet Director Greg Bell was interviewed about software-defined networking, or SDN. SDN is an emerging field that makes it easier for software applications to automatically configure and control the various layers of the network. ESnet has been conducting localized tests to innovate, experiment and demonstrate the value of SDN when applied towards end-to-end support of data-intensive science collaborations and applications. At a meeting in Germany last month, a successful demonstration of multi-layer networking using SDN technologies was announced by ESnet and networking vendors Infinera and Brocade. The demonstration shows how SDN can be used to automatically provision services and optimize network resources, such as dynamically increasing or rerouting data center to data center interconnect bandwidth services, across a multi-layer network as traffic demands change. ESnet, Infinera and Brocade will conduct an online demo of the technologies on Friday, Nov. 22, on SDNCentral.com. As a lead-in to that demo, SDNCentral’s Ray Chua interviewed Bell. Read the interview.
Reminder: MATLAB’s Cleve Moler to Launch CS Distinguished Lecture Series Nov. 13
Computing Sciences is launching a Distinguished Lecturer Series, which will feature noted researchers. The first talk will be given by Cleve Moler at 2 p.m. Wednesday, Nov. 13, in the Bldg. 50 Auditorium. Moler is the creator of MATLAB and a cofounder of MathWorks., where he is currently chairman and chief mathematician of the company.
In his talk, Moler will show how MATLAB has evolved over more than 30 years from a simple matrix calculator to a powerful technical computing environment. He will demonstrate several examples of MATLAB applications, then conclude with a discussion of current developments, including Parallel MATLAB for multicore and multicomputer systems.
CS Staff to Share Expertise in Seven SC13 Tutorials
At the SC13 conference to be held Nov. 17-22 in Denver, computing and networking experts from NERSC, CRD and ESnet will share their expertise and experience in seven tutorials:
Sunday, Nov. 17
Globus Online and the Science DMZ as Scalable Research Data Management Infrastructure for HPC Facilities
Berkeley Lab Presenters: Eli Dart, ESnet, and David Skinner, NERSC
Berkeley Lab Presenter: Eric Roman, CRD
Monday, Nov. 18
Berkeley Lab Presenters: Yili Zheng, CRD, and Kathy Yelick, CS
Presenter: Jason Zurawski, ESnet
Berkeley Lab Presenter: Alice Koniges, NERSC
Berkeley Lab Presenter: Katie Antypas, NERSC
Berkeley Lab Presenters: Hank Childs and Harinarayan Krishnan, CRD
(Note: Not all presenters listed—only those from LBNL)
This Week’s Computing Sciences Seminar
(Open) MPI, Parallel Computing, the Universe, and Everything
Thursday, November 7, 2:30 – 3:30 p.m., Bldg. 54, Room 130 (Perseverance Hall)
Jeffrey M. Squyres, Cisco
Abstract: Open MPI is a high performance, open source implementation of the MPI specification (BSD license FTW!). It is developed by a consortium of academic, research, and industry partners. This talk will discuss the current status of Open MPI, including some of its more advanced features, such as the new MPI-3 "MPI-T" control and performance variables, and the new, highly-flexible, user-specified process affinity system. This talk will also briefly discuss the ongoing work of expanding and evolving MPI by the MPI Forum.
Note: Stay after the feature talk for a deep dive into Cisco's new ultra low latency MPI transport for Ethernet. Topics will include how the Cisco "usNIC" (userspace NIC) device uses SR-IOV to effect OS-bypass, how it is exposed to userspace via the Linux Verbs API, and some novel issues that arose while integrating the usNIC device into Open MPI.
Link of the Week: Is Science Self-Correcting? Reproducibility, False Positives and More
According to a recent article in the Economist, “Academic scientists readily acknowledge that they often get things wrong. But they also hold fast to the idea that these errors get corrected over time as other scientists try to take the work further. Evidence that many more dodgy results are published than are subsequently corrected or withdrawn calls that much-vaunted capacity for self-correction into question. There are errors in a lot more of the scientific papers being published, written about and acted on than anyone would normally suppose, or like to think.” Read the full story.