Visit additional Tabor Communication Publications
February 18, 2009
Canada's High Performance Computing Virtual Laboratory (HPCVL) is a virtual HPC organization spread out over the campuses of eight universities in Ontario. Fully half of the Laboratory's $200 million (CAD) 10-year budget is provided by investments from its industrial partner, Sun. HPCwire spoke with the HPCVL's executive director, Ken Edgecombe about the HPCVL, what it does, and why Sun is so committed to making this effort a success.
The HPCVL is spread out over eight campuses in Ontario, Canada -- Carleton University, Queen's University, The Royal Military College of Canada, the University of Ottawa, Ryerson University, St. Lawrence College, Seneca College, and Loyalist College -- and provides services and expertise to over 800 Canadian researchers using a collection of high end servers and storage from Sun Microsystems.
The HPCVL provides computational services for a fairly traditional set of HPC applications, including everything from biomedical research to computational fluid dynamics. The center has a staff of 13, including 4 who provide user support and education and also assistance with applications. Each user group pays an access fee of $2,000 (CAD) that helps the organization defray unexpected expenses, but they aren't required to pay for the computational hours they consume (or bytes stored). This model helps ensure that those who need the HPCVL's resources to drive their research forward can afford the resources they need.
One of the key tasks for the laboratory's staff is to match users and their applications to a particular set of resources in HPCVL's hardware offering. The HPCVL has a cluster of 8 Sun SPARC Enterprise M9000 servers, each with 64 quad-core 2.52 GHz Sparc64 VII processors supporting two hardware threads per core, for compute intensive jobs with large memory requirements. There is also a cluster of 7 Sun Fire 25000 servers, each of which has 72 dual-core UltraSPARC-IV+ processors, aimed at a similar (but perhaps less demanding) workload. HPCVL's Victoria Falls cluster is built from 73 Sun SPARC Enterprise T5140 Servers, each of which has two UltraSparc T2 chips with 8 cores apiece, each supporting 8 hardware threads. At full capacity this cluster can support just over 9,300 threads, and the system provides a throughput compute platform for HPCVL's users. All of the systems use Sun's Grid Engine workload management tool, and run Solaris.
Something that struck me as unusual for an academic computer center is HPCVL's focus on security. Their Web page calls it "one of Canada's leading secure HPC environments," and Edgecombe referred to security issues several times in the first few minutes of our conversation. Why the focus on security, when university compute environments are typically thought of as a little more relaxed? Edgecombe explains that when the laboratory was started, a key goal was to grow HPC use among non-traditional users. One of the groups they targeted was medical and pharmaceutical industry researchers, who in addition to having regulatory issues around data preservation and protection, also have serious concerns about the protection of intellectual property. "And the integrity of the data itself is a core issue for every researcher," Edgecombe points out.
Although it is comprised of many individual institutions, the HPCVL is a center of Queens University, which provides a funding channel for the organization. The laboratory is funded by grants from a variety of public institutions, including the Canada Foundation for Innovation and the Ontario Ministry of Research and Innovation. Its relationship with Sun forms the private part of this public/private partnership. Edgecombe says that the laboratory's 10-year budget is $200 million (CAD), and fully half of that comes from Sun in the form of funding and in kind donations.
So, just why is Sun so committed to the work that the HPCVL is doing? I talked with Sun's Michael Schulman, who is in charge of HPC marketing, to get a better feel for how relationships like these fit in with Sun's strategy.
Schulman points out that Sun has traditionally had strong relationships with the academic community, pointing to TACC and the Tokyo Institute of Technology as other current examples. For Sun, these academic environments are often great places to find what Schulman calls "launch partners" -- customers willing to accept the very first instance of new gear to help Sun flush out the kinks. According to Schulman, TACC's Ranger incorporated five new technologies, and both Tokyo Tech and HPCVL have also deployed first-of-its-kind Sun technology.
Schulman says that Sun lets these relationships develop organically, rather than building them on a specific schedule or quota. In HPCVL's case, Edgecombe has long been a customer of Sun, and Sun's relationship with the organization has grown over time. Of particular advantage for Sun in HPCVL's case is that the lab has deployed Sun's chip multithreading products for traditional HPC at a time when most in the market are going x86-64. This difference gives Sun the opportunity to evaluate the performance of these products on the wide variety of applications that HPCVL's users are running, and then bring that feedback back into the design process.
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
May 15, 2013 |
Supercomputers at the Department of Energy’s National Energy Research Scientific Computing Center (NERSC) have worked on important computational problems such as collapse of the atomic state, the optimization of chemical catalysts, and now modeling popping bubbles.
May 10, 2013 |
Program provides cash awards up to $10,000 for the best open-source end-user applications deployed on 100G network.
May 09, 2013 |
The Japanese government has revealed its plans to best its previous K Computer efforts with what they hope will be the first exascale system...
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
In this demonstration of SGI DMF ZeroWatt disk solution, Dr. Eng Lim Goh, SGI CTO, discusses a function of SGI DMF software to reduce costs and power consumption in an exascale (Big Data) storage datacenter.
The Cray CS300-AC cluster supercomputer offers energy efficient, air-cooled design based on modular, industry-standard platforms featuring the latest processor and network technologies and a wide range of datacenter cooling requirements.