March 28, 2013
It has been a noteworthy week in the world of scientific and technical computing as two long-awaited supercomputers have been formally revved up for big research action.
The Dell-Intel scientific workhorse, Stampede, at TACC was ushered into the large-scale distributed research fold yesterday. And at the moment of this writing, the rather storied IBM and then Cray-backed Blue Waters system at NCSA is gearing up for its formal intro.
At the heart of both of these systems is some serious monetary backing from the National Science Foundation (NSF), which has committed several million to seeing both supers into the world—no matter how entangled the path. The organization funded the large majority of both projects in the name of furthering some critical human-centered scientific projects related to the environment, gemonics, disaster preparedness and epidemiology.
We chatted earlier this week with Alan Blatecky who directs the NSF’s Division of Advanced Cyberinfrastrcture about where these supers fit into the overarching mission of the NSF--and what the future looks like as applications require systems that are as "big data" ready as they are computationally robust.
Blatecky reiterated that from an NSF standpoint, these are two major investments in HPC, but they aren't necessarily related in terms of anticipated use or application types. As he told us, the two systems are designed for quite different purposes.
One the one hand, the massive Stampede will cater to a large number of users with an emphasis on boosting the breadth of applications—not to mention extending what those extended apps are able to crunch. Blue Waters, on the other hand, will focus on a much smaller number of users, perhaps as many as a dozen, who have very deep, specific research applications.
While grappling with multiple users across a distributed system like Stampede and its XSEDE base is never simple, there are far more pressing challenges. In addition to pointing to extensive application retooling that needs to happen, especially on Blue Waters, there was one phrase we heard several times--"big data".
The ability to take advantage of the large number of cores on a machine like Blue Waters is one of the biggest challenges user will face, says Blatecky, who points to how his organization is providing support on the programming and computer science front to aid domain specialist scientists. He said that going forward, the systems that will shine for the “big science” endeavors of the NSF will be those that can strike a balance between being data-intensive systems while retaining the computational power of massive numbers of cores, some of which are being pushed by accelerators and co-processors.
As Blatecky detailed, “Our point of view at the NSF is focused on the broader base of scientific users. We’re interested in the data-intensive computational requirements, which is part of what’s unique about Blue Waters. It has that needed balance between power, memory and storage to address both the data-intensive and computationally-intensive applications.”
When asked about the supercomputing goals the NSF wants to support over the next five years, Blatecky said that the real mission is to support a broader group of scientific users, especially those working in hot applications like genomics, materials science and environmental research areas. Most of their plans revolve around socially-oriented missions, including studies to predict earthquakes, flood outcomes, disaster response situations, and medically-driven research on the HIV and epidemic modeling fronts.
We also talked briefly about how HPC as we know it--and the NSF funds it--could change over the next five years. "I don't know what it will be," he noted, but he has no doubt that the performance-driven architectures might not be enough to keep up with the very real data explosion across real science applications unless they strike that memory/storage/power balance that Blue Waters has.
While not all HPC application are necessarily hugely data-intensive, a look down the list of applications reveals some of the highest data volume-driven research areas in science, particularly around medical and earth sciences projects. TACC, for instance, will now be the center of some cutting-edge earthquake, environmental and ecological research as scientists from around the world bring their best and brightest ideas --not to mention an unprecedented level of data--to the common table of the shared resource.
As TACC Director Jay Boisseau stated upon the formal announcement of Stampede yesterday, the system has been “designed to support a large, diverse research community. We are as excited about Stampede's comprehensive capabilities and its high usability as we are of its tremendous performance." On that note, 90% of TACC’s new powerhouse will be dedicated to the XSEDE program, which is a unified virtualized system that lets global scientists tap into powerful systems, new data wells and computational tools through one hub.
TACC will tap into the remaining horsepower for larger goals within its own center and in the University of Texas research community. And there is certainly some power to the system. As TACC described cleanly in their own statement on the specs, the Dell and Intel system boasts the following points of pride:
Stampede system components are connected via a fat-tree, FDR InfiniBand interconnect. One hundred and sixty compute racks house compute nodes with dual, eight-core sockets, and feature the new Intel Xeon Phi coprocessors. Additional racks house login, I/O, big-memory, and general hardware management nodes. Each compute node is provisioned with local storage. A high-speed Lustre file system is backed by 76 I/O servers. Stampede also contains 16 large memory nodes, each with 1 TB of RAM and 32 cores, and 128 standard compute nodes, each with an NVIDIA Kepler K20 GPU, giving users access to large shared-memory computing and remote visualization capabilities, respectively. Users will interact with the system via multiple dedicated login servers, and a suite of high-speed data servers. The cluster resource manager for job submission and scheduling will be SLURM (Simple Linux Utility for Resource Management).
Unlike Stampede, which is expected to make a top 5 showing on the Top 500m Blue Waters will not be benchmarking for reasons NCSA's Bill Kramer explained to us in detail right around SC12. Of course, not that it needs to convince us that it will be a scientific powerhouse..
The Blue Waters saga began back in 2007 when the NSF funded the super to the tune of $208 million. At the time, IBM was at the heart of the project but refunded their payments for Blue Waters system after looking at the cost versus return equation. Cray was later selected to take over the project with a $188 million contract that would lead the super into completion.
In the year since the video below was filmed, work on the system was completed and Blue Waters was installed at NCSA. The 11.6 petaflops (peak) supercomputer contains 237 XE cabinets, each with 24 blade assemblies, and 32 cabinets of the Cray XK6 supercomputer with NVIDIA Tesla GPU computing capability.
Currently available in "friendly-user" mode for NCSA-approved teams, Blue Waters provides sustained performance of 1 petaflop or more on a range of real-world science and engineering applications.
"Blue Waters is an example of a high-risk, high-reward research infrastructure project that will enable NSF to achieve its mission of funding basic research at the frontiers of science," said NSF Acting Director Cora Marrett. "Its impact on science and engineering discoveries and innovation, as well as on national priorities, such as health, safety and well-being, will be extraordinary."
What follows are a few examples of the exciting and promising research on Blue Waters (following provided by the National Science Foundation).
Blue Waters is enabling Klaus Schulten and his team at UIUC to describe the HIV genome and its behavior in minute detail, through computations that require the simulations of more than 60 million atoms. They just published a paper in PLOS Pathogens touting an early discovery--not (yet) the structure of the HIV virus, but that of a smaller virus, which could only be achieved through a 10 million atom, molecular dynamics simulation, inconceivable before Blue Waters. The team is using Blue Waters to investigate complex and fundamental molecular dynamics problems requiring atomic level simulations that are 10 to 100 times larger than those modeled to date, providing unprecedented insights.
Global Climate Change
Also featured at the dedication event, Cristiana Stan and James Kinter of George Mason University are using Blue Waters to engage in topical research on the role of clouds in modeling the global climate system during present conditions and in future climate change scenarios.
A team at the Southern California Earthquake Center, led by Thomas Jordan, is carrying out large-scale, high-resolution earthquake simulations that incorporate the entire Los Angeles basin, including all natural and human-built infrastructure, requiring orders of magnitude more computing power than studies done to date. Their work will provide better seismic hazard assessments and inform safer building codes: Preparing for the Big One.
Flood Assessment, Drought Monitoring, and Resource Management
Engineering Professor Patrick Reed and his team from Penn State, Princeton and the Aerospace Corporation, are using Blue Waters to transform understanding and optimization of space-based Earth science satellite constellation designs. "Blue Waters has fundamentally changed the scale and scope of the questions we can explore," he said. "Our hope is that the answers we discover will enhance flood assessment, drought monitoring, and the management of water resources in large river basins world-wide."
Fundamental Properties of Nature
Robert Sugar, professor of physics at the University of California, Santa Barbara is using Blue Waters to more fully understand the fundamental laws of nature and to glean knowledge of the early development of the universe. "Blue Waters packs a one-two punch," said Sugar, "Blue Waters enables us to perform the most detailed and realistic simulations of sub-atomic particles and their interactions to date. Studies such as these are a global endeavor, and the large data sets produced on Blue Waters will be shared with researchers worldwide for further discoveries."
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?