VizWorld.com

One of the winners at this summer’s SciDAC Visualization Night was an impressive visualization of a massive 8.0 earthquake on the San Andreas fault.

The simulation follows the rapid expansion of an earthquake wave front on the San Andreas fault as it approaches the city of San Diego. The strongest motions correspond to a white color and the weakest, a red color, with the ground motion magnitude represented as a height field.

The simulation took almost a quarter-million cores of Jaguar and Kraken (both NSF machines at ORNL), and shows the leading edge of the shock front.

via Riding that wave | iSGTW.

Science earthquake, ornl, scidac, visualization

High-end rendering is becoming more and more popular amongst visualization scientists thanks to it’s ability to enhance the visualization with depth cues like shadows, smooth shading, and nice reflection and refraction effects.  Where I work we use Autodesk 3dsMax and Mental Ray to render our stuff (as evidenced in previous posts), but an article on BlenderNation covers how the folks at Oak Ridge use Blender.

So a very typical render would be to generate 60 seconds of animation at 24 frames per second for 1440 frames. I’d take 128 nodes of roughly 16 cores each ( 2048 cores ) – I’d get back 3 x 128 frames every hour so in less than 4 hours – I’d have 1 minute of HD animation. So it is possible to generate 60-90 second clips in a night without requiring a lot of resources ( compared to what we have anyway ). However, from the number of nodes we have you can see that we could render many minutes of video in less than 30 minutes if we needed to do it.

Our process is very similar, although we have a dedicated Windows cluster for this purpose (3dsMax won’t run on Linux).   While this is good and all, what I’ld really like to see is an MPI-aware version of a tool like this.  Mental Ray has a distributed rendering feature which works up to a few nodes, and even POV-Ray has an unofficial MPI build.  If only Blender would incorporate a true MPI-aware rendersystem, it would be a huge boon to some of the larger datasets we find ourselves dealing with.

via Oak Ridge National Laboratory: Blender on a Supercomputer! | BlenderNation.

Graphics blender, ornl

ORNL is making a play to take back the #1 spot on the Top 500 with another upgrade to their Jaguar frankenputer, I mean supercomputer.  Already part Cray XT4 and part XT5, the new “wing” will be XK6 systems running with NVidia GPU’s.  The initial parts will be Tesla M2090′s, but then later parts will be based on the new Kepler design.  The final system is designed to hold 18,000 GPU’s.

“Oak Ridge’s decision to base Titan on Tesla GPUs underscores the growing belief that GPU-based heterogeneous computing is the best approach to reach exascale computing levels within the next decade,” said Steve Scott, chief technology officer of Tesla products at NVIDIA, referring to computing performance levels of 1,000 petaflops. ”The Tesla GPUs will provide over 85 percent of the peak performance of Titan. You simply can’t get this level of performance in a power- and cost-efficient way with CPUs alone.”

I’ve personally come to believe that adding GPU’s to HPC’s is a short-term solution to a bigger problem.  Until we can come up with some operating systems and better tools for programming these behemoths, the major hindrance will be the development cycle.

via Oak Ridge National Lab Turns to NVIDIA Tesla GPUs to Deploy World’s Leading Supercomputer – NVIDIA Newsroom.

Hardware cray, hpc, nvidia, ornl

Power outages are a standard part of natural disasters, be it earthquakes, hurricanes, or just accidental outages.  New technology called “VERDE”, which stands for Visualizing Energy Resources Dynamically on Earth, merges information from dozens of electrical utility companies into a Google Earth mashup.  The result is a realtime dashboard of the US power grid status.

The visualization program was built after the major Northeast blackout in August 2003, when emergency operations centers got their information secondhand from a panel of eight television screens—one for each major network. “Nobody even knew what was going on the next utility over,” says Budhendra Bhaduri, leader of the Geographic Information Science and Technology group at Oak Ridge, which develops data-mining-based information systems.

via Grid Visualization Efforts Helped Heal After Hurricane – IEEE Spectrum.

Graphics google earth, ornl, power

This Weekend, ORNL’s Phil Andrews passed away of a sudden and unexpected heart attack.  Phil Andrews worked at both UT and ORNL in the leadership of the NICS, including the NSF funded Kraken Supercomputer.

During his career at NICS, the supercomputing centers at San Diego and Pittsburgh and at GA Technologies in San Diego, he authored approximately 40 papers on grid and data intensive computing, documentation and visualization techniques, theoretical plasma physics and nonlinear dynamics. Andrews was involved in high performance computing for more than 30 years in management, software development and as a user. He had a doctorate in theoretical physics from Princeton University, an M.A. from Purdue University and a B.A. in applied mathematics from Cambridge University, England.

via UT and ORNL Communities Mourn the Passing of NICS Project Director | Tennessee Today.

Science hpc, obituary, ornl

A veritable alphabet soup of agencies including University of Tennessee (UT)’s National Institute for Computational Science (NICS), Lawrence Berkeley National Lab (LBNL)’s Computational Research Division (CRD), Oak Ridge National Lab (ORNL), the University of Illinois’ National Center for Supercomputing Applications (NCSA), and the University of Wisconsin at Madison (whew), are collaborating on a new endeavor called the Remote Data Analysis and Visualization (RDAV) Center. When complete, the center will provide remote visualization, image generation, statistical analysis, and a variety of other services to users, making it a leading center for developing new technology and capabilities for researchers.

“Our team of experts has been providing these scientific visualization services to thousands of researchers around the globe for decades, as part of the Department of Energy’s NERSC Analytics and CRD visualization programs. Our experience and track record in this space made us the best qualified to lead this part of the RDAV effort,” says Wes Bethel, who heads the Berkeley Lab’s Scientific Visualization Group in CRD. Bethel will also be coordinating the Berkeley Lab’s contribution to the RDAV center.

You can read more about the RDAV Center at their website.  RDAV will primarily be offered to existing users of the NSF’s TeraGrid project, but hopefully their technology and research will eventually bring Remote Visualization to larger markets.

via Berkeley Lab Researchers Help Establish Next Generation Data Analysis Center.

Science ncsa, ornl, rdav, ut

Remember a few weeks ago, the nasty rumor that Oak Ridge decided to kill the Fermi-based supercomputer they were buying?  The rumor was quickly debunked by both NVidia and ORNL, but after several weeks of digging deep, BSN found out that there is a tiny grain of substance behind the rumor, and it all comes down to George Bush’s Executive Order 13423 and inter-lab rivalries.

Just like police cars started to use Ethanol fuel, the world of governmental supercomputing laboratories had to change their approach. EO 13423 mandates that every new governmental project, including ORNL has to have 10% of their power grown from natural resources. You might guess where this is heading – the problem that ORNL has might significantly limit their future expansion, since the closest natural resource is none . other but the Mississippi river and the Southwest Power Pool As we all know, Oak Ridge is some 450 miles away – not exactly feasible to draw the power lines across states [one of our sources did state that new power lines would actually do good, given the state of power infrastructure around United States].

As the new computer is projected to consume 60,000 MWh (60 GWh?) annually, that makes 6000MWh’s that must come from renewable resources or 14,000 Metric Tons in Carbon Credits, which would put the electrical bill in the $8-10 Million annually.

The other solution is to work out a deal with one of the other similar labs, Sandia and LLNL come to mind, to “trade” credits.  Unfortunatey, both labs seem to be holding out for a ‘better’ deal in their favor.

Now, I’m rather uncertain about all of this.  ORNL already gets most of their power from TVA, and a Hydro dam is relatively close (5 miles?) to ORNL.  Wouldn’t that be considered renewable? BSN has the full scoop, read it there.  My sources are unable to corroborate everything in the article, but they do confirm it’s a possible explanation.

via The Real Story behind Fermi & Oak Ridge: Bushes’ legacy threatens progress? – Bright Side Of News*.

Hardware, Science fermi, hpc, nvidia, ornl

Do you remember the story we posted, ORNL Looks to NVidia GT300 for next Super, back on September 30th? Well, according to SemiAccurate.com, the project was killed since Fermi consumes too much power. However, Legit Reviews contacted several people at NVidia and ORNL who all say that the rumor is false.

Read the original rumor at: Oak Ridge cans Nvidia based Fermi supercomputer

Read the rebuttal at: False Rumor – Oak Ridge Cancels NVIDIA Fermi Based Supercomputer!

Graphics fermi, gpgpu, nvidia, ornl, rumor

The age of GPU-computing got another huge boost today as a press release from NVidia shows that their new GT300 “Fermi” chip is more than vaporware and will, in fact, be the foundation of Oak Ridge’s newest supercomputer.

Jeff Nichols, ORNL associate lab director for Computing and Computational Sciences, joined NVIDIA co-founder and CEO Jen-Hsun Huang on stage during his keynote at NVIDIA’s GPU Technology Conference.  (…)

“This would be the first co-processing architecture that Oak Ridge has deployed for open science, and we are extremely excited about the opportunities it creates to solve huge scientific challenges,” Nichols said. “With the help of NVIDIA technology, Oak Ridge proposes to create a computing platform that will deliver exascale computing within ten years.”

I don’t think this has anything to do with ORNL & UT’s latest announcement of their “Nautilus” NSF-funded machine.  There’s currently no real specs for what this new hybrid supercomputer will be, but they promise exascale compute-capabilities.  Read the full announcement after the break.

Read more…

Hardware, Science fermi, gpgpu, gt300, hpc, nvidia, ornl

Hot on the heels of the TACC announcement, University of Tennessee’s National Institute for Computational Science (NICS) have announced they will receive $10M from the NSF over the next 4 years to build a new “Center for Remote Data Analysis & Visualization (RDAV)”.  Just like TACC, first order of business in a new machine:

Much of RDAV will rely on a new machine named Nautilus that employs the SGI shared-memory processing architecture. The machine will feature 1,024 cores, 4,096 gigabytes of memory, and 16 graphics processing units. The new SGI system can independently scale processor count, memory, and I/O to very large levels in a single system running standard Linux. This flexibility will allow the RDAV team to configure a system uniquely capable of analyzing and visualizing petascale data sets, promising TeraGrid users new levels of scientific understanding.

And this impressive quote from Sean Ahern, research associate professor at the University of Tennesse and visualization task lead at ORNL where the machine will sit:

“I believe this will be the largest shared-memory machine for analysis on the planet,” said the project’s Principal Investigator (PI) Sean Ahern, who is currently the visualization task lead at ORNL and will serve as director of RDAV. “No one has ever done this before. The new system will handle data analysis algorithms that can’t be deployed on more traditional distributed memory systems.”

Of course, hardware isn’t all.  The center will also feature a full staff of visualization & analysis experts to aid researchers, and be available to TeraGrid researchers.

Read the full press release from the University of Tennessee and find some information about the organization of the RDAV center and some of the other individuals involved in this project.after the break, or read the announcement from their National Institute for Computational Sciences.

Read more…

Hardware, Science nsf, ornl, remotedisplay, sgi, visualization