Los Alamos, Stanford and Technical University of Munich Identify Techniques for Using Standard Silicon for Quantum Computers

Physicists at the Technical University of Munich, the Los Alamos National Laboratory and Stanford University (USA) have tracked down semiconductor nanostructure mechanisms that can result in the loss of stored information - and halted the amnesia using an external magnetic field. The new nanostructures comprise common semiconductor materials compatible with standard manufacturing processes.

Quantum bits, qubits for short, are the basic logical elements of quantum information processing (QIP) that may represent the future of computer technology. Since they process problems in a quantum-mechanical manner, such quantum computers might one day solve complex problems much more quickly than currently possible, so the hope of researchers.

link.

Flight Testing of B61-12 Nuclear Gravity Bomb Conducted

The National Nuclear Security Administration (NNSA) and United States Air Force completed the third development flight test of a non-nuclear B61-12 nuclear gravity bomb at Tonopah Test Range in Nevada on October 20, 2015.

“This demonstration of effective end-to-end system performance under representative delivery conditions marks another 2015 achievement in the development of the B61-12 Life Extension Program,” said NNSA Deputy Administrator Madelyn Creedon. “Completing this guided B61-12 flight test provides additional evidence of the nation's continued commitment to our nation’s security and that of our allies and partners.”

The flight test asset consisted of hardware designed by Sandia National and Los Alamos National Laboratories, manufactured by the National Security Enterprise Plants, and mated to the tail-kit assembly section, designed by The Boeing Company under contract with Air Force Nuclear Weapons Center. This development flight test asset contained representative non-nuclear components but no highly enriched uranium or plutonium, consistent with test treaty obligations. Although the tail-kit assembly guided the test unit, the B61-12 nuclear weapon will have no additional capabilities from the legacy B61 nuclear weapons and is not GPS-guided.

This test is the last of three development flight tests for the B61-12 Life Extension Program (LEP). An F-15E from Nellis AFB released the B61-12 test asset and it demonstrated successful performance in a realistic guided flight environment. Initial indications are that all scheduled activities occurred successfully and that telemetry, tracking and video data were properly collected. This test provides additional confidence in the weapon system and instrumentation designs prior to authorizing Phase 6.4, Production Engineering, in 2016.

link.

Transparent Aluminum, ahem, new Metallic Glass may be Coming to Your Windows

What do some high-end golf clubs and your living room window have in common? The answer is glass, but in the golf clubs' case it's a specialized glass product, called metallic glass, with the ability to be bent considerably and spring back into its original form. Your windows, as you know, aren't quite as forgiving of a sudden impact, and they shatter – they are brittle, as opposed to ductile, or more flexible products. For the golf clubs, however, a new generation of flexible metallic glass puts more bounce back into a golf ball, from the metallic glass' high elasticity. They're not unbreakable, but close. And scientists are working toward even stronger and more elastic glass types which would fail in a ductile fashion instead of shattering.

"In glass, localized plastic deformation usually leads to immediate failure," said Seth Imhoff, a Los Alamos National Laboratory materials scientist. "Normally, metal alloys freeze into a collection of crystals in which the atoms line up into very specific patterns. In specially designed metal alloys an amorphous, or random atom arrangement, can be retained in the solid, which can allow us to tailor a wide range of properties such as the ability to be bent severely and spring back into place."

And for scientists, tweaking the shearing characteristics of materials such as glass has important applications well beyond the sporting world, it's a matter of broader impact, aiding such fields as space science, electrical transformers, cell phone cases, and yes, golf clubs, because their mechanical and magnetic properties are highly adjustable.

An international team of scientists from the University of Wisconsin-Madison, Los Alamos National Laboratory, Universitat Autònoma de Barcelona in Spain, and Tohoku University in Japan are hoping their discoveries will lead to glass that can be both stronger and more ductile.

The way that metallic glass deforms plastically is by the formation of what are called shear bands. Shear banding can occur on a macroscopic scale in granular materials, like during an avalanche or landslide, but in glass the bands are generally 10-20 nanometers wide (~3000 times thinner than a human hair!).

In their paper "Nucleation of Shear Bands in Amorphous Alloys" published this week in the Proceedings of the National Academy of Sciences, these researchers are looking at the initiation of shear-banding events in order to better understand how to control the mechanical properties of these materials.

link.

The Greatest Nonproliferation Story Never Told: Plutonium Mountain

Beginning in 1949 and spanning a period of 40 years, the Soviet Union carried out more than 450 nuclear tests in the isolated steppes of eastern Kazakhstan. In 1989, when the socialist state collapsed, the Russians pulled out and left the Kazakhs to their own devices—literally. Enough fissile material for a dozen or more nuclear weapons was left behind in mountain tunnels and bore holes, virtually unguarded and vulnerable to scavengers, rogue states, or potential terrorists.

In a remarkable and highly secretive feat of collaboration among the United States, Russia, and Kazakhstan, engineers and nuclear scientists from the three countries spent 15 years and $150 million to secure many of the tunnels and test areas at the sprawling Semipalatinsk Test Site. Siegfried S. Hecker, a senior fellow at Stanford University’s Center for International Security and Cooperation, launched the project while director of the Los Alamos National Laboratory. He used his personal ties with Russian scientists to prod them into working with the Americans and Kazakhs after a visit to the test site in 1998 left him stunned by the lack of security and the presence of scavengers.

It was one of the greatest nuclear nonproliferation stories never told, until the White House and Pentagon revealed some details in 2012, which David Hoffman and Eben Harrel of Harvard’s Belfer Center made public over the weekend in an in-depth report, Plutonium Mountain. In October 2012, officials from Kazakhstan, Russia, and the United States dedicated a monument that simply reads: The world has become safer.

The interview of Sig is here and the PDF report is here.

Los Alamos has a Functioning Quantum Cryptographic Network...and has for more than 2 years

One of the dreams for security experts is the creation of a quantum internet that allows perfectly secure communication based on the powerful laws of quantum mechanics.

The basic idea here is that the act of measuring a quantum object, such as a photon, always changes it. So any attempt to eavesdrop on a quantum message cannot fail to leave telltale signs of snooping that the receiver can detect. That allows anybody to send a “one-time pad” over a quantum network which can then be used for secure communication using conventional classical communication.

That sets things up nicely for perfectly secure messaging known as quantum cryptography and this is actually a fairly straightforward technique for any half decent quantum optics lab. Indeed, a company called ID Quantique sells an off-the-shelf system that has begun to attract banks and other organisations interested in perfect security.

Pop write up.

Paper.

Southwestern Forests Threatened by Climate Change

Combine the tree-ring growth record with historical information, climate records, and computer-model projections of future climate trends, and you get a grim picture for the future of trees in the southwestern United States. That's the word from a team of scientists from Los Alamos National Laboratory, the U.S. Geological Survey, the University of Arizona, and other partner organizations.

If the Southwest is warmer and drier in the near future, widespread tree death is likely and would cause substantial changes in the distribution of forests and of species, the researchers report this week in the journal Nature Climate Change.

Southwestern forests grow best when total winter precipitation is high combined with a summer and fall that aren't too hot and dry.

The team developed a Forest Drought-Stress Index that combines the amount of winter precipitation, late summer and fall temperatures, and late summer and fall precipitation into one number.

"The new 'Forest Drought-Stress Index' that Williams devised from seasonal precipitation and temperature-related variables matches the records of changing forest conditions in the Southwest remarkably well," said co-author Thomas W. Swetnam, director of the UA Laboratory of Tree-Ring Research.

"Among all climate variables affecting trees and forests that have ever been studied, this new drought index has the strongest correlation with combined tree growth, tree death from drought and insects, and area burned by forest fires that I have ever seen."

A. Park Williams of Los Alamos National Laboratory in New Mexico is the lead author of the paper, "Temperature as a potent driver of regional forest drought stress and tree mortality." Six of the paper's 15 authors are at the UA. A complete list of authors is at the bottom of this release.

To figure out which climate variables affect forests, the researchers aligned some 13,000 tree core samples with known temperature and moisture data. The team also blended in events known from tree-ring, archaeological and other paleorecords, such as the late 1200s megadrought that drove the ancient Pueblo Indians out of longtime settlements such as those at Mesa Verde, Colo.

By comparing the tree-ring record to climate data collected in the Southwest since the late 1800s, the scientists identified two climate variables that estimate annual southwestern tree-growth variability with exceptional accuracy: total winter precipitation and average summer-fall atmospheric evaporative demand, a measure of the overall dryness of the environment.

Williams said, "Atmospheric evaporative demand is primarily driven by temperature. When air is warmer, it can hold more water vapor, thus increasing the pace at which soil and plants dry out. The air literally sucks the moisture out of the soil and plants."

Finding that summer-fall atmospheric evaporative demand is just as important as winter precipitation has critical implications for the future of southwestern forests, he said.

These trends, the researchers noted, are already occurring in the Southwest, where temperatures generally have been increasing for the past century and are expected to continue to do so because of accumulating greenhouse gases in the atmosphere.

There still will be wet winters, but increased frequency of warmer summers will put more stress on trees and limit their growth after wet winters, the study reports.

"We can use the past to learn about the future," Williams said. "For example, satellite fire data from the past 30 years show that there has been a strong and exponential relationship between the regional tree-ring drought-stress record and the area of southwestern forests killed by wildfire each year. This suggests that if drought intensifies, we can expect forests not only to grow more slowly, but also to die more quickly."

The study points out that very large and severe wildfires, bark-beetle outbreaks and a doubling of the proportion of dead trees in response to early 21st-century warmth and drought conditions are evidence that a transition of southwestern forest landscapes toward more open and drought-tolerant ecosystems may already be underway.

And while 2000s drought conditions have been severe, the regional tree-ring record indicates there have been substantially stronger megadrought events during the past 1,000 years.

Cray to Provide Petaflop System to LANL/NNSA Labs

Global supercomputer leader Cray Inc. (NASDAQ: CRAY) today announced that it has signed a sub-contract with Los Alamos National Security, LLC to provide the National Nuclear Security Administration (NNSA) with a next-generation Cray supercomputer. Currently valued at more than $45 million, the multi-year, multi-phase contract can be expanded if the NNSA exercises an option for a future upgrade. The new system will create a new supercomputing platform, named Cielo, for the Advanced Simulation and Computing program at the NNSA.

The Cielo platform will support all three of the NNSA national laboratories, which include Los Alamos National Laboratory, Sandia National Laboratories and Lawrence Livermore National Laboratory. The NNSA will use the new supercomputing system to ensure the safety, security and effectiveness of the United States' nuclear stockpile, and will run the NNSA's largest and most demanding modeling and simulation workload.

"Cielo is being acquired and deployed by the NNSA's New Mexico Alliance for Computing at Extreme Scales (ACES). This is a joint partnership between Los Alamos National Laboratory and Sandia National Laboratories. Both Los Alamos and Sandia have a long history with Cray, going back to the very beginning of the supercomputing era," said John Morrison, High Performance Computing Division Leader at Los Alamos. "With the Cielo platform, that history continues with the next generation of capability computing in support of the U.S. nuclear security enterprise."

"Cielo is the culmination of a two year partnership between Sandia and LANL on ACES," said Sudip Dosanjh, Sandia co-director for ACES. "We look forward to working with Cray to create an order of magnitude increase in capability for key NNSA national security applications. Cielo will target extremely large problems that require production, petascale supercomputing."

"The NNSA plays a critical role in protecting the safety and security of our country, and we are quite proud that some of the organization's most critical scientific research will be done on a Cray supercomputer," said Peter Ungaro, Cray president and CEO. "We have had a great partnership with the NNSA including the development of Red Storm -- a collaboration that enabled the launch of our first Cray XT3 supercomputer. We are honored to be able to continue this important partnership and are encouraged that the NNSA laboratories share in the excitement around our next-generation 'Baker' supercomputer."

The next-generation Cray supercomputer will be housed at the Strategic Computing Complex at the Los Alamos National Laboratory and is expected to be delivered in the second half of 2010. Code-named "Baker," Cray's new supercomputing system will feature a new interconnect chipset known as "Gemini" and enhanced system software that improves the performance, productivity and reliability of the system. Cray's planned "Baker" supercomputer builds on the Cray XT system architecture found in the world's fastest supercomputer and improves it in every key dimension.

no time to comment. I didn't even get a chance to work on the Medea post this weekend.

What Sort of Science Can You Do With a Petaflop?

The world's fastest supercomputer, Roadrunner, at Los Alamos National Laboratory has completed its initial "shakedown" phase doing accelerated petascale computer modeling and simulations of a variety of unclassified, fundamental science projects.

The Roadrunner system is now beginning its transition to classified computing to assure the safety, security, and reliability of the U.S. nuclear deterrent.

Capitalizing on this national security investment, 10 unclassified projects were selected for this opportunity to use Roadrunner, a hybrid-architecture, 1.105 petaflop/s computing system, during a six-month period that ended in September 2009.

These projects were also used to put a "work load" on the Roadrunner system so that scientists could optimize the way large codes are able to run on the machine. The Roadrunner open science projects represent the best of science, and the value of enabling technologies at Los Alamos, and were selected from across the Laboratory by a special committee.

A sampling of the projects include:

* ORIGINS OF THE UNSEEN UNIVERSE
Astrophysicists have created the largest-ever computer model of an expanding, accelerating universe to help scientists understand both dark matter and dark energy, two cosmic constituents that remain a mystery.

* THE LARGEST HIV EVOLUTIONARY TREE
Mapping Darwinian phylogenic evolutionary relationships for large numbers of Human Immunodeficiency Virus genetic sequences results in an HIV family tree that may lead researchers to new vaccine focus areas.

* NONLINEAR PHYSICS OF HIGH-POWERED LASERS
Computer scientists adapt VPIC, a particle-in-cell plasma physics code, to simulate laser plasma interactions on the Roadrunner petascale supercomputer - models critical to understanding inertial confinement fusion at the National Ignition Facility.

* MODELING TINY NANOWIRES AT LONG TIME-SCALES
How nanowires break under stress is simulated atom-by-atom over a period of time that is closer than ever to experimental reality to see how the movement of single atoms can change a material's mechanical or electrical properties.

* EXPLORING MAGNETIC RECONNECTION
Magnetic reconnection is a basic process that occurs within hot ionized gases known as plasmas. This process often leads to an explosive release of energy that is stored within the magnetic fields, and plays a key role in the earth's magnetosphere, solar flares, magnetic fusion machines, and a variety of astrophysical problems.

* HOW SHOCK WAVES CAUSE MATERIALS TO FAIL
Physicists use SPaSM computer code to conduct multibillion-atom molecular dynamics simulations of materials as extreme shock-wave stresses break the materials into pieces, for the first time attempting to create atomic-scale models that describe how voids are created, how materials may swell or shrink under stress, and how a once-broken bond might reform.

Keep in mind, we're still a long ways off from the climate computer ideal: 500 petaflops sustained performance. That machine may be as much as 15 years in the future. But what you can do in the mean time is pretty darned kewl.

New Top 500 List

1 Los Alamos National Laboratory
United States Roadrunner (IBM Cell + Opteron System)

2 Oak Ridge National Laboratory
United States Jaguar (Cray XT5)

3 Forschungszentrum Juelich (FZJ)
Germany JUGENE (IBM Blue Gene/P Solution)

4 NASA/Ames Research Center/NAS
United States Pleiades (SGI Altix)

5 Lawrence Livermore National Laboratory
United States BlueGene/L (IBM Blue Gene)

6 National Institute for Computational Sciences/University of Tennessee
United States Kraken (Cray XT5)

7 Argonne National Laboratory
United States (IBM Blue Gene/P)

8 Texas Advanced Computing Center/Univ. of Texas
United States Ranger (SunBlade x6420, Opteron)

9 Lawrence Livermore National Laboratory
United States Dawn (IBM Blue Gene/P)

10 Forschungszentrum Juelich (FZJ)
Germany JUROPA (Bull Sun Constellation)

And we fell to #11 despite our big upgrade and acceptence we just did. Ah well.

(where did the freakin GERMANS come from?! They're making the Japanese look bad!!!)

(oh and sorry about the delay)

LANL Maps Science Paper Downloads (kewl or creepy?)

Los Alamos National Laboratory scientists have produced the world's first Map of Science—a high-resolution graphic depiction of the virtual trails scientists leave behind when they retrieve information from online services. The research, led by Johan Bollen, appears this week in PLoS ONE (the Public Library of Science).

"This research will be a crucial component of future efforts to study and predict scientific innovation, as well novel methods to determine the true impact of articles and journals," Bollen said.

While science is of tremendous societal importance, it is difficult to probe the often hidden world of scientific creativity. Most studies of scientific activity rely on citation data, which takes a while to become available because both the cited publication and the publication of a particular citation can take years to appear. In other words, citation data observes science as it existed years in the past, not the present.

Bollen and colleagues from LANL and the Santa Fe Institute collected usage-log data gathered from a variety of publishers, aggregators, and universities spanning a period from 2006 to 2008. Their collection totaled nearly 1 billion online information requests. Because scientists typically read articles online well before they can be cited in subsequent publications, usage data reveal scientific activity nearly in real-time. Moreover, because log data reflect the interactions of all users—such as authors, science practitioners, and the informed public—they do not merely reflect the activities of scholarly authors.

Whenever a scientist accesses a paper online from a publisher, aggregator, university, or similar publishing service, the action is recorded by the servers of these Web portals. The resulting usage data contains a detailed record of the sequences of articles that scientists download as they explore their present interests. After counting the number of times that scientists, across hundreds of millions of requests, download one article after another, the research team calculated the probability that an article or journal accessed by a scientist would be followed by a subsequent article or journal as part of the scientists' online behavior. Based on such behavior, the researchers created a map that graphically portrays a network of connected articles and journals.

Bollen and colleagues were surprised by the map's scope and detail. Whereas maps based on citations favor the natural sciences, the team's maps of science showed a prominent and central position for the humanities and social sciences, which, in many places, acted like interdisciplinary bridges connecting various other scientific domains. Sections of the maps were shaped by the activities of practitioners who read the scientific literature but do not frequently publish in its journals.

The maps furthermore revealed unexpected relations between scientific domains that point to emerging relationships that are capturing the collective interest of the scientific community—for instance a connection between ecology and architecture.

"We were surprised by the fine-grained structure of scientific activity that emerges from our maps," said Bollen.

According to Bollen, future work will focus on issues involved in the sustainable management of large-scale usage data, as well the production of models that explain the online behavior of scientists and how it relates to the emergence of scientific innovation. This information will help funding agencies, policy makers, and the public to better understand how best to tap the ebb and flow of scientific inquiry and discovery.

We Iz In Ur Logz Trackin Ur Science! 43@r Uz!

Sec Chu Floats Carbon Tax

US Energy Secretary Steven Chu has floated the idea of a carbon emissions tax to fight global warming, in an interview with The New York Times Thursday.

During the US presidential campaign, the notion was kept largely on the back burner as candidates were reluctant to promote the idea of costlier energy at a time when gasoline prices were soaring.

But since President Barack Obama's administration took office in January, Congress has been working on setting up a system for swapping greenhouse gas emissions quotas similar to the one used in the European Union.

And Chu said "alternatives could emerge, including a tax on carbon emissions," the Times reported.

That's my guy!

Now, Dr Chu, about our sister labs...don't do it!

This Is A *REALLY* Bad Idea

It has been reported in several places that the Obama administration is considering transfering LANL and LLNL from the Department of Energy to the Department of Defense.

...

I cannot explain how bad of an idea this is.

The Bush administration's stupidity wrt the management changes (UC to contractors) was bad enough. It axed hundreds of researcher jobs at LANL and LLNL. Now if the Labs are transfered to the Pentagon, the science there is simply dead. The purpose of the labs would simply be weapons production and research only. Los Alamos would devolve into a nuke production/research facility and really, at that point, why have LLNL and LANL...

...

I cannot even express how depressed this makes me.

Guess Obama really is putting science back in its proper place.

Oh and Chu! How could you?!

Note: This is posted on my time. No opinions here are LBNL's or NERSC's. However, as Chu knows from many an all hands, keeping an LBLer from calling people on the carpet is nigh on impossible.

SCHWEEEET! Congratz, Dr Chu!

Life's been a mess here due tot he fact that Lyuda's PT has been in the fscking shop for the last week. The shop, the dealer really, has blown multiple turbochargers. I'm about to go rain down hell upon them in person, but while I have been so preoccupied with my personal problems, they slipped a fast one past me.

President-Elect Obama has selected my boss' boss' boss, Steve Chu, to be the Secretary of Energy. Because the Director's Page is likely to be updated with a replacement in the not too distant future, here's a small grab of his bio there:

Chu’s own research has resulted in numerous awards, including the 1997 Nobel Prize in Physics, shared with Claude Cohen-Tannoudji and William D. Phillips, for developing methods to cool and trap atoms with laser light. He did the work that led to the prize while at AT&T Bell Laboratories, from 1978-87; in 1987 he joined Stanford University as a professor in the Physics and Applied Physics Departments and was a highly decorated scientist, teacher, and administrator there until he accepted the directorship of Berkeley Lab.

Chu has published more than 220 scientific papers and is a fellow or member of the world’s leading scientific academies. He serves on numerous boards including the Hewlett Foundation, the University of Rochester, and the Executive Committee of the National Academies’ Board on Physics and Astronomy. He has been an advisor to the directors of the National Institutes of Health and the National Nuclear Security Agency.

His undergraduate degrees in physics and mathematics were from the University of Rochester and his Ph.D from UC Berkeley. He has been awarded ten honorary degrees and has held numerous visiting lectureships at universities including Harvard, Cambridge, Oxford, and the Collège de France.

Chu was born in Saint Louis, Missouri on February 2, 1948. He is married to Jean Chu, who was trained as a physicist at Oxford University and was formerly Stanford’s Dean of Admissions and the university president’s chief of staff. He has two grown sons, Geoffrey and Michael.

Oh, if the scuttlebutt is true, his siblings consider him a slacker, relatively speaking, since even though he has a PhD and a Nobel and run a lab and now is going to be a dept head of a nontrivial part of the government, he only has a single PhD. IDK if there's truth to that or not, but still an amusing rumor.

For the rest of you, he's huge into renewable energy, expect that for a major agenda item, and also synthetic biology, so look for that to be added more to the DOE's platform. Oh and he's not been a fan at all to what has been done to LANL and LLNL for management contracts. There's a slight ray of hope there, but only a slight one.

On a personal note, I've met him a few times. A very nice guy and very bright. PHD-itis is not something that has afflicted him.

Congratz, Dr Chu!

The Bean Finds the Rays!

Press release here. Universe Today is better and above. Cosmic rays are getting a lot press these days.

PS Go Sorta Divorced from Us Sister Lab LANL!

Top 500 List

Despite the many press releases to the contrary, Los Alamos (WOO!) continues to hold the top spot with their Roadrunner system (meet-meet!) over Oak Ridge's Jaguar, (note: egg->cpu, not a good pointer). We're on there with our Franklin system at #7: we did a lil upgrade. ;)

The Chinese are present in the top 10, too, btw! Running ... Windows. ew.

There's a small analysis here so you can get a look at the trends.

Oh, yeah, it's Supercomputing 08 in Austin. I'm not there, but there's a lot of news that comes out from this conference. Expect more this week from me.

The New York Times Plays Techno Coyote

An American military supercomputer, assembled from components originally designed for video game machines, has reached a long-sought-after computing milestone by processing more than 1.026 quadrillion calculations per second.

The new machine is more than twice as fast as the previous fastest supercomputer, the I.B.M. BlueGene/L, which is based at Lawrence Livermore National Laboratory in California.

The new $133 million supercomputer, called Roadrunner in a reference to the state bird of New Mexico, was devised and built by engineers and scientists at I.B.M. and Los Alamos National Laboratory, based in Los Alamos, N.M. It will be used principally to solve classified military problems to ensure that the nation’s stockpile of nuclear weapons will continue to work correctly as they age. The Roadrunner will simulate the behavior of the weapons in the first fraction of a second during an explosion.

Before it is placed in a classified environment, it will also be used to explore scientific problems like climate change. The greater speed of the Roadrunner will make it possible for scientists to test global climate models with higher accuracy.

To put the performance of the machine in perspective, Thomas P. D’Agostino, the administrator of the National Nuclear Security Administration, said that if all six billion people on earth used hand calculators and performed calculations 24 hours a day and seven days a week, it would take them 46 years to do what the Roadrunner can in one day.

The machine is an unusual blend of chips used in consumer products and advanced parallel computing technologies. The lessons that computer scientists learn by making it calculate even faster are seen as essential to the future of both personal and mobile consumer computing.

The high-performance computing goal, known as a petaflop — one thousand trillion calculations per second — has long been viewed as a crucial milestone by military, technical and scientific organizations in the United States, as well as a growing group including Japan, China and the European Union. All view supercomputing technology as a symbol of national economic competitiveness.

[...]

The Roadrunner is based on a radical design that includes 12,960 chips that are an improved version of an I.B.M. Cell microprocessor, a parallel processing chip originally created for Sony’s PlayStation 3 video-game machine. The Sony chips are used as accelerators, or turbochargers, for portions of calculations.

The Roadrunner also includes a smaller number of more conventional Opteron processors, made by Advanced Micro Devices, which are already widely used in corporate servers.

“Roadrunner tells us about what will happen in the next decade,” said Horst Simon, associate laboratory director for computer science at the Lawrence Berkeley National Laboratory. “Technology is coming from the consumer electronics market and the innovation is happening first in terms of cellphones and embedded electronics.”

The innovations flowing from this generation of high-speed computers will most likely result from the way computer scientists manage the complexity of the system’s hardware.

Roadrunner, which consumes roughly three megawatts of power, or about the power required by a large suburban shopping center, requires three separate programming tools because it has three types of processors. Programmers have to figure out how to keep all of the 116,640 processor cores in the machine occupied simultaneously in order for it to run effectively.

First, YARGH!

Second, Hi! Horst! How come they didn't quote Kathy?

Third, a few small explanations and clarifications are in order:

The supercomputer that they talk about is emphatically not military. It lives and sucks down power at Los Alamos National Laboratory. It is paid for by the Department of Energy. While LANL lives in a different part of DOE, we're decidedly civilians. Yes, there will classified research done on that machine. In fact, that it's main job: simulations of nuclear weapons. Yes, quite soon, it will be behind the fence and unusable by the regular science crowd. However, until then it will be used for a number of simulations. Most notably, climate sims will be run on the system.

(a Roadrunner node. image courtesy LANL)

Secondly, this system is what we call a 'hybrid.' This is where commodity parts are taken and intermixed with custom components. Sometimes this is accomplished by modifying the original parts as was done on the Cray T3E (mod'ed Alpha processors). Sometimes this is done by hanging relatively off the shelf nodes off a custom interconnect (Cray XT4). Other times, it's done by building mixing and matching that. Or building custom nodes with a semi-specialized OS. This is done with the Roadrunner. These days, truthfully though Infiniband is almost COTS. The scale is what makes the difference here. It's almost OMG, it's the Cloverfield computing platform. However, in the future, the custom side of things may become more and more dominant or so sayeth John et al, amen.

Cluster is a word that gets me hot under the collar, but we'll save that for another time. Roadrunner does appear to qualify. *mutters* another time...another time...

Now as for the comments above about the increased speed. Oy. A speed increase on the computer doesn't always translate into a linear increase for the codes. There are a lot of factors that govern the speed of scientific programs. Memory is the big killer these days for most platforms: COTS memory cannot keep up with the CPU; therefore, the CPU goes idle for really nontrivial amounts of time waiting for a memory fetch. This happens a lot. If the memory subsystem could be improved, this would be fixed. The second reason is a double trouble problem of coding: first, algorithms have to be found that fit the platform and second the compilers often are less than good for intelligently dividing up the code to be run on what and when. In fact, intelligent compilers tend to be not at all. Scientists, even code monkey scientists that run simulations, often don't have time to sit there and break out the code like they used to do ten, fifteen years ago. In fact, they often hired specialists to do just that because they didn't have that time or knowledge. That may be what is needed now as the codes they work on become more and more specialized knowledge of the processors they are going to run on: the Cell is by most accounts a nontrivial beast to code for.

Another bit is the talk of the 'resurgence of American supercomputing.' Gag me. They act as though the US was so trumped and was going to be that way because of the Japanese Earth Simulator. The fact is that this is not the first time it has happened. Lest we forget, the Japanese built an uber'puter that sat at the top of the charts for a looooong time in the 1990s. Every ten or so years, they do this. They spend waaaaaaaaaaay more money on a single computer than the US is willing to do: the Earth Simulator cost over $750 million for a 5x speed up over a $30 million supercomputer of the time. Hmmm. Doesn't sound terribly economically bright. Especially since in a couple years the ES was overshadowed by much, much cheaper systems.

Anyways, I'm sicker than I thought so I'll wrap this up because my brain's in a near meltdown. The thing that angers me about the NYT article is that they use the wrong analogies (turbochargers?! the cells are the whole point, they're the engine. the opterons are the sidekick) and seem to just not understand the stuff they're writing about. I really wish that they could get an intelligent popularizer. Someone that actually was or is an HPC guy/gal that speaks plain English. At least they didn't say "supercomputer in a box..."

Whew.

UC Wins Contract to Run LLNL

Not a big surprise after the fact that they got to keep the LANL contract.