HPCwire: Exaflops Needed to Solve Climate Crisis?

HPCwire >> Blogs

Blog: From the Editor

December 10, 2009

Exaflops Needed to Solve Climate Crisis?

This week Cray announced an Exascale Research Initiative, in which the supercomputer maker will team with a number of European HPC groups to research and develop technologies to support exaflop computing. This mirrors a June announcement by IBM that talks about an exascale research center in Ireland. No big surprises here. Everyone expects Cray and IBM to be pushing the exascale envelope.

But when it comes to talking about exascale applications, I wonder why the prospect of developing more accurate climate models and accelerating energy research is being used as a rationale for why we need such systems. In the Cray press release this week, company CEO Peter Ungaro stated: "We know there are scientific breakthroughs in important areas such as new energy sources and global climate change that are waiting for exascale performance, and we are working hard on building next-generation supercomputers that will be capable of it." It is certainly not the first time the selling of exascale has been linked with climate and energy research, as even a cursory Google search will demonstrate.

Surely I'm not the only one who sees the cognitive disconnect here. The first sustained exaflop machines aren't expected to boot up until the end of the next decade. I hope we're not counting on "scientific breakthroughs" in 2019 to solve our 2009 energy and climate crisis. In case you haven't picked up a newspaper in the last five years or so, a consensus has formed that we're already more than fashionably late to the global housewarming party, the recent "Climategate" dust-up notwithstanding.

A February 2009 article in Scientific American warns that "the risk of catastrophic climate change is getting worse," according to a recent study by United Nations Intergovernmental Panel on Climate Change (IPCC). There's a real possibility that it's already too late to reverse some of the damage resulting from rising sea levels, ocean acidification, and more extreme weather patterns. Quoting Stanford University climatologist Stephen Schneider from the Scientific American piece: "We've dawdled, and if we dawdle more it will get even worse. It's time to move." Notice he didn't say: "Let's run the numbers again with more fidelity and see what gives."

Likewise, relying on exascale computing to help with the development of non-carbon based energy sources seems like a doomed strategy. If we're not well on our way to kicking the oil and gas habit by the end of the next decade, I can't imagine some amped up simulation of wind turbines is going to save us 10 years hence.

It's disheartening to realize how long we've actually known about this problem compared to how little we've done. In watching a several-year-old rerun of a "The West Wing" episode the other day, a discussion of global warming came up that was depressingly similar to the ones we hear today. Let's face it: there are all sorts of low-tech approaches (e.g., conservation, electric vehicles, carbon taxing, etc.) that require nary a FLOP of computing power, but will do a lot to put us on the road to climate redemption. For the past 10 years, the lack of action wasn't related to technological shortcomings, just a lack of political will.

Part of the problem has to be the way we treat the climate and energy research itself, as if it's some sort of lab experiment divorced from reality. We certainly don't demand the same level of scientific scrutiny about decisions related to our personal well-being.

Let's say 9 out of 10 doctors told you that you had a heart condition that will incapacitate you (if not kill you) in ten years, adding that the condition can be remedied by changing your lifestyle. The lifestyle changes would be onerous, but nothing that you wouldn't be able to adapt to. Would you a) demand better proof of the heart condition from the nine doctors in agreement, b) wait for technology that would allow you to eat deep-fried twinkies without the deleterious side-effects or c) suck it up? Only a fool would choose a or b. Yet, so far, those are the two types of options we've chosen in response to our global crisis.

Don't get me wrong. We should certainly continue to employ cutting-edge HPC to drive climate and energy research, from now until forever. The payoff from fusion research alone would be worth it. But to peg exascale computing as a technology lynchpin for our current predicament seems completely misplaced. For the time being we're going to have to make due with our teraflops and petaflops, and hope that when exaflops systems come online we'll still be around for yet grander challenges.

Posted by Michael Feldman - December 10 @ 2:04PM

(Digg, Technorati, more)

Discussion

There are 9 discussion items posted.

Climate Crisis
Submitted by KevinButerbaugh on 12/04/2009 - 7:46AM

Michael,

This is one of your best editorials! I love the 9 of 10 doctors analogy. It is so frustrating that people are jumping all over this stolen e-mail thing and claiming that it's proof that climate change is a hoax.

Unfortunately, I don't see any hope of things changing. We are "reaping what we've sown" by failing to educate our children, especially in math and science.

Kevin

Post #1

Climate Crisis and Exaflops
Submitted by GAH on 12/04/2009 - 10:15AM

I find it ironic that a 10 Gigawatt computer is needed to tell us how to reduce energy consumption. It will churn away for a few years, then print out the answer: "Turn me off and save 100 billion pounds of CO2 annually."

Remember, the consensus on climate change cause and cure is relatively new. A mere 30 years ago, the press was awash in "global cooling" fears: Time, Newsweek, popular books, etc.

Post #2

Climate Crisis and Exaflops
Submitted by John Hules on 12/04/2009 - 10:47AM

Michael,

Your argument is based on a false assumption: using exaflops computers to solve the energy crisis does not necessarily mean doing nothing now.

As Pacala and Socolow demonstrated in their paper on "Stabilization Wedges" (Science 305:968, 2004), we can stabilize the climate for the next 50 years with existing technologies, and we need to start immediately.

But beyond that, the entire planet will need to use 100% carbon-neutral energy technologies; and we will need to mitigate and hopefully reverse the global warming that has already happened. Exascale computing will make major contributions to both of those goals.

John Hules

Post #3

Climate Crisis and Exaflops
Submitted by bdrupp on 12/10/2009 - 12:21PM

Michael,

You truly think we are in a crisis? When scientists destory data then there is an issue with their research.

There are documented times in history when it was warmer than it is now and that is before the industrial revolution.

I also like how the name has been changed from global warming to climate change. Of course the climate is going to change and is not going to happen based on C02.

I agree that we should be more responsible in manufacturing, recycling and such, but to make this into a crisis is just a lie.

Post #4

Response to bdrupp
Submitted by KevinButerbaugh on 12/11/2009 - 8:08AM

Where is your evidence that scientists destroyed data? A couple of scientists *talked about* doing things they shouldn't, but there is no evidence that I'm aware of that they actually did anything.

And the fact that it has been warmer in the past than it is now is relevant how??? Yes, some changes in the past have been due to natural causes (mainly relating to the earth's position relative to the Sun). None of that is going on now and we're still warming.

The fact of the matter is that anthropogenic climate change has been proven beyond a reasonable doubt. Once that's been proven to the point where even you are forced to admit it, however, will likely be too late to avoid serious consequences.

Kevin

Post #5

Response to GAH
Submitted by KevinButerbaugh on 12/11/2009 - 8:12AM

Yes, 30+ years ago there was the fear that we were headed into an ice age. Have you bothered to educate yourself as to why and what has changed?

Up until the 1970's we were pumping so much pollution into the atmosphere that we were actually dimming the Sun. So little sunlight was reaching the surface of the earth that we were in danger of an ice age. However, with the passage of the clean air act (a good thing), the amount of pollution was drastically reduced, more sunlight is reaching the earth, and we are now reaping the consequences of the CO2 we're relentlessly pumping into the atmosphere (still).

You know, I'm not a climate scientist ... just an ordinary Joe. And yet I haven't seen a claim made yet by the AGW folks that even I can't easily refute. Amazing...

Kevin

Post #6

Response to KevinButerbaugh
Submitted by GAH on 12/11/2009 - 9:00AM

"Have you bothered to educate yourself as to why and what has changed?"

Did you even read my post before frothing at the mouth?

My point is it took a long time to reach the current consensus -- scientific, political and social.

To say that we've known about the problem for a long time yet have done nothing (Michael's quip about the "West Wing" rerun) ignores the efforts and progress that has been made to date, and in a sense trivializes the magnitude of the problem.

Post #7

Response to KevinButerbaugh
Submitted by GAH on 12/11/2009 - 9:25AM

Did you even read my post before frothing at the mouth?

Post #8

Response to GAH
Submitted by KevinButerbaugh on 12/11/2009 - 2:18PM

Yes, I did read your post ... in it's entirety and more than once. I just now went back and read it again ... twice. And every time I read it I get the same impression ... you don't understand what caused the "global cooling" fears. If you do, I apologize. Claiming that scientists don't know what they're talking about now because they were predicting an ice age back in the early 70's is one of the major themes of the AGW crowd. Might I humbly suggest that you should make yourself clear as to your position. Thank you...

Kevin

Post #9

Join the Discussion

You must be a registered user in order to comment on HPCwire stories.

Members enjoy:

	Access to Special Content, including Podcasts, Webcasts, and Whitepapers and more!
	Ability to take an active role in the discussions that are shaping the HPC technology discipline!
	Special offers available only to HPCwire members!

Become a Registered User Today!

Registered Users Log in Here to Comment

Email Address:	Password (case sensitive)

Remember me	Forgot Password?

Michael Feldman

Michael Feldman is the editor of HPCwire.

More Michael Feldman

Feature Articles

The Week in Review

C-DAC announces plans for a petaflop system; IBM researchers are working on vertical integration techniques to extend Moore's Law another 15 years. We recap those stories and more in our weekly wrapup.
Read More...

Moscow State University Supercomputer Has Petaflop Aspirations

The Moscow State University supercomputer, Lomonosov, has been selected for a high-performance makeover, with the goal of tripling its processing power to achieve petaflop-level performance in 2010. T-Platforms, who developed and manufactured the supercomputer, is the odds-on favorite to lead the project.
Read More...

Intel Ups Performance Ante with Westmere Server Chips

Right on schedule, Intel has launched its Xeon 5600 processors, codenamed "Westmere EP." The 5600 represents the 32nm sequel to the Xeon 5500 (Nehalem EP) for dual-socket servers. Intel is touting better performance and energy efficiency, along with new security features, as the big selling points of the new Xeons.
Read More...

Read more HPCwire features...

Top Headlines

Australia Commissions Cray Supercomputer

Mar 19 | OfficialWire | New super to support intelligence work Down Under. Read more...

Intel Partners See 'Easy' Upgrade Path With Xeon 5600 Chips

Mar 18 | ChannelWeb | Westmere parts already showing up in HPC machines. Read more...

AMD: OEMs primed for Opteron 6100s

Mar 17 | The Register | But what about the tier ones? Read more...

Arrival of the Desktop Supercomputer

Mar 17 | Cadalyst Magazine | A new generation of workstations is changing the nature of technical computing. Read more...

Scheduling HPC In The Cloud

Mar 17 | Linux Magazine | Latest iteration of Sun Grid Engine able to tap into Cloud. Read more...

Read more headlines...

Featured Whitepapers

Virtualization for Aggregation And The vSMP Architecture™

Jan 12 | | In-depth look at vSMP Foundation server virtualization technology, technical implementation, use cases and capabilities. The technical whitepaper provides an architectural overview and details on the three vSMP Foundation products: vSMP Foundation for SMP, vSMP Foundation for Cluster and vSMP Foundation for Cloud.

Copper Cable Technologies for High Performance Computing

Jan 18 | | This white paper discusses Gore’s copper cable assemblies, and how they continue to exceed the standards for providing reliable, cost-effective solutions for high-performance computer applications.

View the White Paper Library

Multimedia

Webcast: Virtualized Data Center Roundtable

Join this online panel discussion for live Q&A with leading industry experts, analysts, and end-users to discuss the latest innovations, best practices, barriers to implementation, and measurable benefits of server virtualization with a particular focus on today's real world solutions.

Webcast: Watch SC09 Birds of a Feather Video: Scalable Fault-Tolerant HPC Supercomputers

Learn about scalable fault-tolerant architectures and examples of energy efficient and scalable supercomputing clusters using dual QDR InfiniBand to combine capacity computing with network failover capabilities with the help of programming languages such as MPI and a robust Linux cluster management package.

Webcast: High Performance Computing for a Smarter Planet

LIVE@SCO9: The IBM team discusses new innovations in hardware, software and services that help clients better understand their workloads and get insight from their R&D efforts. Technology demonstrations include the soon-to-be-released Power7 HPC processor, the DCS990 system with 2.4 petabytes of storage, the xCAT management tool, secure HPC cloud computing and more. Winners of two HPCwire Readers' and Editors’ Choice Awards! Take the IBM virtual tour at SC09 or more information go online to: http://www-03.ibm.com/systems/deepcomputing/sc09.html