Reed's Ruminations: A Blog by Dan Reed

One Life to Live

A few years ago, a foundation ran a billboard campaign with an image of Kermit the Frog and the caption, "Eats Flies, Dates a Pig, Hollywood Star. Live Your Dreams." Beyond being a huge fan of the Muppet Show and its sardonic humor, especially as offered by Statler and Waldorf, I have always loved this billboard because it captures an essential element of human life, the desire to make a difference, to live life with the passion of commitment. It is a feeling Thoreau captured in Walden, to the enduring delight of secondary school English teachers across North America:

I went to the woods because I wished to live deliberately, to front only the essential facts of life, and see if I could not learn what it had to teach, and not, when I came to die, discover that I had not lived.

I was reflecting on this recently as the world lost two innovators in computing. About the first, Steve Jobs, much has been written, but far less about another pioneer of computing, Dennis Ritchie.

Remembering Ritchie

UNIX and C transformed our notions of operating systems and programming, seeding a cornucopia of software tools and technologies. I still have my dog-eared copy of the 1978 Bell Systems Technical Journal (BSTJ), which was devoted to the "UNIX Timesharing System."

I was a graduate student then, and it brought my first exposure to UNIX on a VAX 11/780 at Purdue. We ran VMS part of the time and UNIX the rest, largely because VMS had a decent FORTRAN compiler. The numerical analysts among us used FORTRAN, but for the rest, it was UNIX and C. It was a heady time, when new tools and approaches were transforming academic computing research from a largely theoretical discipline to an experimental science. I created a compiler for John Backus' FP language using lex and yacc on that VAX, and I wrote a Ph.D. dissertation using troff.

As da Vinci supposedly remarked, "Simplicity is the ultimate sophistication." UNIX was elegant in its simplicity and functionality. It and the C language inspired multiple generations of hackers (and I use that word in its original, pure sense) to create so many things. It is not exaggeration to say that one can date operating systems as pre-UNIX and post-UNIX.

Richie's passing was not noted with great fanfare, but he made a difference. All of us in computing honor that.

Meditations on Dreams

In between the endless work deadlines, the email deluge and the frenzied travel, take a deep breath and ask yourself what matters and what you are doing. The answers may surprise you, particularly as mortality seems more than a tale told by the wise and aged to the young and uncertain. Those are the essential facts Thoreau described.

Throughout my life, I have been able to live many of my dreams. Far too many people are not so fortunate. (For the record, eating flies, dating a pig and being a Hollywood star have not been among them.) I have a few dreams left, both in computing and in life, and I suspect you do too. In my case, there is a book or two trying to escape via my fingers. (See Eudora, You Got the Love?)

Seize the opportunity. Live your dreams. Make a difference. It is all that any of us can hope to do.

It Is Fall: There Must Be Clouds

Today, I testified to the Subcommittee on Technology and Innovation of the U.S. House of Representatives Committee on Space, Science and Technology. The topic of the hearing was "The Next IT Revolution?: Cloud Computing Opportunities and Challenges." At the hearing, I was joined by Mike Capellas (CEO, VCE), Nick Combs (Federal CTO, EMC), and David McClure (Associate Administrator, GSA).

This hearing drew on some of the content from the TechAmerica Commission on the Leadership Opportunity in U.S. Deployment of the Cloud (CLOUD²), on which I had the privilege to serve as the commercial vice-chair. In addition, my own remarks were augmented by Microsoft's cloud engagement experiences with the U.S. National Science Foundation and other research funding agencies. (See Innovation Via Client Plus Cloud: Microsoft-NSF Partnership for background.)

My complete written testimony will ultimately appear on the Subcommittee web site here, and the hearing charter, the subcommittee press release, and the hearing video capture most of context. However, there are a few points from my testimony that seem appropriate to repeat here. These concern research empowerment via the cloud, support for basic research and education and broadband expansion.

Accelerating Scientific Discovery for Research via the Cloud

Throughout the history of science, data has been scarce and precious. Indeed, the modern scientific method is defined by a careful cycle of hypothesis and experiment, which gathers experimental data to test the hypothesis. In a few short years, scientists and engineers have gone from scarcity to an incredible richness, necessitating a significant change in how they manage and extract insight from all this data. In a parallel shift, many of our scientific, engineering and societal questions increasingly lie at the intersections of traditional disciplines.

Increasing data volumes and the complexity of collaboration on interdisciplinary problems are challenging our historical approaches to discovery and innovation via computing. Most researchers and research institutions are ill-prepared for the large-scale computing infrastructure management challenges posed by large data sets and complex models. The cloud and associated applications and tools offer a possible solution to this challenge by letting scientists be scientists.

The U.S. government can accelerate this transition by encouraging the purchase of cloud services, in addition to the acquisition of local IT infrastructure, and by supporting new tools that facilitate distributed collaboration and simplify access to multidisciplinary scientific data. As I have noted before, Microsoft is acting on this belief, working in partnership with the National Science Foundation.

Fostering Continued Support for Computing Research and Education

Today's cloud technology is derived from basic computing research conducted over the past four decades. To ensure that the U.S. continues to remain at the forefront of cloud technology, continued investment in basic research is critical. There are deep and open questions in areas as diverse as the future of silicon scaling and system-on-a-chip design, energy-efficient systems, primary and secondary storage, data mining and analytics, wired and wireless networks, system resilience and reliability, privacy and security, and user interfaces and accessibility, to name just a few. Insights and innovations from this research will spawn new companies, create jobs and reshape our future.

In addition to continued research investment, it is critical to support the pipeline that produces researchers, and others who will able to invent new uses of the cloud and information technology. The U.S. Bureau of Labor Statistics estimates that the computing sector will have 1.5 million job openings over the next 10 years, yet the number of graduates receiving Bachelors, Masters or Ph.D. computer science degrees is far short of that. In addition, we must strengthen the quality of and access to computing education at all levels. Consistent with these concerns about the IT workforce and computing education, Microsoft is a founding member of the Computing in the Core coalition, which supports computer science education, particularly at the K-12 level.

Broadband: The Need for Speed

The web and cloud services depend on broadband communications. Without them, service and information sharing are impossible. Concomitantly, ensuring reliable wired and wireless connectivity, with adequate bandwidth and latency, is critical to ensuring successful adoption of the cloud and realization of its benefits. The phenomenal growth of digital data, the rise of streaming media services, and the explosive growth of Internet-connected devices are all straining our nation's broadband infrastructure.

It is critical that we continue to design and deploy new backbone networks that support higher data rates, develop and deploy new protocols and infrastructure for the next generation of wireless networks and define the global standards that will shape the future of the globe-encircling cloud. We must also remember that digital access to information and services is increasingly the enabler of economic competitiveness, of lifelong education in a rapidly changing world, and of government efficiency and service delivery.

21^st Century Innovation

This is an exciting time, when the future becomes the present. Computing can be a great equalizer, providing access to the world's knowledge base to individuals, anywhere, anytime; empowering entrepreneurs and companies large and small to sell their products and ideas globally; and enabling scientists and engineers to discover and innovate in ways that will define the future.

On Licking the Cookies

All organizations and cultures develop their own idiosyncratic acronyms, abbreviations, lingo and metaphors. (Yes, there are probably a few similes and alliterations as well.) One need look no further than the social networks and Twitter to find a veriable cornucopia of such phrases and acronyms (e.g., LOL or OMG). The hacker community (the original one) also gifted us with the gems RTFM and UTSL.

I was once offered my first full time job in the software industry because I knew what JCL was needed to apply a PTF to BTAM. That's IBM speak for applying a software patch to telecommunications software. In this sense, Microsoft is not unique, for its worldwide employees have developed their own lexicon of metaphors and abbreviations, as well as appropriating others were useful. As a relative newcomer to the corporate world after twenty-five years in academia, several of these abbreviations, words and phrases immediately caught my ear.

Licking the Cookies

Not to be confused with the joy of double stuff Oreos or even licking the spoon, licking the cookies refers to claiming action or skill in an area but in a way that prevents anything from happening. It is intended to conjure an image of a cookie plate, where one licks the cookies then returns them to the plate, rendering them inedible by all. As the phrase suggests, you have not eaten the cookie (i.e., taken action) but you have prevented others from doing so either.

Cookie licking is endemic to any large organization or culture where multiple teams compete for credit and accomplishment. We have all seen this behavior in our organizations and occasionally been guilty of it ourselves. This is one of the more pernicious forms of non-collaborative, non-team play.

After understanding the phrase, I realized that subtle and not so subtle forms of cookie licking occur in academia as well. I have seen it in debates over academic directions, discussions of research priorities and in paper and grant proposal reviewing. Of course, academia has its own set of arcane phrases.

Eating Your Own Dog Food (aka Dogfooding)

Dogfooding is a hoary classic, well used and abused across the computing milieu. It refers to using early (alpha or beta) versions of a system you and others have developed before it is released, often as an informal tester. It's not haute cuisine or even nouveau cuisine; it's dog food, edible and nutritious, but neither elegant nor tasty.

Learnings

Finally, there are learnings, as in "Our learnings on this suggest optimization is our first priority." The first time I heard this linguistic oddity, I was nonplussed and puzzled, confused and uncertain, perhaps even mortified, but I was not chagrined. After hearing it several times, I finally asked if the speaker really meant insights, understanding, observation, or even experience. The answer, of course, was yes. Nobody I have yet asked, however, knows the origin of the usage, though I am sure the exegesis would be fascinating.

BFN, I am OOF.

Information Privacy: Changing Norms and Expectations

N.B. I also write for the Communications of the ACM (CACM). The following essay recently appeared on the CACM blog.

Our notions of privacy and security are deeply tied to our social and historical notions of person and place. The aphorism, "A man's home is his castle," captures that notion and its roots in English common law. This Castle Doctrine followed settlers to the colonies and was later codified in the Fourth Amendment to the U.S. Constitution:

The right of the people to be secure in their persons, houses, papers, and effects, against unreasonable searches and seizures, shall not be violated, and no Warrants shall issue, but upon probable cause, supported by Oath or affirmation, and particularly describing the place to be searched, and the persons or things to be seized.

Your family heirlooms may be secure in your personal castle, but what of the information about you that lives on the Internet? The legacy of physical place and norms around it are far less relevant.

Equally importantly, we often convolve privacy and security without considering their differences. One needs security to protect private information, but one can have security without privacy, as many world events have shown. Security is a topic for another day; let's talk about the evolving notions of electronic information privacy.

Riding the Light

That picture of you at a family reunion, squinting into the sun, can rarely be delimited by a physical location. It might be on disk two, machine nine, rack twenty three in a North Carolina data center, but it probably will not be for long.

Instead, information flows freely, in radio waves among our wireless devices and on photon beams along the fiber optic cables that connect the burgeoning network of worldwide cloud data centers, each themselves larger than the entire Internet was just a few years ago. It's cached, distributed, forwarded, copied, mirrored and indexed.

All of which suggests that we need to rethink our notions of information privacy, moving beyond concepts rooted primarily in person and place, and considering logical privacy. These issues are complex and emotionally charged, for they challenge many of our social, cultural, legal and economic assumptions. I would not presume to offer a definitive answer here. Instead, let me offer three ideas to stimulate our debate the future of information and electronic persona management in this brave new world.

A Simple Family Photo

Let's return to that family reunion photograph, captured on a smartphone and posted to a social network site. What might I, as person in the picture, wish to specify and who else might be involved?

First, I might well like to specify a bounded lifetime for the photograph, after which it would be inaccessible to anyone. Of course, the bound might be infinity, allowing it to remain in the electronic ether forever. That is the current default, as more than one person has learned to their chagrin. I have occasionally noted, tongue in cheek, that one can trace the history of my hair loss on the Internet due to just this default. (For the record, let it be noted that I am at peace with my baldness.)

Second, I might choose to define the transitivity of access. I could share the photograph with my extended family but not allow any of them to share it with their friends. Or, I might limit access to some overlapping circle of personal or professional friends, preventing viral propagation. This is challenging because our overlapping spheres of social, professional and familial influence rarely have hard boundaries, as anyone who has configured their social network privacy settings knows all too well.

The usability of specification interfaces for privacy and security deserves far more attention than it has received. All too often, the only options presented are a broad and vague end user license agreement (EULA) that one must accept to use a service or a byzantine set of confusing service configuration options whose effects are less than obvious. Privacy specifications must be made far simpler and more intuitive.

Third, I might wish to define a claims-based access policy. This is not a binary access specification, but rather a statement that this person or this entity can access this photograph for this and only this purpose. Thus, I might grant my cousin the right to look at this photograph but not to sell it, alter it or combine it with other media.

Ownership, privacy, reputation and decision making are intertwined in subtle ways. What if I posed for a reunion photograph but one of my crazy cousins was dancing on the table behind me? Who controls that family reunion photograph, me, the drunken dancer in the background, the photographer with the smartphone, all of us? The shifting nature of social relationships further exacerbates these challenges.

Let Us Reason Together

Let me end with another aphorism, "Possession is nine tenths of the law." In a digital world where images, video and text can proliferate globally in seconds, we need to rethink what "possession" means.

I don't have all the answers, but I do have lots of questions.

Battling Evil: Dark Silicon

As a boy, I remember reading all the superhero comic books, from the standard Superman and Batman to the Green Lantern, Thor, The Flash and Spider-Man. Some superhero stories and backstories were better than others, but all were escapism from small town life. For me, Thor was always a favorite, though I am not quite sure why. Maybe I just liked the head gear! The summer "action movie" season is upon us, and several of these superheros will grace the screen in new Hollywood fantasies, battling the forces of evil.

All of this made me think about the resident evil now facing us in computing – the rise of dark silicon. The very phrase sounds ominious and it is, for I believe it will profoundly reshape how we think about computing in the next decade. But before we talk about the grand denouement where our Justice League of silicon process experts, computer architects and software gurus do battle with dark silicon, perhaps we should begin with a bit of backstory.

Moore's Law and Silicon Scaling

We are all familiar with Moore's Law, namely that the number of transistors in a given area doubles roughly every two years. It is worth noting that Gordon Moore never really claimed this was a law, merely that it was a statistical truth based on observational data and technology trends. It is also interesting how a rather informal 1965 Electronics paper, entitled "Cramming More Components onto Integrated Circuits," had such impact. Over the past thirty years, the "law" has held true due to the hard work and creativity of a great many people, as well as many billions of dollars of investment in process technology and silicon foundries.

For a detailed understanding of why reducing transistor feature sizes really has been possible, I highly recommend reading the original, seminal paper by Robert Dennard, Fritz Gaensslen, Hwa-Nien Yu, V. Leo Rideout, Ernest Bassous and Andre LeBlanc, entitled "Design of ion-implanted MOSFET's with Very Small Physical Dimensions." It appeared in the October 1974 issue of the IEEE Journal of Solid-State Circuits, and it defined a scaling process that has driven the semiconductor industry ever since.

Simply put, Dennard scaling says that reducing the length, width and gate oxide thickness of transistor features by a constant k results in transistors that are k² times smaller, k times faster, and dissipate k² less power. This was Moore's Law made manifest and has let us move from feature sizes measured in micrometers to nanometers. Since the elucidation of Dennard scaling, all has been well in Metropolis, at least until very recently.

Power and Performance: Evil Lurks

As transistor sizes continued to shrink and clock rates continued to increase, we have seen the rise of high-k dielectrics and silicon on insulator (SOI) to address static current leakage. In that spirit, one of my colleagues recently remarked that transistors are now less like solid doors that keep out the cold (current flow) unless open and more like screen doors that always have some air flow (current leakage) even when closed.

Transistor density, clock rates and chip sizes have also made heat dissipation an ever bigger problem. While at Intel, Pat Gelsinger once remarked that unless things changed, chip temperatures would approach that of the sun's surface, an obvious absurdity only possible in the comic books. All of this has led to multicore designs, bounds on clock rates for most microprocessors and decreases in operating voltages.

We have also seen new semiconductor processes and transistor design options to reduce leakage current. (Intel's recent FinFET announcement is one such example.) Although I expect to see transistor feature sizes continue to shrink, with sub-11 nanometer feature sizes achievable, it will not be easy, nor will it be cheap. Lest there be any doubt, the cheap part really matters, for it is the economics that will determine if scaling continues.

These semiconductor challenges have been mirrored by an increasingly empty bag of general purpose architectural tricks. Almost all of the techniques once found in supercomputer processor designs – superpipelining, scoreboarding, and vectorization – are now in mainstream microprocessors. It is not obvious that we can extract more parallelism while maintaining the illusion of sequential execution. In fact, the evidence is substantial that we cannot.

Battling Evil: Dark Silicon

That's the backstory. Now let's turn to the true evil lurking among us, dark silicon. If one considers process scaling trends and limits on heat dissipation, the conclusion is rather obvious. We soon will have (and in many cases already do have) chips with more transistors than can be concurrently activated. The practical implication is that most of the chip silicon will be "dark" (unpowered) most of the time.

If it's dark most of the time, is it of any value? Yes, but only if we embrace our fears. This is the true end of the hegemony of von Neumann computing and the birth of a new era, one based on chips with a diverse set of specialized functional units, accelerators and tailored architectures that each target specific tasks. The mobile world has already learned this lesson, for functional specialization increases energy efficiency (more operations/joule) and allows designers to mix and match the set of functional units to target domains. Arguably, heterogeneous multicore is one, very tentative step in this direction for client and server computing.

This transition to diverse functional units, accelerators and tailored architectures will also challenge many of our assumptions about programming models and system software, as well as the economics of chip design. In this new world, hardware/software co-design becomes de rigeur, with devices and software systems deeply interdependent.

It is a different ecosystem, with different cultures and different processes. It means far less general-purpose performance increases, much more diversity in the hardware, elevation of multivariate optimization – power, performance, reliability – in programming models, new system software resource management challenges and a plethora of new applications.

More generally, with lots of silicon real estate (dark silicon), chip designers and architects have the space to place functional blocks that are used only part of the time. However, at some point (and we are arguably close to that point now), we will have deployed those functional units that cover the common tasks and adding more will have possibly deleterious effects due to larger chip size. That potentially drives the economics to smaller chip sizes, which, given foundry capacity, leads to lots of small chips. That is the collision of the big chip server world with the small chip mobile and Internet of Things world, a battle already raging.

To address these challenges and battle dark silicon, we need new ideas in computer architecture, system software, programming models and end-to-end user experiences. It's an epic struggle for the future of computing. Giants are battling, and not all will survive, nor will the survivors emerge unscathed. Heroes will also emerge, sometimes from unexpected places.

I think I left my hammer, Mjölnir, around here somewhere. Do you feel your spider sense tingling?

Microsoft/NSF Cloud Research Partnership

Today, Microsoft and the U.S. National Science Foundation (NSF) announced the latest awardees for the joint Microsoft-NSF research partnership in cloud computing. (See the NSF announcement: The Sky Is No Limit: 13 Research Teams Compute in the Clouds.) This is a continuation of the program that then NSF Assistant Director for Computer and Information Science and Engineering (CISE), Jeannette Wing, and I announced in February 2010 (See Microsoft and the National Science Foundation Enable Research in the Cloud and Democratizing Research: How "Client Plus Cloud" Computing Can Amplify What's Possible for Scientists).

As part of this agreement with the NSF, Microsoft is making available access to Windows Azure, Microsoft's cloud computing platform. In addition, a support team of Microsoft researchers and developers is working with grant recipients to equip them with a set of common tools, applications and data collections that can be shared with the broad academic community, and also providing expertise in research, science and cloud computing. Broader details on the program and its research tools and software for Windows Azure can be found here.

Diverse Projects

Increasingly, the important scientific questions lie at the intersections of traditional disciplines, and insights from multidisciplinary collaborations drive innovation, economic development and our response to complex problems and natural disasters. This is one of many reasons I am so pleased with the technical diversity among the list of NSF-Microsoft award recipients.

All of the award recipients were selected via NSF's rigorous peer review process, which emphasized the scientific merit of the proposed work. Projects range from exploring scientific applications of cloud computing as well as extensions of cloud computing with new tools and techniques.

• Cornell University (Kenneth Birman) - Building Scalable Trust in Cloud Computing
• J. Craig Venter Institute (Audrey Tovchigrechko) - Bettering Interactive Protein-Protein Docking
• SUNY at Buffalo (Tevfik Kosar) - Enhancing Stork Data Scheduler for Azure
• University of California, San Diego (Kenneth Yocum) - Utilizing Continuous Bulk Processing
• University of Colorado, Boulder (Richard Han) - Enabling Mobile Cloud Computing
• University of Michigan, Ann Arbor (Qiaozhu Mei) - Refining Language Models using Web-scale Language Networks
• University of North Carolina at Charlotte (Zhengchang Su) - Predicting Transcription Factor Binding Sites for Genes
• University of South Carolina (Jonathan Goodall) and the University of Virginia (Marty A. Humphrey) - Managing Large Watershed Systems
• University of Southern California (Viktor Prasanna) - Tackling Large Scale Graph Problems
• University of Texas at Austin (Michael Walfish) - Storing Data with Minimal Trust
• University of Washington (Magdalena Balazinska) - Understanding Relational Data Markets
• Virginia Tech (Wuchun Feng) - Conducting Intensive Biocomputing
• Virginia Tech (Kwa-Sur Tam) - Effectively and Widely Using Renewable Energy Sources

  Worldwide Reach

The Microsoft/NSF partnership is but one part of a broader international program that the eXtreme Computing Group (XCG) and Microsoft Research are building with the scientific research agencies worldwide. We believe cloud computing, coupled with powerful client tools, can transform the nature of research. This worldwide program currently targets collaborations with several national and international research partnerships, including

• National Institute of Informatics of Japan Info-plosion project
• European Commission FP7 funding program, Venus-C project
• U.K. Engineering and Physical Sciences Research Council (EPSRC) Horizon project
• French INRIA-Microsoft collaboration on cloud computing
• Australian engagements with NICTA, ANU and CSIRO

Power via Simplicity

This Microsoft/government partnership is about so much more than access to cloud computing resources. The deep partnership between academic and Microsoft researchers, creation and release of easy-to-use client tools and an exploration of the new world of massive data are all key elements of our shared journey to a new model of data rich analysis enabled by powerful client tools and cloud services.

Any successful technology ultimately becomes invisible, enabling and empowering without requiring the user to focus on the idiosyncrasies of the technology itself. Technical computing can and should be an invisible intellectual amplifier, as easy to use as any other successful consumer technology. As I wrote last year when we first launched this program, it is really about transforming how we conduct research by broadening researcher capabilities, fostering collaborative research communities, and accelerating scientific discovery by shifting the focus from infrastructure to empowerment.

Intellectual Amplification via Computing

N.B. I also write for the Communications of the ACM (CACM). The following essay recently appeared on the CACM blog.

Many years ago, Fred Brooks relayed a tale about how he chose the first application target domain for his computer graphics research. It was not long after he had left IBM and completed his work on the IBM System/360. He had just moved to Chapel Hill and taken a faculty position at the University of North Carolina.

As Fred tells the story, with a bit of a twinkle in his eye, he went to see one of the senior university administrators. He told the administrator that as a computer scientist, he was in the intelligence amplification business. Who on the campus, Fred wanted to know, might most benefit from having their intelligence amplified?

I have recalled this story many times, always with a smile, as I have reflected on the nature of computing and its power.

Amplification and Universality

Computing systems share many features with other instruments and machines, in amplifying human abilities. However, one aspect distinguishes them – namely, their general utility as an intellectual amplifier. Like a universal Turing machine, which can simulate any other Turing machine with arbitrary inputs, computing is broadly – dare I say universally – applicable to human intellectual endeavors, much as all the variants of the inclined plane and lever are applicable to human physical endeavors.

The English scientist Sir Humphrey Davy could well have been speaking about computing when he said, two centuries ago:

Nothing tends so much to the advancement of knowledge as the application of a new instrument. The native intellectual powers of men in different times are not so much the causes of the different success of their labors, as the peculiar nature of the means and artificial resources in their possession.

In a phrase – success accrues to the talented with access to the most effective and powerful tools.

Supercomputing and its applications to science and engineering have been canonical examples of this universal benefit. Powerful new telescopes advance astronomy, but not materials science. Powerful new particle accelerators advance high-energy physics, but not genetics. In contrast, supercomputing advances all of science and engineering because all disciplines benefit from high-resolution model predictions and theoretical validations.

As exciting as those opportunities remain, new ones are emerging in the world of big data.

Big Data: Structured and Unstructured

The tsunami of structured scientific data, produced by a new generation of sensors, and the growth of semi-structured and unstructured data from business, entertainment, social networks and popular culture have created new needs for creative application of our intellectual amplifier. As the recent performance of IBM's Watson system on the game show Jeopardy! Illustrated, the combination of large-scale data, rich algorithm suites and powerful computing is opening new vistas. Vannevar Bush's 1940s vision of a Memex, a device capable of storing, indexing and retrieving data from a broad knowledge base, is now within our reach.

It really is about how we use computing as an intellectual amplifier, allowing humans to be more productive and more creative by doing what we do best – asking interesting questions, ones that span multiple disciplines and that illuminate opportunities at their interstices – aided by power analytic and computation engines.

HPC and the Excluded Middle

N.B. This essay also appeared on the Communications of the ACM web blog.

As consumers, we have access to diverse software and a wide array of devices on which to use it. ("There's an app for that!") The virtuous cycle between consumer demand and application development ensures that the software ecosystem is rich and responsive. At the other extreme, the world's most powerful high-performance computing systems, experienced teams of computational scientists create research applications that target some of our most complex and pressing problems – energy, environment and climate change, computational fluid and structural dynamics for building and aircraft design, and biological models that illuminate the future of personalized medicine.

Ah, but betwixt and between ubiquitous consumer software and the ethereal realm of ultra-high-performance computing, lies the excluded middle, the world of day-to-day computational science problems. This "no man's land" lacks both the ready availability of application software suitable for solving problems in a host of domains – advanced manufacturing, materials analysis, and biomedical assessment – and the cadre of computational science experts who might develop custom software solutions. The result has been limited uptake of computational science by companies of all sizes, large, medium and small.

The U.S. Council on Competitiveness launched a high-performance computing (HPC) initiative whose goal was to "… facilitate wider usage of HPC across the private sector to propel productivity, innovation and competitiveness." The initiative conducted several surveys and business roundtables to understand what would accelerate adoption of high-performance computing and computational science by business. The overarching insights from these studies were (a) the difficulty in using current HPC systems and (b) the dearth of individuals with the necessary skills to develop computational models.

I recently attended a workshop on advanced manufacturing, organized by the President's Council of Advisors on Science and Technology (PCAST), where the use of computational science was also a topic. The chief technology officers (CTOs) of major multinational companies echoed the same observations. Namely, they would love to exploit HPC for business advantage, but it was too difficult to use and too hard to find the requisite talent.

In other contexts, I have repeatedly been told by both business leaders and academic researchers that they want "turnkey" HPC solutions that have the simplicity of desktop tools but the power of massively parallel computing. Such desktop tools would allow non-experts to create complex models quickly and easily, evaluate those models in parallel and correlate the results with experimental and observational data.

Unlike ultra-high-performance computing, this is about maximizing human productivity rather than obtaining the largest fraction of possible HPC platform performance. Most often, users will trade hardware performance for simplicity and convenience. This is an opportunity and a challenge, an opportunity to create domain-specific tools with high expressivity and a challenge to translate the output of those tools into efficient, parallel computations.

Technology Transfer: A Contact Sport

It is fall and football season in the United States. We are still playing soccer too – football everywhere else – but that is another story. American football has long been called a contact sport, meaning the players intentionally collide to move the ball toward the goal line. However, it remains a far cry from rugby, which seems indistinguishable from unarmed combat to my untrained eye.

How, one may wonder, does football relate to technology transfer? For that matter, what do I mean by the phrase technology transfer itself? There are broader definitions, but for the sake of discussion, let's define technology transfer as the mechanism via which research ideas are communicated to and adopted by companies and their product groups.

The success or failure of technology transfer depends on many factors, from the personalities and skills of the people involved, through the timing and appropriateness of the offering, to the risks and costs associated with the new idea. No single mechanism is guaranteed to succeed, though there are many mechanisms that are likely to fail.

Sharing the Love

Opening the technology transfer conversation with a product group by disparaging the current product or questioning the intelligence of the developers is unlikely to create a receptive audience for one's brilliant research result, no matter how scintillating and erudite the subsequent description may be. Nor will woeful obliviousness to the history that led to the current product design, for it is important to understand context and competition. Finally, neither will bad timing. Reporting a better way to engineer a product just before it is finished will accomplish nothing other than depressing the product team, though it may provide guidance for the next product generation.

One needs to build a long-term, productive and positive relationship between research and product development. It is about creating mutual benefit, sharing the love.

On the positive side, I have observed a continuum of mechanisms that facilitate the transfer of ideas. None is universally successful in isolation, and even in aggregate they may fail. However, the set is far more powerful than the elements, and all can benefit from true contact sport engagement.

Papers. These are the stock and trade of researchers, whether in academia or in government or corporate research laboratories. Yes, members of many product groups read research papers, but an abstract idea, even with supporting experimental data, is rarely the catalyst for uptake of a new idea. A well-written paper does, however, provide the technical details needed when an idea is ultimately adopted.

Demonstrations. These are the "science fair" instantiations of ideas, the early instances that are little more than mockups of the idea. They work on limited data, are constructed using laboratory rather than product components, and they are unreliable at best. However, their virtue is in allowing non-researchers to see and experience the idea in concrete form. Often, seeing really is believing, and a prototype can be convincing in ways that a paper is not.

Prototypes. Prototypes are the next stage, where the demonstration is sufficiently robust that it can be used routinely by individuals and groups other than the creators. The robustness allows product groups and developers to test the idea in more realistic conditions and contexts, and see how it fares relative to existing technologies.

Near Products. Near products are products in all but name, suitable for shipment with little more than cosmetic changes. Creating a near product can be effective if the product team is interested and willing but understaffed, or if they lack the specific technical skills needed to create a product quality instance of the idea.

Contact Engagement

Papers, demonstrations, prototypes and near products help, and they may sometimes be sufficient to transfer an idea into a product. However, they are pale shadows of the true contact sports, either direct embedding with the product team or long-term engagement and partnership. In the embedding model, researchers become members of the product team, working side by side on the product in the same environment as the product developers. Because the utility of so many new ideas depend on culture and context – things rarely written down – as well as personal trust and connections, contact engagement is often the most successful approach.

Remember, game plans, no matter how elaborate, rarely work without modification. The players on the field innovate and adapt. Technology transfer is a contact sport. It can be contentious at times, but the rewards for successful transfers are enormous, both in a sense of personal accomplishment and pride and in the long-term success of the companies involved.

Lessons from the Gulf of Mexico

N.B. My apologies for the absence of recent posts. It's been a bit busy here in HPCDan's world.

What can we learn from the oil well leak in the Gulf of Mexico? That deep water drilling is more common than most people realized? Yes, because much of the near surface oil has already been extracted. That a complex engineering tasks, such as capping an oil well one mile below the ocean's surface, are difficult? Yes, that is why we call them complex. That all engineering projects involve risks? Yes, for all designs involve tradeoffs and error margins. That our civilization is overly dependent on petrolem as an energy source? Yes, but we will forget that lesson again. That nature is not infinitely resilient to human folly? Yes, though we still struggle to believe it. That local events have global consequences? Yes, but we should know that already.

Coupled Models

Though all of these rethorical questions have answers in the affirmative, I suspect all of us in computational science looked at the disaster in the Gulf and saw something else – a devilishly complex multidisciplinary system with emergent behaviors across a wide range of temporal and spatial scales. We saw a modeling problem whose complete solution lies beyond our current reach at a time when we all hoped to be of more help.

Let's begin with the reservior models of subsurface attributes (e.g., porosity, permeability and water mobility) that guide selection of drilling sites. Obtaining accurate numerical solutions from the resulting discretizations remains a challenging parallel computation. In some larger sense, however, this is the easy, relatively well understood problem.

Next up are the computational fluid dynamics (CFD) models of oil dispersion by wind and waves, and their interactions with shallow water features and barrier islands. Turbulence and mixing, viscosity, dispersants, complex geometries and multiple time scales expose the theoretical and practical limits of our parallel, numerical solutions to the Navier-Stokes equations. But we are just getting started.

Next come biophysics models and interactions among surface illumination, bacterial breakdown of oil droplets, and the effects of effulent driven ocean deoxygenation. These coupled models must be embedded in the CFD models to produce time varying estimates of microbiological effects.

Now it is time to get serious.

Next up are the species-specific models of petroleum ingestion and interaction, the effects on organism behavior and longevity, individual population dynamics and their interplay in the food chain. These are followed by long-term ecological models of wetlands and marine estuaries and statistical models of the possible benefits and adverse effects of human remediation. Finally, we reach models of human physiology and public health. These are followed by a host of societal and economic models, ranging from fishing and tourism through the global energy markets to the broader economic markets.

Solution Methodologies

Even the most cursory examination of the models and problems enumerated above exposes three very sobering truths. First, our ability to couple discrete and continuous models, each with their own approximations and limitations, across such enormous temporal and spatial ranges pales before the magnitude and complexity of this problem. We can only solve pieces of it. Second, even given the numerical tools, we lack the software engineering and programming methodologies to assemble, test and verify an integrated solution. Third, even given the first two, the computational demands of an integrated, fully multidisciplinary, parametric simulation study of the oil spill and its effects would make accurate climate modeling seem like child's play on an abacus by comparison.

Let us be humbled by what we cannot do and challenged by how far we have to go. We have much work to do. These are computational science problems of the very highest order.