Reed's Ruminations: A Blog by Dan Reed

The Love of Language

Between the idea
And the reality
Between the motion
And the act
Falls the Shadow

T.S. Elliot, The Hollow Men

I am a logophile (λογοπηιλε) – a lover of words. More than that, I am a lover of well crafted, erudite prose that captures and conveys nuance and subtlety. Such prose brings a smile to the lips, both the writer and the reader's reward for dutiful and diligent background research, thoughtful paragraphs that flow as mellifluously as a mountain stream, and phrases that delight with their craftsmanship.

The words matter, for they are the conduit of our ideas and experiences, of our hopes and fears, and of our passions and dreams. They bind us, yet they separate us, for none of us is truly their master.

Between the idea and the reality – the concept and its expression – falls the shadow.

Sunday Rituals

I have a Sunday ritual, practiced with great reverence and solemnity, that cleanses my soul and prepares me to face the viccisidues of the coming week with all the equanimity I can summon. This ritual involves both a large latte, made with freshly ground beans and frothed milk, and the New York Times. When traveling or in extremis, the Times of London or the Washington Post can be substituted. Under no circumstances, however, will a graven image such as the Podunk Picyune-Gazette be tolerated, for reading it is tantamout to drinking instant coffee, an abomination to the world and all right thinking individuals.

Armed with a massive latte, I spread the New York Times on the kitchen table. (As a non New Yorker, I have never mastered the art of newspaper oragami.) For me, it begins with the front page and its extended stories, then the Week in Review, the editorials and the op-eds. I dally over the obituaries and the wedding announcements, a voyeur inspecting the lives of others.

I scan the business section, seeking surcease for our economic sorrows, then linger over the travel section, thinking about the places I have been and those I have yet to visit. Finally, I turn to the Sunday Book Review, looking for new books to read, and the Sunday Magazine, wondering which topics will warrant extended stories. (And yes, I still miss William Safire's wit in the On Language column.)

I feast my soul on language, sated, albeit briefly, for the coming week.

Nuance Matters

Make no mistake, small words have huge effects. Both war and peace have hung on the interpretation of a single word or phrase. In such circumstances, creative ambiguity can be prized, allowing each party to apply their own, convenient interpretation. Often, though, such translingual ambiguity is simply the subject of embarrassment.

I am reminded of a conversation with a friend from graduate school. It was about 1980, and we were discussing the characteristics of dumb terminals (i.e., terminals with limited intelligence and connected by RS-232 connections to a remote computing system). Though not a native English speaker, he was quite proficient, rarely pausing to search for a word or phrase, even when conveying complex ideas.

Gesticulating enthusastically, my friend opined on the limitations of such devices, expressed his preferences and, as I recall, offered a few pejorative comments on certain vendors' products. It was a technical discussion filled with facts and analyses, similar to countless others held every day by computer scientists and engineers. He finally paused in mid-sentence, nonplussed by my uproarous laughter.

After gathering my composure, I explained that he had been railing about stupid terminals, rather than dumb terminals. Though superfically synonymous, the first was an inadvertant value judgement; the second was a technical term of art. Like all non-native speakers, he had been ensnared by an American idiom, with the inevitably amusing results. Both connotation and denotation matter.

Compare and Contrast

On occasion, I read newspaper stories where I have personal knowledge of the events and participants described in the story. Rarely do those stories capture all the details correctly. Even when the facts are correct, the tone, the implications and the nuance are either lost or subtlety incorrect. Years ago, I asked a reporter about this, and he readily acknowledged this was the case, noting that it was extraordinarily difficult to capture complexity.

If you have ever read multiple accounts of an international event, written by reporters from different cultures, countries and perspectives, you know this to be true. You may even have wondered if they were reporting the same events. Read thoughtfully, interpolate and extrapolate, seek complexity, seek understanding.

Simple HPC Wins – Usually

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

In the 19^th century, writing about his work on mechanical calculating devices, Charles Babbage noted, "The most constant difficulty in contriving the engine has arisen from the desire to reduce the time in which the calculations were executed to the shortest which is possible." Roughly a century later, Daniel Slotnick wrote retrospectively about the ILLIAC IV parallel computing design, "By sacrificing a factor of roughly three in circuit speed, it's possible that we could have built a more reliable multi-quadrant system in less time, for no more money, and with a comparable overall performance."

Babbage's design challenged the machining and manufacturing capabilities of his day, though recently, others were able to build a functioning system using parts fabricated to tolerances achievable with 19^th century processes. Similarly, Slotnick's design challenged electronics and early semiconductor fabrication and assembly. Today, of course, parallel computing designs embodying tens of thousands of processors are now commonplace, leveraging inexpensive, commodity hardware.

Technology Lessons

There is a lesson here, which systems designers repeatedly ignore at their peril. Simple designs usually triumph, and artful exploitation of mainstream technologies usually bests radical change. Or, as Damon Runyon once archly observed, "The race may not always be to the swift, nor the victory to the strong, but that's how you bet."

All of which is to say that incrementalism wins repeatedly, right up to the point when a dislocating phase transition occurs. There are, of course, many paths to failure. One can be too early or too late. Or to put it another way, you want to be the first person to design a successful, transistorized computer system, not the last person to design vacuum tube computer. The same is true of design approaches such as pipelining, out of order issue and completion, superscalar dispatch, cache design, system software and programming tools.

Innovator's Dilemma

Any designer's challenge is to pick the right technologies at the right time, recognizing when inflection points – maturing, disruptive technologies – are near. This is the essence of Clayton Christensen's well-documented innovator's dilemma.

The shift from largely proprietary high-performance computing (HPC) designs to predominantly commodity clusters a decade ago was but one of the most recent transitions. Arguably, we are near another disruptive technology point. The embedded hardware ecosystem offers one intriguing new performance-power-price point, particularly as we consider trans-petascale and exascale designs that are energy constrained. The experiences of cloud providers in building massive scale infrastructures for data analytics and on-demand computing are another possibility.

As I frequently told my graduate students at Illinois, the great thing about parallel computing is the question never changes – "How can I increase performance?" – but the answers do. Babbage would have understood.