Reflections on science, technology, and computing — leavened by personal experience


On the Microsoft blog, I posted a few thoughts on SC10, the rise of clouds and the power of simplicity in high-performance computing. There is also a video of my smiling face expounding on this topic.

Not that long ago, a megabyte was a lot of storage, whether primary or secondary. Not long ago supercomputers were defined by the number of megaflops they achieved. Times change. Bigger is not just bigger, bigger is different. Quantitative change begets qualitative change.

The history of modern digital computing is unusual in one regard. Most of its advances have occurred during the professional lifetimes of many of its current practicioners. For those of us who came of age in the mainframe era, it is instructive (and sometimes humorous) to remember what has changed.

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.

You want to be the first person to design a successful, transistorized computer system, not the last person to design vacuum tube computer. 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…

Had Thoreau had a smartphone, he would not have been texting his best bud, Ralph (Waldo Emerson), about the joys of solitude, nor would he have been tweeting or posting photos of his house construction. I am rather more confident he would have espoused the healing virtues of periodic digital seclusion and contemplation.