(For new reader and those who request 好友请求, please read my 公告栏 first)

Another event ( in addition to the Markov Centennial I reported in my previous article) of the Harvard Winter Compufest is a symposium titled ” Computing at Exa Scale” . If you are like me, then the first question is what is “Exa”?. I have “giga” bytes of storage on my own computer. I know the fastest supercomputer perform at teraflops (floating point operations per seconds). “Exa” on the number scale is 10 raised to the 15^th power. It is 1000 “tera”, i.e., 1000 times faster than the fastest super computer.

Thus, why do we need such speed? And do they exist? This is what I learned as an outsider from attending the conference.

1.       Yes, we have very specialized computer employing massive parallel architecture for specific problems (bioinformatics problems) that indeed can run 1000 times faster than the fastest super computers.

2.       In molecular biology scholars are interest in how molecules come together to form proteins and how proteins folds into a stable shape; and how drug molecules get attached to cells at the right place. Currently knowledge on these questions are very meager. Thus, we start from basic atoms and molecules following Newton’s law of motion and brute force compute their 3D motion and observe what happens. This is a “many body problem”. Computations to produce these motions for tens and hundreds of molecules just over a period of 1 milliseconds require ability to process at Exaflops.

3.       Over 80% of the population of the US live in cities and their urban areas. A typical city has 3 million population forming 1 million household and 200k business using some 500K vehicle. As a nation we have 300 million cell phones, 400K ATMS and 30 million surveillance cameras.  All of these produce huge amount of data involving services, infra-structures, and the environment.

What can be done to produce meaningful monitoring, optimization, and planning constitutes the new discipline of “Urban-Informatics”

4.       Just as an example, it is possible to determine using publically available records whether or not a person living at a particular address has been tested HIV positive. In the past, manually looking at these public records and correlating the information is an impossible task. But with everything available digitally, such correlation and inference are possible. Thus the issue of privacy and security becomes important. This is the era of ”BIG DATA” and hence the need for exascale computing

Subsequent to the symposium, New York Times today ran a related article on literature analysis http://www.nytimes.com/2013/01/27/technology/literary-history-seen-through-big-datas-lens.html?nl=todaysheadlines&emc=edit_ae_20130127&_r=0.  I quote  

“It is this ability to collect, measure and analyze data for meaningful insights that is the promise of Big Data technology. In the humanities and social sciences, the flood of new data comes from many sources including books scanned into digital form, Web sites, blog posts and social network communications. Data-centric specialties are growing fast, giving rise to a new vocabulary. In political science, this quantitative analysis is called political methodology. In history, there is cliometrics, which applies econometrics to history. In literature, stylometry is the study of an author’s writing style, and these days it leans heavily on computing and statistical analysis. Culturomics is the umbrella term used to describe rigorous quantitative inquiries in the social sciences and humanities.”

Young scholars looking for new worlds to conquer take note.