Dorai’s LearnLog

June 26, 2008

Children of the Petabyte Age

Filed under: Models, Trends, theories — dorai @ 9:25 am
Tags: , , ,

Is it really the End of Theory, as Chris Anderson predicts?

Sixty years ago, digital computers made information readable. Twenty years ago, the Internet made it reachable. Ten years ago, the first search engine crawlers made it a single database. Now Google and like-minded companies are sifting through the most measured age in history, treating this massive corpus as a laboratory of the human condition. They are the children of the Petabyte Age.

At the petabyte scale, information is not a matter of simple three- and four-dimensional taxonomy and order but of dimensionally agnostic statistics.

I do believe, as they say in  AstronomyCast that knowing  “not just what we know but how we know what we know” gives you the ability to reason about hypotheses, models and theories. A new kind of analysis with petabytes of data may lead us down the path. But the examples are far fewer and not very convincing - yet.

I would love to watch this conversation and see where it takes us.

Updated: 1st Jul 08

I did not have to wait long. Here is a great article on Why the cloud cannot obscure the scientific method.

February 23, 2008

Resources: Parallel Programming Research

Filed under: Models, Programming — dorai @ 6:41 am
Tags: ,

Parallel Path from Berkeley, CA

I got this from ACM Tech News. Look at the links below the article. They lead to some cool resources.

Parallel Computing Lab, Berkeley, CA

Download the presentation from this page. It has a wealth of useful information.

Parallel Programming Model Watch

There is not just one model for parallel programming. I watch this page (with InfoMinder)

Dwarf Mine

A dwarf is an algorithmic method that captures a pattern of computation and communication.

I blogged about 13 dwarfs last year. I guess, they now changed the title to Dwarf Mine to keep the idea of mining more patterns.

Research at Intel

Intel, Microsoft have lots of efforts going on in this area. They fund research (like this Berkeley paralabs initiative. Sun is active too.

Parallel Programming will have the deepest impact on a wide variety of solutions to computational problems. It is an exciting area to follow.

See Also:

Design Patterns for Parallel Programming

Thirteen Dwarfs - Computational Kernels

The Fundamental Paradigms for Programming are going to be Challenged 

Next Page »

Blog at WordPress.com.