Towards programming environment for personal supercomputing


Prof. Nikolay Mirenkov, Rentaro Yoshioka, and Yutaka Watanobe
University of Aizu, Japan

!!!NEW BY SKYPE NEW!!!

TUESDAY, November 13, 2007
07.00 am - 08.00 am California Time
10.00 am - 11.00 am New York Time
03.00 pm - 04.00 pm UK Time
04.00 pm - 05.00 pm Central Europe Time
05.00 pm - 06.00 pm Eastern Europe Time
11.00 pm - 12.00 pm Peking/China Time
12.00 pm - 01.00* am Tokyo Time
01.30* am - 02.30* am Adelaide/Australia Time
02.00* am - 3.00* am Melbourne/Australia Time
* Next Day (November 14)

Abstract
========

PCs are on track to keep adding processing power as Intel, AMD, and IBM, add more cores to chips. PCs are becoming parallel, providing performances previously available only to users of supercomputers; the Cell Processor of Playstation3 is a good example within this trend. Breakthrough research and education are needed to tap that horsepower.

A new programming paradigm based on "filmification" of computational methods and on environment supporting the development of self-explanatory software components will be presented. Algorithmic cyberFilm is an abstraction combining both mathematical and physical concepts. It is a set of multimedia frames representing a variety of algorithmic features. These features are a basis for bridging the gap between "syntax and semantics" and understanding the corresponding component meaning. The self-explanatory concept is also an abstraction; however, it is intuitively much more understandable and allows employing a number of "fuzzy" views to represent the accurate meaning. CyberFilms as pieces of "active" knowledge are acquired in a film database. The cyberFilm frames are watchable and editable in a non-linear order according to the user's demands. Examples of algorithmic cyberFilms, as well as their compactness and understandability for users will be presented. Code generation from cyberFilm specifications and how to minimize sacrificing performance will also be considered.

Link to the Skypecast

Slides (PPT 6000 kB)