Coarse-grained reconfigurable fabrics have great promise for achieving energy-efficient flexible designs for an application domain. In order to use these fabrics for practical applications, however, there is a great need to develop smart mapping algorithms to implement applications of interest onto these fabrics. This research is focused on discovering new mapping strategies for customized coarse-grained devices through crowd sourcing.
The main thrust of the proposed research is to develop a science game to discover better mapping algorithms by making use of human intuition and ability to recognize patterns and opportunities even in complex problems. Players are presented with successively more difficult mapping problems in a game environment, and the vast dataset of players. Moves are analyzed to recognize common patterns used by successful game players. The insights gained from strategic moves humans make while solving problems based on their visual intuition and experience can be used to discover new mapping approaches that are beyond what can be conceived with traditional algorithms. If time permits, architectural innovations will also be investigated by giving players opportunities to make architectural changes in the game environment. New energy-efficient architectures and mapping algorithms that are developed in this research will spur development of a broad range of portable/wearable computing applications critical to health, safety and security, personal multimedia, and aerospace.
The main thrust of this research is to discover novel mapping algorithms by making use of human intuition and ability to recognize patterns and opportunities even in complex problems. Players are presented with successively more difficult mapping problems in a game environment, and the vast dataset of players moves is analyzed to recognize common patterns used by successful game players. The insights gained from strategic moves humans make while solving problems based on their visual intuition and experience can be used to discover new mapping approaches that are beyond what can be conceived with traditional algorithms. We have delivered an online version of our game UNTANGLED, designed to uncover human mapping strategies. In our game, users compete to create the most compact and perhaps beautiful layouts of circuit elements onto a grid. Although the game is presented to players abstractly, as connected elements in bold colors that must be untangled and arranged, it actually consists of real algorithms that players are mapping onto different chip architectures that could be manufactured in silicon. Our game has been available online now continuously since May 2012, and new players around the world are continuously joining, exploring the mapping problem, and adding to our database of good mappings. We carried out an online mapping competition that attracted hundreds of players. It gave us a vast database of manually created mappings to mine, explore, and analyze. We have analyzed players' mapping strategies and created algorithms that outperform the long-term standard solutions by a significant amount. Fast and effective mapping techniques have the potential to inspire architectural innovation and can result in production of devices that are smaller, smarter, and have longer battery life, which could have great influence on health, communication, and general quality of life. UNTANGLED has received the People’s Choice Award in the Games and Apps category of the 2012 International Science and Engineering Visualization Challenge conducted by the National Science Foundation and Science, and it has been recognized in a number of press releases. We conducted a freshmen game night to increase student interest in Electrical Engineering and Computer Engineering. One of the most exciting broader impacts of our research to date is our finding that our game can promote computational thinking among non-scientists and engineers.
