DECEMBER 2008 (Vol. 41, No. 12) p. 4
0018-9162/08/$31.00 © 2008 IEEE
Published by the IEEE Computer Society
Published by the IEEE Computer Society
Extending Amdahl's Law for Energy-Efficient Computing in the Many-Core Era
Dong Hyuk Woo and Hsien-Hsin S. Lee
In 1967, Gene Amdahl proposed an often overlooked law of scaling: A program's sequential computation largely limits the maximum achievable speedup. This implies that any nonparallel execution or intercore communication will rapidly diminish the performance scalability for parallel applications. Amdahl's law serves as a guideline for parallel programmers to assess the upper bounds of attainable performance.
Unfortunately, beyond performance, computer architects face another Grand Challenge: energy efficiency. Architects should carefully design a future many-core processor so that its power consumption doesn't exceed its power budget.
Universal Systems Language: Lessons Learned from Apollo
Margaret H. Hamilton and William R. Hackler
System engineers and software developers can significantly reduce the well-known problems associated with doing business as usual by using a language based on a radically different, preventive instead of curative approach. The Universal Systems Language is such a language.
Based on systems theory—to a great extent derived from lessons learned from the Apollo onboard flight software effort—USL has evolved over several decades and taken on multiple dimensions. Its purpose has been to solve problems considered next to impossible to solve with traditional approaches, at least in the foreseeable future.
Autonomy for Mars Rovers: Past, Present, and Future
Max Bajracharya, Mark W. Maimone, and Daniel Helmick
The vehicles used to explore the Martian surface require a high degree of autonomy to navigate challenging and unknown terrain, investigate targets, and detect scientific events. Autonomy software allows such vehicles to make decisions and command actuators based on their observations of the environment or sensor feedback. Increased autonomy will be critical to the success of future missions, in which rovers will be expected to travel over long distances in a short time and handle dynamic processes such as taking a core sample from a rock while slipping on a slope.
An Integrated Hydrologic Modeling and Data Assimilation Framework
Sujay Kumar, Christa Peters-Lidard, Yudong Tian, Rolf Reichle, James Geiger, Charles Alonge, John Eylander, and Paul Houser
Recent advances in remote sensing technologies have enabled the monitoring and measurement of Earth's land surface. Such observations provide data about Earth's vegetation, water, and energy fluxes. These must be integrated with state-of-the-art land-surface model forecasts using data assimilation tools to generate spatially and temporally continuous estimates of environmental conditions.
The need to develop modeling systems that identify and represent connections between land-surface hydrology and different components of the Earth system provides another key requirement for advancing hydrological prediction capabilities.
Using Genetic Algorithms to Model Road Networks
Maria Pinninghoff, Ricardo Contreras, and John Atkinson
Transportation planners analyze solutions in terms of designing or reshaping an urban transport network, the set of roads that lets people and vehicles move within a city area. With efficiency a top concern, planners view network design as an optimization problem whose solution must minimize the generalized cost of trips within the network.
To make transport network planning more efficient, researchers have investigated automating network design. The authors' model uses genetic algorithms to optimize the assignment of private transport within a city area. With it, they investigate claims that automated methods provide more network choices and higher-quality solutions than do manual procedures alone.