jPoP/Jojo

Note: this project have been dead for years. this page is just for archive.

jPoP

For combinatorial optimization problems, which compute the optimal value of a multi-dimensional parameter function, serveral methods are known to be effective, such as Branch-and-Bound methods, Genetic Algorithm, etc. Since these methods can be massively parallelized and the granularities of computation tasks are easily controllable, they are considered to be suitable for executing on the Grid. However, distributed parallel programming on the Grid is quite complicated and furthermore setting up the Grid-wide computing environment is a heavy burden.

Here, we propose a system called jPoP, which makes it easy to develop and execute optimization-problem solvers on the Grid. To support the development, the jPoP provides a template class for each algorithm. And to reduce the cost of the setup, it automatically stages the user programs to the Grid environment.

Jojo

Jojo is a distributed programming environment suitable for hierarchal Grid, implemented in Java. Jojo provides several features, including remote invocation using Globus GRAM, intuitive message passing API suitable for parallel execution and automatic user program staging. Using Jojo, users can construct parallel distributed application on the Grid.