Parallel Software for Graph Algorithms

Viewing the current advances in the field of multi-core architectures and high-performance computing, there is a great thrust on researchers and developers to come up with parallel algorithms and their implementations to utilize the available hardware. Graph algorithms is one of the most widely studied areas in the field of computer science and engineering. Various problems in the field of computer science and other fields of science and engineering are reducible to standard graph problems such as Network Flows, All-Pairs Shortest Path and Spanning Trees. Many such problems have efficient sequential algorithms. However, the sizes of these problems have seen a rapid increase in the past few years. A single processor can not satisfy the computational and power needs of such large problem sizes. Hence it becomes necessary to develop efficient parallel implementations of such algorithms which can make use of the present-day and future multi-core and other parallel architectures like clusters and MPPs. These solutions compiled in form of a library similar to the C math library can be of great use to application developers and even researchers.

The project is being supported by Microsoft India under its open source technology program.



Coming soon..