Work place: Department of Computer Science and Engineering, National Institute of Technology, Tiruchirappalli, India
E-mail: rmohan@nitt.edu
Website:
Research Interests: Computer Architecture and Organization, Distributed Computing, Data Structures and Algorithms
Biography
R.Mohan is an Assistant Professor of Computer Science and Engineering Department, National Institute of Technology, Tiruchirappalli, Tamil Nadu, India. His research interests include Distributed Computing, Data Structures and Algorithms.
DOI: https://doi.org/10.5815/ijisa.2014.05.07, Pub. Date: 8 Apr. 2014
To get maximum performance on the many-core graphics processors, it is important to have an even balance of the workload so that all processing units contribute equally to the task at hand. This can be hard to achieve when the cost of a task is not known beforehand and when new sub-tasks are created dynamically during execution. Both the dynamic load balancing methods using Static task assignment and work stealing using deques are compared to see which one is more suited to the highly parallel world of graphics processors. They have been evaluated on the task of simulating a computer move against the human move, in the famous four in a row game. The experiments showed that synchronization can be very expensive, and those new methods which use graphics processor features wisely might be required.
[...] Read more.DOI: https://doi.org/10.5815/ijitcs.2013.10.08, Pub. Date: 8 Sep. 2013
Task assignment is one of the most fundamental combinatorial optimization problems. Solving the Task Assignment Problem is very important for many real time and computational scenarios where a lot of small tasks need to be solved by multiple processors simultaneously. In this paper a Heuristic and Parallel Algorithm for Task Assignment Problem is proposed. Results obtained for certain cases are presented and compared with the optimal solutions obtained by already available algorithms. It is observed that the proposed algorithm works much faster and efficient than the existing algorithms .The paper also demonstrates how the proposed algorithm could be extended to multiple distributed processors.
[...] Read more.Subscribe to receive issue release notifications and newsletters from MECS Press journals