Jambhlekar Pushkar Arun

Learn More
GPUs have brought supercomputing-at-desk by offering hundreds of processing cores at a very cheap cost. This has motivated researchers to implement and test parallel solutions to compute-intensive problems on GPU. Most real-world optimization problems are NP-hard and therefore compute intensive. Meta-heuristics are frequently used to solve these(More)
Communication overhead is an issue in a parallel implementation of algorithm on loosely coupled systems. Pipeline is a technique used to achieve parallelism at instruction level by dividing task into different stages and for every stage, it's output is the input for next the stage. Thus, pipeline limits the communication overhead by restricting it to only(More)
Particle swarm optimization has been shown to solve many real world optimization problems. When PSO is implemented in multi-objective domain, it archives the potential solutions. While solving multi-objective problems using PSO, global best selection from archive impacts on the overall quality of the solution set. In this paper, I present new approach to(More)
  • 1