Affiliations: [a] Department of CSE, Chandigarh University, Gharuan, Mohali, Punjab, India
| [b] Department of EEE, MAU, Baddi, H.P., India
Correspondence:
[*]
Corresponding author. Rohit K. Bhullar, Department of CSE, Chandigarh University, Gharuan, Mohali, Punjab, India. Tel.: +919802039898; Fax: +911734257693; E-mail: [email protected].
Abstract: Parallel Processing has been a widely studied field, used and implemented in computational systems. Many different types of topologies of processors have been implemented and their performance has been analyzed. The processor technology keeps evolving so their computational capability must be utilized accordingly when employed in parallel systems. In this article, new intra-parallel processor architectures (segmented/heterogeneous) has been used and an intelligent co-operative protocol has been implemented to optimally utilize the parallel components of the parallel processor design. More precisely a friendship based intelligent load balancing strategy has been designed and implemented to maximally utilize the parallel processor, which takes care of overloading and starvation problems and makes intelligent decisions regarding job scheduling. Context switching policies must also be designed carefully to stop performance degradation and with intelligent techniques this switching time can be reduced considerably. Work proposed in this article performs and executes load stability with feasible priori information about processors utilization, depending upon and based on this metric value the entire process space is partitioned among different categories. Based on the load status and state of affairs, processors are categorized and labeled and a suitable set out of those is figured-out that act as buddy for others and handles incoming process queue for overloaded processors. Further history and statistics of each processors is maintained and is utilized to make intelligent future scheduling decisions.
