Research Paper

profilethrishalini
Abstractforloadimbalance1.docx

Improved Method for Reduction of Load Imbalance in Multiprocessor

Systems

Abstract: In the multiprocessor systems, the parallel programming plays an important role. Because of the lots of computation in the high-performance applications, there is the need for the parallel computing in the multiprocessor systems. As there is the different capacity of the processing for the different applications, therefore, the system used to get overloaded which in turn affect the performance of the application. In the previous paper, the load imbalance and overload problem of the multiprocessor system has been resolved by using the RAIM (Redundant Array of Independent Memory) technique. This technique has shown the improved results as compared to the previous works that have been done for the same problem. In this paper, the review will be done for the nature-inspired algorithm that can be used to solve the problem of the load imbalance in the multiprocessor systems. The main aim of this paper will be to provide the theoretical base of using the nature-inspired algorithm to handle the problem of the load imbalance so that there can be more optimization in the processing time and there can be prioritization of the tasks in the table so that applications can run smoothly.

Keywords: Parallel Processing, Multiprocessors, Processing time, Prioritizing, Nature Inspired

Algorithms.

Reference:

Ruohuang Zheng and Michael C. Huang. (2017). Redundant Memory Array Architecture for

Efficient Selective Protection. In Proceedings of the 44th Annual International Symposium on

Computer Architecture (ISCA’17). ACM, NY, USA, 214-227. doi:10.1145/3079856.3080213

1