Load balancing strategy for multicore systems

E. Chovancova, J. Mihal'ov
2015 2015 13th International Conference on Emerging eLearning Technologies and Applications (ICETA)  
High performance computing including parallel and distributing systems now focus on power efficient execution. This is not only to the rising energy cost but these systems are playing a major role in global warming and greenhouse gas emissions. The birth of multicore systems is a major cause of huge power consumption and producing a lot of heat. Cores are the fundamental units that read and execute instructions in a computer program. A single core CPU has only one core that executes single
more » ... uction at a time. A multicore CPU has more than one independent processing core on a single chip to increase throughput and performance. Theoretically, by adding extra core to the same chip double the performance, but in practice speed of each core is slower than the single core processor. Likewise executing more instructions increases power consumption and thus produce extra high temperature. Soft-wares are written for multicore platform that distribute the workload amongst multiple identical or different cores. This functionality is called thread-level parallelism. These particular methods are called load balancing mechanism. In this paper we have summarized a number of load balancing algorithms that minimize the power consumption of multicore technology while maintaining performance to the best level. We have also compared two important algorithms proposed in the literature in terms of faster execution time and power efficiency.
doi:10.1109/iceta.2015.7558473 fatcat:ffoxzd7j6jc4loehhunoppfhwe