No abstract

No abstract

This work is focused on the issue of job scheduling in a high performance computing systems such as grid, cloud or systems with hybrid environments. The goal is based on the analysis of scheduling models of tasks in grid and cloud, design and implementation of the simulator on the base of GPGPU. The simulator is verified by our own proposed model of job scheduling. The simulator consists of a scheduler that is using GPGPU to process large amounts of data by parallel way. For design of the scheduler we take into account that computing resources are used and enable the transfer of files between tasks. We consider a system with non-preemptive tasks. In order to ensure the optimization of the scheduling process we have implemented a simulated annealing algorithm. GPGPU model was compared to the CPU when the number of machines is changing from 32 to 512. Improving the implementation based on GPGPU had a significant impact on the system with 512 machines and with an increasing number of machines further accelerates in comparison with sequential algorithm. The outcome is that the proposed implementation of the GPGPU is relevant in job scheduling for high-performance computing.

This work is focused on the issue of job scheduling in a high performance computing systems. The goal is based on the analysis of scheduling models of tasks in grid and cloud, design and implementation of the simulator on the base of GPGPU. The simulator is verified by our own proposed model of job scheduling. The simulator consists of a centralized scheduler that is using GPGPU to process large amounts of data by parallel way. In order to ensure the optimization of the scheduling process we have implemented a simulated annealing algorithm. GPGPU model was compared to the CPU when the number of nodes from 32 to 2048. Improving the implementation based on GPGPU had a significant impact on the system with 512 nodes and with an increasing number of nodes further accelerates in comparison with sequential algorithm. In this work are designed new scheduling criteria which are experimentally evaluated.

No abstract