Particle-in-cell (PIC) method has got much benefits from GPU-accelerated heterogeneous systems.However,the performance of PIC is constrained by the interpolation operations in the weighting process on GPU (graphic pro...Particle-in-cell (PIC) method has got much benefits from GPU-accelerated heterogeneous systems.However,the performance of PIC is constrained by the interpolation operations in the weighting process on GPU (graphic processing unit).Aiming at this problem,a fast weighting method for PIC simulation on GPU-accelerated systems was proposed to avoid the atomic memory operations during the weighting process.The method was implemented by taking advantage of GPU's thread synchronization mechanism and dividing the problem space properly.Moreover,software managed shared memory on the GPU was employed to buffer the intermediate data.The experimental results show that the method achieves speedups up to 3.5 times compared to previous works,and runs 20.08 times faster on one NVIDIA Tesla M2090 GPU compared to a single core of Intel Xeon X5670 CPU.展开更多
This paper provides a mathematical model for Three Gorges-Gezhou dam co-scheduling problem, based on full analysis of Three Corges-Gezhou dam＇s actual needs, to maximize the total throughput of Three Gorges-Cezhou da...This paper provides a mathematical model for Three Gorges-Gezhou dam co-scheduling problem, based on full analysis of Three Corges-Gezhou dam＇s actual needs, to maximize the total throughput of Three Gorges-Cezhou dam and the utilization ratio of shiplock area and minimize the total navigation shiplock waiting time under multiple constraints. This paper proposes a series queuing network （SQN） scheduling algorithm to divide the total ships that intend to pass through the shiplocks into four queues and calculate dynamically the weight of priority for each ship. The SQN scheduling algorithm schedules ships according to their priority weights which is determined by the characteristics of each ship, such as length, width, affiliation, waiting time, and so on. In the process, the operation conditions of Gezhou dam related to the navigable shiplocks and the task balancing among different shiplocks also should be considered. The SQN algorithm schedules ships circularly and optimizes the results step by step. Real operation data from our project shows that our SQN scheduling algorithm outperforms the traditional manual scheduling in which the less computational time is taken, the area utilization ratio of the five shiplocks is increased, the waiting time of high-prioritized ships is shorten, and a better balanced and alternating run-mode is provided for the three shiplocks in the Gezhou dam.展开更多
基金Projects(61170049,60903044)supported by National Natural Science Foundation of ChinaProject(2012AA010903)supported by National High Technology Research and Development Program of China
文摘Particle-in-cell (PIC) method has got much benefits from GPU-accelerated heterogeneous systems.However,the performance of PIC is constrained by the interpolation operations in the weighting process on GPU (graphic processing unit).Aiming at this problem,a fast weighting method for PIC simulation on GPU-accelerated systems was proposed to avoid the atomic memory operations during the weighting process.The method was implemented by taking advantage of GPU's thread synchronization mechanism and dividing the problem space properly.Moreover,software managed shared memory on the GPU was employed to buffer the intermediate data.The experimental results show that the method achieves speedups up to 3.5 times compared to previous works,and runs 20.08 times faster on one NVIDIA Tesla M2090 GPU compared to a single core of Intel Xeon X5670 CPU.
基金supported by the National Natural Science Foundation of China under Grant No. 60904074the Natural Science Foundation of Hubei Province of China under Grant No. 2008CDB012the Specialized Research Fund for the Doctoral Program of Higher Education of China under Grant No. 200804871150
文摘This paper provides a mathematical model for Three Gorges-Gezhou dam co-scheduling problem, based on full analysis of Three Corges-Gezhou dam＇s actual needs, to maximize the total throughput of Three Gorges-Cezhou dam and the utilization ratio of shiplock area and minimize the total navigation shiplock waiting time under multiple constraints. This paper proposes a series queuing network （SQN） scheduling algorithm to divide the total ships that intend to pass through the shiplocks into four queues and calculate dynamically the weight of priority for each ship. The SQN scheduling algorithm schedules ships according to their priority weights which is determined by the characteristics of each ship, such as length, width, affiliation, waiting time, and so on. In the process, the operation conditions of Gezhou dam related to the navigable shiplocks and the task balancing among different shiplocks also should be considered. The SQN algorithm schedules ships circularly and optimizes the results step by step. Real operation data from our project shows that our SQN scheduling algorithm outperforms the traditional manual scheduling in which the less computational time is taken, the area utilization ratio of the five shiplocks is increased, the waiting time of high-prioritized ships is shorten, and a better balanced and alternating run-mode is provided for the three shiplocks in the Gezhou dam.
