Cost-Effective Data-Parallel Load Balancing
نویسندگان
چکیده
Load balancing algorithms improve a program’s performance on unbalanced datasets, but can degrade performance on balanced datasets, because unnecessary load redistributions occur. This paper presents a cost-effective data-parallel load balancing algorithm which performs load redistributions only when the possible savings outweigh the redistribution costs. Experiments with a data-parallelpolygon renderer show a performance improvement of up to a factor of 33 on unbalanced datasets and a maximum performance loss of only 27 percent on balanced datasets when using this algorithm.
منابع مشابه
A Geometry Data Independent Load Balancing Method For Graphics Parallel Rendering
We describe a novel load-balancing method for sort-first parallel graphics rendering systems. It gives up geometry data which could be very large and tends to cause unacceptable cost. Instead it takes rendering time as the measurement of render nodes’ work load and produces new screen decomposition using a time-to-space algorithm. Test results show that the geometry data independent method is v...
متن کاملLoad Balancing Approaches for Web Servers: A Survey of Recent Trends
Numerous works has been done for load balancing of web servers in grid environment. Reason behinds popularity of grid environment is to allow accessing distributed resources which are located at remote locations. For effective utilization, load must be balanced among all resources. Importance of load balancing is discussed by distinguishing the system between without load balancing and with loa...
متن کاملCost-eeective Data-parallel Load Balancing Cost-eeective Data-parallel Load Balancing
Load balancing algorithms improve a program's performance on unbalanced datasets, but can degrade performance on balanced datasets, because unnecessary load redistributions occur. This paper presents a cost-eeective data-parallel load balancing algorithm which performs load redistributions only when the possible savings outweigh the redistribution costs. Experiments with a data-parallel polygon...
متن کاملDynamic Load Balancing for Finite Element Calculations on Parallel Computers
Computational requirements of full scale computational fluid dynamics change as computation progresses on a parallel machine. The change in computational intensity causes workload imbalance of processors, which in turn requires a large amount of data movement at runtime. If parallel CFD is to be successful on a parallel or massively parallel machine, balancing of the runtime load is indispensab...
متن کاملCost - E ective Data - Parallel Load Balancing
Load balancing algorithms improve a program's performance on unbalanced datasets, but can degrade performance on balanced datasets, because unnecessary load redistributions occur. This paper presents a cost-e ective data-parallel load balancing algorithm which performs load redistributions only when the possible savings outweigh the redistribution costs. Experiments with a data-parallel polygon...
متن کامل